learning_model 1.0.2 → 1.0.3

package/dist/index.bundle.js

@@ -0,0 +1,2 @@
+/*! For license information please see index.bundle.js.LICENSE.txt */
+(()=>{var e={401:(e,t,n)=>{"use strict";n.r(t),n.d(t,{Abs:()=>et,Acos:()=>tt,Acosh:()=>nt,AdadeltaOptimizer:()=>jo,AdagradOptimizer:()=>Ko,AdamOptimizer:()=>Zo,AdamaxOptimizer:()=>sl,Add:()=>st,AddN:()=>rt,All:()=>at,Any:()=>it,ArgMax:()=>ot,ArgMin:()=>lt,Asin:()=>ut,Asinh:()=>ct,Atan:()=>ht,Atan2:()=>dt,Atanh:()=>pt,AvgPool:()=>ft,AvgPool3D:()=>gt,AvgPool3DGrad:()=>yt,AvgPoolGrad:()=>mt,BatchMatMul:()=>bt,BatchToSpaceND:()=>xt,Bincount:()=>wt,BitwiseAnd:()=>vt,BroadcastArgs:()=>It,BroadcastTo:()=>kt,Callback:()=>gS,CallbackList:()=>Yx,Cast:()=>Nt,Ceil:()=>St,ClipByValue:()=>Tt,Complex:()=>Ct,ComplexAbs:()=>$t,Concat:()=>Et,Conv2D:()=>At,Conv2DBackpropFilter:()=>Rt,Conv2DBackpropInput:()=>Ft,Conv3D:()=>_t,Conv3DBackpropFilterV2:()=>Dt,Conv3DBackpropInputV2:()=>Ot,Cos:()=>Mt,Cosh:()=>Lt,CropAndResize:()=>Bt,Cumprod:()=>zt,Cumsum:()=>Pt,CustomCallback:()=>Qx,DataStorage:()=>X,DenseBincount:()=>Wt,DepthToSpace:()=>Vt,DepthwiseConv2dNative:()=>Ut,DepthwiseConv2dNativeBackpropFilter:()=>Gt,DepthwiseConv2dNativeBackpropInput:()=>Ht,Diag:()=>jt,Dilation2D:()=>qt,Dilation2DBackpropFilter:()=>Xt,Dilation2DBackpropInput:()=>Kt,Draw:()=>Yt,ENV:()=>Ze,EarlyStopping:()=>xS,Einsum:()=>Jt,Elu:()=>Qt,EluGrad:()=>en,Environment:()=>qe,Equal:()=>nn,Erf:()=>tn,Exp:()=>sn,ExpandDims:()=>rn,Expm1:()=>an,FFT:()=>on,Fill:()=>ln,FlipLeftRight:()=>un,Floor:()=>cn,FloorDiv:()=>hn,FromPixels:()=>fr,FusedBatchNorm:()=>pn,FusedConv2D:()=>yr,FusedDepthwiseConv2D:()=>br,GPGPUContext:()=>HM,GatherNd:()=>fn,GatherV2:()=>dn,GraphModel:()=>WT,Greater:()=>mn,GreaterEqual:()=>gn,History:()=>Jx,IFFT:()=>bn,Identity:()=>yn,Imag:()=>xn,InputSpec:()=>tx,IsFinite:()=>wn,IsInf:()=>vn,IsNan:()=>kn,KernelBackend:()=>Y,LRN:()=>On,LRNGrad:()=>Mn,LayerVariable:()=>Jb,LayersModel:()=>rv,LeakyRelu:()=>In,Less:()=>Nn,LessEqual:()=>Sn,LinSpace:()=>Tn,Log:()=>Cn,Log1p:()=>$n,LogSoftmax:()=>_n,LogicalAnd:()=>En,LogicalNot:()=>An,LogicalOr:()=>Rn,LogicalXor:()=>Fn,LowerBound:()=>Dn,MathBackendCPU:()=>s$,MathBackendWebGL:()=>fz,MatrixBandPart:()=>Ln,Max:()=>zn,MaxPool:()=>Bn,MaxPool3D:()=>Vn,MaxPool3DGrad:()=>Un,MaxPoolGrad:()=>Wn,MaxPoolWithArgmax:()=>Gn,Maximum:()=>Pn,Mean:()=>Hn,Min:()=>jn,Minimum:()=>qn,MirrorPad:()=>Kn,Mod:()=>Xn,MomentumOptimizer:()=>al,Multinomial:()=>Yn,Multiply:()=>Zn,Neg:()=>Jn,NonMaxSuppressionV3:()=>es,NonMaxSuppressionV4:()=>ts,NonMaxSuppressionV5:()=>ns,NotEqual:()=>Qn,OP_SCOPE_SUFFIX:()=>Ya,OneHot:()=>rs,OnesLike:()=>ss,Optimizer:()=>Ho,OptimizerConstructors:()=>Eu,Pack:()=>as,PadV2:()=>is,Pool:()=>os,Pow:()=>ls,Prelu:()=>us,Prod:()=>cs,RMSPropOptimizer:()=>il,RNN:()=>pk,RaggedGather:()=>hs,RaggedRange:()=>ps,RaggedTensorToTensor:()=>ds,Range:()=>fs,Rank:()=>xa,Real:()=>ms,RealDiv:()=>Zt,Reciprocal:()=>gs,Reduction:()=>gf,Relu:()=>ys,Relu6:()=>Is,Reshape:()=>bs,ResizeBilinear:()=>vs,ResizeBilinearGrad:()=>ks,ResizeNearestNeighbor:()=>xs,ResizeNearestNeighborGrad:()=>ws,Reverse:()=>Ns,RotateWithOffset:()=>mr,Round:()=>Ss,Rsqrt:()=>Ts,SGDOptimizer:()=>rl,ScatterNd:()=>Cs,SearchSorted:()=>Es,Select:()=>As,Selu:()=>Rs,Sequential:()=>lv,Sigmoid:()=>Ms,Sign:()=>Os,Sin:()=>_s,Sinh:()=>Ds,Slice:()=>Fs,Softmax:()=>Vs,Softplus:()=>Ls,SpaceToBatchND:()=>Bs,SparseFillEmptyRows:()=>Us,SparseReshape:()=>Gs,SparseSegmentMean:()=>Hs,SparseSegmentSum:()=>js,SparseToDense:()=>qs,SplitV:()=>Ws,Sqrt:()=>zs,Square:()=>Xs,SquaredDifference:()=>Ks,StaticRegexReplace:()=>Ys,Step:()=>dr,StridedSlice:()=>Zs,StringNGrams:()=>Js,StringSplit:()=>Qs,StringToHashBucketFast:()=>er,Sub:()=>tr,Sum:()=>Ps,SymbolicTensor:()=>nx,Tan:()=>nr,Tanh:()=>sr,Tensor:()=>ga,TensorBuffer:()=>pa,TensorScatterUpdate:()=>$s,Tile:()=>rr,TopK:()=>ar,Transform:()=>ir,Transpose:()=>or,Unique:()=>lr,Unpack:()=>ur,UnsortedSegmentSum:()=>cr,UpperBound:()=>hr,Variable:()=>ba,ZerosLike:()=>pr,_FusedMatMul:()=>gr,abs:()=>Jo,acos:()=>Au,acosh:()=>Ru,add:()=>Co,addN:()=>Fu,all:()=>_u,any:()=>Du,argMax:()=>Ou,argMin:()=>Mu,asin:()=>Lu,asinh:()=>zu,atan:()=>Pu,atan2:()=>Bu,atanh:()=>Wu,avgPool:()=>rc,avgPool3d:()=>ac,backend:()=>So,backend_util:()=>y,basicLSTMCell:()=>cc,batchNorm:()=>pc,batchNorm2d:()=>dc,batchNorm3d:()=>fc,batchNorm4d:()=>mc,batchToSpaceND:()=>hc,bincount:()=>gc,bitwiseAnd:()=>yc,booleanMaskAsync:()=>bd,broadcastArgs:()=>bc,broadcastTo:()=>xc,broadcast_util:()=>o,browser:()=>c,buffer:()=>to,callbacks:()=>wS,cast:()=>no,ceil:()=>wc,clipByValue:()=>vc,clone:()=>so,complex:()=>Ja,concat:()=>ic,concat1d:()=>kc,concat2d:()=>Ic,concat3d:()=>Nc,concat4d:()=>Sc,constraints:()=>x,conv1d:()=>Cc,conv2d:()=>Tc,conv2dTranspose:()=>Ec,conv3d:()=>Ac,conv3dTranspose:()=>Fc,copyRegisteredKernels:()=>Ar,cos:()=>_c,cosh:()=>Dc,cosineWindow:()=>Sd,cumprod:()=>Oc,cumsum:()=>Mc,customGrad:()=>Po,data:()=>H,denseBincount:()=>Lc,deprecationWarn:()=>lo,depthToSpace:()=>zc,depthwiseConv2d:()=>Pc,deregisterOp:()=>TS,device_util:()=>a,diag:()=>Bc,dilation2d:()=>Wc,disableDeprecationWarnings:()=>oo,dispose:()=>mo,disposeVariables:()=>uo,div:()=>Eo,divNoNan:()=>Gc,dot:()=>Hc,dropout:()=>Id,einsum:()=>jc,elu:()=>qc,enableDebugMode:()=>io,enableProdMode:()=>ao,enclosingPowerOfTwo:()=>Nd,engine:()=>co,ensureShape:()=>Kc,env:()=>Xe,equal:()=>Vc,erf:()=>Xc,euclideanNorm:()=>uh,exp:()=>ch,expandDims:()=>hh,expm1:()=>ph,eye:()=>fh,fft:()=>jp,fill:()=>qo,findBackend:()=>ko,findBackendFactory:()=>Io,floor:()=>mh,floorDiv:()=>$o,forceHalfFloat:()=>gz,fused:()=>m,gather:()=>gh,gatherND:()=>kd,gather_util:()=>h,getBackend:()=>wo,getGradient:()=>Nr,getKernel:()=>Ir,getKernelsForBackend:()=>Sr,gpgpu_util:()=>K,grad:()=>Do,grads:()=>Oo,greater:()=>yh,greaterEqual:()=>bh,ifft:()=>qp,imag:()=>Al,image:()=>Mf,inTopKAsync:()=>Td,initializers:()=>w,input:()=>hv,io:()=>l,irfft:()=>Kp,isFinite:()=>xh,isInf:()=>wh,isNaN:()=>vh,keep:()=>go,kernel_impls:()=>b,layers:()=>v,leakyRelu:()=>kh,less:()=>Ih,lessEqual:()=>Nh,linalg:()=>Lf,linspace:()=>Sh,loadGraphModel:()=>VT,loadGraphModelSync:()=>UT,loadLayersModel:()=>ov,localResponseNormalization:()=>Th,log:()=>Ch,log1p:()=>$h,logSigmoid:()=>Ah,logSoftmax:()=>Rh,logSumExp:()=>Fh,logicalAnd:()=>_h,logicalNot:()=>Dh,logicalOr:()=>Oh,logicalXor:()=>Mh,losses:()=>zf,lowerBound:()=>Ph,matMul:()=>$l,math:()=>u,max:()=>rh,maxPool:()=>Bh,maxPool3d:()=>Wh,maxPoolWithArgmax:()=>Vh,maximum:()=>nl,mean:()=>Uh,memory:()=>ho,meshgrid:()=>jh,metrics:()=>k,min:()=>ah,minimum:()=>qh,mirrorPad:()=>Kh,mod:()=>Xh,model:()=>uv,models:()=>I,moments:()=>Yh,movingAverage:()=>xd,mul:()=>Ao,multiRNNCell:()=>Zh,multinomial:()=>Jh,neg:()=>Rl,nextFrame:()=>Uf,norm:()=>lh,notEqual:()=>Qh,oneHot:()=>El,ones:()=>Hh,onesLike:()=>ep,op:()=>Za,outerProduct:()=>tp,pad:()=>np,pad1d:()=>sp,pad2d:()=>rp,pad3d:()=>ap,pad4d:()=>ip,pool:()=>lp,pow:()=>Xo,prelu:()=>up,print:()=>ro,prod:()=>cp,profile:()=>po,raggedGather:()=>hp,raggedRange:()=>pp,raggedTensorToTensor:()=>dp,rand:()=>fp,randomGamma:()=>xp,randomNormal:()=>wp,randomStandardNormal:()=>vp,randomUniform:()=>kp,randomUniformInt:()=>Ip,range:()=>Np,ready:()=>xo,real:()=>Fl,reciprocal:()=>Sp,registerBackend:()=>No,registerCallbackConstructor:()=>pv,registerGradient:()=>Cr,registerKernel:()=>Tr,registerOp:()=>NS,regularizers:()=>N,relu:()=>Tp,relu6:()=>Cp,removeBackend:()=>vo,reshape:()=>sc,reverse:()=>$p,reverse1d:()=>Ep,reverse2d:()=>Ap,reverse3d:()=>Rp,reverse4d:()=>Fp,rfft:()=>Yp,round:()=>_p,rsqrt:()=>Dp,scalar:()=>Wo,scatterND:()=>wd,scatter_util:()=>p,searchSorted:()=>zh,selu:()=>Op,separableConv2d:()=>Mp,sequential:()=>cv,serialization:()=>i,setBackend:()=>bo,setPlatform:()=>To,setWebGLContext:()=>zD,setdiff1dAsync:()=>Lp,shared:()=>j,sigmoid:()=>oc,sign:()=>zp,signal:()=>Of,sin:()=>Pp,sinh:()=>Bp,slice:()=>lc,slice1d:()=>Wp,slice2d:()=>Vp,slice3d:()=>Up,slice4d:()=>Gp,slice_util:()=>d,softmax:()=>Hp,softplus:()=>Eh,spaceToBatchND:()=>op,sparse:()=>Pf,sparseToDense:()=>vd,spectral:()=>Df,split:()=>Xp,sqrt:()=>Ro,square:()=>Fo,squaredDifference:()=>Zp,squeeze:()=>Jp,stack:()=>Qp,step:()=>ed,stridedSlice:()=>td,string:()=>Bf,sub:()=>Yo,sum:()=>ih,sumOutType:()=>Ta,tan:()=>nd,tanh:()=>uc,tensor:()=>ei,tensor1d:()=>sd,tensor2d:()=>rd,tensor3d:()=>Ol,tensor4d:()=>ad,tensor5d:()=>id,tensor6d:()=>od,tensorScatterUpdate:()=>ld,tensor_util:()=>r,test_util:()=>f,tidy:()=>fo,tile:()=>dh,time:()=>yo,topk:()=>ud,train:()=>Wf,transpose:()=>_l,truncatedNormal:()=>cd,unique:()=>hd,unregisterGradient:()=>Er,unregisterKernel:()=>$r,unsortedSegmentSum:()=>pd,unstack:()=>dd,upcastType:()=>Sa,upperBound:()=>fd,util:()=>s,valueAndGrad:()=>Mo,valueAndGrads:()=>Lo,variable:()=>md,variableGrads:()=>zo,version:()=>hH,version_converter:()=>GT,version_core:()=>$u,version_cpu:()=>AA,version_layers:()=>zw,version_webgl:()=>mz,webgl:()=>yz,webgl_util:()=>q,where:()=>Uc,whereAsync:()=>yd,zeros:()=>Gh,zerosLike:()=>_o});var s={};n.r(s),n.d(s,{arraysEqual:()=>pe,arraysEqualWithNull:()=>he,assert:()=>ie,assertNonNegativeIntegerDimensions:()=>Ve,assertNonNull:()=>le,assertShapesMatch:()=>oe,bytesFromStringArray:()=>$e,bytesPerElement:()=>Ce,checkConversionForErrors:()=>Ne,clamp:()=>ee,computeStrides:()=>Oe,convertBackendValuesAndArrayBuffer:()=>ze,createScalarValue:()=>qr,createShuffledIndices:()=>ge,decodeString:()=>Jr,distSquared:()=>ae,encodeString:()=>Zr,fetch:()=>Yr,fingerPrint64:()=>jr,flatten:()=>ea,getArrayFromDType:()=>Ie,getTypedArrayFromDType:()=>ke,hasEncodingLoss:()=>Te,hexToLong:()=>Or,indexToLoc:()=>Ge,inferDtype:()=>Fe,inferFromImplicitShape:()=>xe,isBoolean:()=>Ae,isFunction:()=>_e,isInt:()=>de,isNumber:()=>Re,isPromise:()=>He,isScalarShape:()=>ce,isString:()=>Ee,isTypedArray:()=>Qr,isValidDtype:()=>Se,locToIndex:()=>Ue,makeOnesTypedArray:()=>Pe,makeZerosNestedTypedArray:()=>We,makeZerosTypedArray:()=>Be,nearestDivisor:()=>De,nearestLargerEven:()=>te,now:()=>Xr,parseAxisParam:()=>we,randUniform:()=>re,repeatedTry:()=>be,rightPad:()=>ye,shuffle:()=>J,shuffleCombo:()=>Q,sizeFromShape:()=>ue,sizeToSquarishShape:()=>me,squeezeShape:()=>ve,sum:()=>se,swap:()=>ne,tanh:()=>fe,toNestedArray:()=>Le,toTypedArray:()=>Kr});var r={};n.r(r),n.d(r,{assertTypesMatch:()=>Aa,getTensorsInContainer:()=>Fa,isTensorInList:()=>Ra,makeTypesMatch:()=>Ea});var a={};n.r(a),n.d(a,{isBrowser:()=>Ua,isMobile:()=>Va,mockIsMobile:()=>Wa});var i={};n.r(i),n.d(i,{Serializable:()=>Vo,SerializationMap:()=>Uo,registerClass:()=>Go});var o={};n.r(o),n.d(o,{assertAndGetBroadcastShape:()=>tl,getBroadcastDims:()=>Qo,getReductionAxes:()=>el});var l={};n.r(l),n.d(l,{CompositeArrayBuffer:()=>ni,browserFiles:()=>hl,browserHTTPRequest:()=>wl,concatenateArrayBuffers:()=>ui,copyModel:()=>Xi,decodeWeights:()=>ai,encodeWeights:()=>ri,fromMemory:()=>Nl,fromMemorySync:()=>Sl,getLoadHandlers:()=>vi,getModelArtifactsForJSON:()=>di,getModelArtifactsForJSONSync:()=>pi,getModelArtifactsInfoForJSON:()=>fi,getSaveHandlers:()=>wi,getWeightSpecs:()=>mi,http:()=>xl,isHTTPScheme:()=>yl,listModels:()=>qi,loadWeights:()=>fl,moveModel:()=>Yi,registerLoadRouter:()=>xi,registerSaveRouter:()=>bi,removeModel:()=>Ki,weightsLoaderFactory:()=>ml,withSaveHandler:()=>Tl,withSaveHandlerSync:()=>Cl});var u={};n.r(u),n.d(u,{confusionMatrix:()=>Dl});var c={};n.r(c),n.d(c,{draw:()=>Ul,fromPixels:()=>Gl,fromPixelsAsync:()=>Bl,toPixels:()=>Vl});var h={};n.r(h),n.d(h,{prepareAndValidate:()=>Hl});var p={};n.r(p),n.d(p,{calculateShapes:()=>Kl,validateInput:()=>ql,validateUpdateShape:()=>jl});var d={};n.r(d),n.d(d,{assertParamsValid:()=>Zl,computeFlatOffset:()=>cu,computeOutShape:()=>Ql,getNormalizedAxes:()=>su,isSliceContinous:()=>uu,maskToAxes:()=>Jl,parseSliceParams:()=>hu,sliceInfo:()=>pu,startForAxis:()=>ou,startIndicesWithElidedDims:()=>ru,stopForAxis:()=>lu,stopIndicesWithElidedDims:()=>au,stridesForAxis:()=>iu,stridesWithElidedDims:()=>eu});var f={};n.r(f),n.d(f,{TEST_EPSILON_FLOAT16:()=>mu,createVideoElement:()=>Tu,encodeStrings:()=>Su,expectArrayBuffersEqual:()=>Nu,expectArraysClose:()=>gu,expectArraysEqual:()=>wu,expectNumbersClose:()=>vu,expectPromiseToFail:()=>xu,expectValuesInRange:()=>Iu,play:()=>Cu,testEpsilon:()=>yu});var m={};n.r(m),n.d(m,{conv2d:()=>Fd,depthwiseConv2d:()=>Od,matMul:()=>Md});var g={};n.r(g),n.d(g,{collectGatherOpShapeInfo:()=>jm,computeOutShape:()=>Hm,segOpComputeOptimalWindowSize:()=>Gm});var y={};n.r(y),n.d(y,{ERF_A1:()=>lm,ERF_A2:()=>um,ERF_A3:()=>cm,ERF_A4:()=>hm,ERF_A5:()=>pm,ERF_P:()=>om,PARALLELIZE_THRESHOLD:()=>Zf,RowPartitionType:()=>jf,SELU_SCALE:()=>im,SELU_SCALEALPHA:()=>am,applyActivation:()=>Ad,assertAndGetBroadcastShape:()=>tl,assertAxesAreInnerMostDims:()=>eh,assertParamsConsistent:()=>Gf,assignToTypedArray:()=>bm,axesAreInnerMostDims:()=>Yc,calculateShapes:()=>Kl,checkEinsumDimSizes:()=>Cm,checkPadOnDimRoundingMode:()=>nc,combineLocations:()=>Zc,combineRaggedTensorToTensorShapes:()=>qf,complexWithEvenIndex:()=>mm,complexWithOddIndex:()=>gm,computeConv2DInfo:()=>Hu,computeConv3DInfo:()=>ju,computeDefaultPad:()=>qu,computeDilation2DInfo:()=>Vu,computeOptimalWindowSize:()=>Jf,computeOutAndReduceShapes:()=>Jc,computeOutShape:()=>Hf,computePool2DInfo:()=>Uu,computePool3DInfo:()=>Gu,convertConv2DDataFormat:()=>tc,decodeEinsumEquation:()=>Sm,eitherStridesOrDilationsAreOne:()=>Qu,expandShapeToKeepDim:()=>Qc,exponent:()=>wm,exponents:()=>xm,fromStringArrayToUint8:()=>Km,fromUint8ToStringArray:()=>qm,getAxesPermutation:()=>th,getBroadcastDims:()=>Qo,getComplexWithIndex:()=>ym,getEinsumComputePath:()=>$m,getEinsumPermutation:()=>Tm,getFusedBiasGradient:()=>Ed,getFusedDyActivation:()=>$d,getImageCenter:()=>Qf,getInnerMostAxes:()=>sh,getPermuted:()=>tm,getRaggedRank:()=>Xf,getReductionAxes:()=>el,getReshaped:()=>em,getReshapedPermuted:()=>nm,getRowPartitionTypesHelper:()=>Kf,getSliceBeginCoords:()=>sm,getSliceSize:()=>rm,getSparseFillEmptyRowsIndicesDenseShapeMismatch:()=>Fm,getSparseFillEmptyRowsNegativeIndexErrorMessage:()=>_m,getSparseFillEmptyRowsOutOfRangeIndexErrorMessage:()=>Dm,getSparseReshapeEmptyTensorZeroOutputDimErrorMessage:()=>Lm,getSparseReshapeInputOutputMismatchErrorMessage:()=>Pm,getSparseReshapeInputOutputMultipleErrorMessage:()=>zm,getSparseReshapeMultipleNegativeOneOutputDimErrorMessage:()=>Om,getSparseReshapeNegativeOutputDimErrorMessage:()=>Mm,getSparseSegmentReductionIndicesOutOfRangeErrorMessage:()=>Um,getSparseSegmentReductionNegativeSegmentIdsErrorMessage:()=>Bm,getSparseSegmentReductionNonIncreasingSegmentIdsErrorMessage:()=>Wm,getSparseSegmentReductionSegmentIdOutOfRangeErrorMessage:()=>Vm,getUndoAxesPermutation:()=>nh,isIdentityPermutation:()=>Em,log:()=>wr,mergeRealAndImagArrays:()=>dm,prepareAndValidate:()=>Hl,prepareSplitSize:()=>Rm,segment_util:()=>g,shouldFuse:()=>Rd,slice_util:()=>d,splitRealAndImagArrays:()=>fm,stridesOrDilationsArePositive:()=>ec,tupleValuesAreOne:()=>Ju,upcastType:()=>Sa,validateDefaultValueShape:()=>Yf,validateInput:()=>ql,validateUpdateShape:()=>jl,warn:()=>xr});var b={};n.r(b),n.d(b,{nonMaxSuppressionV3Impl:()=>Xd,nonMaxSuppressionV4Impl:()=>Yd,nonMaxSuppressionV5Impl:()=>Zd,whereImpl:()=>gd});var x={};n.r(x),n.d(x,{maxNorm:()=>Cx,minMaxNorm:()=>Ax,nonNeg:()=>Ex,unitNorm:()=>$x});var w={};n.r(w),n.d(w,{constant:()=>_x,glorotNormal:()=>Bx,glorotUniform:()=>Px,heNormal:()=>Wx,heUniform:()=>Vx,identity:()=>Lx,leCunNormal:()=>Ux,leCunUniform:()=>Gx,ones:()=>Fx,orthogonal:()=>Hx,randomNormal:()=>Ox,randomUniform:()=>Dx,truncatedNormal:()=>Mx,varianceScaling:()=>zx,zeros:()=>Rx});var v={};n.r(v),n.d(v,{Layer:()=>ix,RNN:()=>pk,RNNCell:()=>dk,activation:()=>jI,add:()=>tN,alphaDropout:()=>HN,average:()=>nN,averagePooling1d:()=>hN,averagePooling2d:()=>fN,averagePooling3d:()=>yN,avgPool1d:()=>pN,avgPool2d:()=>mN,avgPool3d:()=>bN,avgPooling1d:()=>dN,avgPooling2d:()=>gN,avgPooling3d:()=>xN,batchNormalization:()=>lN,bidirectional:()=>LN,categoryEncoding:()=>YN,centerCrop:()=>KN,concatenate:()=>sN,conv1d:()=>LI,conv2d:()=>zI,conv2dTranspose:()=>PI,conv3d:()=>BI,conv3dTranspose:()=>WI,convLstm2d:()=>_N,convLstm2dCell:()=>DN,cropping2D:()=>UI,dense:()=>qI,depthwiseConv2d:()=>HI,dot:()=>oN,dropout:()=>KI,elu:()=>RI,embedding:()=>eN,flatten:()=>YI,gaussianDropout:()=>GN,gaussianNoise:()=>UN,globalAveragePooling1d:()=>wN,globalAveragePooling2d:()=>vN,globalMaxPool1d:()=>PN,globalMaxPool2d:()=>BN,globalMaxPooling1d:()=>kN,globalMaxPooling2d:()=>IN,gru:()=>CN,gruCell:()=>$N,input:()=>hv,inputLayer:()=>AI,layerNormalization:()=>uN,leakyReLU:()=>_I,lstm:()=>EN,lstmCell:()=>AN,masking:()=>jN,maxPool1d:()=>WN,maxPool2d:()=>VN,maxPooling1d:()=>NN,maxPooling2d:()=>SN,maxPooling3d:()=>TN,maximum:()=>rN,minimum:()=>aN,multiply:()=>iN,permute:()=>QI,prelu:()=>DI,randomWidth:()=>ZN,reLU:()=>FI,repeatVector:()=>ZI,rescaling:()=>qN,reshape:()=>JI,resizing:()=>XN,rnn:()=>ON,separableConv2d:()=>VI,simpleRNN:()=>RN,simpleRNNCell:()=>FN,softmax:()=>OI,spatialDropout1d:()=>XI,stackedRNNCells:()=>MN,thresholdedReLU:()=>MI,timeDistributed:()=>zN,upSampling2d:()=>GI,zeroPadding2d:()=>cN});var k={};n.r(k),n.d(k,{MAPE:()=>lS,MSE:()=>hS,binaryAccuracy:()=>JN,binaryCrossentropy:()=>QN,categoricalAccuracy:()=>tS,categoricalCrossentropy:()=>nS,cosineProximity:()=>aS,mape:()=>uS,meanAbsoluteError:()=>iS,meanAbsolutePercentageError:()=>oS,meanSquaredError:()=>cS,mse:()=>pS,precision:()=>sS,recall:()=>rS,sparseCategoricalAccuracy:()=>eS});var I={};n.r(I),n.d(I,{modelFromJSON:()=>iv});var N={};n.r(N),n.d(N,{l1:()=>fS,l1l2:()=>dS,l2:()=>mS});var S={};n.r(S),n.d(S,{json:()=>OS});var T={};n.r(T),n.d(T,{json:()=>MS});var C={};n.r(C),n.d(C,{json:()=>LS});var $={};n.r($),n.d($,{json:()=>zS});var E={};n.r(E),n.d(E,{json:()=>PS});var A={};n.r(A),n.d(A,{json:()=>BS});var R={};n.r(R),n.d(R,{json:()=>WS});var F={};n.r(F),n.d(F,{json:()=>VS});var _={};n.r(_),n.d(_,{json:()=>US});var D={};n.r(D),n.d(D,{json:()=>GS});var O={};n.r(O),n.d(O,{json:()=>HS});var M={};n.r(M),n.d(M,{json:()=>jS});var L={};n.r(L),n.d(L,{json:()=>qS});var z={};n.r(z),n.d(z,{json:()=>KS});var P={};n.r(P),n.d(P,{json:()=>XS});var B={};n.r(B),n.d(B,{json:()=>YS});var W={};n.r(W),n.d(W,{json:()=>ZS});var V={};n.r(V),n.d(V,{json:()=>JS});var U={};n.r(U),n.d(U,{json:()=>QS});var G={};n.r(G),n.d(G,{OP_SCOPE_SUFFIX:()=>Ya,abs:()=>Jo,acos:()=>Au,acosh:()=>Ru,add:()=>Co,addN:()=>Fu,all:()=>_u,any:()=>Du,argMax:()=>Ou,argMin:()=>Mu,asin:()=>Lu,asinh:()=>zu,atan:()=>Pu,atan2:()=>Bu,atanh:()=>Wu,avgPool:()=>rc,avgPool3d:()=>ac,basicLSTMCell:()=>cc,batchNorm:()=>pc,batchNorm2d:()=>dc,batchNorm3d:()=>fc,batchNorm4d:()=>mc,batchToSpaceND:()=>hc,bincount:()=>gc,bitwiseAnd:()=>yc,booleanMaskAsync:()=>bd,broadcastArgs:()=>bc,broadcastTo:()=>xc,buffer:()=>to,cast:()=>no,ceil:()=>wc,clipByValue:()=>vc,clone:()=>so,complex:()=>Ja,concat:()=>ic,concat1d:()=>kc,concat2d:()=>Ic,concat3d:()=>Nc,concat4d:()=>Sc,conv1d:()=>Cc,conv2d:()=>Tc,conv2dTranspose:()=>Ec,conv3d:()=>Ac,conv3dTranspose:()=>Fc,cos:()=>_c,cosh:()=>Dc,cosineWindow:()=>Sd,cumprod:()=>Oc,cumsum:()=>Mc,denseBincount:()=>Lc,depthToSpace:()=>zc,depthwiseConv2d:()=>Pc,diag:()=>Bc,dilation2d:()=>Wc,div:()=>Eo,divNoNan:()=>Gc,dot:()=>Hc,dropout:()=>Id,einsum:()=>jc,elu:()=>qc,enclosingPowerOfTwo:()=>Nd,ensureShape:()=>Kc,equal:()=>Vc,erf:()=>Xc,euclideanNorm:()=>uh,exp:()=>ch,expandDims:()=>hh,expm1:()=>ph,eye:()=>fh,fft:()=>jp,fill:()=>qo,floor:()=>mh,floorDiv:()=>$o,fused:()=>m,gather:()=>gh,gatherND:()=>kd,greater:()=>yh,greaterEqual:()=>bh,ifft:()=>qp,imag:()=>Al,image:()=>Mf,inTopKAsync:()=>Td,irfft:()=>Kp,isFinite:()=>xh,isInf:()=>wh,isNaN:()=>vh,leakyRelu:()=>kh,less:()=>Ih,lessEqual:()=>Nh,linalg:()=>Lf,linspace:()=>Sh,localResponseNormalization:()=>Th,log:()=>Ch,log1p:()=>$h,logSigmoid:()=>Ah,logSoftmax:()=>Rh,logSumExp:()=>Fh,logicalAnd:()=>_h,logicalNot:()=>Dh,logicalOr:()=>Oh,logicalXor:()=>Mh,losses:()=>zf,lowerBound:()=>Ph,matMul:()=>$l,max:()=>rh,maxPool:()=>Bh,maxPool3d:()=>Wh,maxPoolWithArgmax:()=>Vh,maximum:()=>nl,mean:()=>Uh,meshgrid:()=>jh,min:()=>ah,minimum:()=>qh,mirrorPad:()=>Kh,mod:()=>Xh,moments:()=>Yh,movingAverage:()=>xd,mul:()=>Ao,multiRNNCell:()=>Zh,multinomial:()=>Jh,neg:()=>Rl,norm:()=>lh,notEqual:()=>Qh,oneHot:()=>El,ones:()=>Hh,onesLike:()=>ep,op:()=>Za,outerProduct:()=>tp,pad:()=>np,pad1d:()=>sp,pad2d:()=>rp,pad3d:()=>ap,pad4d:()=>ip,pool:()=>lp,pow:()=>Xo,prelu:()=>up,print:()=>ro,prod:()=>cp,raggedGather:()=>hp,raggedRange:()=>pp,raggedTensorToTensor:()=>dp,rand:()=>fp,randomGamma:()=>xp,randomNormal:()=>wp,randomStandardNormal:()=>vp,randomUniform:()=>kp,randomUniformInt:()=>Ip,range:()=>Np,real:()=>Fl,reciprocal:()=>Sp,relu:()=>Tp,relu6:()=>Cp,reshape:()=>sc,reverse:()=>$p,reverse1d:()=>Ep,reverse2d:()=>Ap,reverse3d:()=>Rp,reverse4d:()=>Fp,rfft:()=>Yp,round:()=>_p,rsqrt:()=>Dp,scalar:()=>Wo,scatterND:()=>wd,searchSorted:()=>zh,selu:()=>Op,separableConv2d:()=>Mp,setdiff1dAsync:()=>Lp,sigmoid:()=>oc,sign:()=>zp,signal:()=>Of,sin:()=>Pp,sinh:()=>Bp,slice:()=>lc,slice1d:()=>Wp,slice2d:()=>Vp,slice3d:()=>Up,slice4d:()=>Gp,softmax:()=>Hp,softplus:()=>Eh,spaceToBatchND:()=>op,sparse:()=>Pf,sparseToDense:()=>vd,spectral:()=>Df,split:()=>Xp,sqrt:()=>Ro,square:()=>Fo,squaredDifference:()=>Zp,squeeze:()=>Jp,stack:()=>Qp,step:()=>ed,stridedSlice:()=>td,string:()=>Bf,sub:()=>Yo,sum:()=>ih,tan:()=>nd,tanh:()=>uc,tensor:()=>ei,tensor1d:()=>sd,tensor2d:()=>rd,tensor3d:()=>Ol,tensor4d:()=>ad,tensor5d:()=>id,tensor6d:()=>od,tensorScatterUpdate:()=>ld,tile:()=>dh,topk:()=>ud,transpose:()=>_l,truncatedNormal:()=>cd,unique:()=>hd,unsortedSegmentSum:()=>pd,unstack:()=>dd,upperBound:()=>fd,variable:()=>md,where:()=>Uc,whereAsync:()=>yd,zeros:()=>Gh,zerosLike:()=>_o});var H={};n.r(H),n.d(H,{CSVDataset:()=>DC,Dataset:()=>kC,FileDataSource:()=>qC,TextLineDataset:()=>CC,URLDataSource:()=>KC,array:()=>NC,csv:()=>XC,func:()=>YC,generator:()=>ZC,microphone:()=>QC,version_data:()=>e$,webcam:()=>JC,zip:()=>SC});var j={};n.r(j),n.d(j,{addImpl:()=>x$,bincountImpl:()=>I$,bincountReduceImpl:()=>N$,bitwiseAndImpl:()=>S$,castImpl:()=>f$,ceilImpl:()=>R$,concatImpl:()=>D$,equalImpl:()=>O$,expImpl:()=>z$,expm1Impl:()=>W$,floorDivImpl:()=>q$,floorImpl:()=>G$,gatherNdImpl:()=>Y$,gatherV2Impl:()=>Z$,greaterEqualImpl:()=>tE,greaterImpl:()=>J$,lessEqualImpl:()=>oE,lessImpl:()=>rE,linSpaceImpl:()=>cE,logImpl:()=>hE,maxImpl:()=>fE,maximumImpl:()=>mE,minimumImpl:()=>bE,multiplyImpl:()=>vE,negImpl:()=>SE,notEqualImpl:()=>CE,prodImpl:()=>_E,raggedGatherImpl:()=>zE,raggedRangeImpl:()=>BE,raggedTensorToTensorImpl:()=>HE,rangeImpl:()=>jE,rsqrtImpl:()=>qE,scatterImpl:()=>YE,sigmoidImpl:()=>ZE,simpleAbsImpl:()=>r$,sliceImpl:()=>eA,sparseFillEmptyRowsImpl:()=>sA,sparseReshapeImpl:()=>rA,sparseSegmentReductionImpl:()=>aA,sqrtImpl:()=>iA,squaredDifferenceImpl:()=>uA,staticRegexReplaceImpl:()=>pA,stridedSliceImpl:()=>mA,stringNGramsImpl:()=>yA,stringSplitImpl:()=>xA,stringToHashBucketFastImpl:()=>wA,subImpl:()=>vA,tileImpl:()=>SA,topKImpl:()=>$A,transposeImpl:()=>AE,uniqueImpl:()=>EA});var q={};n.r(q),n.d(q,{assertNotComplex:()=>GO,bindCanvasToFramebuffer:()=>bO,bindColorTextureToFramebuffer:()=>xO,bindTextureToProgramUniformSampler:()=>yO,bindTextureUnit:()=>dO,bindVertexBufferToProgramAttribute:()=>pO,callAndCheck:()=>qD,canBeRepresented:()=>YD,createFragmentShader:()=>eO,createFramebuffer:()=>hO,createProgram:()=>sO,createStaticIndexBuffer:()=>oO,createStaticVertexBuffer:()=>iO,createTexture:()=>uO,createVertexShader:()=>QD,getBatchDim:()=>SO,getExtensionOrThrow:()=>JD,getFramebufferErrorMessage:()=>kO,getMaxTexturesInShader:()=>MO,getNumChannels:()=>lO,getProgramUniformLocation:()=>gO,getProgramUniformLocationOrThrow:()=>mO,getRowsCols:()=>TO,getShapeAs3D:()=>CO,getTextureShapeFromLogicalShape:()=>$O,getWebGLDisjointQueryTimerVersion:()=>LO,getWebGLErrorMessage:()=>ZD,getWebGLMaxTextureSize:()=>_O,hasExtension:()=>zO,isCapableOfRenderingToFloatTexture:()=>BO,isDownloadFloatTextureEnabled:()=>WO,isReshapeFree:()=>AO,isWebGLFenceEnabled:()=>UO,isWebGLVersionEnabled:()=>PO,linkProgram:()=>rO,logShaderSourceAndInfoLog:()=>nO,resetMaxTextureSize:()=>DO,resetMaxTexturesInShader:()=>OO,unbindColorTextureFromFramebuffer:()=>wO,unbindTextureUnit:()=>fO,validateFramebuffer:()=>vO,validateProgram:()=>aO,validateTextureSize:()=>cO});var K={};n.r(K),n.d(K,{bindVertexProgramAttributeStreams:()=>LM,createBufferFromOutputTexture:()=>BM,createFloat16MatrixTexture:()=>AM,createFloat16PackedMatrixTexture:()=>MM,createFloat32MatrixTexture:()=>$M,createIndexBuffer:()=>SM,createPackedMatrixTexture:()=>DM,createUnsignedBytesMatrixTexture:()=>FM,createVertexBuffer:()=>NM,createVertexShader:()=>IM,downloadByteEncodedFloatMatrixFromOutputTexture:()=>VM,downloadFloat32MatrixFromBuffer:()=>WM,downloadMatrixFromPackedOutputTexture:()=>GM,downloadPackedMatrixFromBuffer:()=>UM,getInternalFormatForFloat16MatrixTexture:()=>EM,getInternalFormatForFloat16PackedMatrixTexture:()=>OM,getInternalFormatForFloat32MatrixTexture:()=>CM,getInternalFormatForPackedMatrixTexture:()=>_M,getInternalFormatForUnsignedBytesMatrixTexture:()=>RM,uploadDenseMatrixToTexture:()=>zM,uploadPixelDataToTexture:()=>PM});class X{constructor(e,t){this.backend=e,this.dataMover=t,this.data=new WeakMap,this.dataIdsCount=0}get(e){return this.data.has(e)||this.dataMover.moveData(this.backend,e),this.data.get(e)}set(e,t){this.dataIdsCount++,this.data.set(e,t)}has(e){return this.data.has(e)}delete(e){return this.dataIdsCount--,this.data.delete(e)}numDataIds(){return this.dataIdsCount}}class Y{refCount(e){return Z("refCount")}incRef(e){return Z("incRef")}timerAvailable(){return!0}time(e){return Z("time")}read(e){return Z("read")}readSync(e){return Z("readSync")}readToGPU(e,t){return Z("readToGPU")}numDataIds(){return Z("numDataIds")}disposeData(e,t){return Z("disposeData")}write(e,t,n){return Z("write")}move(e,t,n,s,r){return Z("move")}createTensorFromGPUData(e,t,n){return Z("createTensorFromGPUData")}memory(){return Z("memory")}floatPrecision(){return Z("floatPrecision")}epsilon(){return 32===this.floatPrecision()?1e-7:1e-4}dispose(){return Z("dispose")}}function Z(e){throw new Error(`'${e}' not yet implemented or not found in the registry. This kernel may not be supported by the tfjs backend you have chosen`)}function J(e){let t=e.length,n=0;for(;t>0;)n=Math.random()*t|0,t--,ne(e,t,n)}function Q(e,t){if(e.length!==t.length)throw new Error(`Array sizes must match to be shuffled together First array length was ${e.length}Second array length was ${t.length}`);let n=e.length,s=0;for(;n>0;)s=Math.random()*n|0,n--,ne(e,n,s),ne(t,n,s)}function ee(e,t,n){return Math.max(e,Math.min(t,n))}function te(e){return e%2==0?e:e+1}function ne(e,t,n){const s=e[t];e[t]=e[n],e[n]=s}function se(e){let t=0;for(let n=0;n<e.length;n++)t+=e[n];return t}function re(e,t){const n=Math.random();return t*n+(1-n)*e}function ae(e,t){let n=0;for(let s=0;s<e.length;s++){const r=Number(e[s])-Number(t[s]);n+=r*r}return n}function ie(e,t){if(!e)throw new Error("string"==typeof t?t:t())}function oe(e,t,n=""){ie(pe(e,t),(()=>n+` Shapes ${e} and ${t} must match`))}function le(e){ie(null!=e,(()=>"The input to the tensor constructor must be a non-null value."))}function ue(e){if(0===e.length)return 1;let t=e[0];for(let n=1;n<e.length;n++)t*=e[n];return t}function ce(e){return 0===e.length}function he(e,t){if(e===t)return!0;if(null==e||null==t)return!1;if(e.length!==t.length)return!1;for(let n=0;n<e.length;n++)if(null!==e[n]&&null!==t[n]&&e[n]!==t[n])return!1;return!0}function pe(e,t){if(e===t)return!0;if(null==e||null==t)return!1;if(e.length!==t.length)return!1;for(let n=0;n<e.length;n++)if(e[n]!==t[n])return!1;return!0}function de(e){return e%1==0}function fe(e){if(null!=Math.tanh)return Math.tanh(e);if(e===1/0)return 1;if(e===-1/0)return-1;{const t=Math.exp(2*e);return(t-1)/(t+1)}}function me(e){const t=Math.ceil(Math.sqrt(e));return[t,Math.ceil(e/t)]}function ge(e){const t=new Uint32Array(e);for(let n=0;n<e;++n)t[n]=n;return J(t),t}function ye(e,t){return t<=e.length?e:e+" ".repeat(t-e.length)}function be(e,t=(e=>0),n,s){return new Promise(((r,a)=>{let i=0;const o=()=>{if(e())return void r();i++;const l=t(i);null!=n&&i>=n?a():null!=s?s(o,l):setTimeout(o,l)};o()}))}function xe(e,t){let n=1,s=-1;for(let t=0;t<e.length;++t)if(e[t]>=0)n*=e[t];else if(-1===e[t]){if(-1!==s)throw Error(`Shapes can only have 1 implicit size. Found -1 at dim ${s} and dim ${t}`);s=t}else if(e[t]<0)throw Error(`Shapes can not be < 0. Found ${e[t]} at dim ${t}`);if(-1===s){if(t>0&&t!==n)throw Error(`Size(${t}) must match the product of shape ${e}`);return e}if(0===n)throw Error(`Cannot infer the missing size in [${e}] when there are 0 elements`);if(t%n!=0)throw Error(`The implicit shape can't be a fractional number. Got ${t} / ${n}`);const r=e.slice();return r[s]=t/n,r}function we(e,t){const n=t.length;return ie((e=null==e?t.map(((e,t)=>t)):[].concat(e)).every((e=>e>=-n&&e<n)),(()=>`All values in axis param must be in range [-${n}, ${n}) but got axis ${e}`)),ie(e.every((e=>de(e))),(()=>`All values in axis param must be integers but got axis ${e}`)),e.map((e=>e<0?n+e:e))}function ve(e,t){const n=[],s=[],r=null!=t&&Array.isArray(t)&&0===t.length,a=null==t||r?null:we(t,e).sort();let i=0;for(let t=0;t<e.length;++t){if(null!=a){if(a[i]===t&&1!==e[t])throw new Error(`Can't squeeze axis ${t} since its dim '${e[t]}' is not 1`);(null==a[i]||a[i]>t)&&1===e[t]&&(n.push(e[t]),s.push(t)),a[i]<=t&&i++}1!==e[t]&&(n.push(e[t]),s.push(t))}return{newShape:n,keptDims:s}}function ke(e,t){return Ie(e,t)}function Ie(e,t){let n=null;if(null==e||"float32"===e)n=new Float32Array(t);else if("int32"===e)n=new Int32Array(t);else if("bool"===e)n=new Uint8Array(t);else{if("string"!==e)throw new Error(`Unknown data type ${e}`);n=new Array(t)}return n}function Ne(e,t){for(let n=0;n<e.length;n++){const s=e[n];if(isNaN(s)||!isFinite(s))throw Error(`A tensor of type ${t} being uploaded contains ${s}.`)}}function Se(e){return"bool"===e||"complex64"===e||"float32"===e||"int32"===e||"string"===e}function Te(e,t){return"complex64"!==t&&(("float32"!==t||"complex64"===e)&&(("int32"!==t||"float32"===e||"complex64"===e)&&("bool"!==t||"bool"!==e)))}function Ce(e){if("float32"===e||"int32"===e)return 4;if("complex64"===e)return 8;if("bool"===e)return 1;throw new Error(`Unknown dtype ${e}`)}function $e(e){if(null==e)return 0;let t=0;return e.forEach((e=>t+=e.length)),t}function Ee(e){return"string"==typeof e||e instanceof String}function Ae(e){return"boolean"==typeof e}function Re(e){return"number"==typeof e}function Fe(e){return Array.isArray(e)?Fe(e[0]):e instanceof Float32Array?"float32":e instanceof Int32Array||e instanceof Uint8Array||e instanceof Uint8ClampedArray?"int32":Re(e)?"float32":Ee(e)?"string":Ae(e)?"bool":"float32"}function _e(e){return!!(e&&e.constructor&&e.call&&e.apply)}function De(e,t){for(let n=t;n<e;++n)if(e%n==0)return n;return e}function Oe(e){const t=e.length;if(t<2)return[];const n=new Array(t-1);n[t-2]=e[t-1];for(let s=t-3;s>=0;--s)n[s]=n[s+1]*e[s+1];return n}function Me(e,t,n,s=!1){const r=new Array;if(1===t.length){const a=t[0]*(s?2:1);for(let t=0;t<a;t++)r[t]=n[e+t]}else{const a=t[0],i=t.slice(1),o=i.reduce(((e,t)=>e*t))*(s?2:1);for(let t=0;t<a;t++)r[t]=Me(e+t*o,i,n,s)}return r}function Le(e,t,n=!1){if(0===e.length)return t[0];const s=e.reduce(((e,t)=>e*t))*(n?2:1);if(0===s)return[];if(s!==t.length)throw new Error(`[${e}] does not match the input size ${t.length}${n?" for a complex tensor":""}.`);return Me(0,e,t,n)}function ze(e,t){if(Array.isArray(e))return e;if("float32"===t)return e instanceof Float32Array?e:new Float32Array(e);if("int32"===t)return e instanceof Int32Array?e:new Int32Array(e);if("bool"===t||"string"===t)return Uint8Array.from(new Int32Array(e));throw new Error(`Unknown dtype ${t}`)}function Pe(e,t){const n=Be(e,t);for(let e=0;e<n.length;e++)n[e]=1;return n}function Be(e,t){if(null==t||"float32"===t||"complex64"===t)return new Float32Array(e);if("int32"===t)return new Int32Array(e);if("bool"===t)return new Uint8Array(e);throw new Error(`Unknown data type ${t}`)}function We(e,t){const n=e.reduce(((e,t)=>e*t),1);if(null==t||"float32"===t)return Le(e,new Float32Array(n));if("int32"===t)return Le(e,new Int32Array(n));if("bool"===t)return Le(e,new Uint8Array(n));throw new Error(`Unknown data type ${t}`)}function Ve(e){e.forEach((t=>{ie(Number.isInteger(t)&&t>=0,(()=>`Tensor must have a shape comprised of positive integers but got shape [${e}].`))}))}function Ue(e,t,n){if(0===t)return 0;if(1===t)return e[0];let s=e[e.length-1];for(let t=0;t<e.length-1;++t)s+=n[t]*e[t];return s}function Ge(e,t,n){if(0===t)return[];if(1===t)return[e];const s=new Array(t);for(let t=0;t<s.length-1;++t)s[t]=Math.floor(e/n[t]),e-=s[t]*n[t];return s[s.length-1]=e,s}function He(e){return e&&e.then&&"function"==typeof e.then}const je="tfjsflags";class qe{constructor(e){this.global=e,this.flags={},this.flagRegistry={},this.urlFlags={},this.getQueryParams=Ke,this.populateURLFlags()}setPlatform(e,t){null!=this.platform&&(Xe().getBool("IS_TEST")||Xe().getBool("PROD")||console.warn(`Platform ${this.platformName} has already been set. Overwriting the platform with ${e}.`)),this.platformName=e,this.platform=t}registerFlag(e,t,n){if(this.flagRegistry[e]={evaluationFn:t,setHook:n},null!=this.urlFlags[e]){const t=this.urlFlags[e];Xe().getBool("IS_TEST")||Xe().getBool("PROD")||console.warn(`Setting feature override from URL ${e}: ${t}.`),this.set(e,t)}}async getAsync(e){return e in this.flags||(this.flags[e]=await this.evaluateFlag(e)),this.flags[e]}get(e){if(e in this.flags)return this.flags[e];const t=this.evaluateFlag(e);if(He(t))throw new Error(`Flag ${e} cannot be synchronously evaluated. Please use getAsync() instead.`);return this.flags[e]=t,this.flags[e]}getNumber(e){return this.get(e)}getBool(e){return this.get(e)}getString(e){return this.get(e)}getFlags(){return this.flags}get features(){return this.flags}set(e,t){if(null==this.flagRegistry[e])throw new Error(`Cannot set flag ${e} as it has not been registered.`);this.flags[e]=t,null!=this.flagRegistry[e].setHook&&this.flagRegistry[e].setHook(t)}evaluateFlag(e){if(null==this.flagRegistry[e])throw new Error(`Cannot evaluate flag '${e}': no evaluation function found.`);return this.flagRegistry[e].evaluationFn()}setFlags(e){this.flags=Object.assign({},e)}reset(){this.flags={},this.urlFlags={},this.populateURLFlags()}populateURLFlags(){if(void 0===this.global||void 0===this.global.location||void 0===this.global.location.search)return;const e=this.getQueryParams(this.global.location.search);if(je in e){e[je].split(",").forEach((e=>{const[t,n]=e.split(":");this.urlFlags[t]=function(e,t){const n=t.toLowerCase();return"true"===n||"false"===n?"true"===n:""+ +n===n?+n:t}(0,n)}))}}}function Ke(e){const t={};return e.replace(/[?&]([^=?&]+)(?:=([^&]*))?/g,((e,...n)=>(function(e,t,n){e[decodeURIComponent(t)]=decodeURIComponent(n||"")}(t,n[0],n[1]),n.join("=")))),t}function Xe(){return Ze}let Ye,Ze=null;function Je(){if(null==Ye){let e;if("undefined"!=typeof window)e=window;else if(void 0!==n.g)e=n.g;else if("undefined"!=typeof process)e=process;else{if("undefined"==typeof self)throw new Error("Could not find a global object");e=self}Ye=e}return Ye}function Qe(e,t){const n=function(){const e=Je();return null==e._tfGlobals&&(e._tfGlobals=new Map),e._tfGlobals}();if(n.has(e))return n.get(e);{const s=t();return n.set(e,s),n.get(e)}}const et="Abs",tt="Acos",nt="Acosh",st="Add",rt="AddN",at="All",it="Any",ot="ArgMax",lt="ArgMin",ut="Asin",ct="Asinh",ht="Atan",pt="Atanh",dt="Atan2",ft="AvgPool",mt="AvgPoolGrad",gt="AvgPool3D",yt="AvgPool3DGrad",bt="BatchMatMul",xt="BatchToSpaceND",wt="Bincount",vt="BitwiseAnd",kt="BroadcastTo",It="BroadcastArgs",Nt="Cast",St="Ceil",Tt="ClipByValue",Ct="Complex",$t="ComplexAbs",Et="Concat",At="Conv2D",Rt="Conv2DBackpropFilter",Ft="Conv2DBackpropInput",_t="Conv3D",Dt="Conv3DBackpropFilterV2",Ot="Conv3DBackpropInputV2",Mt="Cos",Lt="Cosh",zt="Cumprod",Pt="Cumsum",Bt="CropAndResize",Wt="DenseBincount",Vt="DepthToSpace",Ut="DepthwiseConv2dNative",Gt="DepthwiseConv2dNativeBackpropFilter",Ht="DepthwiseConv2dNativeBackpropInput",jt="Diag",qt="Dilation2D",Kt="Dilation2DBackpropInput",Xt="Dilation2DBackpropFilter",Yt="Draw",Zt="RealDiv",Jt="Einsum",Qt="Elu",en="EluGrad",tn="Erf",nn="Equal",sn="Exp",rn="ExpandDims",an="Expm1",on="FFT",ln="Fill",un="FlipLeftRight",cn="Floor",hn="FloorDiv",pn="FusedBatchNorm",dn="GatherV2",fn="GatherNd",mn="Greater",gn="GreaterEqual",yn="Identity",bn="IFFT",xn="Imag",wn="IsFinite",vn="IsInf",kn="IsNan",In="LeakyRelu",Nn="Less",Sn="LessEqual",Tn="LinSpace",Cn="Log",$n="Log1p",En="LogicalAnd",An="LogicalNot",Rn="LogicalOr",Fn="LogicalXor",_n="LogSoftmax",Dn="LowerBound",On="LRN",Mn="LRNGrad",Ln="MatrixBandPart",zn="Max",Pn="Maximum",Bn="MaxPool",Wn="MaxPoolGrad",Vn="MaxPool3D",Un="MaxPool3DGrad",Gn="MaxPoolWithArgmax",Hn="Mean",jn="Min",qn="Minimum",Kn="MirrorPad",Xn="Mod",Yn="Multinomial",Zn="Multiply",Jn="Neg",Qn="NotEqual",es="NonMaxSuppressionV3",ts="NonMaxSuppressionV4",ns="NonMaxSuppressionV5",ss="OnesLike",rs="OneHot",as="Pack",is="PadV2",os="Pool",ls="Pow",us="Prelu",cs="Prod",hs="RaggedGather",ps="RaggedRange",ds="RaggedTensorToTensor",fs="Range",ms="Real",gs="Reciprocal",ys="Relu",bs="Reshape",xs="ResizeNearestNeighbor",ws="ResizeNearestNeighborGrad",vs="ResizeBilinear",ks="ResizeBilinearGrad",Is="Relu6",Ns="Reverse",Ss="Round",Ts="Rsqrt",Cs="ScatterNd",$s="TensorScatterUpdate",Es="SearchSorted",As="Select",Rs="Selu",Fs="Slice",_s="Sin",Ds="Sinh",Os="Sign",Ms="Sigmoid",Ls="Softplus",zs="Sqrt",Ps="Sum",Bs="SpaceToBatchND",Ws="SplitV",Vs="Softmax",Us="SparseFillEmptyRows",Gs="SparseReshape",Hs="SparseSegmentMean",js="SparseSegmentSum",qs="SparseToDense",Ks="SquaredDifference",Xs="Square",Ys="StaticRegexReplace",Zs="StridedSlice",Js="StringNGrams",Qs="StringSplit",er="StringToHashBucketFast",tr="Sub",nr="Tan",sr="Tanh",rr="Tile",ar="TopK",ir="Transform",or="Transpose",lr="Unique",ur="Unpack",cr="UnsortedSegmentSum",hr="UpperBound",pr="ZerosLike",dr="Step",fr="FromPixels",mr="RotateWithOffset",gr="_FusedMatMul",yr="FusedConv2D",br="FusedDepthwiseConv2D";function xr(...e){Xe().getBool("IS_TEST")||Xe().getBool("PROD")||console.warn(...e)}function wr(...e){Xe().getBool("IS_TEST")||Xe().getBool("PROD")||console.log(...e)}const vr=Qe("kernelRegistry",(()=>new Map)),kr=Qe("gradRegistry",(()=>new Map));function Ir(e,t){const n=Rr(e,t);return vr.get(n)}function Nr(e){return kr.get(e)}function Sr(e){const t=vr.entries(),n=[];for(;;){const{done:s,value:r}=t.next();if(s)break;const[a,i]=r,[o]=a.split("_");o===e&&n.push(i)}return n}function Tr(e){const{kernelName:t,backendName:n}=e,s=Rr(t,n);vr.has(s)&&xr(`The kernel '${t}' for backend '${n}' is already registered`),vr.set(s,e)}function Cr(e){const{kernelName:t}=e;kr.has(t)&&Xe().getBool("DEBUG")&&xr(`Overriding the gradient for '${t}'`),kr.set(t,e)}function $r(e,t){const n=Rr(e,t);if(!vr.has(n))throw new Error(`The kernel '${e}' for backend '${t}' is not registered`);vr.delete(n)}function Er(e){if(!kr.has(e))throw new Error(`The gradient '${e}' for backend is not registered`);kr.delete(e)}function Ar(e,t){Sr(e).forEach((e=>{Tr(Object.assign({},e,{backendName:t}))}))}function Rr(e,t){return`${t}_${e}`}function Fr(e){return e instanceof Float32Array||e instanceof Int32Array||e instanceof Uint8Array||e instanceof Uint8ClampedArray}var _r=n(720);const Dr=n.n(_r)()||_r;function Or(e){return Dr.fromString(e,!0,16)}const Mr=Or("c3a5c85c97cb3127"),Lr=Or("b492b66fbe98f273"),zr=Or("9ae16a3b2f90404f");function Pr(e){return e.xor(e.shru(47))}function Br(e,t,n){const s=e.slice(t,t+n);return Dr.fromBytes(Array.from(s),!0,!0)}function Wr(e,t){return Br(e,t,8)}function Vr(e,t){return Br(e,t,4)}function Ur(e,t){return 0===t?e:e.shru(t).or(e.shl(64-t))}function Gr(e,t,n=Or("9ddfea08eb382d69")){let s=e.xor(t).mul(n);s=s.xor(s.shru(47));let r=t.xor(s).mul(n);return r=r.xor(r.shru(47)),r=r.mul(n),r}function Hr(e,t,n,s){return function(e,t,n,s,r,a){r=r.add(e),a=Ur(a.add(r).add(s),21);const i=r;return r=(r=r.add(t)).add(n),a=a.add(Ur(r,44)),[r.add(s),a.add(i)]}(Wr(e,t),Wr(e,t+8),Wr(e,t+16),Wr(e,t+24),n,s)}function jr(e,t=e.length){const n=Dr.fromNumber(81,!0);if(t<=32)return t<=16?function(e,t=e.length){if(t>=8){const n=zr.add(2*t),s=Wr(e,0).add(zr),r=Wr(e,t-8);return Gr(Ur(r,37).mul(n).add(s),Ur(s,25).add(r).mul(n),n)}if(t>=4){const n=zr.add(2*t);return Gr(Vr(e,0).shl(3).add(t),Vr(e,t-4),n)}if(t>0){const n=e[0]+(e[t>>1]<<8),s=t+(e[t-1]<<2);return Pr(zr.mul(n).xor(Mr.mul(s))).mul(zr)}return zr}(e,t):function(e,t=e.length){const n=zr.add(2*t),s=Wr(e,0).mul(Lr),r=Wr(e,8),a=Wr(e,t-8).mul(n),i=Wr(e,t-16).mul(zr);return Gr(Ur(s.add(r),43).add(Ur(a,30)).add(i),s.add(Ur(r.add(zr),18)).add(a),n)}(e,t);if(t<=64)return function(e,t=e.length){const n=zr.add(2*t),s=Wr(e,0).mul(zr),r=Wr(e,8),a=Wr(e,t-8).mul(n),i=Wr(e,t-16).mul(zr),o=Ur(s.add(r),43).add(Ur(a,30)).add(i),l=Gr(o,s.add(Ur(r.add(zr),18)).add(a),n),u=Wr(e,16).mul(n),c=Wr(e,24),h=o.add(Wr(e,t-32)).mul(n),p=l.add(Wr(e,t-24)).mul(n);return Gr(Ur(u.add(c),43).add(Ur(h,30)).add(p),u.add(Ur(c.add(s),18)).add(h),n)}(e,t);let s=n,r=n.mul(Lr).add(113),a=Pr(r.mul(zr).add(113)).mul(zr),i=[Dr.UZERO,Dr.UZERO],o=[Dr.UZERO,Dr.UZERO];s=s.mul(zr).add(Wr(e,0));let l=0;const u=64*(t-1>>6),c=u+(t-1&63)-63;do{s=Ur(s.add(r).add(i[0]).add(Wr(e,l+8)),37).mul(Lr),r=Ur(r.add(i[1]).add(Wr(e,l+48)),42).mul(Lr),s=s.xor(o[1]),r=r.add(i[0]).add(Wr(e,l+40)),a=Ur(a.add(o[0]),33).mul(Lr),i=Hr(e,l,i[1].mul(Lr),s.add(o[0])),o=Hr(e,l+32,a.add(o[1]),r.add(Wr(e,l+16))),[a,s]=[s,a],l+=64}while(l!==u);const h=Lr.add(a.and(255).shl(1));return l=c,o[0]=o[0].add(t-1&63),i[0]=i[0].add(o[0]),o[0]=o[0].add(i[0]),s=Ur(s.add(r).add(i[0]).add(Wr(e,l+8)),37).mul(h),r=Ur(r.add(i[1]).add(Wr(e,l+48)),42).mul(h),s=s.xor(o[1].mul(9)),r=r.add(i[0].mul(9).add(Wr(e,l+40))),a=Ur(a.add(o[0]),33).mul(h),i=Hr(e,l,i[1].mul(h),s.add(o[0])),o=Hr(e,l+32,a.add(o[1]),r.add(Wr(e,l+16))),[a,s]=[s,a],Gr(Gr(i[0],o[0],h).add(Pr(r).mul(Mr)).add(a),Gr(i[1],o[1],h).add(s),h)}function qr(e,t){return"string"===t?Zr(e):Kr([e],t)}function Kr(e,t){if("string"===t)throw new Error("Cannot convert a string[] to a TypedArray");if(Array.isArray(e)&&(e=ea(e)),Xe().getBool("DEBUG")&&Ne(e,t),function(e,t){return e instanceof Float32Array&&"float32"===t||e instanceof Int32Array&&"int32"===t||e instanceof Uint8Array&&"bool"===t}(e,t))return e;if(null==t||"float32"===t||"complex64"===t)return new Float32Array(e);if("int32"===t)return new Int32Array(e);if("bool"===t){const t=new Uint8Array(e.length);for(let n=0;n<t.length;++n)0!==Math.round(e[n])&&(t[n]=1);return t}throw new Error(`Unknown data type ${t}`)}function Xr(){return Xe().platform.now()}function Yr(e,t){return Xe().platform.fetch(e,t)}function Zr(e,t="utf-8"){return t=t||"utf-8",Xe().platform.encode(e,t)}function Jr(e,t="utf-8"){return t=t||"utf-8",Xe().platform.decode(e,t)}function Qr(e){return null!=Xe().platform.isTypedArray?Xe().platform.isTypedArray(e):Fr(e)}function ea(e,t=[],n=!1){if(null==t&&(t=[]),"boolean"==typeof e||"number"==typeof e||"string"==typeof e||He(e)||null==e||Qr(e)&&n)t.push(e);else if(Array.isArray(e)||Qr(e))for(let s=0;s<e.length;++s)ea(e[s],t,n);else{let s=-1;for(const t of Object.keys(e))/^([1-9]+[0-9]*|0)$/.test(t)&&(s=Math.max(s,Number(t)));for(let r=0;r<=s;r++)ea(e[r],t,n)}return t}class ta{constructor(e,t){this.backendTimer=e,this.logger=t,null==t&&(this.logger=new sa)}profileKernel(e,t,n){let s;const r=()=>{s=n()};let a;const i=Xr();if(this.backendTimer.timerAvailable())a=this.backendTimer.time(r);else{r();for(const e of s)e.dataSync();a=Promise.resolve({kernelMs:Xr()-i})}if(Xe().getBool("CHECK_COMPUTATION_FOR_ERRORS"))for(let t=0;t<s.length;t++){const n=s[t];n.data().then((t=>{na(t,n.dtype,e)}))}return{kernelName:e,outputs:s,inputs:t,timeMs:a.then((e=>e.kernelMs)),extraInfo:a.then((e=>null!=e.getExtraProfileInfo?e.getExtraProfileInfo():""))}}logKernelProfile(e){const{kernelName:t,outputs:n,timeMs:s,inputs:r,extraInfo:a}=e;n.forEach((e=>{Promise.all([e.data(),s,a]).then((n=>{this.logger.logKernelProfile(t,e,n[0],n[1],r,n[2])}))}))}}function na(e,t,n){if("float32"!==t)return!1;for(let t=0;t<e.length;t++){const s=e[t];if(isNaN(s)||!isFinite(s))return console.warn(`Found ${s} in the result of '${n}'`),!0}return!1}class sa{logKernelProfile(e,t,n,s,r,a){const i="number"==typeof s?ye(`${s}ms`,9):s.error,o=ye(e,25),l=t.rank,u=t.size,c=ye(t.shape.toString(),14);let h="";for(const e in r){const n=r[e];if(null!=n){const s=n.shape||t.shape,r=s.length;h+=`${e}: ${r}D ${r>0?s:""} `}}console.log(`%c${o}\t%c${i}\t%c${l}D ${c}\t%c${u}\t%c${h}\t%c${a}`,"font-weight:bold","color:red","color:blue","color: orange","color: green","color: steelblue")}}const ra=20,aa=3,ia=7;function oa(e,t,n,s){const r=Oe(t),a=function(e,t,n,s){const r=ue(t),a=s[s.length-1],i=new Array(a).fill(0),o=t.length,l="complex64"===n?ha(e):e;if(o>1)for(let e=0;e<r/a;e++){const t=e*a;for(let e=0;e<a;e++)i[e]=Math.max(i[e],la(l[t+e],0,n).length)}return i}(e,t,n,r),i=t.length,o=ca(e,t,n,r,a),l=["Tensor"];return s&&(l.push(`  dtype: ${n}`),l.push(`  rank: ${i}`),l.push(`  shape: [${t}]`),l.push("  values:")),l.push(o.map((e=>"    "+e)).join("\n")),l.join("\n")}function la(e,t,n){let s;return s=Array.isArray(e)?`${parseFloat(e[0].toFixed(ia))} + ${parseFloat(e[1].toFixed(ia))}j`:Ee(e)?`'${e}'`:"bool"===n?ua(e):parseFloat(e.toFixed(ia)).toString(),ye(s,t)}function ua(e){return 0===e?"false":"true"}function ca(e,t,n,s,r,a=!0){const i="complex64"===n?2:1,o=t[0],l=t.length;if(0===l){if("complex64"===n){return[la(ha(e)[0],0,n)]}return"bool"===n?[ua(e[0])]:[e[0].toString()]}if(1===l){if(o>ra){const t=aa*i;let s=Array.from(e.slice(0,t)),a=Array.from(e.slice((o-aa)*i,o*i));return"complex64"===n&&(s=ha(s),a=ha(a)),["["+s.map(((e,t)=>la(e,r[t],n))).join(", ")+", ..., "+a.map(((e,t)=>la(e,r[o-aa+t],n))).join(", ")+"]"]}return["["+("complex64"===n?ha(e):Array.from(e)).map(((e,t)=>la(e,r[t],n))).join(", ")+"]"]}const u=t.slice(1),c=s.slice(1),h=s[0]*i,p=[];if(o>ra){for(let t=0;t<aa;t++){const s=t*h,a=s+h;p.push(...ca(e.slice(s,a),u,n,c,r,!1))}p.push("...");for(let t=o-aa;t<o;t++){const s=t*h,a=s+h;p.push(...ca(e.slice(s,a),u,n,c,r,t===o-1))}}else for(let t=0;t<o;t++){const s=t*h,a=s+h;p.push(...ca(e.slice(s,a),u,n,c,r,t===o-1))}const d=2===l?",":"";p[0]="["+(o>0?p[0]+d:"");for(let e=1;e<p.length-1;e++)p[e]=" "+p[e]+d;let f=",\n";for(let e=2;e<l;e++)f+="\n";return p[p.length-1]=" "+p[p.length-1]+"]"+(a?"":f),p}function ha(e){const t=[];for(let n=0;n<e.length;n+=2)t.push([e[n],e[n+1]]);return t}class pa{constructor(e,t,n){if(this.dtype=t,this.shape=e.slice(),this.size=ue(e),null!=n){const e=n.length;ie(e===this.size,(()=>`Length of values '${e}' does not match the size inferred by the shape '${this.size}'.`))}if("complex64"===t)throw new Error("complex64 dtype TensorBuffers are not supported. Please create a TensorBuffer for the real and imaginary parts separately and call tf.complex(real, imag).");this.values=n||Ie(t,this.size),this.strides=Oe(e)}set(e,...t){0===t.length&&(t=[0]),ie(t.length===this.rank,(()=>`The number of provided coordinates (${t.length}) must match the rank (${this.rank})`));const n=this.locToIndex(t);this.values[n]=e}get(...e){0===e.length&&(e=[0]);let t=0;for(const n of e){if(n<0||n>=this.shape[t]){const t=`Requested out of range element at ${e}.   Buffer shape=${this.shape}`;throw new Error(t)}t++}let n=e[e.length-1];for(let t=0;t<e.length-1;++t)n+=this.strides[t]*e[t];return this.values[n]}locToIndex(e){if(0===this.rank)return 0;if(1===this.rank)return e[0];let t=e[e.length-1];for(let n=0;n<e.length-1;++n)t+=this.strides[n]*e[n];return t}indexToLoc(e){if(0===this.rank)return[];if(1===this.rank)return[e];const t=new Array(this.shape.length);for(let n=0;n<t.length-1;++n)t[n]=Math.floor(e/this.strides[n]),e-=t[n]*this.strides[n];return t[t.length-1]=e,t}get rank(){return this.shape.length}toTensor(){return da().makeTensor(this.values,this.shape,this.dtype)}}let da=null,fa=null,ma=null;class ga{constructor(e,t,n,s){this.kept=!1,this.isDisposedInternal=!1,this.shape=e.slice(),this.dtype=t||"float32",this.size=ue(e),this.strides=Oe(e),this.dataId=n,this.id=s,this.rankType=this.rank<5?this.rank.toString():"higher"}get rank(){return this.shape.length}async buffer(){const e=await this.data();return fa.buffer(this.shape,this.dtype,e)}bufferSync(){return fa.buffer(this.shape,this.dtype,this.dataSync())}async array(){const e=await this.data();return Le(this.shape,e,"complex64"===this.dtype)}arraySync(){return Le(this.shape,this.dataSync(),"complex64"===this.dtype)}async data(){this.throwIfDisposed();const e=da().read(this.dataId);if("string"===this.dtype){const t=await e;try{return t.map((e=>Jr(e)))}catch(e){throw new Error("Failed to decode the string bytes into utf-8. To get the original bytes, call tensor.bytes().")}}return e}dataToGPU(e){return this.throwIfDisposed(),da().readToGPU(this.dataId,e)}dataSync(){this.throwIfDisposed();const e=da().readSync(this.dataId);if("string"===this.dtype)try{return e.map((e=>Jr(e)))}catch(e){throw new Error("Failed to decode the string bytes into utf-8. To get the original bytes, call tensor.bytes().")}return e}async bytes(){this.throwIfDisposed();const e=await da().read(this.dataId);return"string"===this.dtype?e:new Uint8Array(e.buffer)}dispose(){this.isDisposed||(da().disposeTensor(this),this.isDisposedInternal=!0)}get isDisposed(){return this.isDisposedInternal}throwIfDisposed(){if(this.isDisposed)throw new Error("Tensor is disposed.")}print(e=!1){return fa.print(this,e)}clone(){return this.throwIfDisposed(),fa.clone(this)}toString(e=!1){return oa(this.dataSync(),this.shape,this.dtype,e)}cast(e){return this.throwIfDisposed(),fa.cast(this,e)}variable(e=!0,t,n){return this.throwIfDisposed(),da().makeVariable(this,e,t,n)}}function ya(){return Qe("Tensor",(()=>ga))}Object.defineProperty(ga,Symbol.hasInstance,{value:e=>!!e&&null!=e.data&&null!=e.dataSync&&null!=e.throwIfDisposed}),ya();class ba extends ga{constructor(e,t,n,s){super(e.shape,e.dtype,e.dataId,s),this.trainable=t,this.name=n}assign(e){if(e.dtype!==this.dtype)throw new Error(`dtype of the new value (${e.dtype}) and previous value (${this.dtype}) must match`);if(!pe(e.shape,this.shape))throw new Error(`shape of the new value (${e.shape}) and previous value (${this.shape}) must match`);da().disposeTensor(this),this.dataId=e.dataId,da().incRef(this,null)}dispose(){da().disposeVariable(this),this.isDisposedInternal=!0}}var xa,wa,va,ka,Ia;Object.defineProperty(ba,Symbol.hasInstance,{value:e=>e instanceof ga&&null!=e.assign&&e.assign instanceof Function}),function(e){e.R0="R0",e.R1="R1",e.R2="R2",e.R3="R3",e.R4="R4",e.R5="R5",e.R6="R6"}(xa||(xa={})),function(e){e.float32="float32",e.int32="int32",e.bool="int32",e.complex64="complex64"}(wa||(wa={})),function(e){e.float32="float32",e.int32="int32",e.bool="bool",e.complex64="complex64"}(va||(va={})),function(e){e.float32="float32",e.int32="float32",e.bool="float32",e.complex64="complex64"}(ka||(ka={})),function(e){e.float32="complex64",e.int32="complex64",e.bool="complex64",e.complex64="complex64"}(Ia||(Ia={}));const Na={float32:ka,int32:wa,bool:va,complex64:Ia};function Sa(e,t){if("string"===e||"string"===t){if("string"===e&&"string"===t)return"string";throw new Error(`Can not upcast ${e} with ${t}`)}return Na[e][t]}function Ta(e){return Sa(e,"int32")}function Ca(e){return null!=e&&"object"==typeof e&&"texture"in e&&e.texture instanceof WebGLTexture}function $a(e){return"undefined"!=typeof GPUBuffer&&null!=e&&"object"==typeof e&&"buffer"in e&&e.buffer instanceof GPUBuffer}function Ea(e,t){if(e.dtype===t.dtype)return[e,t];const n=Sa(e.dtype,t.dtype);return[e.cast(n),t.cast(n)]}function Aa(e,t){ie(e.dtype===t.dtype,(()=>`The dtypes of the first(${e.dtype}) and second(${t.dtype}) input must match`))}function Ra(e,t){return t.some((t=>t.id===e.id))}function Fa(e){const t=[];return _a(e,t,new Set),t}function _a(e,t,n){if(null==e)return;if(e instanceof ga)return void t.push(e);if(s=e,!Array.isArray(s)&&"object"!=typeof s)return;var s;const r=e;for(const e in r){const s=r[e];n.has(s)||(n.add(s),_a(s,t,n))}}function Da(e){return null!=e.kernelName}class Oa{constructor(){this.registeredVariables={},this.nextTapeNodeId=0,this.numBytes=0,this.numTensors=0,this.numStringTensors=0,this.numDataBuffers=0,this.gradientDepth=0,this.kernelDepth=0,this.scopeStack=[],this.numDataMovesStack=[],this.nextScopeId=0,this.tensorInfo=new WeakMap,this.profiling=!1,this.activeProfile={newBytes:0,newTensors:0,peakBytes:0,kernels:[],result:null,get kernelNames(){return Array.from(new Set(this.kernels.map((e=>e.name))))}}}dispose(){for(const e in this.registeredVariables)this.registeredVariables[e].dispose()}}class Ma{constructor(e){this.ENV=e,this.registry={},this.registryFactory={},this.pendingBackendInitId=0,this.state=new Oa}async ready(){if(null!=this.pendingBackendInit)return this.pendingBackendInit.then((()=>{}));if(null!=this.backendInstance)return;const e=this.getSortedBackends();for(let t=0;t<e.length;t++){const n=e[t];if(await this.initializeBackend(n).success)return void await this.setBackend(n)}throw new Error("Could not initialize any backends, all backend initializations failed.")}get backend(){if(null!=this.pendingBackendInit)throw new Error(`Backend '${this.backendName}' has not yet been initialized. Make sure to await tf.ready() or await tf.setBackend() before calling other methods`);if(null==this.backendInstance){const{name:e,asyncInit:t}=this.initializeBackendsAndReturnBest();if(t)throw new Error(`The highest priority backend '${e}' has not yet been initialized. Make sure to await tf.ready() or await tf.setBackend() before calling other methods`);this.setBackend(e)}return this.backendInstance}backendNames(){return Object.keys(this.registryFactory)}findBackend(e){if(!(e in this.registry)){if(!(e in this.registryFactory))return null;{const{asyncInit:t}=this.initializeBackend(e);if(t)return null}}return this.registry[e]}findBackendFactory(e){return e in this.registryFactory?this.registryFactory[e].factory:null}registerBackend(e,t,n=1){return e in this.registryFactory?(xr(`${e} backend was already registered. Reusing existing backend factory.`),!1):(this.registryFactory[e]={factory:t,priority:n},!0)}async setBackend(e){if(null==this.registryFactory[e])throw new Error(`Backend name '${e}' not found in registry`);if(this.backendName=e,null==this.registry[e]){this.backendInstance=null;const{success:t,asyncInit:n}=this.initializeBackend(e);if(!(n?await t:t))return!1}return this.backendInstance=this.registry[e],this.setupRegisteredKernels(),this.profiler=new ta(this.backendInstance),!0}setupRegisteredKernels(){Sr(this.backendName).forEach((e=>{null!=e.setupFunc&&e.setupFunc(this.backendInstance)}))}disposeRegisteredKernels(e){Sr(e).forEach((t=>{null!=t.disposeFunc&&t.disposeFunc(this.registry[e])}))}initializeBackend(e){const t=this.registryFactory[e];if(null==t)throw new Error(`Cannot initialize backend ${e}, no registration found.`);try{const n=t.factory();if(!n||n instanceof Y||"function"!=typeof n.then)return this.registry[e]=n,{success:!0,asyncInit:!1};{const t=++this.pendingBackendInitId,s=n.then((n=>!(t<this.pendingBackendInitId)&&(this.registry[e]=n,this.pendingBackendInit=null,!0))).catch((n=>(t<this.pendingBackendInitId||(this.pendingBackendInit=null,xr(`Initialization of backend ${e} failed`),xr(n.stack||n.message)),!1)));return this.pendingBackendInit=s,{success:s,asyncInit:!0}}}catch(t){return xr(`Initialization of backend ${e} failed`),xr(t.stack||t.message),{success:!1,asyncInit:!1}}}removeBackend(e){if(!(e in this.registryFactory))throw new Error(`${e} backend not found in registry`);this.backendName===e&&null!=this.pendingBackendInit&&this.pendingBackendInitId++,e in this.registry&&(this.disposeRegisteredKernels(e),this.registry[e].dispose(),delete this.registry[e]),delete this.registryFactory[e],this.backendName===e&&(this.pendingBackendInit=null,this.backendName=null,this.backendInstance=null)}getSortedBackends(){if(0===Object.keys(this.registryFactory).length)throw new Error("No backend found in registry.");return Object.keys(this.registryFactory).sort(((e,t)=>this.registryFactory[t].priority-this.registryFactory[e].priority))}initializeBackendsAndReturnBest(){const e=this.getSortedBackends();for(let t=0;t<e.length;t++){const n=e[t],{success:s,asyncInit:r}=this.initializeBackend(n);if(r||s)return{name:n,asyncInit:r}}throw new Error("Could not initialize any backends, all backend initializations failed.")}moveData(e,t){const n=this.state.tensorInfo.get(t),s=n.backend,r=this.readSync(t),a=s.refCount(t);s.disposeData(t,!0),n.backend=e,e.move(t,r,n.shape,n.dtype,a),this.shouldCheckForMemLeaks()&&this.state.numDataMovesStack[this.state.numDataMovesStack.length-1]++}tidy(e,t){let n,s=null;if(null==t){if("function"!=typeof e)throw new Error("Please provide a function to tidy()");t=e}else{if("string"!=typeof e&&!(e instanceof String))throw new Error("When calling with two arguments, the first argument to tidy() must be a string");if("function"!=typeof t)throw new Error("When calling with two arguments, the 2nd argument to tidy() must be a function");s=e}return this.scopedRun((()=>this.startScope(s)),(()=>this.endScope(n)),(()=>(n=t(),n instanceof Promise&&console.error("Cannot return a Promise inside of tidy."),n)))}scopedRun(e,t,n){e();try{const e=n();return t(),e}catch(e){throw t(),e}}nextTensorId(){return Ma.nextTensorId++}nextVariableId(){return Ma.nextVariableId++}clone(e){const t=za.runKernel(yn,{x:e}),n={x:e};return this.addTapeNode(this.state.activeScope.name,n,[t],(e=>({x:()=>{const t={x:e},n={dtype:"float32"};return za.runKernel(Nt,t,n)}})),[],{}),t}runKernel(e,t,n){null==this.backendName&&this.backend;if(!(null!=Ir(e,this.backendName)))throw new Error(`Kernel '${e}' not registered for backend '${this.backendName}'`);return this.runKernelFunc({kernelName:e,inputs:t,attrs:n})}shouldCheckForMemLeaks(){return this.ENV.getBool("IS_TEST")}checkKernelForMemLeak(e,t,n){const s=this.backend.numDataIds();let r=0;n.forEach((e=>{r+="complex64"===e.dtype?3:1}));const a=this.state.numDataMovesStack[this.state.numDataMovesStack.length-1],i=s-t-r-a;if(i>0)throw new Error(`Backend '${this.backendName}' has an internal memory leak (${i} data ids) after running '${e}'`)}runKernelFunc(e){let t,n=[];const s=this.isTapeOn(),r=this.state.numBytes,a=this.state.numTensors;let i,o;this.shouldCheckForMemLeaks()&&this.state.numDataMovesStack.push(0),null==this.backendName&&this.backend;const l=Da(e)?e.kernelName:null!=this.state.activeScope?this.state.activeScope.name:"";if(Da(e)){const{kernelName:t,inputs:r,attrs:a}=e;null==this.backendName&&this.backend;const l=Ir(t,this.backendName);ie(null!=l,(()=>`Cannot find registered kernel '${t}' for backend '${this.backendName}'`)),i=()=>{const e=this.backend.numDataIds();o=l.kernelFunc({inputs:r,attrs:a,backend:this.backend});const i=Array.isArray(o)?o:[o];this.shouldCheckForMemLeaks()&&this.checkKernelForMemLeak(t,e,i);const u=i.map((e=>null!=e.rank?e:this.makeTensorFromTensorInfo(e)));if(s){const e=this.getTensorsForGradient(t,r,u);n=this.saveTensorsForBackwardMode(e)}return u}}else{const{forwardFunc:t}=e,r=e=>{s&&(n=e.map((e=>this.keep(this.clone(e)))))};i=()=>{const e=this.backend.numDataIds();o=this.tidy((()=>t(this.backend,r)));const n=Array.isArray(o)?o:[o];return this.shouldCheckForMemLeaks()&&this.checkKernelForMemLeak(l,e,n),n}}const{inputs:u,attrs:c}=e,h=Da(e)?null:e.backwardsFunc;let p;return this.scopedRun((()=>this.state.kernelDepth++),(()=>this.state.kernelDepth--),(()=>{this.ENV.getBool("DEBUG")||this.state.profiling?(p=this.profiler.profileKernel(l,u,(()=>i())),this.ENV.getBool("DEBUG")&&this.profiler.logKernelProfile(p),t=p.outputs):t=i()})),s&&this.addTapeNode(l,u,t,h,n,c),this.state.profiling&&this.state.activeProfile.kernels.push({name:l,bytesAdded:this.state.numBytes-r,totalBytesSnapshot:this.state.numBytes,tensorsAdded:this.state.numTensors-a,totalTensorsSnapshot:this.state.numTensors,inputShapes:Object.keys(u).map((e=>null!=u[e]?u[e].shape:null)),outputShapes:t.map((e=>e.shape)),kernelTimeMs:p.timeMs,extraInfo:p.extraInfo}),Array.isArray(o)?t:t[0]}saveTensorsForBackwardMode(e){const t=e.map((e=>this.keep(this.clone(e))));return t}getTensorsForGradient(e,t,n){const s=Nr(e);if(null!=s){const e=s.inputsToSave||[],r=s.outputsToSave||[];let a;s.saveAllInputs?(ie(Array.isArray(t),(()=>"saveAllInputs is true, expected inputs to be an array.")),a=Object.keys(t).map((e=>t[e]))):a=e.map((e=>t[e]));const i=n.filter(((e,t)=>r[t]));return a.concat(i)}return[]}makeTensor(e,t,n,s){if(null==e)throw new Error("Values passed to engine.makeTensor() are null");n=n||"float32",s=s||this.backend;let r=e;"string"===n&&Ee(e[0])&&(r=e.map((e=>Zr(e))));const a=s.write(r,t,n),i=new ga(t,n,a,this.nextTensorId());if(this.trackTensor(i,s),"string"===n){const e=this.state.tensorInfo.get(a),t=$e(r);this.state.numBytes+=t-e.bytes,e.bytes=t}return i}makeTensorFromDataId(e,t,n,s){const r={dataId:e,shape:t,dtype:n=n||"float32"};return this.makeTensorFromTensorInfo(r,s)}makeTensorFromTensorInfo(e,t){const{dataId:n,shape:s,dtype:r}=e,a=new ga(s,r,n,this.nextTensorId());return this.trackTensor(a,t),a}makeVariable(e,t=!0,n,s){n=n||this.nextVariableId().toString(),null!=s&&s!==e.dtype&&(e=e.cast(s));const r=new ba(e,t,n,this.nextTensorId());if(null!=this.state.registeredVariables[r.name])throw new Error(`Variable with name ${r.name} was already registered`);return this.state.registeredVariables[r.name]=r,this.incRef(r,this.backend),r}trackTensor(e,t){this.state.numTensors++,"string"===e.dtype&&this.state.numStringTensors++;let n=0;"complex64"!==e.dtype&&"string"!==e.dtype&&(n=e.size*Ce(e.dtype)),this.state.numBytes+=n,this.state.tensorInfo.has(e.dataId)||(this.state.numDataBuffers++,this.state.tensorInfo.set(e.dataId,{backend:t||this.backend,dtype:e.dtype,shape:e.shape,bytes:n})),e instanceof ba||this.track(e)}incRef(e,t){this.trackTensor(e,t),this.backend.incRef(e.dataId)}removeDataId(e,t){this.state.tensorInfo.has(e)&&this.state.tensorInfo.get(e).backend===t&&(this.state.tensorInfo.delete(e),this.state.numDataBuffers--)}disposeTensor(e){if(!this.state.tensorInfo.has(e.dataId))return;const t=this.state.tensorInfo.get(e.dataId);if(this.state.numTensors--,"string"===e.dtype&&(this.state.numStringTensors--,this.state.numBytes-=t.bytes),"complex64"!==e.dtype&&"string"!==e.dtype){const t=e.size*Ce(e.dtype);this.state.numBytes-=t}t.backend.disposeData(e.dataId)&&this.removeDataId(e.dataId,t.backend)}disposeVariables(){for(const e in this.state.registeredVariables){const t=this.state.registeredVariables[e];this.disposeVariable(t)}}disposeVariable(e){this.disposeTensor(e),null!=this.state.registeredVariables[e.name]&&delete this.state.registeredVariables[e.name]}memory(){const e=this.backend.memory();return e.numTensors=this.state.numTensors,e.numDataBuffers=this.state.numDataBuffers,e.numBytes=this.state.numBytes,this.state.numStringTensors>0&&(e.unreliable=!0,null==e.reasons&&(e.reasons=[]),e.reasons.push("Memory usage by string tensors is approximate (2 bytes per character)")),e}async profile(e){this.state.profiling=!0;const t=this.state.numBytes,n=this.state.numTensors;this.state.activeProfile.kernels=[],this.state.activeProfile.result=await e(),this.state.profiling=!1,this.state.activeProfile.peakBytes=Math.max(...this.state.activeProfile.kernels.map((e=>e.totalBytesSnapshot))),this.state.activeProfile.newBytes=this.state.numBytes-t,this.state.activeProfile.newTensors=this.state.numTensors-n;for(const e of this.state.activeProfile.kernels)e.kernelTimeMs=await e.kernelTimeMs,e.extraInfo=await e.extraInfo;return this.state.activeProfile}isTapeOn(){return this.state.gradientDepth>0&&0===this.state.kernelDepth}addTapeNode(e,t,n,s,r,a){const i={id:this.state.nextTapeNodeId++,kernelName:e,inputs:t,outputs:n,saved:r},o=Nr(e);null!=o&&(s=o.gradFunc),null!=s&&(i.gradient=e=>(e=e.map(((e,t)=>{if(null==e){const e=n[t],s=Be(e.size,e.dtype);return this.makeTensor(s,e.shape,e.dtype)}return e})),s(e.length>1?e:e[0],r,a))),this.state.activeTape.push(i)}keep(e){return e.kept=!0,e}startTape(){0===this.state.gradientDepth&&(this.state.activeTape=[]),this.state.gradientDepth++}endTape(){this.state.gradientDepth--}startScope(e){const t={track:[],name:"unnamed scope",id:this.state.nextScopeId++};e&&(t.name=e),this.state.scopeStack.push(t),this.state.activeScope=t}endScope(e){const t=Fa(e),n=new Set(t.map((e=>e.id)));for(let e=0;e<this.state.activeScope.track.length;e++){const t=this.state.activeScope.track[e];t.kept||n.has(t.id)||t.dispose()}const s=this.state.scopeStack.pop();this.state.activeScope=0===this.state.scopeStack.length?null:this.state.scopeStack[this.state.scopeStack.length-1],t.forEach((e=>{e.kept||e.scopeId!==s.id||this.track(e)}))}gradients(e,t,n,s=!1){if(ie(t.length>0,(()=>"gradients() received an empty list of xs.")),null!=n&&"float32"!==n.dtype)throw new Error(`dy must have 'float32' dtype, but has '${n.dtype}'`);const r=this.scopedRun((()=>this.startTape()),(()=>this.endTape()),(()=>this.tidy("forward",e)));ie(r instanceof ga,(()=>"The result y returned by f() must be a tensor."));const a=function(e,t,n){const s={},r={};for(let e=0;e<t.length;e++)s[t[e].id]=!0;for(let n=0;n<e.length;n++){const a=e[n],i=a.inputs;for(const e in i){const n=i[e];let o=!1;for(let e=0;e<t.length;e++)if(s[n.id]){a.outputs.forEach((e=>s[e.id]=!0)),o=!0,r[a.id]=!0;break}if(o)break}}const a={};a[n.id]=!0;const i={};for(let t=e.length-1;t>=0;t--){const n=e[t],s=n.inputs;for(let e=0;e<n.outputs.length;e++)if(a[n.outputs[e].id]){for(const e in s)a[s[e].id]=!0,i[n.id]=!0;break}}const o=[];for(let t=0;t<e.length;t++){const n=e[t];if(r[n.id]&&i[n.id]){const e={};for(const t in n.inputs){const r=n.inputs[t];s[r.id]&&(e[t]=r)}const t=Object.assign({},n);t.inputs=e,t.outputs=n.outputs,o.push(t)}}return o}(this.state.activeTape,t,r);if(!s&&0===a.length&&t.length>0)throw new Error("Cannot compute gradient of y=f(x) with respect to x. Make sure that the f you passed encloses all operations that lead from x to y.");return this.tidy("backward",(()=>{const e={};e[r.id]=null==n?function(e){const t=Pe(ue(e),"float32");return za.makeTensor(t,e,"float32")}(r.shape):n,function(e,t,n,s){for(let r=t.length-1;r>=0;r--){const a=t[r],i=[];if(a.outputs.forEach((t=>{const n=e[t.id];null!=n?i.push(n):i.push(null)})),null==a.gradient)throw new Error(`Cannot compute gradient: gradient function not found for ${a.kernelName}.`);const o=a.gradient(i);for(const t in a.inputs){if(!(t in o))throw new Error(`Cannot backprop through input ${t}. Available gradients found: ${Object.keys(o)}.`);const r=n((()=>o[t]()));if("float32"!==r.dtype)throw new Error(`Error in gradient for op ${a.kernelName}. The gradient of input ${t} must have 'float32' dtype, but has '${r.dtype}'`);const i=a.inputs[t];if(!pe(r.shape,i.shape))throw new Error(`Error in gradient for op ${a.kernelName}. The gradient of input '${t}' has shape '${r.shape}', which does not match the shape of the input '${i.shape}'`);if(null==e[i.id])e[i.id]=r;else{const t=e[i.id];e[i.id]=s(t,r),t.dispose()}}}}(e,a,(e=>this.tidy(e)),Pa);const s=t.map((t=>e[t.id]));return 0===this.state.gradientDepth&&(this.state.activeTape.forEach((e=>{for(const t of e.saved)t.dispose()})),this.state.activeTape=null),{value:r,grads:s}}))}customGrad(e){return ie(_e(e),(()=>"The f passed in customGrad(f) must be a function.")),(...t)=>{let n;ie(t.every((e=>e instanceof ga)),(()=>"The args passed in customGrad(f)(x1, x2,...) must all be tensors"));const s={};t.forEach(((e,t)=>{s[t]=e}));return this.runKernelFunc({forwardFunc:(s,r)=>(n=e(...t,r),ie(n.value instanceof ga,(()=>"The function f passed in customGrad(f) must return an object where `obj.value` is a tensor")),ie(_e(n.gradFunc),(()=>"The function f passed in customGrad(f) must return an object where `obj.gradFunc` is a function.")),n.value),backwardsFunc:(e,s)=>{const r=n.gradFunc(e,s),a=Array.isArray(r)?r:[r];ie(a.length===t.length,(()=>"The function f passed in customGrad(f) must return an object where `obj.gradFunc` is a function that returns the same number of tensors as inputs passed to f(...).")),ie(a.every((e=>e instanceof ga)),(()=>"The function f passed in customGrad(f) must return an object where `obj.gradFunc` is a function that returns a list of only tensors."));const i={};return a.forEach(((e,t)=>{i[t]=()=>e})),i},inputs:s})}}readSync(e){return this.state.tensorInfo.get(e).backend.readSync(e)}read(e){return this.state.tensorInfo.get(e).backend.read(e)}readToGPU(e,t){return this.state.tensorInfo.get(e).backend.readToGPU(e,t)}async time(e){const t=Xr(),n=await this.backend.time(e);return n.wallMs=Xr()-t,n}track(e){return null!=this.state.activeScope&&(e.scopeId=this.state.activeScope.id,this.state.activeScope.track.push(e)),e}get registeredVariables(){return this.state.registeredVariables}reset(){this.pendingBackendInitId++,this.state.dispose(),this.ENV.reset(),this.state=new Oa;for(const e in this.registry)this.disposeRegisteredKernels(e),this.registry[e].dispose(),delete this.registry[e];this.backendName=null,this.backendInstance=null,this.pendingBackendInit=null}}function La(){const e=Je();if(null==e._tfengine){const t=new qe(e);e._tfengine=new Ma(t)}var t;return t=e._tfengine.ENV,Ze=t,da=()=>e._tfengine,e._tfengine}Ma.nextTensorId=0,Ma.nextVariableId=0;const za=La();function Pa(e,t){const n={a:e,b:t};return za.runKernel(st,n)}let Ba;function Wa(e){Ba=e}function Va(e){if(void 0!==Ba)return Ba;if(e||"undefined"!=typeof navigator&&null!=navigator){if(e||(e=navigator),"ReactNative"===e.product)return!0;const t=e.userAgent||e.vendor||("undefined"!=typeof window?window.opera:"");if(!t){const t=e;return t.userAgentData&&t.userAgentData.mobile}return/(android|bb\d+|meego).+mobile|avantgo|bada\/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)\/|plucker|pocket|psp|series(4|6)0|symbian|treo|up\.(browser|link)|vodafone|wap|windows ce|xda|xiino/i.test(t)||/1207|6310|6590|3gso|4thp|50[1-6]i|770s|802s|a wa|abac|ac(er|oo|s\-)|ai(ko|rn)|al(av|ca|co)|amoi|an(ex|ny|yw)|aptu|ar(ch|go)|as(te|us)|attw|au(di|\-m|r |s )|avan|be(ck|ll|nq)|bi(lb|rd)|bl(ac|az)|br(e|v)w|bumb|bw\-(n|u)|c55\/|capi|ccwa|cdm\-|cell|chtm|cldc|cmd\-|co(mp|nd)|craw|da(it|ll|ng)|dbte|dc\-s|devi|dica|dmob|do(c|p)o|ds(12|\-d)|el(49|ai)|em(l2|ul)|er(ic|k0)|esl8|ez([4-7]0|os|wa|ze)|fetc|fly(\-|_)|g1 u|g560|gene|gf\-5|g\-mo|go(\.w|od)|gr(ad|un)|haie|hcit|hd\-(m|p|t)|hei\-|hi(pt|ta)|hp( i|ip)|hs\-c|ht(c(\-| |_|a|g|p|s|t)|tp)|hu(aw|tc)|i\-(20|go|ma)|i230|iac( |\-|\/)|ibro|idea|ig01|ikom|im1k|inno|ipaq|iris|ja(t|v)a|jbro|jemu|jigs|kddi|keji|kgt( |\/)|klon|kpt |kwc\-|kyo(c|k)|le(no|xi)|lg( g|\/(k|l|u)|50|54|\-[a-w])|libw|lynx|m1\-w|m3ga|m50\/|ma(te|ui|xo)|mc(01|21|ca)|m\-cr|me(rc|ri)|mi(o8|oa|ts)|mmef|mo(01|02|bi|de|do|t(\-| |o|v)|zz)|mt(50|p1|v )|mwbp|mywa|n10[0-2]|n20[2-3]|n30(0|2)|n50(0|2|5)|n7(0(0|1)|10)|ne((c|m)\-|on|tf|wf|wg|wt)|nok(6|i)|nzph|o2im|op(ti|wv)|oran|owg1|p800|pan(a|d|t)|pdxg|pg(13|\-([1-8]|c))|phil|pire|pl(ay|uc)|pn\-2|po(ck|rt|se)|prox|psio|pt\-g|qa\-a|qc(07|12|21|32|60|\-[2-7]|i\-)|qtek|r380|r600|raks|rim9|ro(ve|zo)|s55\/|sa(ge|ma|mm|ms|ny|va)|sc(01|h\-|oo|p\-)|sdk\/|se(c(\-|0|1)|47|mc|nd|ri)|sgh\-|shar|sie(\-|m)|sk\-0|sl(45|id)|sm(al|ar|b3|it|t5)|so(ft|ny)|sp(01|h\-|v\-|v )|sy(01|mb)|t2(18|50)|t6(00|10|18)|ta(gt|lk)|tcl\-|tdg\-|tel(i|m)|tim\-|t\-mo|to(pl|sh)|ts(70|m\-|m3|m5)|tx\-9|up(\.b|g1|si)|utst|v400|v750|veri|vi(rg|te)|vk(40|5[0-3]|\-v)|vm40|voda|vulc|vx(52|53|60|61|70|80|81|83|85|98)|w3c(\-| )|webc|whit|wi(g |nc|nw)|wmlb|wonu|x700|yas\-|your|zeto|zte\-/i.test(t.substr(0,4))}return!1}function Ua(){return"undefined"!=typeof window&&null!=window.document||"undefined"!=typeof WorkerGlobalScope}const Ga=Xe();function Ha(e,t){let n=e;if(Qr(e))return"string"===t?[]:[e.length];if(Ca(e)){const t=e.channels||"RGBA";return[e.height,e.width*t.length]}if($a(e))return[e.buffer.size/(null==t?4:Ce(t))];if(!Array.isArray(e))return[];const s=[];for(;Array.isArray(n)||Qr(n)&&"string"!==t;)s.push(n.length),n=n[0];return Array.isArray(e)&&Xe().getBool("TENSORLIKE_CHECK_SHAPE_CONSISTENCY")&&ja(e,s,[]),s}function ja(e,t,n){if(n=n||[],!Array.isArray(e)&&!Qr(e))return void ie(0===t.length,(()=>`Element arr[${n.join("][")}] is a primitive, but should be an array/TypedArray of ${t[0]} elements`));ie(t.length>0,(()=>`Element arr[${n.join("][")}] should be a primitive, but is an array of ${e.length} elements`)),ie(e.length===t[0],(()=>`Element arr[${n.join("][")}] should have ${t[0]} elements, but has ${e.length} elements`));const s=t.slice(1);for(let t=0;t<e.length;++t)ja(e[t],s,n.concat(t))}function qa(e,t,n,s){if("string_or_numeric"!==e){if(null==e)throw new Error("Expected dtype cannot be null.");if("numeric"!==e&&e!==t||"numeric"===e&&"string"===t)throw new Error(`Argument '${n}' passed to '${s}' must be ${e} tensor, but got ${t} tensor`)}}function Ka(e,t,n,s="numeric"){if(e instanceof ga)return qa(s,e.dtype,t,n),e;let r=Fe(e);if("string"!==r&&["bool","int32","float32"].indexOf(s)>=0&&(r=s),qa(s,r,t,n),null==e||!Qr(e)&&!Array.isArray(e)&&"number"!=typeof e&&"boolean"!=typeof e&&"string"!=typeof e){const s=null==e?"null":e.constructor.name;throw new Error(`Argument '${t}' passed to '${n}' must be a Tensor or TensorLike, but got '${s}'`)}const a=Ha(e,r);Qr(e)||Array.isArray(e)||(e=[e]);const i="string"!==r?Kr(e,r):ea(e,[],!0);return za.makeTensor(i,a,r)}function Xa(e,t,n,s="numeric"){if(!Array.isArray(e))throw new Error(`Argument ${t} passed to ${n} must be a \`Tensor[]\` or \`TensorLike[]\``);return e.map(((e,r)=>Ka(e,`${t}[${r}]`,n,s)))}Ga.registerFlag("DEBUG",(()=>!1),(e=>{e&&console.warn("Debugging mode is ON. The output of every math call will be downloaded to CPU and checked for NaNs. This significantly impacts performance.")})),Ga.registerFlag("IS_BROWSER",(()=>Ua())),Ga.registerFlag("IS_NODE",(()=>"undefined"!=typeof process&&void 0!==process.versions&&void 0!==process.versions.node)),Ga.registerFlag("IS_CHROME",(()=>"undefined"!=typeof navigator&&null!=navigator&&null!=navigator.userAgent&&/Chrome/.test(navigator.userAgent)&&/Google Inc/.test(navigator.vendor))),Ga.registerFlag("IS_SAFARI",(()=>"undefined"!=typeof navigator&&null!=navigator&&null!=navigator.userAgent&&/Safari/.test(navigator.userAgent)&&/Apple/.test(navigator.vendor))),Ga.registerFlag("PROD",(()=>!1)),Ga.registerFlag("TENSORLIKE_CHECK_SHAPE_CONSISTENCY",(()=>Ga.getBool("DEBUG"))),Ga.registerFlag("DEPRECATION_WARNINGS_ENABLED",(()=>!0)),Ga.registerFlag("IS_TEST",(()=>!1)),Ga.registerFlag("CHECK_COMPUTATION_FOR_ERRORS",(()=>Ga.getBool("DEBUG"))),Ga.registerFlag("WRAP_TO_IMAGEBITMAP",(()=>!1)),Ga.registerFlag("CANVAS2D_WILL_READ_FREQUENTLY_FOR_GPU",(()=>!1)),Ga.registerFlag("USE_SETTIMEOUTCUSTOM",(()=>!1));const Ya="__op";function Za(e){const t=Object.keys(e);if(1!==t.length)throw new Error(`Please provide an object with a single key (operation name) mapping to a function. Got an object with ${t.length} keys.`);let n=t[0];const s=e[n];n.endsWith("_")&&(n=n.substring(0,n.length-1)),n+=Ya;const r=(...e)=>{za.startScope(n);try{const t=s(...e);return He(t)&&console.error("Cannot return a Promise inside of tidy."),za.endScope(t),t}catch(e){throw za.endScope(null),e}};return Object.defineProperty(r,"name",{value:n,configurable:!0}),r}const Ja=Za({complex_:function(e,t){const n=Ka(e,"real","complex"),s=Ka(t,"imag","complex");oe(n.shape,s.shape,`real and imag shapes, ${n.shape} and ${s.shape}, must match in call to tf.complex().`);const r={real:n,imag:s};return za.runKernel(Ct,r)}});function Qa(e,t,n,s){if(null==s)s=Fe(e);else if("complex64"===s)throw new Error("Cannot construct a complex64 tensor directly. Please use tf.complex(real, imag).");if($a(e)||Ca(e)){if("float32"!==s&&"int32"!==s)throw new Error(`Creating tensor from GPU data only supports 'float32'|'int32' dtype, while the dtype is ${s}.`);return za.backend.createTensorFromGPUData(e,t||n,s)}if(!Qr(e)&&!Array.isArray(e)&&"number"!=typeof e&&"boolean"!=typeof e&&"string"!=typeof e)throw new Error("values passed to tensor(values) must be a number/boolean/string or an array of numbers/booleans/strings, or a TypedArray");if(null!=t){Ve(t);const e=ue(t),s=ue(n);ie(e===s,(()=>`Based on the provided shape, [${t}], the tensor should have ${e} values but has ${s}`));for(let e=0;e<n.length;++e){const s=n[e],r=e!==n.length-1||s!==ue(t.slice(e));ie(n[e]===t[e]||!r,(()=>`Error creating a new Tensor. Inferred shape (${n}) does not match the provided shape (${t}). `))}}return Qr(e)||Array.isArray(e)||(e=[e]),t=t||n,e="string"!==s?Kr(e,s):ea(e,[],!0),za.makeTensor(e,t,s)}function ei(e,t,n){return Qa(e,t,Ha(e,n),n)}const ti={float32:4,float16:2,int32:4,uint16:2,uint8:1,bool:1,complex64:8};class ni{static join(e){return new ni(e).slice()}constructor(e){if(this.shards=[],this.previousShardIndex=0,null==e)return;if(e instanceof Array||(e=[e]),0===(e=e.map((e=>Qr(e)?e.buffer:e))).length)return;this.bufferUniformSize=e[0].byteLength;let t=0;for(let n=0;n<e.length;n++){const s=e[n];n!==e.length-1&&s.byteLength!==this.bufferUniformSize&&(this.bufferUniformSize=void 0);const r=t+s.byteLength;this.shards.push({buffer:s,start:t,end:r}),t=r}0===this.shards.length&&(this.byteLength=0),this.byteLength=this.shards[this.shards.length-1].end}slice(e=0,t=this.byteLength){if(0===this.shards.length)return new ArrayBuffer(0);if(e=isNaN(Number(e))?0:e,t=isNaN(Number(t))?0:t,e=Math.max(0,e),(t=Math.min(this.byteLength,t))<=e)return new ArrayBuffer(0);const n=this.findShardForByte(e);if(-1===n)throw new Error(`Could not find start shard for byte ${e}`);const s=new ArrayBuffer(t-e),r=new Uint8Array(s);let a=0;for(let s=n;s<this.shards.length;s++){const n=this.shards[s],i=e+a-n.start,o=a,l=Math.min(t,n.end)-n.start,u=new Uint8Array(n.buffer,i,l-i);if(r.set(u,o),a+=u.length,t<n.end)break}return s}findShardForByte(e){if(0===this.shards.length||e<0||e>=this.byteLength)return-1;if(null!=this.bufferUniformSize)return this.previousShardIndex=Math.floor(e/this.bufferUniformSize),this.previousShardIndex;function t(t){return e<t.start?-1:e>=t.end?1:0}if(0===t(this.shards[this.previousShardIndex]))return this.previousShardIndex;const n=function(e,t){let n=0,s=e.length;for(;n<=s;){const r=Math.floor((s-n)/2)+n,a=t(e[r]);if(0===a)return r;a<0?s=r:n=r+1}return-1}(this.shards,t);return-1===n?-1:(this.previousShardIndex=n,this.previousShardIndex)}}const si=4;async function ri(e,t){const n=[],s=[],r=Array.isArray(e)?e.map((e=>e.name)):Object.keys(e);for(let a=0;a<r.length;++a){const i=r[a],o=Array.isArray(e)?e[a].tensor:e[i];if("float32"!==o.dtype&&"int32"!==o.dtype&&"bool"!==o.dtype&&"string"!==o.dtype&&"complex64"!==o.dtype)throw new Error(`Unsupported dtype in weight '${i}': ${o.dtype}`);const l={name:i,shape:o.shape,dtype:o.dtype};if("string"===o.dtype){const e=new Promise((async e=>{const t=await o.bytes(),n=t.reduce(((e,t)=>e+t.length),0)+si*t.length,s=new Uint8Array(n);let r=0;for(let e=0;e<t.length;e++){const n=t[e],a=new Uint8Array(new Uint32Array([n.length]).buffer);s.set(a,r),r+=si,s.set(n,r),r+=n.length}e(s)}));s.push(e)}else s.push(o.data());null!=t&&(l.group=t),n.push(l)}return{data:ii(await Promise.all(s)),specs:n}}function ai(e,t){const n=new ni(e),s={};let r,a=0;for(const e of t){const t=e.name,i=e.dtype,o=e.shape,l=ue(o);let u;if("quantization"in e){const s=e.quantization;if("uint8"===s.dtype||"uint16"===s.dtype){if(!("min"in s)||!("scale"in s))throw new Error(`Weight ${e.name} with quantization ${s.dtype} doesn't have corresponding metadata min and scale.`)}else{if("float16"!==s.dtype)throw new Error(`Weight ${e.name} has unknown quantization dtype ${s.dtype}. Supported quantization dtypes are: 'uint8', 'uint16', and 'float16'.`);if("float32"!==i)throw new Error(`Weight ${e.name} is quantized with ${s.dtype} which only supports weights of type float32 not ${i}.`)}const o=ti[s.dtype],c=n.slice(a,a+l*o),h="uint8"===s.dtype?new Uint8Array(c):new Uint16Array(c);if("float32"===i)if("uint8"===s.dtype||"uint16"===s.dtype){u=new Float32Array(h.length);for(let e=0;e<h.length;e++){const t=h[e];u[e]=t*s.scale+s.min}}else{if("float16"!==s.dtype)throw new Error(`Unsupported quantization type ${s.dtype} for weight type float32.`);void 0===r&&(r=gi()),u=r(h)}else{if("int32"!==i)throw new Error(`Unsupported dtype in weight '${t}': ${i}`);if("uint8"!==s.dtype&&"uint16"!==s.dtype)throw new Error(`Unsupported quantization type ${s.dtype} for weight type int32.`);u=new Int32Array(h.length);for(let e=0;e<h.length;e++){const t=h[e];u[e]=Math.round(t*s.scale+s.min)}}a+=l*o}else if("string"===i){const t=ue(e.shape);u=[];for(let e=0;e<t;e++){const e=new Uint32Array(n.slice(a,a+si))[0];a+=si;const t=new Uint8Array(n.slice(a,a+e));u.push(t),a+=e}}else{const e=ti[i],r=n.slice(a,a+l*e);if("float32"===i)u=new Float32Array(r);else if("int32"===i)u=new Int32Array(r);else if("bool"===i)u=new Uint8Array(r);else{if("complex64"!==i)throw new Error(`Unsupported dtype in weight '${t}': ${i}`);{u=new Float32Array(r);const e=new Float32Array(u.length/2),n=new Float32Array(u.length/2);for(let t=0;t<e.length;t++)e[t]=u[2*t],n[t]=u[2*t+1];const a=ei(e,o,"float32"),i=ei(n,o,"float32");s[t]=Ja(a,i),a.dispose(),i.dispose()}}a+=l*e}"complex64"!==i&&(s[t]=ei(u,o,i))}return s}function ii(e){if(null===e)throw new Error(`Invalid input value: ${JSON.stringify(e)}`);let t=0;const n=[];e.forEach((e=>{if(t+=e.byteLength,n.push(e.byteLength===e.buffer.byteLength?e:new e.constructor(e)),!(e instanceof Float32Array||e instanceof Int32Array||e instanceof Uint8Array))throw new Error(`Unsupported TypedArray subtype: ${e.constructor.name}`)}));const s=new Uint8Array(t);let r=0;return n.forEach((e=>{s.set(new Uint8Array(e.buffer),r),r+=e.byteLength})),s.buffer}const oi="undefined"!=typeof Buffer&&("undefined"==typeof Blob||"undefined"==typeof atob||"undefined"==typeof btoa);function li(e){return oi?Buffer.byteLength(e,"utf8"):new Blob([e]).size}function ui(e){return ni.join(e)}function ci(e){for(e=e.trim();e.endsWith("/");)e=e.slice(0,e.length-1);const t=e.split("/");return t[t.length-1]}function hi(e,t){const n={modelTopology:e.modelTopology,format:e.format,generatedBy:e.generatedBy,convertedBy:e.convertedBy,weightsManifest:t};return null!=e.signature&&(n.signature=e.signature),null!=e.userDefinedMetadata&&(n.userDefinedMetadata=e.userDefinedMetadata),null!=e.modelInitializer&&(n.modelInitializer=e.modelInitializer),null!=e.initializerSignature&&(n.initializerSignature=e.initializerSignature),null!=e.trainingConfig&&(n.trainingConfig=e.trainingConfig),n}function pi(e,t,n){const s={modelTopology:e.modelTopology,format:e.format,generatedBy:e.generatedBy,convertedBy:e.convertedBy};if(null!=e.trainingConfig&&(s.trainingConfig=e.trainingConfig),null!=e.weightsManifest){if(!t)throw new Error("modelJSON has weightsManifest but weightSpecs is null");if(!n)throw new Error("modelJSON has weightsManifest but weightData is null");s.weightSpecs=t,s.weightData=n}return null!=e.signature&&(s.signature=e.signature),null!=e.userDefinedMetadata&&(s.userDefinedMetadata=e.userDefinedMetadata),null!=e.modelInitializer&&(s.modelInitializer=e.modelInitializer),null!=e.initializerSignature&&(s.initializerSignature=e.initializerSignature),s}async function di(e,t){let n,s;return null!=e.weightsManifest&&([n,s]=await t(e.weightsManifest)),pi(e,n,s)}function fi(e){if(e.modelTopology instanceof ArrayBuffer)throw new Error("Expected JSON model topology, received ArrayBuffer.");return{dateSaved:new Date,modelTopologyType:"JSON",modelTopologyBytes:null==e.modelTopology?0:li(JSON.stringify(e.modelTopology)),weightSpecsBytes:null==e.weightSpecs?0:li(JSON.stringify(e.weightSpecs)),weightDataBytes:null==e.weightData?0:new ni(e.weightData).byteLength}}function mi(e){const t=[];for(const n of e)t.push(...n.weights);return t}function gi(){const e=function(){const e=e=>{let t=e<<13,n=0;for(;0==(8388608&t);)n-=8388608,t<<=1;return t&=-8388609,n+=947912704,t|n},t=new Uint32Array(2048);t[0]=0;for(let n=1;n<1024;n++)t[n]=e(n);for(let e=1024;e<2048;e++)t[e]=939524096+(e-1024<<13);return t}(),t=function(){const e=new Uint32Array(64);e[0]=0,e[31]=1199570944,e[32]=2147483648,e[63]=3347054592;for(let t=1;t<31;t++)e[t]=t<<23;for(let t=33;t<63;t++)e[t]=2147483648+(t-32<<23);return e}(),n=function(){const e=new Uint32Array(64);for(let t=0;t<64;t++)e[t]=1024;return e[0]=e[32]=0,e}();return s=>{const r=new ArrayBuffer(4*s.length),a=new Uint32Array(r);for(let r=0;r<s.length;r++){const i=s[r],o=e[n[i>>10]+(1023&i)]+t[i>>10];a[r]=o}return new Float32Array(r)}}class yi{constructor(){this.saveRouters=[],this.loadRouters=[]}static getInstance(){return null==yi.instance&&(yi.instance=new yi),yi.instance}static registerSaveRouter(e){yi.getInstance().saveRouters.push(e)}static registerLoadRouter(e){yi.getInstance().loadRouters.push(e)}static getSaveHandlers(e){return yi.getHandlers(e,"save")}static getLoadHandlers(e,t){return yi.getHandlers(e,"load",t)}static getHandlers(e,t,n){const s=[];return("load"===t?yi.getInstance().loadRouters:yi.getInstance().saveRouters).forEach((t=>{const r=t(e,n);null!==r&&s.push(r)})),s}}const bi=e=>yi.registerSaveRouter(e),xi=e=>yi.registerLoadRouter(e),wi=e=>yi.getSaveHandlers(e),vi=(e,t)=>yi.getLoadHandlers(e,t),ki="tensorflowjs",Ii="models_store",Ni="model_info_store";function Si(){if(!Xe().getBool("IS_BROWSER"))throw new Error("Failed to obtain IndexedDB factory because the current environmentis not a web browser.");const e="undefined"==typeof window?self:window,t=e.indexedDB||e.mozIndexedDB||e.webkitIndexedDB||e.msIndexedDB||e.shimIndexedDB;if(null==t)throw new Error("The current browser does not appear to support IndexedDB.");return t}function Ti(e){const t=e.result;t.createObjectStore(Ii,{keyPath:"modelPath"}),t.createObjectStore(Ni,{keyPath:"modelPath"})}class Ci{constructor(e){if(this.indexedDB=Si(),null==e||!e)throw new Error("For IndexedDB, modelPath must not be null, undefined or empty.");this.modelPath=e}async save(e){if(e.modelTopology instanceof ArrayBuffer)throw new Error("BrowserLocalStorage.save() does not support saving model topology in binary formats yet.");return this.databaseAction(this.modelPath,e)}async load(){return this.databaseAction(this.modelPath)}databaseAction(e,t){return new Promise(((e,n)=>{const s=this.indexedDB.open(ki,1);s.onupgradeneeded=()=>Ti(s),s.onsuccess=()=>{const r=s.result;if(null==t){const t=r.transaction(Ii,"readonly"),s=t.objectStore(Ii).get(this.modelPath);s.onsuccess=()=>{if(null==s.result)return r.close(),n(new Error(`Cannot find model with path '${this.modelPath}' in IndexedDB.`));e(s.result.modelArtifacts)},s.onerror=e=>(r.close(),n(s.error)),t.oncomplete=()=>r.close()}else{const s=fi(t),a=r.transaction(Ni,"readwrite");let i,o,l=a.objectStore(Ni);try{i=l.put({modelPath:this.modelPath,modelArtifactsInfo:s})}catch(e){return n(e)}i.onsuccess=()=>{o=r.transaction(Ii,"readwrite");const i=o.objectStore(Ii);let u;try{u=i.put({modelPath:this.modelPath,modelArtifacts:t,modelArtifactsInfo:s})}catch(e){return n(e)}u.onsuccess=()=>e({modelArtifactsInfo:s}),u.onerror=e=>{l=a.objectStore(Ni);const t=l.delete(this.modelPath);t.onsuccess=()=>(r.close(),n(u.error)),t.onerror=e=>(r.close(),n(u.error))}},i.onerror=e=>(r.close(),n(i.error)),a.oncomplete=()=>{null==o?r.close():o.oncomplete=()=>r.close()}}},s.onerror=e=>n(s.error)}))}}Ci.URL_SCHEME="indexeddb://";const $i=e=>{return Xe().getBool("IS_BROWSER")&&!Array.isArray(e)&&e.startsWith(Ci.URL_SCHEME)?(t=e.slice(Ci.URL_SCHEME.length),new Ci(t)):null;var t};yi.registerSaveRouter($i),yi.registerLoadRouter($i);class Ei{constructor(){this.indexedDB=Si()}async listModels(){return new Promise(((e,t)=>{const n=this.indexedDB.open(ki,1);n.onupgradeneeded=()=>Ti(n),n.onsuccess=()=>{const s=n.result,r=s.transaction(Ni,"readonly"),a=r.objectStore(Ni).getAll();a.onsuccess=()=>{const t={};for(const e of a.result)t[e.modelPath]=e.modelArtifactsInfo;e(t)},a.onerror=e=>(s.close(),t(a.error)),r.oncomplete=()=>s.close()},n.onerror=e=>t(n.error)}))}async removeModel(e){var t;return e=(t=e).startsWith(Ci.URL_SCHEME)?t.slice(Ci.URL_SCHEME.length):t,new Promise(((t,n)=>{const s=this.indexedDB.open(ki,1);s.onupgradeneeded=()=>Ti(s),s.onsuccess=()=>{const r=s.result,a=r.transaction(Ni,"readwrite"),i=a.objectStore(Ni),o=i.get(e);let l;o.onsuccess=()=>{if(null==o.result)return r.close(),n(new Error(`Cannot find model with path '${e}' in IndexedDB.`));{const s=i.delete(e),a=()=>{l=r.transaction(Ii,"readwrite");const s=l.objectStore(Ii).delete(e);s.onsuccess=()=>t(o.result.modelArtifactsInfo),s.onerror=e=>n(o.error)};s.onsuccess=a,s.onerror=e=>(a(),r.close(),n(o.error))}},o.onerror=e=>(r.close(),n(o.error)),a.oncomplete=()=>{null==l?r.close():l.oncomplete=()=>r.close()}},s.onerror=e=>n(s.error)}))}}const Ai="/",Ri="tensorflowjs_models",Fi="info",_i="model_topology",Di="weight_specs",Oi="weight_data",Mi="model_metadata";function Li(e){return{info:[Ri,e,Fi].join(Ai),topology:[Ri,e,_i].join(Ai),weightSpecs:[Ri,e,Di].join(Ai),weightData:[Ri,e,Oi].join(Ai),modelMetadata:[Ri,e,Mi].join(Ai)}}function zi(e){for(const t of Object.values(e))window.localStorage.removeItem(t)}function Pi(e){const t=e.split(Ai);if(t.length<3)throw new Error(`Invalid key format: ${e}`);return t.slice(1,t.length-1).join(Ai)}class Bi{constructor(e){if(!Xe().getBool("IS_BROWSER")||"undefined"==typeof window||void 0===window.localStorage)throw new Error("The current environment does not support local storage.");if(this.LS=window.localStorage,null==e||!e)throw new Error("For local storage, modelPath must not be null, undefined or empty.");this.modelPath=e,this.keys=Li(this.modelPath)}async save(e){if(e.modelTopology instanceof ArrayBuffer)throw new Error("BrowserLocalStorage.save() does not support saving model topology in binary formats yet.");{const t=JSON.stringify(e.modelTopology),n=JSON.stringify(e.weightSpecs),s=fi(e),r=ni.join(e.weightData);try{this.LS.setItem(this.keys.info,JSON.stringify(s)),this.LS.setItem(this.keys.topology,t),this.LS.setItem(this.keys.weightSpecs,n),this.LS.setItem(this.keys.weightData,function(e){if(oi)return Buffer.from(e).toString("base64");const t=new Uint8Array(e);let n="";for(let e=0,s=t.length;e<s;e++)n+=String.fromCharCode(t[e]);return btoa(n)}(r));const a={format:e.format,generatedBy:e.generatedBy,convertedBy:e.convertedBy,signature:null!=e.signature?e.signature:void 0,userDefinedMetadata:null!=e.userDefinedMetadata?e.userDefinedMetadata:void 0,modelInitializer:null!=e.modelInitializer?e.modelInitializer:void 0,initializerSignature:null!=e.initializerSignature?e.initializerSignature:void 0,trainingConfig:null!=e.trainingConfig?e.trainingConfig:void 0};return this.LS.setItem(this.keys.modelMetadata,JSON.stringify(a)),{modelArtifactsInfo:s}}catch(e){throw zi(this.keys),new Error(`Failed to save model '${this.modelPath}' to local storage: size quota being exceeded is a possible cause of this failure: modelTopologyBytes=${s.modelTopologyBytes}, weightSpecsBytes=${s.weightSpecsBytes}, weightDataBytes=${s.weightDataBytes}.`)}}}async load(){const e=JSON.parse(this.LS.getItem(this.keys.info));if(null==e)throw new Error(`In local storage, there is no model with name '${this.modelPath}'`);if("JSON"!==e.modelTopologyType)throw new Error("BrowserLocalStorage does not support loading non-JSON model topology yet.");const t={},n=JSON.parse(this.LS.getItem(this.keys.topology));if(null==n)throw new Error(`In local storage, the topology of model '${this.modelPath}' is missing.`);t.modelTopology=n;const s=JSON.parse(this.LS.getItem(this.keys.weightSpecs));if(null==s)throw new Error(`In local storage, the weight specs of model '${this.modelPath}' are missing.`);t.weightSpecs=s;const r=this.LS.getItem(this.keys.modelMetadata);if(null!=r){const e=JSON.parse(r);t.format=e.format,t.generatedBy=e.generatedBy,t.convertedBy=e.convertedBy,null!=e.signature&&(t.signature=e.signature),null!=e.userDefinedMetadata&&(t.userDefinedMetadata=e.userDefinedMetadata),null!=e.modelInitializer&&(t.modelInitializer=e.modelInitializer),null!=e.initializerSignature&&(t.initializerSignature=e.initializerSignature),null!=e.trainingConfig&&(t.trainingConfig=e.trainingConfig)}const a=this.LS.getItem(this.keys.weightData);if(null==a)throw new Error(`In local storage, the binary weight values of model '${this.modelPath}' are missing.`);return t.weightData=function(e){if(oi){const t=Buffer.from(e,"base64");return t.buffer.slice(t.byteOffset,t.byteOffset+t.byteLength)}const t=atob(e),n=new Uint8Array(t.length);for(let e=0;e<t.length;++e)n.set([t.charCodeAt(e)],e);return n.buffer}(a),t}}Bi.URL_SCHEME="localstorage://";const Wi=e=>{return Xe().getBool("IS_BROWSER")&&!Array.isArray(e)&&e.startsWith(Bi.URL_SCHEME)?(t=e.slice(Bi.URL_SCHEME.length),new Bi(t)):null;var t};yi.registerSaveRouter(Wi),yi.registerLoadRouter(Wi);class Vi{constructor(){ie(Xe().getBool("IS_BROWSER"),(()=>"Current environment is not a web browser")),ie("undefined"==typeof window||void 0!==window.localStorage,(()=>"Current browser does not appear to support localStorage")),this.LS=window.localStorage}async listModels(){const e={},t=Ri+Ai,n=Ai+Fi;for(let s=0;s<this.LS.length;++s){const r=this.LS.key(s);if(r.startsWith(t)&&r.endsWith(n)){e[Pi(r)]=JSON.parse(this.LS.getItem(r))}}return e}async removeModel(e){var t;const n=Li(e=(t=e).startsWith(Bi.URL_SCHEME)?t.slice(Bi.URL_SCHEME.length):t);if(null==this.LS.getItem(n.info))throw new Error(`Cannot find model at path '${e}'`);const s=JSON.parse(this.LS.getItem(n.info));return zi(n),s}}const Ui="://";class Gi{constructor(){this.managers={}}static getInstance(){return null==Gi.instance&&(Gi.instance=new Gi),Gi.instance}static registerManager(e,t){ie(null!=e,(()=>"scheme must not be undefined or null.")),e.endsWith(Ui)&&(e=e.slice(0,e.indexOf(Ui))),ie(e.length>0,(()=>"scheme must not be an empty string."));const n=Gi.getInstance();ie(null==n.managers[e],(()=>`A model store manager is already registered for scheme '${e}'.`)),n.managers[e]=t}static getManager(e){const t=Gi.getInstance().managers[e];if(null==t)throw new Error(`Cannot find model manager for scheme '${e}'`);return t}static getSchemes(){return Object.keys(Gi.getInstance().managers)}}function Hi(e){if(-1===e.indexOf(Ui))throw new Error(`The url string provided does not contain a scheme. Supported schemes are: ${Gi.getSchemes().join(",")}`);return{scheme:e.split(Ui)[0],path:e.split(Ui)[1]}}async function ji(e,t,n=!1){ie(e!==t,(()=>`Old path and new path are the same: '${e}'`));const s=yi.getLoadHandlers(e);ie(s.length>0,(()=>`Copying failed because no load handler is found for source URL ${e}.`)),ie(s.length<2,(()=>`Copying failed because more than one (${s.length}) load handlers for source URL ${e}.`));const r=s[0],a=yi.getSaveHandlers(t);ie(a.length>0,(()=>`Copying failed because no save handler is found for destination URL ${t}.`)),ie(a.length<2,(()=>`Copying failed because more than one (${s.length}) save handlers for destination URL ${t}.`));const i=a[0],o=Hi(e).scheme,l=Hi(e).path,u=o===Hi(e).scheme,c=await r.load();n&&u&&await Gi.getManager(o).removeModel(l);const h=await i.save(c);return n&&!u&&await Gi.getManager(o).removeModel(l),h.modelArtifactsInfo}async function qi(){const e=Gi.getSchemes(),t={};for(const n of e){const e=await Gi.getManager(n).listModels();for(const s in e){t[n+Ui+s]=e[s]}}return t}async function Ki(e){const t=Hi(e);return Gi.getManager(t.scheme).removeModel(t.path)}async function Xi(e,t){return ji(e,t,!1)}async function Yi(e,t){return ji(e,t,!0)}class Zi{constructor(){this.messageName="setTimeoutCustom",this.functionRefs=[],this.handledMessageCount=0,this.hasEventListener=!1}fetch(e,t){return fetch(e,t)}now(){return performance.now()}encode(e,t){if("utf-8"!==t&&"utf8"!==t)throw new Error(`Browser's encoder only supports utf-8, but got ${t}`);return null==this.textEncoder&&(this.textEncoder=new TextEncoder),this.textEncoder.encode(e)}decode(e,t){return new TextDecoder(t).decode(e)}setTimeoutCustom(e,t){"undefined"!=typeof window&&Xe().getBool("USE_SETTIMEOUTCUSTOM")?(this.functionRefs.push(e),setTimeout((()=>{window.postMessage({name:this.messageName,index:this.functionRefs.length-1},"*")}),t),this.hasEventListener||(this.hasEventListener=!0,window.addEventListener("message",(e=>{if(e.source===window&&e.data.name===this.messageName){e.stopPropagation();(0,this.functionRefs[e.data.index])(),this.handledMessageCount++,this.handledMessageCount===this.functionRefs.length&&(this.functionRefs=[],this.handledMessageCount=0)}}),!0))):setTimeout(e,t)}isTypedArray(e){return Fr(e)}}if(Xe().get("IS_BROWSER")){Xe().setPlatform("browser",new Zi);try{Gi.registerManager(Bi.URL_SCHEME,new Vi)}catch(e){}try{Gi.registerManager(Ci.URL_SCHEME,new Ei)}catch(e){}}const Ji=()=>n(410);let Qi;class eo{constructor(){this.util=n(628),this.textEncoder=new this.util.TextEncoder}fetch(e,t){return null!=Xe().global.fetch?Xe().global.fetch(e,t):(null==Qi&&(Qi=Ji()),Qi(e,t))}now(){const e=process.hrtime();return 1e3*e[0]+e[1]/1e6}encode(e,t){if("utf-8"!==t&&"utf8"!==t)throw new Error(`Node built-in encoder only supports utf-8, but got ${t}`);return this.textEncoder.encode(e)}decode(e,t){return 0===e.length?"":new this.util.TextDecoder(t).decode(e)}isTypedArray(e){return this.util.types.isFloat32Array(e)||this.util.types.isInt32Array(e)||this.util.types.isUint8Array(e)||this.util.types.isUint8ClampedArray(e)}}function to(e,t="float32",n){return t=t||"float32",Ve(e),new pa(e,t,n)}Xe().get("IS_NODE")&&!Xe().get("IS_BROWSER")&&Xe().setPlatform("node",new eo);const no=Za({cast_:function(e,t){const n=Ka(e,"x","cast");if(!Se(t))throw new Error(`Failed to cast to unknown dtype ${t}`);if("string"===t&&"string"!==n.dtype||"string"!==t&&"string"===n.dtype)throw new Error("Only strings can be casted to strings");const s={x:n},r={dtype:t};return za.runKernel(Nt,s,r)}});const so=Za({clone_:function(e){const t={x:Ka(e,"x","clone","string_or_numeric")};return za.runKernel(yn,t)}});function ro(e,t=!1){console.log(e.toString(t))}La();function ao(){Xe().set("PROD",!0)}function io(){Xe().set("DEBUG",!0)}function oo(){Xe().set("DEPRECATION_WARNINGS_ENABLED",!1),console.warn("TensorFlow.js deprecation warnings have been disabled.")}function lo(e){Xe().getBool("DEPRECATION_WARNINGS_ENABLED")&&console.warn(e+" You can disable deprecation warnings with tf.disableDeprecationWarnings().")}function uo(){za.disposeVariables()}function co(){return za}function ho(){return za.memory()}function po(e){return za.profile(e)}function fo(e,t){return za.tidy(e,t)}function mo(e){Fa(e).forEach((e=>e.dispose()))}function go(e){return za.keep(e)}function yo(e){return za.time(e)}function bo(e){return za.setBackend(e)}function xo(){return za.ready()}function wo(){return za.backendName}function vo(e){za.removeBackend(e)}function ko(e){return za.findBackend(e)}function Io(e){return za.findBackendFactory(e)}function No(e,t,n=1){return za.registerBackend(e,t,n)}function So(){return za.backend}function To(e,t){Xe().setPlatform(e,t)}fa={buffer:to,cast:no,clone:so,print:ro},ma=lo;const Co=Za({add_:function(e,t){let n=Ka(e,"a","add"),s=Ka(t,"b","add");[n,s]=Ea(n,s);const r={a:n,b:s};return za.runKernel(st,r)}});const $o=Za({floorDiv_:function(e,t){let n=Ka(e,"a","floorDiv"),s=Ka(t,"b","floorDiv");[n,s]=Ea(n,s);const r={a:n,b:s};return za.runKernel(hn,r)}});const Eo=Za({div_:function(e,t){let n=Ka(e,"a","div"),s=Ka(t,"b","div");if([n,s]=Ea(n,s),"int32"===n.dtype&&"int32"===s.dtype)return $o(n,s);const r={a:n,b:s};return za.runKernel(Zt,r,{})}});const Ao=Za({mul_:function(e,t){let n=Ka(e,"a","mul"),s=Ka(t,"b","mul");[n,s]=Ea(n,s);const r={a:n,b:s};return za.runKernel(Zn,r)}});const Ro=Za({sqrt_:function(e){const t={x:Ka(e,"x","sqrt","float32")};return za.runKernel(zs,t)}});const Fo=Za({square_:function(e){const t=Ka(e,"x","square");return za.runKernel("Square",{x:t},{})}});const _o=Za({zerosLike_:function(e){const t={x:Ka(e,"x","zerosLike")};return za.runKernel(pr,t)}});function Do(e){return ie(_e(e),(()=>"The f passed in grad(f) must be a function")),(t,n)=>{const s=Ka(t,"x","tf.grad","string_or_numeric"),r=null!=n?Ka(n,"dy","tf.grad"):null;return za.tidy((()=>{const{value:t,grads:n}=za.gradients((()=>e(s)),[s],r);return null!=r&&oe(t.shape,r.shape,"The shape of dy passed in grad(f)(x, dy) must match the shape returned by f(x)"),Bo(n),n[0]}))}}function Oo(e){return ie(_e(e),(()=>"The f passed in grads(f) must be a function")),(t,n)=>{ie(Array.isArray(t),(()=>"The args passed in grads(f)(args) must be an array of `Tensor`s or `TensorLike`s"));const s=Xa(t,"args","tf.grads","string_or_numeric"),r=null!=n?Ka(n,"dy","tf.grads"):null;return za.tidy((()=>{const{value:t,grads:n}=za.gradients((()=>e(...s)),s,r);return null!=r&&oe(t.shape,r.shape,"The shape of dy passed in grads(f)([x1,...], dy) must match the shape returned by f([x1,...])"),Bo(n),n}))}}function Mo(e){return ie(_e(e),(()=>"The f passed in valueAndGrad(f) must be a function")),(t,n)=>{ie(t instanceof ga,(()=>"The x passed in valueAndGrad(f)(x) must be a tensor")),ie(null==n||n instanceof ga,(()=>"The dy passed in valueAndGrad(f)(x, dy) must be a tensor"));const{grads:s,value:r}=za.gradients((()=>e(t)),[t],n);return Bo(s),{grad:s[0],value:r}}}function Lo(e){return ie(_e(e),(()=>"The f passed in valueAndGrads(f) must be a function")),(t,n)=>{ie(Array.isArray(t)&&t.every((e=>e instanceof ga)),(()=>"The args passed in valueAndGrads(f)(args) must be array of tensors")),ie(null==n||n instanceof ga,(()=>"The dy passed in valueAndGrads(f)(args, dy) must be a tensor"));const s=za.gradients((()=>e(...t)),t,n);return null!=n&&oe(s.value.shape,n.shape,"The shape of dy passed in valueAndGrads(f)([x1,...], dy) must match the shape returned by f([x1,...])"),Bo(s.grads),s}}function zo(e,t){ie(_e(e),(()=>"The f passed in variableGrads(f) must be a function")),ie(null==t||Array.isArray(t)&&t.every((e=>e instanceof ba)),(()=>"The varList passed in variableGrads(f, varList) must be an array of variables"));const n=null!=t;if(!n){t=[];for(const e in za.registeredVariables)t.push(za.registeredVariables[e])}const s=n?t.filter((e=>!e.trainable)):null,r=t.length;t=t.filter((e=>e.trainable)),ie(t.length>0,(()=>`variableGrads() expects at least one of the input variables to be trainable, but none of the ${r} variables is trainable.`));const{value:a,grads:i}=za.gradients(e,t,null,!0);ie(i.some((e=>null!=e)),(()=>"Cannot find a connection between any variable and the result of the loss function y=f(x). Please make sure the operations that use variables are inside the function f passed to minimize().")),ie(0===a.rank,(()=>`The f passed in variableGrads(f) must return a scalar, but it returned a rank-${a.rank} tensor`));const o={};return t.forEach(((e,t)=>{null!=i[t]&&(o[e.name]=i[t])})),null!=s&&s.forEach((e=>o[e.name]=null)),{value:a,grads:o}}function Po(e){return za.customGrad(e)}function Bo(e){if(e.filter((e=>null==e)).length>0)throw new Error("Cannot compute gradient of y=f(x) with respect to x. Make sure that\n    the f you passed encloses all operations that lead from x to y.")}function Wo(e,t){if((Qr(e)&&"string"!==t||Array.isArray(e))&&"complex64"!==t)throw new Error("Error creating a new Scalar: value must be a primitive (number|boolean|string)");if("string"===t&&Qr(e)&&!(e instanceof Uint8Array))throw new Error("When making a scalar from encoded string, the value must be `Uint8Array`.");return Qa(e,[],[],t)}class Vo{getClassName(){return this.constructor.className}static fromConfig(e,t){return new e(t)}}class Uo{constructor(){this.classNameMap={}}static getMap(){return null==Uo.instance&&(Uo.instance=new Uo),Uo.instance}static register(e){Uo.getMap().classNameMap[e.className]=[e,e.fromConfig]}}function Go(e){ie(null!=e.className,(()=>"Class being registered does not have the static className property defined.")),ie("string"==typeof e.className,(()=>"className is required to be a string, but got type "+typeof e.className)),ie(e.className.length>0,(()=>"Class being registered has an empty-string as its className, which is disallowed.")),Uo.register(e)}class Ho extends Vo{minimize(e,t=!1,n){const{value:s,grads:r}=this.computeGradients(e,n);if(null!=n){const e=n.map((e=>({name:e.name,tensor:r[e.name]})));this.applyGradients(e)}else this.applyGradients(r);return mo(r),t?s:(s.dispose(),null)}get iterations(){return null==this.iterations_&&(this.iterations_=0),this.iterations_}incrementIterations(){this.iterations_=this.iterations+1}computeGradients(e,t){return zo(e,t)}dispose(){null!=this.iterations_&&mo(this.iterations_)}async saveIterations(){return null==this.iterations_&&(this.iterations_=0),{name:"iter",tensor:Wo(this.iterations_,"int32")}}async getWeights(){throw new Error("getWeights() is not implemented for this optimizer yet.")}async setWeights(e){throw new Error(`setWeights() is not implemented for this optimizer class ${this.getClassName()}`)}async extractIterations(e){return this.iterations_=(await e[0].tensor.data())[0],e.slice(1)}}Object.defineProperty(Ho,Symbol.hasInstance,{value:e=>null!=e.minimize&&null!=e.computeGradients&&null!=e.applyGradients});class jo extends Ho{static get className(){return"Adadelta"}constructor(e,t,n=null){super(),this.learningRate=e,this.rho=t,this.epsilon=n,this.accumulatedGrads=[],this.accumulatedUpdates=[],null==n&&(this.epsilon=za.backend.epsilon())}applyGradients(e){(Array.isArray(e)?e.map((e=>e.name)):Object.keys(e)).forEach(((t,n)=>{const s=za.registeredVariables[t];null==this.accumulatedGrads[n]&&(this.accumulatedGrads[n]={originalName:`${t}/accum_grad`,variable:fo((()=>_o(s).variable(false)))}),null==this.accumulatedUpdates[n]&&(this.accumulatedUpdates[n]={originalName:`${t}/accum_var`,variable:fo((()=>_o(s).variable(false)))});const r=Array.isArray(e)?e[n].tensor:e[t];if(null==r)return;const a=this.accumulatedGrads[n].variable,i=this.accumulatedUpdates[n].variable;fo((()=>{const e=Co(Ao(a,this.rho),Ao(Fo(r),1-this.rho)),t=Ao(Eo(Ro(Co(i,this.epsilon)),Ro(Co(a,this.epsilon))),r),n=Co(Ao(i,this.rho),Ao(Fo(t),1-this.rho));a.assign(e),i.assign(n);const o=Co(Ao(t,-this.learningRate),s);s.assign(o)}))})),this.incrementIterations()}dispose(){null!=this.accumulatedUpdates&&(mo(this.accumulatedGrads.map((e=>e.variable))),mo(this.accumulatedUpdates.map((e=>e.variable))))}async getWeights(){const e=[...this.accumulatedGrads,...this.accumulatedUpdates];return[await this.saveIterations()].concat(e.map((e=>({name:e.originalName,tensor:e.variable}))))}async setWeights(e){const t=(e=await this.extractIterations(e)).length/2;this.accumulatedGrads=e.slice(0,t).map((e=>({originalName:e.name,variable:e.tensor.variable(false)}))),this.accumulatedUpdates=e.slice(t,2*t).map((e=>({originalName:e.name,variable:e.tensor.variable(false)})))}getConfig(){return{learningRate:this.learningRate,rho:this.rho,epsilon:this.epsilon}}static fromConfig(e,t){return new e(t.learningRate,t.rho,t.epsilon)}}function qo(e,t,n){Ve(e);const s={shape:e,value:t,dtype:n=n||Fe(t)};return za.runKernel(ln,{},s)}class Ko extends Ho{static get className(){return"Adagrad"}constructor(e,t=.1){super(),this.learningRate=e,this.initialAccumulatorValue=t,this.accumulatedGrads=[]}applyGradients(e){(Array.isArray(e)?e.map((e=>e.name)):Object.keys(e)).forEach(((t,n)=>{const s=za.registeredVariables[t];if(null==this.accumulatedGrads[n]){const e=!1;this.accumulatedGrads[n]={originalName:`${t}/accumulator`,variable:fo((()=>qo(s.shape,this.initialAccumulatorValue).variable(e)))}}const r=Array.isArray(e)?e[n].tensor:e[t];if(null==r)return;const a=this.accumulatedGrads[n].variable;fo((()=>{const e=Co(a,Fo(r));a.assign(e);const t=Co(Ao(Eo(r,Ro(Co(e,za.backend.epsilon()))),-this.learningRate),s);s.assign(t)}))})),this.incrementIterations()}dispose(){null!=this.accumulatedGrads&&mo(this.accumulatedGrads.map((e=>e.variable)))}async getWeights(){return[await this.saveIterations()].concat(this.accumulatedGrads.map((e=>({name:e.originalName,tensor:e.variable}))))}async setWeights(e){e=await this.extractIterations(e);this.accumulatedGrads=e.map((e=>({originalName:e.name,variable:e.tensor.variable(false)})))}getConfig(){return{learningRate:this.learningRate,initialAccumulatorValue:this.initialAccumulatorValue}}static fromConfig(e,t){return new e(t.learningRate,t.initialAccumulatorValue)}}const Xo=Za({pow_:function(e,t){let n=Ka(e,"base","pow"),s=Ka(t,"exp","pow");[n,s]=Ea(n,s);const r={a:n,b:s};return za.runKernel(ls,r)}});const Yo=Za({sub_:function(e,t){let n=Ka(e,"a","sub"),s=Ka(t,"b","sub");[n,s]=Ea(n,s);const r={a:n,b:s};return za.runKernel(tr,r)}});class Zo extends Ho{static get className(){return"Adam"}constructor(e,t,n,s=null){super(),this.learningRate=e,this.beta1=t,this.beta2=n,this.epsilon=s,this.accumulatedFirstMoment=[],this.accumulatedSecondMoment=[],fo((()=>{this.accBeta1=Wo(t).variable(),this.accBeta2=Wo(n).variable()})),null==s&&(this.epsilon=za.backend.epsilon())}applyGradients(e){const t=Array.isArray(e)?e.map((e=>e.name)):Object.keys(e);fo((()=>{const n=Yo(1,this.accBeta1),s=Yo(1,this.accBeta2);t.forEach(((t,r)=>{const a=za.registeredVariables[t];null==this.accumulatedFirstMoment[r]&&(this.accumulatedFirstMoment[r]={originalName:`${t}/m`,variable:fo((()=>_o(a).variable(false)))}),null==this.accumulatedSecondMoment[r]&&(this.accumulatedSecondMoment[r]={originalName:`${t}/v`,variable:fo((()=>_o(a).variable(false)))});const i=Array.isArray(e)?e[r].tensor:e[t];if(null==i)return;const o=this.accumulatedFirstMoment[r].variable,l=this.accumulatedSecondMoment[r].variable,u=Co(Ao(o,this.beta1),Ao(i,1-this.beta1)),c=Co(Ao(l,this.beta2),Ao(Fo(i),1-this.beta2)),h=Eo(u,n),p=Eo(c,s);o.assign(u),l.assign(c);const d=Co(Ao(Eo(h,Co(Ro(p),this.epsilon)),-this.learningRate),a);a.assign(d)})),this.accBeta1.assign(Ao(this.accBeta1,this.beta1)),this.accBeta2.assign(Ao(this.accBeta2,this.beta2))})),this.incrementIterations()}dispose(){this.accBeta1.dispose(),this.accBeta2.dispose(),null!=this.accumulatedFirstMoment&&mo(this.accumulatedFirstMoment.map((e=>e.variable))),null!=this.accumulatedSecondMoment&&mo(this.accumulatedSecondMoment.map((e=>e.variable)))}async getWeights(){const e=[...this.accumulatedFirstMoment,...this.accumulatedSecondMoment];return[await this.saveIterations()].concat(e.map((e=>({name:e.originalName,tensor:e.variable}))))}async setWeights(e){e=await this.extractIterations(e),fo((()=>{this.accBeta1.assign(Xo(this.beta1,this.iterations_+1)),this.accBeta2.assign(Xo(this.beta2,this.iterations_+1))}));const t=e.length/2;this.accumulatedFirstMoment=e.slice(0,t).map((e=>({originalName:e.name,variable:e.tensor.variable(false)}))),this.accumulatedSecondMoment=e.slice(t,2*t).map((e=>({originalName:e.name,variable:e.tensor.variable(false)})))}getConfig(){return{learningRate:this.learningRate,beta1:this.beta1,beta2:this.beta2,epsilon:this.epsilon}}static fromConfig(e,t){return new e(t.learningRate,t.beta1,t.beta2,t.epsilon)}}const Jo=Za({abs_:function(e){const t=Ka(e,"x","abs");if("complex64"===t.dtype){const e={x:t};return za.runKernel($t,e)}{const e={x:t};return za.runKernel(et,e)}}});function Qo(e,t){const n=e.length,s=[];for(let r=0;r<n;r++){const a=n-1-r,i=e[a]||1;(t[t.length-1-r]||1)>1&&1===i&&s.unshift(a)}return s}function el(e,t){const n=[];for(let s=0;s<t.length;s++){const r=e[e.length-s-1],a=t.length-s-1,i=t[a];(null==r||1===r&&i>1)&&n.unshift(a)}return n}function tl(e,t){const n=Math.max(e.length,t.length),s=new Array(n);for(let r=0;r<n;r++){let a=e[e.length-r-1];null==a&&(a=1);let i=t[t.length-r-1];if(null==i&&(i=1),1===a)s[n-r-1]=i;else if(1===i)s[n-r-1]=a;else{if(a!==i){throw Error(`Operands could not be broadcast together with shapes ${e} and ${t}.`)}s[n-r-1]=a}}return s}const nl=Za({maximum_:function(e,t){let n=Ka(e,"a","maximum"),s=Ka(t,"b","maximum");[n,s]=Ea(n,s),"bool"===n.dtype&&(n=no(n,"int32"),s=no(s,"int32")),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(Pn,r)}});class sl extends Ho{static get className(){return"Adamax"}constructor(e,t,n,s=null,r=0){super(),this.learningRate=e,this.beta1=t,this.beta2=n,this.epsilon=s,this.decay=r,this.accumulatedFirstMoment=[],this.accumulatedWeightedInfNorm=[],fo((()=>{this.iteration=Wo(0).variable(),this.accBeta1=Wo(t).variable()})),null==s&&(this.epsilon=za.backend.epsilon())}applyGradients(e){const t=Array.isArray(e)?e.map((e=>e.name)):Object.keys(e);fo((()=>{const n=Yo(1,this.accBeta1),s=Eo(-this.learningRate,Co(Ao(this.iteration,this.decay),1));t.forEach(((t,r)=>{const a=za.registeredVariables[t];null==this.accumulatedFirstMoment[r]&&(this.accumulatedFirstMoment[r]={originalName:`${t}/m`,variable:_o(a).variable(false)}),null==this.accumulatedWeightedInfNorm[r]&&(this.accumulatedWeightedInfNorm[r]={originalName:`${t}/v`,variable:_o(a).variable(false)});const i=Array.isArray(e)?e[r].tensor:e[t];if(null==i)return;const o=this.accumulatedFirstMoment[r].variable,l=this.accumulatedWeightedInfNorm[r].variable,u=Co(Ao(o,this.beta1),Ao(i,1-this.beta1)),c=Ao(l,this.beta2),h=Jo(i),p=nl(c,h);o.assign(u),l.assign(p);const d=Co(Ao(Eo(s,n),Eo(u,Co(p,this.epsilon))),a);a.assign(d)})),this.iteration.assign(Co(this.iteration,1)),this.accBeta1.assign(Ao(this.accBeta1,this.beta1))})),this.incrementIterations()}dispose(){this.accBeta1.dispose(),this.iteration.dispose(),null!=this.accumulatedFirstMoment&&mo(this.accumulatedFirstMoment.map((e=>e.variable))),null!=this.accumulatedWeightedInfNorm&&mo(this.accumulatedWeightedInfNorm.map((e=>e.variable)))}async getWeights(){throw new Error("getWeights() is not implemented for Adamax yet.")}async setWeights(e){throw new Error("setWeights() is not implemented for Adamax yet.")}getConfig(){return{learningRate:this.learningRate,beta1:this.beta1,beta2:this.beta2,epsilon:this.epsilon,decay:this.decay}}static fromConfig(e,t){return new e(t.learningRate,t.beta1,t.beta2,t.epsilon,t.decay)}}class rl extends Ho{static get className(){return"SGD"}constructor(e){super(),this.learningRate=e,this.setLearningRate(e)}applyGradients(e){(Array.isArray(e)?e.map((e=>e.name)):Object.keys(e)).forEach(((t,n)=>{const s=Array.isArray(e)?e[n].tensor:e[t];if(null==s)return;const r=za.registeredVariables[t];fo((()=>{const e=Co(Ao(this.c,s),r);r.assign(e)}))})),this.incrementIterations()}setLearningRate(e){this.learningRate=e,null!=this.c&&this.c.dispose(),this.c=go(Wo(-e))}dispose(){this.c.dispose()}async getWeights(){return[await this.saveIterations()]}async setWeights(e){if(0!==(e=await this.extractIterations(e)).length)throw new Error("SGD optimizer does not have settable weights.")}getConfig(){return{learningRate:this.learningRate}}static fromConfig(e,t){return new e(t.learningRate)}}class al extends rl{static get className(){return"Momentum"}constructor(e,t,n=!1){super(e),this.learningRate=e,this.momentum=t,this.useNesterov=n,this.accumulations=[],this.m=Wo(this.momentum)}applyGradients(e){(Array.isArray(e)?e.map((e=>e.name)):Object.keys(e)).forEach(((t,n)=>{const s=za.registeredVariables[t];if(null==this.accumulations[n]){const e=!1;this.accumulations[n]={originalName:`${t}/momentum`,variable:fo((()=>_o(s).variable(e)))}}const r=this.accumulations[n].variable,a=Array.isArray(e)?e[n].tensor:e[t];null!=a&&fo((()=>{let e;const t=Co(Ao(this.m,r),a);e=this.useNesterov?Co(Ao(this.c,Co(a,Ao(t,this.m))),s):Co(Ao(this.c,t),s),r.assign(t),s.assign(e)}))})),this.incrementIterations()}dispose(){this.m.dispose(),null!=this.accumulations&&mo(this.accumulations.map((e=>e.variable)))}setMomentum(e){this.momentum=e}async getWeights(){return[await this.saveIterations()].concat(this.accumulations.map((e=>({name:e.originalName,tensor:e.variable}))))}async setWeights(e){e=await this.extractIterations(e);this.accumulations=e.map((e=>({originalName:e.name,variable:e.tensor.variable(false)})))}getConfig(){return{learningRate:this.learningRate,momentum:this.momentum,useNesterov:this.useNesterov}}static fromConfig(e,t){return new e(t.learningRate,t.momentum,t.useNesterov)}}class il extends Ho{static get className(){return"RMSProp"}constructor(e,t=.9,n=0,s=null,r=!1){if(super(),this.learningRate=e,this.decay=t,this.momentum=n,this.epsilon=s,this.accumulatedMeanSquares=[],this.accumulatedMoments=[],this.accumulatedMeanGrads=[],this.centered=r,null==s&&(this.epsilon=za.backend.epsilon()),null==e)throw new Error("learningRate for RMSPropOptimizer must be defined.")}applyGradients(e){(Array.isArray(e)?e.map((e=>e.name)):Object.keys(e)).forEach(((t,n)=>{const s=za.registeredVariables[t],r=!1;null==this.accumulatedMeanSquares[n]&&(this.accumulatedMeanSquares[n]={originalName:`${t}/rms`,variable:fo((()=>_o(s).variable(r)))}),null==this.accumulatedMoments[n]&&(this.accumulatedMoments[n]={originalName:`${t}/momentum`,variable:fo((()=>_o(s).variable(r)))}),null==this.accumulatedMeanGrads[n]&&this.centered&&(this.accumulatedMeanGrads[n]={originalName:`${t}/mg`,variable:fo((()=>_o(s).variable(r)))});const a=Array.isArray(e)?e[n].tensor:e[t];if(null==a)return;const i=this.accumulatedMeanSquares[n].variable,o=this.accumulatedMoments[n].variable;fo((()=>{const e=Co(Ao(i,this.decay),Ao(Fo(a),1-this.decay));if(this.centered){const t=this.accumulatedMeanGrads[n].variable,r=Co(Ao(t,this.decay),Ao(a,1-this.decay)),l=Eo(Ao(a,this.learningRate),Ro(Yo(e,Co(Fo(r),this.epsilon)))),u=Co(Ao(o,this.momentum),l);i.assign(e),t.assign(r),o.assign(u);const c=Yo(s,u);s.assign(c)}else{const e=Co(Ao(i,this.decay),Ao(Fo(a),1-this.decay)),t=Co(Ao(o,this.momentum),Eo(Ao(a,this.learningRate),Ro(Co(e,this.epsilon))));i.assign(e),o.assign(t);const n=Yo(s,t);s.assign(n)}}))})),this.incrementIterations()}dispose(){null!=this.accumulatedMeanSquares&&mo(this.accumulatedMeanSquares.map((e=>e.variable))),null!=this.accumulatedMeanGrads&&this.centered&&mo(this.accumulatedMeanGrads.map((e=>e.variable))),null!=this.accumulatedMoments&&mo(this.accumulatedMoments.map((e=>e.variable)))}async getWeights(){const e=[...this.accumulatedMeanSquares,...this.accumulatedMoments];return this.centered&&e.push(...this.accumulatedMeanGrads),[await this.saveIterations()].concat(e.map((e=>({name:e.originalName,tensor:e.variable}))))}async setWeights(e){e=await this.extractIterations(e);const t=this.centered?e.length/3:e.length/2,n=!1;this.accumulatedMeanSquares=e.slice(0,t).map((e=>({originalName:e.name,variable:e.tensor.variable(n)}))),this.accumulatedMoments=e.slice(t,2*t).map((e=>({originalName:e.name,variable:e.tensor.variable(n)}))),this.centered&&(this.accumulatedMeanGrads=e.slice(2*t,3*t).map((e=>({originalName:e.name,variable:e.tensor.variable(n)}))))}getConfig(){return{learningRate:this.learningRate,decay:this.decay,momentum:this.momentum,epsilon:this.epsilon,centered:this.centered}}static fromConfig(e,t){return new e(t.learningRate,t.decay,t.momentum,t.epsilon,t.centered)}}const ol=[jo,Ko,Zo,sl,al,il,rl];function ll(e){return new Promise((e=>setTimeout(e))).then(e)}class ul{constructor(e){if(!Xe().getBool("IS_BROWSER"))throw new Error("browserDownloads() cannot proceed because the current environment is not a browser.");e.startsWith(ul.URL_SCHEME)&&(e=e.slice(ul.URL_SCHEME.length)),null!=e&&0!==e.length||(e="model"),this.modelJsonFileName=e+".json",this.weightDataFileName=e+".weights.bin"}async save(e){if("undefined"==typeof document)throw new Error("Browser downloads are not supported in this environment since `document` is not present");const t=ni.join(e.weightData),n=window.URL.createObjectURL(new Blob([t],{type:"application/octet-stream"}));if(e.modelTopology instanceof ArrayBuffer)throw new Error("BrowserDownloads.save() does not support saving model topology in binary formats yet.");{const t=hi(e,[{paths:["./"+this.weightDataFileName],weights:e.weightSpecs}]),s=window.URL.createObjectURL(new Blob([JSON.stringify(t)],{type:"application/json"})),r=null==this.modelJsonAnchor?document.createElement("a"):this.modelJsonAnchor;if(r.download=this.modelJsonFileName,r.href=s,await ll((()=>r.dispatchEvent(new MouseEvent("click")))),null!=e.weightData){const e=null==this.weightDataAnchor?document.createElement("a"):this.weightDataAnchor;e.download=this.weightDataFileName,e.href=n,await ll((()=>e.dispatchEvent(new MouseEvent("click"))))}return{modelArtifactsInfo:fi(e)}}}}ul.URL_SCHEME="downloads://";class cl{constructor(e){if(null==e||e.length<1)throw new Error(`When calling browserFiles, at least 1 file is required, but received ${e}`);this.jsonFile=e[0],this.weightsFiles=e.slice(1)}async load(){return new Promise(((e,t)=>{const n=new FileReader;n.onload=n=>{const s=JSON.parse(n.target.result),r=s.modelTopology;if(null==r)return void t(new Error(`modelTopology field is missing from file ${this.jsonFile.name}`));if(null==s.weightsManifest)return void t(new Error(`weightManifest field is missing from file ${this.jsonFile.name}`));if(0===this.weightsFiles.length)return void e({modelTopology:r});const a=di(s,(e=>this.loadWeights(e)));e(a)},n.onerror=e=>t(`Failed to read model topology and weights manifest JSON from file '${this.jsonFile.name}'. BrowserFiles supports loading Keras-style tf.Model artifacts only.`),n.readAsText(this.jsonFile)}))}loadWeights(e){const t=[],n=[];for(const s of e)t.push(...s.weights),n.push(...s.paths);const s=this.checkManifestAndWeightFiles(e),r=n.map((e=>this.loadWeightsFile(e,s[e])));return Promise.all(r).then((e=>[t,e]))}loadWeightsFile(e,t){return new Promise(((n,s)=>{const r=new FileReader;r.onload=e=>{const t=e.target.result;n(t)},r.onerror=t=>s(`Failed to weights data from file of path '${e}'.`),r.readAsArrayBuffer(t)}))}checkManifestAndWeightFiles(e){const t=[],n=this.weightsFiles.map((e=>ci(e.name))),s={};for(const r of e)r.paths.forEach((e=>{const r=ci(e);if(-1!==t.indexOf(r))throw new Error(`Duplicate file basename found in weights manifest: '${r}'`);if(t.push(r),-1===n.indexOf(r))throw new Error(`Weight file with basename '${r}' is not provided.`);s[e]=this.weightsFiles[n.indexOf(r)]}));if(t.length!==this.weightsFiles.length)throw new Error(`Mismatch in the number of files in weights manifest (${t.length}) and the number of weight files provided (${this.weightsFiles.length}).`);return s}}function hl(e){return new cl(e)}function pl(e,t,n,s){!function(e){ie(null!=e&&Array.isArray(e)&&e.length>0,(()=>"promises must be a none empty array"))}(e),function(e,t){ie(e>=0&&e<=1,(()=>`Progress fraction must be in range [0, 1], but got startFraction ${e}`)),ie(t>=0&&t<=1,(()=>`Progress fraction must be in range [0, 1], but got endFraction ${t}`)),ie(t>=e,(()=>`startFraction must be no more than endFraction, but got startFraction ${e} and endFraction ${t}`))}(n=null==n?0:n,s=null==s?1:s);let r=0;return Promise.all(e.map((a=>(a.then((a=>{const i=n+ ++r/e.length*(s-n);return t(i),a})),a))))}async function dl(e,t){null==t&&(t={});const n=null==t.fetchFunc?Xe().platform.fetch:t.fetchFunc,s=e.map((e=>n(e,t.requestInit,{isBinary:!0}))),r=(null==t.onProgress?await Promise.all(s):await pl(s,t.onProgress,0,.5)).map((e=>e.arrayBuffer()));return null==t.onProgress?await Promise.all(r):await pl(r,t.onProgress,.5,1)}async function fl(e,t="",n,s){return ml((e=>dl(e,{requestInit:s})))(e,t,n)}function ml(e){return async(t,n="",s)=>{const r=t.map((()=>!1)),a={},i=null!=s?s.map((()=>!1)):[],o=[];if(t.forEach(((e,t)=>{let n=0;e.weights.forEach((e=>{const l="quantization"in e?e.quantization.dtype:e.dtype,u=ti[l]*ue(e.shape),c=()=>{r[t]=!0,null==a[t]&&(a[t]=[]),a[t].push({manifestEntry:e,groupOffset:n,sizeBytes:u})};null!=s?s.forEach(((t,n)=>{t===e.name&&(c(),i[n]=!0)})):c(),o.push(e.name),n+=u}))})),!i.every((e=>e))){const e=s.filter(((e,t)=>!i[t]));throw new Error(`Could not find weights in manifest with names: ${e.join(", ")}. \nManifest JSON has weights with names: ${o.join(", ")}.`)}const l=r.reduce(((e,t,n)=>(t&&e.push(n),e)),[]),u=[];l.forEach((e=>{t[e].paths.forEach((e=>{const t=n+(n.endsWith("/")?"":"/")+e;u.push(t)}))}));const c=await e(u),h={};let p=0;return l.forEach((e=>{const n=t[e].paths.length,s=new ni(c.slice(p,p+n));a[e].forEach((e=>{const t=ai(s.slice(e.groupOffset,e.groupOffset+e.sizeBytes),[e.manifestEntry]);for(const e in t)h[e]=t[e]})),p+=n})),h}}yi.registerSaveRouter((e=>Xe().getBool("IS_BROWSER")&&!Array.isArray(e)&&e.startsWith(ul.URL_SCHEME)?function(e="model"){return new ul(e)}(e.slice(ul.URL_SCHEME.length)):null));class gl{constructor(e,t){if(this.DEFAULT_METHOD="POST",null==t&&(t={}),this.weightPathPrefix=t.weightPathPrefix,this.onProgress=t.onProgress,this.weightUrlConverter=t.weightUrlConverter,null!=t.fetchFunc?(ie("function"==typeof t.fetchFunc,(()=>"Must pass a function that matches the signature of `fetch` (see https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API)")),this.fetch=t.fetchFunc):this.fetch=Xe().platform.fetch,ie(null!=e&&e.length>0,(()=>"URL path for http must not be null, undefined or empty.")),Array.isArray(e)&&ie(2===e.length,(()=>`URL paths for http must have a length of 2, (actual length is ${e.length}).`)),this.path=e,null!=t.requestInit&&null!=t.requestInit.body)throw new Error("requestInit is expected to have no pre-existing body, but has one.");this.requestInit=t.requestInit||{}}async save(e){if(e.modelTopology instanceof ArrayBuffer)throw new Error("BrowserHTTPRequest.save() does not support saving model topology in binary formats yet.");const t=Object.assign({method:this.DEFAULT_METHOD},this.requestInit);t.body=new FormData;const n=hi(e,[{paths:["./model.weights.bin"],weights:e.weightSpecs}]);if(t.body.append("model.json",new Blob([JSON.stringify(n)],{type:"application/json"}),"model.json"),null!=e.weightData){const n=ni.join(e.weightData);t.body.append("model.weights.bin",new Blob([n],{type:"application/octet-stream"}),"model.weights.bin")}const s=await this.fetch(this.path,t);if(s.ok)return{modelArtifactsInfo:fi(e),responses:[s]};throw new Error(`BrowserHTTPRequest.save() failed due to HTTP response status ${s.status}.`)}async load(){const e=await this.fetch(this.path,this.requestInit);if(!e.ok)throw new Error(`Request to ${this.path} failed with status code ${e.status}. Please verify this URL points to the model JSON of the model to load.`);let t;try{t=await e.json()}catch(e){let t=`Failed to parse model JSON of response from ${this.path}.`;throw this.path.endsWith(".pb")?t+=" Your path contains a .pb file extension. Support for .pb models have been removed in TensorFlow.js 1.0 in favor of .json models. You can re-convert your Python TensorFlow model using the TensorFlow.js 1.0 conversion scripts or you can convert your.pb models with the 'pb2json'NPM script in the tensorflow/tfjs-converter repository.":t+=" Please make sure the server is serving valid JSON for this request.",new Error(t)}const n=t.modelTopology,s=t.weightsManifest;if(null==n&&null==s)throw new Error(`The JSON from HTTP path ${this.path} contains neither model topology or manifest for weights.`);return di(t,(e=>this.loadWeights(e)))}async loadWeights(e){const t=Array.isArray(this.path)?this.path[1]:this.path,[n,s]=function(e){const t=e.lastIndexOf("/"),n=e.lastIndexOf("?"),s=e.substring(0,t),r=n>t?e.substring(n):"";return[s+"/",r]}(t),r=this.weightPathPrefix||n,a=mi(e),i=[],o=[];for(const t of e)for(const e of t.paths)null!=this.weightUrlConverter?o.push(this.weightUrlConverter(e)):i.push(r+e+s);this.weightUrlConverter&&i.push(...await Promise.all(o));return[a,await dl(i,{requestInit:this.requestInit,fetchFunc:this.fetch,onProgress:this.onProgress})]}}function yl(e){return null!=e.match(gl.URL_SCHEME_REGEX)}gl.URL_SCHEME_REGEX=/^https?:\/\//;const bl=(e,t)=>{if("undefined"==typeof fetch&&(null==t||null==t.fetchFunc))return null;{let n=!0;if(n=Array.isArray(e)?e.every((e=>yl(e))):yl(e),n)return xl(e,t)}return null};function xl(e,t){return new gl(e,t)}function wl(e,t){return xl(e,t)}yi.registerSaveRouter(bl),yi.registerLoadRouter(bl);class vl{constructor(e){this.modelArtifacts=e}load(){return this.modelArtifacts}}class kl{constructor(e){this.saveHandler=e}save(e){return this.saveHandler(e)}}class Il{constructor(e){e.load&&(this.load=()=>Promise.resolve(e.load())),e.save&&(this.save=t=>Promise.resolve(e.save(t)))}}function Nl(e,t,n,s){return new Il(Sl(...arguments))}function Sl(e,t,n,s){if(1===arguments.length){return null!=e.modelTopology||null!=e.weightSpecs?new vl(e):(console.warn("Please call tf.io.fromMemory() with only one argument. The argument should be of type ModelArtifacts. The multi-argument signature of tf.io.fromMemory() has been deprecated and will be removed in a future release."),new vl({modelTopology:e}))}return console.warn("Please call tf.io.fromMemory() with only one argument. The argument should be of type ModelArtifacts. The multi-argument signature of tf.io.fromMemory() has been deprecated and will be removed in a future release."),new vl({modelTopology:e,weightSpecs:t,weightData:n,trainingConfig:s})}function Tl(e){return new kl(e)}function Cl(e){return new kl(e)}const $l=Za({matMul_:function(e,t,n=!1,s=!1){let r=Ka(e,"a","matMul"),a=Ka(t,"b","matMul");[r,a]=Ea(r,a);const i={a:r,b:a},o={transposeA:n,transposeB:s};return za.runKernel(bt,i,o)}});const El=Za({oneHot_:function(e,t,n=1,s=0,r="int32"){if(t<2)throw new Error(`Error in oneHot: depth must be >=2, but it is ${t}`);const a={indices:Ka(e,"indices","oneHot","int32")},i={dtype:r,depth:t,onValue:n,offValue:s};return za.runKernel(rs,a,i)}});const Al=Za({imag_:function(e){const t={input:Ka(e,"input","imag")};return za.runKernel(xn,t)}});const Rl=Za({neg_:function(e){const t={x:Ka(e,"x","neg")};return za.runKernel(Jn,t)}});const Fl=Za({real_:function(e){const t={input:Ka(e,"input","real")};return za.runKernel(ms,t)}});const _l=Za({transpose_:function(e,t,n){const s=Ka(e,"x","transpose");if(null==t&&(t=s.shape.map(((e,t)=>t)).reverse()),ie(s.rank===t.length,(()=>`Error in transpose: rank of input ${s.rank} must match length of perm ${t}.`)),t.forEach((e=>{ie(e>=0&&e<s.rank,(()=>"All entries in 'perm' must be between 0 and "+(s.rank-1)+` but got ${t}`))})),s.rank<=1)return s.clone();const r={x:s},a={perm:t};return"complex64"===s.dtype?fo((()=>{let e=Fl(s),t=Al(s);return e=za.runKernel(or,{x:e},a),t=za.runKernel(or,{x:t},a),n&&(t=Rl(t)),Ja(e,t)})):za.runKernel(or,r,a)}});const Dl=Za({confusionMatrix_:function(e,t,n){const s=Ka(e,"labels","confusionMatrix"),r=Ka(t,"predictions","confusionMatrix");ie(null==n||n>0&&Number.isInteger(n),(()=>`If provided, numClasses must be a positive integer, but got ${n}`)),ie(1===s.rank,(()=>`Expected the rank of labels to be 1, but got ${s.rank}`)),ie(1===r.rank,(()=>`Expected the rank of predictions to be 1, but got ${r.rank}`)),ie(s.shape[0]===r.shape[0],(()=>`Mismatch in the number of examples: ${s.shape[0]} vs. ${r.shape[0]}. Labels and predictions should have the same number of elements.`)),ie(n>0&&Number.isInteger(n),(()=>`numClasses is required to be a positive integer, but got ${n}`));const a=El(no(s,"int32"),n),i=El(no(r,"int32"),n),o=_l(a),l=$l(o,i);return no(l,"int32")}});function Ol(e,t,n){if(le(e),null!=t&&3!==t.length)throw new Error("tensor3d() requires shape to have three numbers");const s=Ha(e,n);if(3!==s.length&&1!==s.length)throw new Error("tensor3d() requires values to be number[][][] or flat/TypedArray");if(1===s.length&&null==t)throw new Error("tensor3d() requires shape to be provided when `values` are a flat array");return Qa(e,t,s,n)}let Ml,Ll=!1;function zl(e,t=3){if(t>4)throw new Error("Cannot construct Tensor with more than 4 channels from pixels.");if(null==e)throw new Error("pixels passed to tf.browser.fromPixels() can not be null");let n=!1,s=!1,r=!1,a=!1,i=!1,o=!1;if(e.data instanceof Uint8Array)n=!0;else if("undefined"!=typeof ImageData&&e instanceof ImageData)s=!0;else if("undefined"!=typeof HTMLVideoElement&&e instanceof HTMLVideoElement)r=!0;else if("undefined"!=typeof HTMLImageElement&&e instanceof HTMLImageElement)a=!0;else if(null!=e.getContext)i=!0;else{if(!("undefined"!=typeof ImageBitmap&&e instanceof ImageBitmap))throw new Error(`pixels passed to tf.browser.fromPixels() must be either an HTMLVideoElement, HTMLImageElement, HTMLCanvasElement, ImageData in browser, or OffscreenCanvas, ImageData in webworker or {data: Uint32Array, width: number, height: number}, but was ${e.constructor.name}`);o=!0}if(null!=Ir(fr,za.backendName)){const n={pixels:e},s={numChannels:t};return za.runKernel(fr,n,s)}const[l,u]=r?[e.videoWidth,e.videoHeight]:[e.width,e.height];let c,h;if(i)c=e.getContext("2d").getImageData(0,0,l,u).data;else if(s||n)c=e.data;else if(a||r||o){if(null==Ml)if("undefined"==typeof document){if("undefined"==typeof OffscreenCanvas||"undefined"==typeof OffscreenCanvasRenderingContext2D)throw new Error("Cannot parse input in current context. Reason: OffscreenCanvas Context2D rendering is not supported.");Ml=new OffscreenCanvas(1,1).getContext("2d")}else Ml=document.createElement("canvas").getContext("2d",{willReadFrequently:!0});Ml.canvas.width=l,Ml.canvas.height=u,Ml.drawImage(e,0,0,l,u),c=Ml.getImageData(0,0,l,u).data}if(4===t)h=new Int32Array(c);else{const e=l*u;h=new Int32Array(e*t);for(let n=0;n<e;n++)for(let e=0;e<t;++e)h[n*t+e]=c[4*n+e]}return Ol(h,[u,l,t],"int32")}function Pl(e){return"undefined"!=typeof window&&"undefined"!=typeof ImageBitmap&&window.hasOwnProperty("createImageBitmap")&&!(e instanceof ImageBitmap)&&function(e){return null!=e&&0!==e.width&&0!==e.height}(e)&&!function(e){return null!=e&&e.data instanceof Uint8Array}(e)}async function Bl(e,t=3){let n=null;if(Xe().getBool("WRAP_TO_IMAGEBITMAP")&&Pl(e)){let t;try{t=await createImageBitmap(e,{premultiplyAlpha:"none"})}catch(e){t=null}n=null!=t&&t.width===e.width&&t.height===e.height?t:e}else n=e;return zl(n,t)}function Wl(e){if(2!==e.rank&&3!==e.rank)throw new Error(`toPixels only supports rank 2 or 3 tensors, got rank ${e.rank}.`);const t=2===e.rank?1:e.shape[2];if(t>4||2===t)throw new Error(`toPixels only supports depth of size 1, 3 or 4 but got ${t}`);if("float32"!==e.dtype&&"int32"!==e.dtype)throw new Error(`Unsupported type for toPixels: ${e.dtype}. Please use float32 or int32 tensors.`)}async function Vl(e,t){let n=Ka(e,"img","toPixels");if(!(e instanceof ga)){const e=n;n=no(e,"int32"),e.dispose()}Wl(n);const[s,r]=n.shape.slice(0,2),a=2===n.rank?1:n.shape[2],i=await n.data(),o="float32"===n.dtype?255:1,l=new Uint8ClampedArray(r*s*4);for(let e=0;e<s*r;++e){const t=[0,0,0,255];for(let s=0;s<a;s++){const r=i[e*a+s];if("float32"===n.dtype){if(r<0||r>1)throw new Error(`Tensor values for a float32 Tensor must be in the range [0 - 1] but encountered ${r}.`)}else if("int32"===n.dtype&&(r<0||r>255))throw new Error(`Tensor values for a int32 Tensor must be in the range [0 - 255] but encountered ${r}.`);1===a?(t[0]=r*o,t[1]=r*o,t[2]=r*o):t[s]=r*o}const s=4*e;l[s+0]=Math.round(t[0]),l[s+1]=Math.round(t[1]),l[s+2]=Math.round(t[2]),l[s+3]=Math.round(t[3])}if(null!=t){Ll||(console.warn("tf.browser.toPixels is not efficient to draw tensor on canvas. Please try tf.browser.draw instead."),Ll=!0),t.width=r,t.height=s;const e=t.getContext("2d"),n=new ImageData(l,r,s);e.putImageData(n,0,0)}return n!==e&&n.dispose(),l}function Ul(e,t,n){let s=Ka(e,"img","draw");if(!(e instanceof ga)){const e=s;s=no(e,"int32"),e.dispose()}Wl(s),function(e){const t=(null==e?void 0:e.alpha)||1;if(t>1||t<0)throw new Error(`Alpha value ${t} is suppoed to be in range [0 - 1].`)}(null==n?void 0:n.imageOptions);const r={image:s},a={canvas:t,options:n};za.runKernel(Yt,r,a)}const Gl=Za({fromPixels_:zl});function Hl(e,t){const n=e.shape.length,s=t.shape.length;if(n<1)throw new Error(`tf.gatherND() expects the input to be rank 1 or higher, but the rank was ${n}.`);if(s<1)throw new Error(`tf.gatherND() expects the indices to be rank 1 or higher, but the rank was ${s}.`);if("int32"!==t.dtype)throw new Error(`tf.gatherND() expects the indices to be int32 type, but the dtype was ${t.dtype}.`);if(t.shape[s-1]>n)throw new Error(`index innermost dimension length must be <= tensor rank; saw: ${t.shape[s-1]} vs. ${n}`);if(0===ue(e.shape))throw new Error(`Requested more than 0 entries, but input is empty. Input shape: ${e.shape}.`);const r=t.shape,a=r[r.length-1];let i=1;for(let e=0;e<r.length-1;++e)i*=r[e];const o=e.shape,l=r.slice();l.pop();let u=1;for(let e=a;e<n;++e)u*=o[e],l.push(o[e]);const c=[...Oe(e.shape).map((e=>e/u)),1].slice(0,a);return[l,i,u,c]}function jl(e,t,n){const s=t.rank>1?t.shape[t.rank-1]:1,r=t.rank>1?t.rank-1:1,a=`Must have updates.shape = indices.shape[:batchDim] + shape[sliceDim:], got updates.shape: ${n.shape}, indices.shape: ${t.shape}, shape: ${e}, sliceDim: ${s}, and batchDim: ${r}.`;if(n.rank<r)throw new Error(a+` update.rank < ${r}. `);if(e.length<s+(n.rank-r))throw new Error(a+` Output shape length < ${s+(n.rank-r)}`);if(n.rank!==r+e.length-s)throw new Error(a+" update.rank != "+(r+e.length-s));for(let e=0;e<r;++e)if(n.shape[e]!==t.shape[e])throw new Error(a+` updates.shape[${e}] (${n.shape[e]}) != indices.shape[${e}] (${t.shape[e]}).`);for(let t=0;t<n.rank-r;++t)if(n.shape[t+r]!==e[t+s])throw new Error(a+` updates.shape[${t+r}] (${n.shape[t+r]}) != shape[${t+r}] (${e[t+r]})`)}function ql(e,t,n){if(t.rank<1)throw new Error(`tf.scatterND() expects the indices to be rank 1 or higher, but the rank was ${t.rank}.`);if(e.rank<1)throw new Error(`tf.scatterND() expects the updates to be rank 1 or higher, but the rank was ${e.rank}.`);if("int32"!==t.dtype)throw new Error(`The dtype of 'indices' should be int32, but got dtype: ${t.dtype}`);if(n.length<1)throw new Error(`Output rank must be greater or equal to 1, but got shape: ${n}`);if(0===n.length){if(0===t.size)throw new Error(`Indices specified for empty output. indices shape: ${t.shape}`);if(0===e.size)throw new Error(`Updates specified for empty output. updates shape: ${e.shape}`)}jl(n,t,e)}function Kl(e,t,n){const s=t.shape.length,r=s>1?t.shape[s-1]:1,a=n.length;let i=1;for(let e=r;e<a;++e)i*=n[e];const o=r<1?1:r;return{sliceRank:r,numUpdates:ue(t.shape)/o,sliceSize:i,strides:[...Oe(n.slice(0,r)),1],outputSize:ue(n)}}const Xl=-2,Yl=-1;function Zl(e,t,n){const s=e.shape.length;ie(s===t.length,(()=>`Error in slice${s}D: Length of begin ${t} must match the rank of the array (${s}).`)),ie(s===n.length,(()=>`Error in slice${s}D: Length of size ${n} must match the rank of the array (${s}).`));for(let r=0;r<s;++r)ie(t[r]+n[r]<=e.shape[r],(()=>`Error in slice${s}D: begin[${r}] + size[${r}] (${t[r]+n[r]}) would overflow input.shape[${r}] (${e.shape[r]})`))}function Jl(e){const t=[];let n=0;for(;e>0;)1&e&&t.push(n),e/=2,n++;return t}function Ql(e,t,n){const s=[];for(let r=0;r<e.length;r++)s[r]=Math.ceil((t[r]-e[r])/n[r]);return s}function eu(e,t,n,s){const r=[...e];for(let e=r.length;e<s.length;e++)r.push(1);for(let e=0;e<n;e++)0===e?r[t]=1:(r.splice(t,0,1),r.pop());return r}function tu(e,t,n){return n<=e?n:n-(t-1)}function nu(e,t){const n=[];for(let s=0;s<e;s++)n.push(t+s);return n}function su(e,t,n,s,r,a,i,o,l){const u=e.length;let c=new Array(u),h=new Array(u),p=new Array(u);if(t.length&&n>0){const l=t[0],u=n+1;c=ru(i,l,u,s,e),h=au(o,l,u,r,e),p=eu(a,l,u,e)}else for(let t=0;t<u;t++)c[t]=ou(i,s,a,e,t,l),h[t]=lu(o,r,a,e,t,l),p[t]=iu(a,t,l);return{begin:c,end:h,strides:p}}function ru(e,t,n,s,r){const a=[...r],i=nu(n,t);for(let r=0;r<a.length;r++)if(i.indexOf(r)>-1)a[r]=0;else{const i=tu(t,n,r);let o=s[i];e&1<<i&&(o=0),a[r]=o}return a}function au(e,t,n,s,r){const a=[...r],i=nu(n,t);for(let r=0;r<a.length;r++)if(i.indexOf(r)>-1)a[r]=Number.MAX_SAFE_INTEGER;else{const i=tu(t,n,r);let o=s[i];e&1<<i&&(o=Number.MAX_SAFE_INTEGER),a[r]=o}for(let e=0;e<a.length;e++){const t=r[e];a[e]<0&&(a[e]+=t),a[e]=ee(0,a[e],r[e])}return a}function iu(e,t,n){let s=e[t];return(n&1<<t||null==s)&&(s=1),s}function ou(e,t,n,s,r,a){let i=t[r];const o=n[r]||1;(e&1<<r||a&1<<r||null==i)&&(i=o>0?Number.MIN_SAFE_INTEGER:Number.MAX_SAFE_INTEGER);const l=s[r];return i<0&&(i+=l),i=ee(0,i,l-1),i}function lu(e,t,n,s,r,a){let i=t[r];const o=n[r]||1;(e&1<<r||a&1<<r||null==i)&&(i=o>0?Number.MAX_SAFE_INTEGER:Number.MIN_SAFE_INTEGER);const l=s[r];return i<0&&(i+=l),i=o>0?ee(0,i,l):ee(-1,i,l-1),i}function uu(e,t,n){let s=n.length;for(let e=0;e<n.length;e++)if(n[e]>1){s=e;break}for(let r=s+1;r<n.length;r++)if(t[r]>0||n[r]!==e[r])return!1;return!0}function cu(e,t){let n=e.length>0?e[e.length-1]:1;for(let s=0;s<e.length-1;s++)n+=e[s]*t[s];return n}function hu(e,t,n){let s;const r=e.shape.length;let a;return s="number"==typeof t?[t,...new Array(r-1).fill(0)]:t.length<r?t.concat(new Array(r-t.length).fill(0)):t.slice(),s.forEach((e=>{ie(-1!==e,(()=>"slice() does not support negative begin indexing."))})),a=null==n?new Array(r).fill(-1):"number"==typeof n?[n,...new Array(r-1).fill(-1)]:n.length<r?n.concat(new Array(r-n.length).fill(-1)):n,a=a.map(((t,n)=>t>=0?t:(ie(-1===t,(()=>`Negative size values should be exactly -1 but got ${t} for the slice() size at index ${n}.`)),e.shape[n]-s[n]))),[s,a]}function pu(e,t,n,s,r,a,i,o,l){let u;if(null==s?(u=new Array(t.length),u.fill(1)):u=s,null!=i&&0!=(i&i-1))throw new Error("Multiple ellipses in slice is not allowed.");let c=!1;const h={dims:u.length,numAddAxisAfterEllipsis:0,begin:t.slice(),end:n.slice(),strides:u.slice(),beginMask:r,endMask:a,ellipsisMask:i,newAxisMask:o,shrinkAxisMask:l};for(let e=0;e<h.dims;e++)c&&0!=(1<<e&o)&&h.numAddAxisAfterEllipsis++,1<<e&i&&(c=!0);c||(h.ellipsisMask|=1<<h.dims,h.dims++);const p={dims:e.length,beginMask:0,endMask:0,beginValid:!1,endValid:!1};!function(e,t){t.beginMask=0,t.endMask=0,t.shrinkAxisMask=0;let n=0;t.beginValid=null!=e.begin,t.endValid=null!=e.end,t.begin=new Array(t.dims),t.end=new Array(t.dims),t.strides=new Array(t.dims),t.finalShapeGatherIndices=[],t.finalShapeGatherIndicesSparse=[],t.inputShapeGatherIndicesSparse=new Array(t.dims);for(let s=0;s<e.dims;s++)if(1<<s&e.ellipsisMask){const r=Math.min(t.dims-(e.dims-s)+1+e.numAddAxisAfterEllipsis,t.dims);for(;n<r;n++)t.begin[n]=0,t.end[n]=0,t.strides[n]=1,t.beginMask|=1<<n,t.endMask|=1<<n,t.finalShapeGatherIndices.push(n),t.finalShapeGatherIndicesSparse.push(-1),t.inputShapeGatherIndicesSparse[n]=s}else if(1<<s&e.newAxisMask)t.finalShapeGatherIndices.push(Xl),t.finalShapeGatherIndicesSparse.push(-1);else{if(n===t.begin.length)throw Error(`Index out of range using input dim ${n}; input has only ${t.dims} dims, ${t.begin.length}.`);null!=e.begin&&(t.begin[n]=e.begin[s]),null!=e.end&&(t.end[n]=e.end[s]),t.strides[n]=e.strides[s],e.beginMask&1<<s&&(t.beginMask|=1<<n),e.endMask&1<<s&&(t.endMask|=1<<n),e.shrinkAxisMask&1<<s?(t.finalShapeGatherIndices.push(Yl),t.finalShapeGatherIndicesSparse.push(-1),t.shrinkAxisMask|=1<<n):(t.finalShapeGatherIndices.push(n),t.finalShapeGatherIndicesSparse.push(s)),t.inputShapeGatherIndicesSparse[n]=s,n++}}(h,p);let d=!0,f=!0,m=!0;const g=[],y=[];for(let t=0;t<e.length;++t){if(0===p.strides[t])throw Error(`strides[${t}] must be non-zero`);const n=!!(p.shrinkAxisMask&1<<t),s=e[t];if(-1===s){g.push(n?1:-1);continue}const r=[p.beginMask&1<<t,p.endMask&1<<t],a=[p.strides[t]>0?0:-1,p.strides[t]>0?s:s-1];if(n&&p.strides[t]<=0)throw Error("only stride 1 allowed on non-range indexing.");m=m&&1===p.strides[t];const i=!!(p.beginMask&1<<t&&p.endMask&1<<t);if(p.beginValid&&p.endValid){if(n){const e=p.begin[t]<0?s+p.begin[t]:p.begin[t];if(p.begin[t]=e,p.end[t]=p.begin[t]+1,e<0||e>=s)throw Error(`slice index ${p.begin[t]} of dimension ${t} out of bounds.`)}else p.begin[t]=du(p.begin[t],0,p.strides[t],s,r,a),p.end[t]=du(p.end[t],1,p.strides[t],s,r,a);const e=1===p.strides[t]&&0===p.begin[t]&&p.end[t]===s;d=d&&e,f=f&&(0===t&&1===p.strides[t]||e)}else d=d&&1===p.strides[t]&&i,f=f&&(0===t&&1===p.strides[t]||i);let o,l=!1;if(p.beginValid&&p.endValid?(o=p.end[t]-p.begin[t],l=!0):n?(o=1,l=!0):i&&s>=0&&(o=p.strides[t]<0?-s:s,l=!0),l){let e;e=0===o||o<0!=p.strides[t]<0?0:Math.trunc(o/p.strides[t])+(o%p.strides[t]!=0?1:0),g.push(e)}else g.push(-1)}for(let e=0;e<p.finalShapeGatherIndices.length;++e){const t=p.finalShapeGatherIndices[e];t>=0?y.push(g[t]):t===Xl&&y.push(1)}return{finalShapeSparse:y.filter(((e,t)=>p.finalShapeGatherIndices[t]!==Xl)),finalShape:y,isIdentity:d,sliceDim0:f,isSimpleSlice:m,begin:p.begin,end:p.end,strides:p.strides}}function du(e,t,n,s,r,a){if(r[t])return n>0?a[t]:a[t+1&1];{const t=e<0?s+e:e;return t<a[0]?a[0]:t>a[1]?a[1]:t}}const fu=.001,mu=.1;function gu(e,t,n){return null==n&&(n=yu()),bu(e,t,((e,t)=>ku(e,t,n)))}function yu(){return 32===za.backend.floatPrecision()?fu:mu}function bu(e,t,n){let s=!0;if((Qr(e)||Qr(t))&&(s=!1),Qr(e)&&Qr(t)&&(s=!0),s){const n=e.constructor.name,s=t.constructor.name;if(n!==s)throw new Error(`Arrays are of different type. Actual: ${n}. Expected: ${s}`)}if(Array.isArray(e)&&Array.isArray(t)){const n=Ha(e),s=Ha(t);if(!pe(n,s))throw new Error(`Arrays have different shapes. Actual: [${n}]. Expected: [${s}]`)}const r=Qr(e)?e:ea(e),a=Qr(t)?t:ea(t);if(r.length!==a.length)throw new Error(`Arrays have different lengths actual: ${r.length} vs expected: ${a.length}.\nActual:   ${r}.\nExpected: ${a}.`);for(let e=0;e<a.length;++e){const t=r[e],s=a[e];if(!n(t,s))throw new Error(`Arrays differ: actual[${e}] = ${t}, expected[${e}] = ${s}.\nActual:   ${r}.\nExpected: ${a}.`)}"undefined"!=typeof expect&&expect().nothing()}function xu(e,t){e().then((()=>t.fail()),(()=>t())),"undefined"!=typeof expect&&expect().nothing()}function wu(e,t){const n="string"==typeof t||"number"==typeof t||"boolean"==typeof t?[t]:t;return Ee(e)||Ee(e[0])||Ee(t)||Ee(t[0])?bu(e,n,((e,t)=>e==t)):bu(e,t,((e,t)=>ku(e,t,0)))}function vu(e,t,n){if(null==n&&(n=yu()),!ku(e,t,n))throw new Error(`Numbers differ: actual === ${e}, expected === ${t}`);"undefined"!=typeof expect&&expect().nothing()}function ku(e,t,n){return!isFinite(e)&&!isFinite(t)||!(isNaN(e)||isNaN(t)||Math.abs(e-t)>n)}function Iu(e,t,n){for(let s=0;s<e.length;s++)if(e[s]<t||e[s]>n)throw new Error(`Value out of range:${e[s]} low: ${t}, high: ${n}`)}function Nu(e,t){const n=new Float32Array(e),s=new Float32Array(t);if(n.length!==s.length)throw new Error(`Expected ArrayBuffer to be of length ${s.length}, but it was ${n.length}`);for(let e=0;e<s.length;e++)if(n[e]!==s[e])throw new Error(`Expected ArrayBuffer value at ${e} to be ${s[e]} but got ${n[e]} instead`)}function Su(e){for(let t=0;t<e.length;t++){const n=e[t];Array.isArray(n)?Su(n):e[t]=Zr(n)}return e}function Tu(e){const t=document.createElement("video");return"playsInline"in t&&(t.playsInline=!0),t.muted=!0,t.loop=!0,t.style.position="fixed",t.style.left="0px",t.style.top="0px",t.preload="auto",t.appendChild(e),new Promise((e=>{t.addEventListener("loadeddata",(n=>e(t))),t.load()}))}async function Cu(e){await e.play(),"requestVideoFrameCallback"in e&&await new Promise((t=>{e.requestVideoFrameCallback(t)}))}const $u="4.6.0";class Eu{static sgd(e){return new rl(e)}static momentum(e,t,n=!1){return new al(e,t,n)}static rmsprop(e,t=.9,n=0,s=null,r=!1){return new il(e,t,n,s,r)}static adam(e=.001,t=.9,n=.999,s=null){return new Zo(e,t,n,s)}static adadelta(e=.001,t=.95,n=null){return new jo(e,t,n)}static adamax(e=.002,t=.9,n=.999,s=null,r=0){return new sl(e,t,n,s,r)}static adagrad(e,t=.1){return new Ko(e,t)}}const Au=Za({acos_:function(e){const t={x:Ka(e,"x","acos")};return za.runKernel(tt,t)}});const Ru=Za({acosh_:function(e){const t={x:Ka(e,"x","acosh")};return za.runKernel(nt,t)}});const Fu=Za({addN_:function(e){ie(Array.isArray(e),(()=>"The argument passed to tf.addN() must be a list of tensors")),ie(e.length>=1,(()=>`Must pass at least one tensor to tf.addN(), but got ${e.length}`));const t=e.map(((e,t)=>Ka(e,`tensors${t}`,"addN"))),n=t[0];t.forEach((e=>{if(e.dtype!==n.dtype)throw new Error("All tensors passed to tf.addN() must have the same dtype")})),t.forEach((e=>{if(!pe(e.shape,n.shape))throw new Error("All tensors passed to tf.addN() must have the same shape")}));const s=t;return za.runKernel(rt,s)}});const _u=Za({all_:function(e,t=null,n=!1){const s={x:Ka(e,"x","all","bool")},r={axis:t,keepDims:n};return za.runKernel(at,s,r)}});const Du=Za({any_:function(e,t=null,n=!1){const s={x:Ka(e,"x","any","bool")},r={axis:t,keepDims:n};return za.runKernel(it,s,r)}});const Ou=Za({argMax_:function(e,t=0){const n={x:Ka(e,"x","argMax")},s={axis:t};return za.runKernel(ot,n,s)}});const Mu=Za({argMin_:function(e,t=0){const n={x:Ka(e,"x","argMin")},s={axis:t};return za.runKernel(lt,n,s)}});const Lu=Za({asin_:function(e){const t={x:Ka(e,"x","asin")};return za.runKernel(ut,t)}});const zu=Za({asinh_:function(e){const t={x:Ka(e,"x","asinh")};return za.runKernel(ct,t)}});const Pu=Za({atan_:function(e){const t={x:Ka(e,"x","atan")};return za.runKernel(ht,t)}});const Bu=Za({atan2_:function(e,t){let n=Ka(e,"a","atan2"),s=Ka(t,"b","atan2");[n,s]=Ea(n,s);const r={a:n,b:s};return za.runKernel(dt,r)}});const Wu=Za({atanh_:function(e){const t={x:Ka(e,"x","atanh")};return za.runKernel(pt,t)}});function Vu(e,t,n,s,r="NHWC",a){return Hu(e,[...t,e[3]],n,a,s,null,null,tc(r))}function Uu(e,t,n,s,r,a,i="channelsLast"){const[o,l]=Ku(t);let u;if("channelsLast"===i)u=[o,l,e[3],e[3]];else{if("channelsFirst"!==i)throw new Error(`Unknown dataFormat ${i}`);u=[o,l,e[1],e[1]]}return Hu(e,u,n,s,r,a,!1,i)}function Gu(e,t,n,s,r,a,i="NDHWC"){const[o,l,u]=Xu(t);let c,h;if("NDHWC"===i)h="channelsLast",c=[o,l,u,e[4],e[4]];else{if("NCDHW"!==i)throw new Error(`Unknown dataFormat ${i}`);h="channelsFirst",c=[o,l,u,e[1],e[1]]}return ju(e,c,n,s,r,!1,h,a)}function Hu(e,t,n,s,r,a,i=!1,o="channelsLast"){let[l,u,c,h]=[-1,-1,-1,-1];if("channelsLast"===o)[l,u,c,h]=e;else{if("channelsFirst"!==o)throw new Error(`Unknown dataFormat ${o}`);[l,h,u,c]=e}const[p,d,,f]=t,[m,g]=Ku(n),[y,b]=Ku(s),x=Yu(p,y),w=Yu(d,b),{padInfo:v,outHeight:k,outWidth:I}=function(e,t,n,s,r,a,i,o,l){let u,c,h;if("number"==typeof e){u={top:e,bottom:e,left:e,right:e,type:0===e?"VALID":"NUMBER"};const r=function(e,t,n,s,r){null==s&&(s=qu(e,t,n));const a=e[0],i=e[1],o=Zu((a-t+2*s)/n+1,r),l=Zu((i-t+2*s)/n+1,r);return[o,l]}([t,n],a,s,e,o);c=r[0],h=r[1]}else if("same"===e){c=Math.ceil(t/s),h=Math.ceil(n/r);const e=Math.max(0,(c-1)*s+a-t),o=Math.max(0,(h-1)*r+i-n),l=Math.floor(e/2),p=e-l,d=Math.floor(o/2);u={top:l,bottom:p,left:d,right:o-d,type:"SAME"}}else if("valid"===e)u={top:0,bottom:0,left:0,right:0,type:"VALID"},c=Math.ceil((t-a+1)/s),h=Math.ceil((n-i+1)/r);else{if("object"!=typeof e)throw Error(`Unknown padding parameter: ${e}`);{const p="channelsLast"===l?e[1][0]:e[2][0],d="channelsLast"===l?e[1][1]:e[2][1],f="channelsLast"===l?e[2][0]:e[3][0],m="channelsLast"===l?e[2][1]:e[3][1];u={top:p,bottom:d,left:f,right:m,type:0===p&&0===d&&0===f&&0===m?"VALID":"EXPLICIT"},c=Zu((t-a+p+d)/s+1,o),h=Zu((n-i+f+m)/r+1,o)}}return{padInfo:u,outHeight:c,outWidth:h}}(r,u,c,m,g,x,w,a,o),N=i?f*h:f;let S;return"channelsFirst"===o?S=[l,N,k,I]:"channelsLast"===o&&(S=[l,k,I,N]),{batchSize:l,dataFormat:o,inHeight:u,inWidth:c,inChannels:h,outHeight:k,outWidth:I,outChannels:N,padInfo:v,strideHeight:m,strideWidth:g,filterHeight:p,filterWidth:d,effectiveFilterHeight:x,effectiveFilterWidth:w,dilationHeight:y,dilationWidth:b,inShape:e,outShape:S,filterShape:t}}function ju(e,t,n,s,r,a=!1,i="channelsLast",o){let[l,u,c,h,p]=[-1,-1,-1,-1,-1];if("channelsLast"===i)[l,u,c,h,p]=e;else{if("channelsFirst"!==i)throw new Error(`Unknown dataFormat ${i}`);[l,p,u,c,h]=e}const[d,f,m,,g]=t,[y,b,x]=Xu(n),[w,v,k]=Xu(s),I=Yu(d,w),N=Yu(f,v),S=Yu(m,k),{padInfo:T,outDepth:C,outHeight:$,outWidth:E}=function(e,t,n,s,r,a,i,o,l,u,c){let h,p,d,f;"valid"===e&&(e=0);if("number"==typeof e){h={top:e,bottom:e,left:e,right:e,front:e,back:e,type:0===e?"VALID":"NUMBER"};const m=function(e,t,n,s,r,a){null==r&&(r=qu(e,t[0],s[0]));const i=[0,0,0,n];for(let n=0;n<3;n++)e[n]+2*r>=t[n]&&(i[n]=Zu((e[n]-t[n]+2*r)/s[n]+1,a));return i}([t,n,s,1],[o,l,u],1,[r,a,i],e,c);p=m[0],d=m[1],f=m[2]}else{if("same"!==e)throw Error(`Unknown padding parameter: ${e}`);{p=Math.ceil(t/r),d=Math.ceil(n/a),f=Math.ceil(s/i);const e=(p-1)*r+o-t,c=(d-1)*a+l-n,m=(f-1)*i+u-s,g=Math.floor(e/2),y=e-g,b=Math.floor(c/2),x=c-b,w=Math.floor(m/2);h={top:b,bottom:x,left:w,right:m-w,front:g,back:y,type:"SAME"}}}return{padInfo:h,outDepth:p,outHeight:d,outWidth:f}}(r,u,c,h,y,b,x,I,N,S,o),A=a?g*p:g;let R;return"channelsFirst"===i?R=[l,A,C,$,E]:"channelsLast"===i&&(R=[l,C,$,E,A]),{batchSize:l,dataFormat:i,inDepth:u,inHeight:c,inWidth:h,inChannels:p,outDepth:C,outHeight:$,outWidth:E,outChannels:A,padInfo:T,strideDepth:y,strideHeight:b,strideWidth:x,filterDepth:d,filterHeight:f,filterWidth:m,effectiveFilterDepth:I,effectiveFilterHeight:N,effectiveFilterWidth:S,dilationDepth:w,dilationHeight:v,dilationWidth:k,inShape:e,outShape:R,filterShape:t}}function qu(e,t,n,s=1){const r=Yu(t,s);return Math.floor((e[0]*(n-1)-n+r)/2)}function Ku(e){return"number"==typeof e?[e,e,e]:2===e.length?[e[0],e[1],1]:e}function Xu(e){return"number"==typeof e?[e,e,e]:e}function Yu(e,t){return t<=1?e:e+(e-1)*(t-1)}function Zu(e,t){if(!t)return Math.trunc(e);switch(t){case"round":return Math.round(e);case"ceil":return Math.ceil(e);case"floor":return Math.floor(e);default:throw new Error(`Unknown roundingMode ${t}`)}}function Ju(e){const[t,n,s]=Ku(e);return 1===t&&1===n&&1===s}function Qu(e,t){return Ju(e)||Ju(t)}function ec(e){return Ku(e).every((e=>e>0))}function tc(e){if("NHWC"===e)return"channelsLast";if("NCHW"===e)return"channelsFirst";throw new Error(`Unknown dataFormat ${e}`)}function nc(e,t,n){if(null!=n){if("string"==typeof t)throw Error(`Error in ${e}: pad must be an integer when using dimRoundingMode ${n} but got pad ${t}.`);if("number"==typeof t)ie(de(t),(()=>`Error in ${e}: pad must be an integer when using dimRoundingMode ${n} but got pad ${t}.`));else{if("object"!=typeof t)throw Error(`Error in ${e}: Unknown padding parameter: ${t}`);t.forEach((t=>{t.forEach((t=>{ie(de(t),(()=>`Error in ${e}: pad must be an integer when using dimRoundingMode ${n} but got pad ${t}.`))}))}))}}}const sc=Za({reshape_:function(e,t){const n={x:Ka(e,"x","reshape","string_or_numeric")},s={shape:t};return za.runKernel(bs,n,s)}});const rc=Za({avgPool_:function(e,t,n,s,r){const a=Ka(e,"x","avgPool","float32");ie(Qu(n,1),(()=>`Error in avgPool: Either strides or dilations must be 1. Got strides ${n} and dilations '1'`));let i=a,o=!1;3===a.rank&&(o=!0,i=sc(a,[1,a.shape[0],a.shape[1],a.shape[2]])),ie(4===i.rank,(()=>`Error in avgPool: x must be rank 4 but got rank ${i.rank}.`)),nc("avgPool",s,r);const l={x:i},u={filterSize:t,strides:n,pad:s,dimRoundingMode:r};let c=za.runKernel(ft,l,u);return c=no(c,a.dtype),o?sc(c,[c.shape[1],c.shape[2],c.shape[3]]):c}});const ac=Za({avgPool3d_:function(e,t,n,s,r,a="NDHWC"){const i=Ka(e,"x","avgPool3d","float32");let o=i,l=!1;4===i.rank&&(l=!0,o=sc(i,[1,i.shape[0],i.shape[1],i.shape[2],i.shape[3]])),ie(5===o.rank,(()=>`Error in avgPool3d: x must be rank 5 but got rank ${o.rank}.`)),ie("NDHWC"===a,(()=>`Error in avgPool3d: Only NDHWC is currently supported, but got dataFormat of ${a}`)),ie("number"==typeof n&&n>0||Array.isArray(n)&&n[0]>0&&n[1]>0&&n[2]>0,(()=>`Error in avgPool3d: Stride must be > 0, but got '${n}'`)),nc("avgPool3d",s,r);const u={x:o},c={filterSize:t,strides:n,pad:s,dimRoundingMode:r,dataFormat:a};let h=za.runKernel(gt,u,c);return h=no(h,o.dtype),l?sc(h,[h.shape[1],h.shape[2],h.shape[3],h.shape[4]]):h}});const ic=Za({concat_:function(e,t=0){ie(e.length>=1,(()=>"Pass at least one tensor to concat"));const n=Xa(e,"tensors","concat","string_or_numeric");if("complex64"===n[0].dtype&&n.forEach((e=>{if("complex64"!==e.dtype)throw new Error(`Cannot concatenate complex64 tensors with a tensor\n          with dtype ${e.dtype}. `)})),1===n.length)return so(n[0]);const s=n,r={axis:t};return za.runKernel(Et,s,r)}});const oc=Za({sigmoid_:function(e){const t={x:Ka(e,"x","sigmoid","float32")};return za.runKernel(Ms,t)}});const lc=Za({slice_:function(e,t,n){const s=Ka(e,"x","slice","string_or_numeric");if(0===s.rank)throw new Error("Slicing scalar is not possible");const r={x:s},a={begin:t,size:n};return za.runKernel(Fs,r,a)}});const uc=Za({tanh_:function(e){const t={x:Ka(e,"x","tanh","float32")};return za.runKernel(sr,t)}});const cc=Za({basicLSTMCell_:function(e,t,n,s,r,a){const i=Ka(e,"forgetBias","basicLSTMCell"),o=Ka(t,"lstmKernel","basicLSTMCell"),l=Ka(n,"lstmBias","basicLSTMCell"),u=Ka(s,"data","basicLSTMCell"),c=Ka(r,"c","basicLSTMCell"),h=Ka(a,"h","basicLSTMCell"),p=ic([u,h],1),d=$l(p,o),f=Co(d,l),m=f.shape[0],g=f.shape[1]/4,y=[m,g],b=lc(f,[0,0],y),x=lc(f,[0,g],y),w=lc(f,[0,2*g],y),v=lc(f,[0,3*g],y),k=Co(Ao(oc(b),uc(x)),Ao(c,oc(Co(i,w))));return[k,Ao(uc(k),oc(v))]}});const hc=Za({batchToSpaceND_:function(e,t,n){const s=Ka(e,"x","batchToSpaceND"),r=t.reduce(((e,t)=>e*t));ie(s.rank>=1+t.length,(()=>`input rank is ${s.rank} but should be > than blockShape.length ${t.length}`)),ie(n.length===t.length,(()=>`crops.length is ${n.length} but should be equal to blockShape.length  ${t.length}`)),ie(s.shape[0]%r==0,(()=>`input tensor batch is ${s.shape[0]} but is not divisible by the product of the elements of blockShape ${t.join(" * ")} === ${r}`));const a={x:s},i={blockShape:t,crops:n};return za.runKernel(xt,a,i)}});const pc=Za({batchNorm_:function(e,t,n,s,r,a){null==a&&(a=.001);const i=Ka(e,"x","batchNorm"),o=Ka(t,"mean","batchNorm"),l=Ka(n,"variance","batchNorm");let u,c;null!=r&&(u=Ka(r,"scale","batchNorm")),null!=s&&(c=Ka(s,"offset","batchNorm")),ie(o.rank===l.rank,(()=>"Batch normalization gradient requires mean and variance to have equal ranks.")),ie(null==c||o.rank===c.rank,(()=>"Batch normalization gradient requires mean and offset to have equal ranks.")),ie(null==u||o.rank===u.rank,(()=>"Batch normalization gradient requires mean and scale to have equal ranks."));const h={x:function(e){let t;return t=0===e.rank||1===e.rank?sc(e,[1,1,1,e.size]):2===e.rank?sc(e,[1,1,e.shape[0],e.shape[1]]):3===e.rank?sc(e,[1,e.shape[0],e.shape[1],e.shape[2]]):e,t}(i),scale:u,offset:c,mean:o,variance:l},p={varianceEpsilon:a},d=za.runKernel(pn,h,p);return sc(d,i.shape)}});const dc=Za({batchNorm2d_:function(e,t,n,s,r,a){const i=Ka(e,"x","batchNorm"),o=Ka(t,"mean","batchNorm"),l=Ka(n,"variance","batchNorm");let u,c;return null!=r&&(u=Ka(r,"scale","batchNorm")),null!=s&&(c=Ka(s,"offset","batchNorm")),ie(2===i.rank,(()=>`Error in batchNorm2D: x must be rank 2 but got rank ${i.rank}.`)),ie(2===o.rank||1===o.rank,(()=>`Error in batchNorm2D: mean must be rank 2 or rank 1 but got rank ${o.rank}.`)),ie(2===l.rank||1===l.rank,(()=>`Error in batchNorm2D: variance must be rank 2 or rank 1 but got rank ${l.rank}.`)),null!=u&&ie(2===u.rank||1===u.rank,(()=>`Error in batchNorm2D: scale must be rank 2 or rank 1 but got rank ${u.rank}.`)),null!=c&&ie(2===c.rank||1===c.rank,(()=>`Error in batchNorm2D: offset must be rank 2 or rank 1 but got rank ${c.rank}.`)),pc(i,o,l,c,u,a)}});const fc=Za({batchNorm3d_:function(e,t,n,s,r,a){const i=Ka(e,"x","batchNorm"),o=Ka(t,"mean","batchNorm"),l=Ka(n,"variance","batchNorm");let u,c;return null!=r&&(u=Ka(r,"scale","batchNorm")),null!=s&&(c=Ka(s,"offset","batchNorm")),ie(3===i.rank,(()=>`Error in batchNorm3D: x must be rank 3 but got rank ${i.rank}.`)),ie(3===o.rank||1===o.rank,(()=>`Error in batchNorm3D: mean must be rank 3 or rank 1 but got rank ${o.rank}.`)),ie(3===l.rank||1===l.rank,(()=>`Error in batchNorm3D: variance must be rank 3 or rank 1 but got rank ${l.rank}.`)),null!=u&&ie(3===u.rank||1===u.rank,(()=>`Error in batchNorm3D: scale must be rank 3 or rank 1 but got rank ${u.rank}.`)),null!=c&&ie(3===c.rank||1===c.rank,(()=>`Error in batchNorm3D: offset must be rank 3 or rank 1 but got rank ${c.rank}.`)),pc(i,o,l,c,u,a)}});const mc=Za({batchNorm4d_:function(e,t,n,s,r,a){const i=Ka(e,"x","batchNorm"),o=Ka(t,"mean","batchNorm"),l=Ka(n,"variance","batchNorm");let u,c;return null!=r&&(u=Ka(r,"scale","batchNorm")),null!=s&&(c=Ka(s,"offset","batchNorm")),ie(4===i.rank,(()=>`Error in batchNorm4D: x must be rank 4 but got rank ${i.rank}.`)),ie(4===o.rank||1===o.rank,(()=>`Error in batchNorm4D: mean must be rank 4 or rank 1 but got rank ${o.rank}.`)),ie(4===l.rank||1===l.rank,(()=>`Error in batchNorm4D: variance must be rank 4 or rank 1 but got rank ${l.rank}.`)),null!=u&&ie(4===u.rank||1===u.rank,(()=>`Error in batchNorm4D: scale must be rank 4 or rank 1 but got rank ${u.rank}.`)),null!=c&&ie(4===c.rank||1===c.rank,(()=>`Error in batchNorm4D: offset must be rank 4 or rank 1 but got rank ${c.rank}.`)),pc(i,o,l,c,u,a)}});const gc=Za({bincount_:function(e,t,n){const s=Ka(e,"x","bincount"),r=Ka(t,"weights","bincount");ie("int32"===s.dtype,(()=>`Error in bincount: input dtype must be int32, but got ${s.dtype}`)),ie(n>=0,(()=>`size must be non-negative, but got ${n}.`)),ie(r.size===s.size||0===r.size,(()=>`Error in bincount: weights must have the same size as input or0-length, but got input shape: ${s.shape}, weights shape: ${r.shape}.`));const a={x:s,weights:r},i={size:n};return za.runKernel(wt,a,i)}});const yc=Za({bitwiseAnd_:function(e,t){const n=Ka(e,"x","bitwiseAnd"),s=Ka(t,"y","bitwiseAnd");if(!pe(n.shape,s.shape))throw new Error(`BitwiseAnd: Tensors must have the same shape. x: ${n.shape}, y: ${s.shape}`);if("int32"!==n.dtype||"int32"!==s.dtype)throw new Error(`BitwiseAnd: Only supports 'int32' values in tensor, found type of x: ${n.dtype} and type of y: ${s.dtype}`);const r={a:n,b:s};return za.runKernel(vt,r)}});const bc=Za({broadcastArgs_:function(e,t){const n=Ka(e,"s0","broadcastArgs","int32"),s=Ka(t,"s1","broadcastArgs","int32");if(1!==n.rank)throw new Error(`broadcastArgs(): first input must be a vector (rank=1). Has rank ${n.rank}`);if(1!==s.rank)throw new Error(`broadcastArgs(): second input must be a vector (rank=1). Has rank ${s.rank}`);const r={s0:n,s1:s};return za.runKernel(It,r)}});const xc=Za({broadcastTo_:function(e,t){let n=Ka(e,"broadcastTo","x");const s=n.shape;if(Ve(t),t.length<n.rank)throw new Error(`broadcastTo(): shape.length=${t.length} < input.rank=${n.rank}.`);if(t.length>n.rank){const e=n.shape.slice();for(;e.length<t.length;)e.unshift(1);n=sc(n,e)}const r=n.shape,a=Array.from(t);for(let e=t.length-1;e>=0;e--)if(r[e]===t[e])a[e]=1;else if(1!==n.shape[e])throw new Error(`broadcastTo(): [${s}] cannot be broadcast to [${t}].`);if(0===a.map(((e,t)=>e>1?t:-1)).filter((e=>e>=0)).length)return so(n);const i={x:n},o={reps:a};return za.runKernel(rr,i,o)}});const wc=Za({ceil_:function(e){const t={x:Ka(e,"x","ceil","float32")};return za.runKernel(St,t)}});const vc=Za({clipByValue_:function(e,t,n){const s=Ka(e,"x","clipByValue");if(ie(t<=n,(()=>`Error in clip: min (${t}) must be less than or equal to max (${n}).`)),t===n)return qo(s.shape,t,s.dtype);const r={x:s},a={clipValueMin:t,clipValueMax:n};return za.runKernel(Tt,r,a)}});const kc=Za({concat1d_:function(e){return ic(e,0)}});const Ic=Za({concat2d_:function(e,t){return ic(e,t)}});const Nc=Za({concat3d_:function(e,t){return ic(e,t)}});const Sc=Za({concat4d_:function(e,t){return ic(e,t)}});const Tc=Za({conv2d_:function(e,t,n,s,r="NHWC",a=[1,1],i){const o=Ka(e,"x","conv2d","float32"),l=Ka(t,"filter","conv2d","float32");let u=o,c=!1;3===o.rank&&(c=!0,u=sc(o,[1,o.shape[0],o.shape[1],o.shape[2]])),ie(4===u.rank,(()=>`Error in conv2d: input must be rank 4, but got rank ${u.rank}.`)),ie(4===l.rank,(()=>`Error in conv2d: filter must be rank 4, but got rank ${l.rank}.`)),nc("conv2d",s,i);const h="NHWC"===r?u.shape[3]:u.shape[1];ie(h===l.shape[2],(()=>`Error in conv2d: depth of input (${h}) must match input depth for filter ${l.shape[2]}.`)),ie(Qu(n,a),(()=>`Error in conv2D: Either strides or dilations must be 1. Got strides ${n} and dilations '${a}'`)),ie(ec(a),(()=>"Error in conv2D: Dilated rates should be larger than 0.")),ie(ec(n),(()=>"Error in conv2D: Strides should be larger than 0."));const p={x:u,filter:l},d={strides:n,pad:s,dataFormat:r,dilations:a,dimRoundingMode:i},f=za.runKernel(At,p,d);return c?sc(f,[f.shape[1],f.shape[2],f.shape[3]]):f}});const Cc=Za({conv1d_:function(e,t,n,s,r="NWC",a=1,i){const o=Ka(e,"x","conv1d"),l=Ka(t,"filter","conv1d");let u=o,c=!1;2===o.rank&&(c=!0,u=sc(o,[1,o.shape[0],o.shape[1]])),ie(3===u.rank,(()=>`Error in conv1d: input must be rank 3, but got rank ${u.rank}.`)),ie(3===l.rank,(()=>`Error in conv1d: filter must be rank 3, but got rank ${l.rank}.`)),nc("conv1d",s,i),ie(u.shape[2]===l.shape[1],(()=>`Error in conv1d: depth of input (${u.shape[2]}) must match input depth for filter ${l.shape[1]}.`)),ie(Qu(n,a),(()=>`Error in conv1D: Either stride or dilation must be 1. Got stride ${n} and dilation '${a}'`)),ie(ec(a),(()=>"Error in conv1D: Dilated rates should be larger than 0.")),ie(ec(n),(()=>"Error in conv1D: Stride should be larger than 0.")),ie("NWC"===r,(()=>`Error in conv1d: got dataFormat of ${r} but only NWC is currently supported.`));const h=sc(l,[1,l.shape[0],l.shape[1],l.shape[2]]),p=sc(u,[u.shape[0],1,u.shape[1],u.shape[2]]),d=Tc(p,h,[1,n],s,"NHWC",[1,a],i);return sc(d,c?[d.shape[2],d.shape[3]]:[d.shape[0],d.shape[2],d.shape[3]])}});const $c=Za({conv2DBackpropInput_:function(e,t,n,s,r,a="NHWC",i){ie(e.length===t.rank,(()=>`Length of inShape (${e.length}) and rank of dy (${t.rank}) must match`));let o=e,l=t,u=!1;3===t.rank&&(u=!0,l=sc(t,[1,t.shape[0],t.shape[1],t.shape[2]]),o=[1,e[0],e[1],e[2]]),ie(4===o.length,(()=>`Error in conv2dDerInput: inShape must be length 4, but got length ${o.length}.`)),ie(4===l.rank,(()=>`Error in conv2dDerInput: dy must be rank 4, but got rank ${l.rank}`)),ie(4===n.rank,(()=>`Error in conv2dDerInput: filter must be rank 4, but got rank ${n.rank}`));const c="NHWC"===a?o[3]:o[1],h="NHWC"===a?l.shape[3]:l.shape[1];ie(c===n.shape[2],(()=>`Error in conv2dDerInput: depth of input (${c}) must match input depth for filter ${n.shape[2]}.`)),ie(h===n.shape[3],(()=>`Error in conv2dDerInput: depth of output (${h}) must match output depth for filter ${n.shape[3]}.`)),nc("conv2dDerInput",r,i);const p={dy:l,filter:n},d={strides:s,pad:r,dataFormat:a,dimRoundingMode:i,inputShape:o},f=za.runKernel(Ft,p,d);return u?sc(f,[f.shape[1],f.shape[2],f.shape[3]]):f}});const Ec=Za({conv2dTranspose_:function(e,t,n,s,r,a){const i=Ka(e,"x","conv2dTranspose"),o=Ka(t,"filter","conv2dTranspose");return $c(n,i,o,s,r,"NHWC",a)}});const Ac=Za({conv3d_:function(e,t,n,s,r="NDHWC",a=[1,1,1]){const i=Ka(e,"x","conv3d"),o=Ka(t,"filter","conv3d");let l=i,u=!1;4===i.rank&&(u=!0,l=sc(i,[1,i.shape[0],i.shape[1],i.shape[2],i.shape[3]])),ie(5===l.rank,(()=>`Error in conv3d: input must be rank 5, but got rank ${l.rank}.`)),ie(5===o.rank,(()=>`Error in conv3d: filter must be rank 5, but got rank ${o.rank}.`)),ie(l.shape[4]===o.shape[3],(()=>`Error in conv3d: depth of input (${l.shape[4]}) must match input depth for filter ${o.shape[3]}.`)),ie(Qu(n,a),(()=>`Error in conv3D: Either strides or dilations must be 1. Got strides ${n} and dilations '${a}'`)),ie("NDHWC"===r,(()=>`Error in conv3d: got dataFormat of ${r} but only NDHWC is currently supported.`)),ie(ec(a),(()=>"Error in conv3D: Dilated rates should be larger than 0.")),ie(ec(n),(()=>"Error in conv3D: Strides should be larger than 0."));const c={x:l,filter:o},h={strides:n,pad:s,dataFormat:r,dilations:a},p=za.runKernel(_t,c,h);return u?sc(p,[p.shape[1],p.shape[2],p.shape[3],p.shape[4]]):p}});const Rc=Za({conv3DBackpropInput_:function(e,t,n,s,r){ie(e.length===t.rank,(()=>`Length of inShape (${e.length}) and rank of dy (${t.rank}) must match`));let a=e,i=t,o=!1;4===t.rank&&(o=!0,i=sc(t,[1,t.shape[0],t.shape[1],t.shape[2],t.shape[3]]),a=[1,e[0],e[1],e[2],e[3]]);const l=a[4],u=i.shape[4];ie(5===a.length,(()=>`Error in conv3dDerInput: inShape must be length 5, but got length ${a.length}.`)),ie(5===i.rank,(()=>`Error in conv3dDerInput: dy must be rank 5, but got rank ${i.rank}`)),ie(5===n.rank,(()=>`Error in conv3dDerInput: filter must be rank 5, but got rank ${n.rank}`)),ie(l===n.shape[3],(()=>`Error in conv3dDerInput: depth of input (${l}) must match input depth for filter ${n.shape[3]}.`)),ie(u===n.shape[4],(()=>`Error in conv3dDerInput: depth of output (${u}) must match output depth for filter ${n.shape[4]}.`));const c={dy:i,filter:n},h={pad:r,strides:s,inputShape:a},p=za.runKernel(Ot,c,h);return o?sc(p,[p.shape[1],p.shape[2],p.shape[3],p.shape[4]]):p}});const Fc=Za({conv3dTranspose_:function(e,t,n,s,r){const a=Ka(e,"x","conv3dTranspose"),i=Ka(t,"filter","conv3dTranspose");return Rc(n,a,i,s,r)}});const _c=Za({cos_:function(e){const t={x:Ka(e,"x","cos","float32")};return za.runKernel(Mt,t)}});const Dc=Za({cosh_:function(e){const t={x:Ka(e,"x","cosh","float32")};return za.runKernel(Lt,t)}});const Oc=Za({cumprod_:function(e,t=0,n=!1,s=!1){const r={x:Ka(e,"x","cumprod")},a={axis:t,exclusive:n,reverse:s};return za.runKernel(zt,r,a)}});const Mc=Za({cumsum_:function(e,t=0,n=!1,s=!1){const r={x:Ka(e,"x","cumsum")},a={axis:t,exclusive:n,reverse:s};return za.runKernel(Pt,r,a)}});const Lc=Za({denseBincount_:function(e,t,n,s=!1){const r=Ka(e,"x","denseBincount"),a=Ka(t,"weights","denseBincount");ie("int32"===r.dtype,(()=>`Error in denseBincount: input dtype must be int32, but got ${r.dtype}`)),ie(r.rank<=2,(()=>`Error in denseBincount: input must be at most rank 2, but got rank ${r.rank}.`)),ie(n>=0,(()=>`size must be non-negative, but got ${n}.`)),ie(a.size===r.size||0===a.size,(()=>`Error in denseBincount: weights must have the same shape as x or 0-length, but got x shape: ${r.shape}, weights shape: ${a.shape}.`));const i={x:r,weights:a},o={size:n,binaryOutput:s};return za.runKernel(Wt,i,o)}});const zc=Za({depthToSpace_:function(e,t,n="NHWC"){const s=Ka(e,"x","depthToSpace","float32"),r="NHWC"===n?s.shape[1]:s.shape[2],a="NHWC"===n?s.shape[2]:s.shape[3],i="NHWC"===n?s.shape[3]:s.shape[1];ie(t>1,(()=>`blockSize should be > 1 for depthToSpace, but was: ${t}`)),ie(r*t>=0,(()=>`Negative dimension size caused by overflow when multiplying\n    ${r} and ${t}  for depthToSpace with input shape\n    ${s.shape}`)),ie(a*t>=0,(()=>`Negative dimension size caused by overflow when multiplying\n    ${a} and ${t} for depthToSpace with input shape\n        ${s.shape}`)),ie(i%(t*t)==0,(()=>`Dimension size must be evenly divisible by ${t*t} but is ${i} for depthToSpace with input shape ${s.shape}`));const o={x:s},l={blockSize:t,dataFormat:n};return za.runKernel(Vt,o,l)}});const Pc=Za({depthwiseConv2d_:function(e,t,n,s,r="NHWC",a=[1,1],i){const o=Ka(e,"x","depthwiseConv2d","float32"),l=Ka(t,"filter","depthwiseConv2d","float32");let u=o,c=!1;3===o.rank&&(c=!0,u=sc(o,[1,o.shape[0],o.shape[1],o.shape[2]])),ie(4===u.rank,(()=>`Error in depthwiseConv2d: input must be rank 4, but got rank ${u.rank}.`)),ie(4===l.rank,(()=>`Error in depthwiseConv2d: filter must be rank 4, but got rank ${l.rank}.`));const h="NHWC"===r?u.shape[3]:u.shape[1];ie(h===l.shape[2],(()=>`Error in depthwiseConv2d: number of input channels (${h}) must match the inChannels dimension in filter ${l.shape[2]}.`)),nc("depthwiseConv2d",s,i);const p={x:u,filter:l},d={strides:n,pad:s,dataFormat:r,dilations:a,dimRoundingMode:i},f=za.runKernel(Ut,p,d);return c?sc(f,[f.shape[1],f.shape[2],f.shape[3]]):f}});const Bc=Za({diag_:function(e){const t={x:Ka(e,"x","diag")};return za.runKernel(jt,t)}});const Wc=Za({dilation2d_:function(e,t,n,s,r=[1,1],a="NHWC"){const i=Ka(e,"x","dilation2d"),o=Ka(t,"filter","dilation2d");ie(3===i.rank||4===i.rank,(()=>`Error in dilation2d: input must be rank 3 or 4, but got rank ${i.rank}.`)),ie(3===o.rank,(()=>`Error in dilation2d: filter must be rank 3, but got rank ${o.rank}.`)),ie("NHWC"===a,(()=>`Error in dilation2d: Only NHWC is currently supported, but got dataFormat of ${a}`));let l=i,u=!1;3===i.rank&&(l=sc(i,[1,i.shape[0],i.shape[1],i.shape[2]]),u=!0),ie(l.shape[3]===o.shape[2],(()=>`Error in dilation2d:  input and filter must have the same depth: ${l.shape[3]} vs ${o.shape[2]}`));const c={x:l,filter:o},h={strides:n,pad:s,dilations:r},p=za.runKernel(qt,c,h);return u?sc(p,[p.shape[1],p.shape[2],p.shape[3]]):p}});const Vc=Za({equal_:function(e,t){let n=Ka(e,"a","equal","string_or_numeric"),s=Ka(t,"b","equal","string_or_numeric");[n,s]=Ea(n,s),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(nn,r)}});const Uc=Za({where_:function(e,t,n){const s=Ka(t,"a","where"),r=Ka(n,"b","where"),a=Ka(e,"condition","where","bool"),i=tl(tl(a.shape,s.shape),r.shape),o={condition:xc(a,i),t:xc(s,i),e:xc(r,i)};return za.runKernel(As,o)}});const Gc=Za({divNoNan_:function(e,t){let n=Ka(e,"a","div"),s=Ka(t,"b","div");[n,s]=Ea(n,s);const r=Eo(n,s),a=_o(r),i=Vc(s,a);return Uc(i,a,r)}});const Hc=Za({dot_:function(e,t){const n=Ka(e,"t1","dot"),s=Ka(t,"t2","dot");ie(!(1!==n.rank&&2!==n.rank||1!==s.rank&&2!==s.rank),(()=>`Error in dot: inputs must all be rank 1 or 2, but got ranks ${n.rank} and ${s.rank}.`));const r=1===n.rank?n.size:n.shape[1],a=1===s.rank?s.size:s.shape[0];if(ie(r===a,(()=>`Error in dot: inner dimensions of inputs must match, but got ${r} and ${a}.`)),1===n.rank&&1===s.rank){const e=sc(n,[1,-1]),t=sc(s,[-1,1]),r=$l(e,t);return sc(r,[])}if(1===n.rank&&2===s.rank){const e=sc(n,[1,-1]),t=sc(s,[s.shape[0],s.shape[1]]),r=$l(e,t);return sc(r,[r.size])}if(2===n.rank&&1===s.rank){const e=sc(s,[-1,1]),t=$l(n,e);return sc(t,[t.size])}{const e=sc(s,[s.shape[0],s.shape[1]]);return $l(n,e)}}});const jc=Za({einsum_:function(e,...t){const n=t.map(((e,t)=>Ka(e,`tensors${t}`,"einsum"))),s={equation:e};return za.runKernel(Jt,n,s)}});const qc=Za({elu_:function(e){const t={x:Ka(e,"x","elu","float32")};return za.runKernel(Qt,t)}});const Kc=Za({ensureShape_:function(e,t){const n=Ka(e,"x","ensureShape","string_or_numeric");if(!he(n.shape,t))throw new Error(`EnsureShape: Shape of tensor ${n.shape} is not compatible with expected shape ${t}`);return e}});const Xc=Za({erf_:function(e){let t=Ka(e,"x","erf");ie("int32"===t.dtype||"float32"===t.dtype,(()=>"Input dtype must be `int32` or `float32`.")),"int32"===t.dtype&&(t=no(t,"float32"));const n={x:t};return za.runKernel(tn,n)}});function Yc(e,t){for(let n=0;n<e.length;++n)if(e[e.length-n-1]!==t-1-n)return!1;return!0}function Zc(e,t,n){const s=e.length+t.length,r=[];let a=0,i=0;for(let o=0;o<s;o++)-1===n.indexOf(o)?r.push(e[a++]):r.push(t[i++]);return r}function Jc(e,t){const n=[],s=e.length;for(let r=0;r<s;r++)-1===t.indexOf(r)&&n.push(e[r]);return[n,t.map((t=>e[t]))]}function Qc(e,t){return Zc(e,t.map((e=>1)),t)}function eh(e,t,n){ie(Yc(t,n),(()=>`${e} supports only inner-most axes for now. Got axes ${t} and rank-${n} input.`))}function th(e,t){if(Yc(e,t))return null;const n=[];for(let s=0;s<t;++s)-1===e.indexOf(s)&&n.push(s);return e.forEach((e=>n.push(e))),n}function nh(e){return e.map(((e,t)=>[t,e])).sort(((e,t)=>e[1]-t[1])).map((e=>e[0]))}function sh(e,t){const n=[];for(let s=t-e;s<t;++s)n.push(s);return n}const rh=Za({max_:function(e,t=null,n=!1){const s={x:Ka(e,"x","max")},r={reductionIndices:t,keepDims:n};return za.runKernel(zn,s,r)}});const ah=Za({min_:function(e,t=null,n=!1){const s={x:Ka(e,"x","min")},r={axis:t,keepDims:n};return za.runKernel(jn,s,r)}});const ih=Za({sum_:function(e,t=null,n=!1){let s=Ka(e,"x","sum");"bool"===s.dtype&&(s=no(s,"int32"));const r={x:s},a={axis:t,keepDims:n};return za.runKernel(Ps,r,a)}});function oh(e,t,n=null){if(0===e.rank)return Jo(e);if(1!==e.rank&&null===n)return oh(sc(e,[-1]),t,n);if(1===e.rank||"number"==typeof n||Array.isArray(n)&&1===n.length){if(1===t)return ih(Jo(e),n);if(t===1/0)return rh(Jo(e),n);if(t===-1/0)return ah(Jo(e),n);if("euclidean"===t||2===t)return Ro(ih(Xo(Jo(e),Wo(2,"int32")),n));throw new Error(`Error in norm: invalid ord value: ${t}`)}if(Array.isArray(n)&&2===n.length){if(1===t)return rh(ih(Jo(e),n[0]),n[1]-1);if(t===1/0)return rh(ih(Jo(e),n[1]),n[0]);if(t===-1/0)return ah(ih(Jo(e),n[1]),n[0]);if("fro"===t||"euclidean"===t)return Ro(ih(Fo(e),n));throw new Error(`Error in norm: invalid ord value: ${t}`)}throw new Error(`Error in norm: invalid axis: ${n}`)}const lh=Za({norm_:function(e,t="euclidean",n=null,s=!1){const r=oh(e=Ka(e,"x","norm"),t,n);let a=r.shape;if(s){const t=we(n,e.shape);a=Qc(r.shape,t)}return sc(r,a)}});const uh=Za({euclideanNorm_:function(e,t=null,n=!1){return lh(e,"euclidean",t,n)}});const ch=Za({exp_:function(e){const t={x:Ka(e,"x","exp")};return za.runKernel(sn,t)}});const hh=Za({expandDims_:function(e,t=0){const n=Ka(e,"x","expandDims","string_or_numeric");ie(t<=n.rank,(()=>"Axis must be <= rank of the tensor"));const s={input:n},r={dim:t};return za.runKernel(rn,s,r)}});const ph=Za({expm1_:function(e){const t={x:Ka(e,"x","expm1")};return za.runKernel(an,t)}});const dh=Za({tile_:function(e,t){const n=Ka(e,"x","tile","string_or_numeric");ie(n.rank===t.length,(()=>`Error in transpose: rank of input ${n.rank} must match length of reps ${t}.`));const s={x:n},r={reps:t};return za.runKernel(rr,s,r)}});const fh=Za({eye_:function(e,t,n,s="float32"){null==t&&(t=e);const r=to([e,t],s),a=e<=t?e:t;for(let e=0;e<a;++e)r.set(1,e,e);const i=sc(r.toTensor(),[e,t]);if(null==n)return i;if(1===n.length)return dh(hh(i,0),[n[0],1,1]);if(2===n.length)return dh(hh(hh(i,0),0),[n[0],n[1],1,1]);if(3===n.length)return dh(hh(hh(hh(i,0),0),0),[n[0],n[1],n[2],1,1]);throw new Error(`eye() currently supports only 1D and 2D batchShapes, but received ${n.length}D.`)}});const mh=Za({floor_:function(e){const t={x:Ka(e,"x","floor","float32")};return za.runKernel(cn,t)}});const gh=Za({gather_:function(e,t,n=0,s=0){const r={x:Ka(e,"x","gather"),indices:Ka(t,"indices","gather","int32")},a={axis:n,batchDims:s};return za.runKernel(dn,r,a)}});const yh=Za({greater_:function(e,t){let n=Ka(e,"a","greater","string_or_numeric"),s=Ka(t,"b","greater","string_or_numeric");[n,s]=Ea(n,s),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(mn,r)}});const bh=Za({greaterEqual_:function(e,t){let n=Ka(e,"a","greaterEqual","string_or_numeric"),s=Ka(t,"b","greaterEqual","string_or_numeric");[n,s]=Ea(n,s),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(gn,r)}});const xh=Za({isFinite_:function(e){const t={x:Ka(e,"x","isFinite")};return za.runKernel(wn,t)}});const wh=Za({isInf_:function(e){const t={x:Ka(e,"x","isInf")};return za.runKernel(vn,t)}});const vh=Za({isNaN_:function(e){const t={x:Ka(e,"x","isNaN")};return za.runKernel(kn,t)}});const kh=Za({leakyRelu_:function(e,t=.2){const n={x:Ka(e,"x","leakyRelu")},s={alpha:t};return za.runKernel(In,n,s)}});const Ih=Za({less_:function(e,t){let n=Ka(e,"a","less","string_or_numeric"),s=Ka(t,"b","less","string_or_numeric");[n,s]=Ea(n,s),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(Nn,r)}});const Nh=Za({lessEqual_:function(e,t){let n=Ka(e,"a","lessEqual","string_or_numeric"),s=Ka(t,"b","lessEqual","string_or_numeric");[n,s]=Ea(n,s),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(Sn,r)}});function Sh(e,t,n){if(n<=0)throw new Error("The number of values should be positive.");const s={start:e,stop:t,num:n};return za.runKernel(Tn,{},s)}const Th=Za({localResponseNormalization_:function(e,t=5,n=1,s=1,r=.5){const a=Ka(e,"x","localResponseNormalization");ie(4===a.rank||3===a.rank,(()=>`Error in localResponseNormalization: x must be rank 3 or 4 but got\n               rank ${a.rank}.`)),ie(de(t),(()=>`Error in localResponseNormalization: depthRadius must be an integer but got depthRadius ${t}.`));let i=a,o=!1;3===a.rank&&(o=!0,i=sc(a,[1,a.shape[0],a.shape[1],a.shape[2]]));const l={x:i},u={depthRadius:t,bias:n,alpha:s,beta:r},c=za.runKernel(On,l,u);return o?sc(c,[c.shape[1],c.shape[2],c.shape[3]]):c}});const Ch=Za({log_:function(e){const t={x:Ka(e,"x","log","float32")};return za.runKernel(Cn,t)}});const $h=Za({log1p_:function(e){const t={x:Ka(e,"x","log1p")};return za.runKernel($n,t)}});const Eh=Za({softplus_:function(e){const t={x:Ka(e,"x","softplus")};return za.runKernel(Ls,t)}});const Ah=Za({logSigmoid_:function(e){const t=Ka(e,"x","logSigmoid");return Po((e=>({value:Rl(Eh(Rl(e))),gradFunc:t=>Ao(t,oc(Rl(e)))})))(t)}});const Rh=Za({logSoftmax_:function(e,t=-1){const n=Ka(e,"logits","logSoftmax");if(-1===t&&(t=n.rank-1),t!==n.rank-1)throw Error(`Log Softmax along a non-last dimension is not yet supported. Logits was rank ${n.rank} and axis was ${t}`);const s=Po(((e,n)=>{const s=rh(e,t,!0),r=Yo(e,s),a=Yo(no(r,"float32"),Ch(ih(ch(r),t,!0)));n([a]);return{value:a,gradFunc:(e,n)=>{const[s]=n,r=ch(s);return Yo(e,Ao(ih(e,t,!0),r))}}}));return s(n)}});const Fh=Za({logSumExp_:function(e,t=null,n=!1){const s=Ka(e,"x","logSumExp"),r=we(t,s.shape),a=rh(s,r,!0),i=Yo(s,a),o=ch(i),l=ih(o,r),u=Ch(l),c=Co(sc(a,u.shape),u);if(n){const e=Qc(c.shape,r);return sc(c,e)}return c}});const _h=Za({logicalAnd_:function(e,t){const n=Ka(e,"a","logicalAnd","bool"),s=Ka(t,"b","logicalAnd","bool");tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(En,r)}});const Dh=Za({logicalNot_:function(e){const t={x:Ka(e,"x","logicalNot","bool")};return za.runKernel(An,t)}});const Oh=Za({logicalOr_:function(e,t){const n=Ka(e,"a","logicalOr","bool"),s=Ka(t,"b","logicalOr","bool");tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(Rn,r)}});const Mh=Za({logicalXor_:function(e,t){const n=Ka(e,"a","logicalXor","bool"),s=Ka(t,"b","logicalXor","bool");return tl(n.shape,s.shape),_h(Oh(e,t),Dh(_h(e,t)))}}),Lh=2147483648;const zh=Za({searchSorted_:function(e,t,n="left"){const s=Ka(e,"sortedSequence","searchSorted"),r=Ka(t,"values","searchSorted"),a=s.shape[s.shape.length-1],i=r.shape[r.shape.length-1],o=sc(s,[-1,a]),l=sc(r,[-1,i]);if(o.rank<2)throw new Error("Sorted input argument must be at least 2-dimensional");if(o.shape[0]!==l.shape[0])throw new Error("Leading dimension of 'sortedSequence' and 'values' must match.");if(ue(l.shape)>=Lh)throw new Error("values tensor size must less than 2147483648");if(o.shape[1]>=Lh)throw new Error(`trailing dim_size must less than 2147483648 for int32 output type, was ${o.shape[1]}`);const u={sortedSequence:o,values:l},c={side:n};return za.runKernel(Es,u,c)}});function Ph(e,t){return zh(e,t,"left")}const Bh=Za({maxPool_:function(e,t,n,s,r){const a=Ka(e,"x","maxPool");let i=a,o=!1;3===a.rank&&(o=!0,i=sc(a,[1,a.shape[0],a.shape[1],a.shape[2]])),ie(4===i.rank,(()=>`Error in maxPool: input must be rank 4 but got rank ${i.rank}.`)),ie(Qu(n,1),(()=>`Error in maxPool: Either strides or dilations must be 1. Got strides ${n} and dilations '1'`)),nc("maxPool",s,r);const l={x:i},u={filterSize:t,strides:n,pad:s,dimRoundingMode:r},c=za.runKernel(Bn,l,u);return o?sc(c,[c.shape[1],c.shape[2],c.shape[3]]):c}});const Wh=Za({maxPool3d_:function(e,t=[1,1,1],n,s,r,a="NDHWC"){const i=Ka(e,"x","maxPool3d");let o=i,l=!1;4===i.rank&&(l=!0,o=sc(i,[1,i.shape[0],i.shape[1],i.shape[2],i.shape[3]])),ie(5===o.rank,(()=>`Error in maxPool3d: x must be rank 5 but got rank ${o.rank}.`)),ie("NDHWC"===a,(()=>`Error in maxPool3d: Only NDHWC is currently supported, but got dataFormat of ${a}`)),nc("maxPool3d",s,r);const u={x:o},c={filterSize:t,strides:n,pad:s,dimRoundingMode:r,dataFormat:a},h=za.runKernel(Vn,u,c);return l?sc(h,[h.shape[1],h.shape[2],h.shape[3],h.shape[4]]):h}});const Vh=Za({maxPoolWithArgmax_:function(e,t,n,s,r=!1){const a={x:Ka(e,"x","maxPoolWithArgmax")},i={filterSize:t,strides:n,pad:s,includeBatchInIndex:r},o=za.runKernel(Gn,a,i);return{result:o[0],indexes:o[1]}}});const Uh=Za({mean_:function(e,t=null,n=!1){const s={x:Ka(e,"x","mean")},r={axis:t,keepDims:n};return za.runKernel(Hn,s,r)}});function Gh(e,t="float32"){if(Ve(e),"complex64"===t){const t=Gh(e,"float32"),n=Gh(e,"float32");return Ja(t,n)}const n=Be(ue(e),t);return za.makeTensor(n,e,t)}function Hh(e,t="float32"){if(Ve(e),"complex64"===t){const t=Hh(e,"float32"),n=Gh(e,"float32");return Ja(t,n)}const n=Pe(ue(e),t);return za.makeTensor(n,e,t)}function jh(e,t,{indexing:n="xy"}={}){if("xy"!==n&&"ij"!==n)throw new TypeError(`${n} is not a valid third argument to meshgrid`);if(void 0===e)return[];let s=Ka(e,"x","meshgrid",e instanceof ga?e.dtype:"float32");if(void 0===t)return[s];let r=Ka(t,"y","meshgrid",t instanceof ga?t.dtype:"float32");const a=ue(s.shape),i=ue(r.shape);return"xy"===n?(s=sc(s,[1,-1]),r=sc(r,[-1,1]),[$l(Hh([i,1],s.dtype),s),$l(r,Hh([1,a],r.dtype))]):(s=sc(s,[-1,1]),r=sc(r,[1,-1]),[$l(s,Hh([1,i],s.dtype)),$l(Hh([a,1],r.dtype),r)])}const qh=Za({minimum_:function(e,t){let n=Ka(e,"a","minimum"),s=Ka(t,"b","minimum");[n,s]=Ea(n,s),"bool"===n.dtype&&(n=no(n,"int32"),s=no(s,"int32")),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(qn,r)}});const Kh=Za({mirrorPad_:function(e,t,n){ie("reflect"===n||"symmetric"===n,(()=>`Invalid mode. Mode must be either reflect or symmetric. Got ${n}.`));const s=Ka(e,"x","mirrorPad");if(0===s.rank)throw new Error("mirrorPad(scalar) is not defined. Pass non-scalar to mirrorPad");ie(t.length===s.rank,(()=>`Padding doesn't match input. Must be ${s.rank}. Got ${t.length}.`));const r="reflect"===n?1:0;for(let e=0;e<s.rank;e++)ie(2===t[e].length,(()=>"Invalid number of paddings. Must be length of 2 each.")),ie(t[e][0]>=0&&t[e][0]<=s.shape[e]-r&&t[e][1]>=0&&t[e][1]<=s.shape[e]-r,(()=>`Padding in dimension ${e} cannot be greater than or equal to ${s.shape[e]-r} or less than 0 for input of shape ${s.shape}`));const a={paddings:t,mode:n},i={x:s};return za.runKernel(Kn,i,a)}});const Xh=Za({mod_:function(e,t){let n=Ka(e,"a","mod"),s=Ka(t,"b","mod");[n,s]=Ea(n,s);const r={a:n,b:s};return za.runKernel(Xn,r)}});const Yh=Za({moments_:function(e,t=null,n=!1){const s=we(t,(e=Ka(e,"x","moments")).shape),r=Uh(e,s,n);let a=r.shape;n||(a=Qc(r.shape,s));const i=Fo(Yo(no(e,"float32"),sc(r,a)));return{mean:r,variance:Uh(i,s,n)}}});const Zh=Za({multiRNNCell_:function(e,t,n,s){const r=Ka(t,"data","multiRNNCell"),a=Xa(n,"c","multiRNNCell"),i=Xa(s,"h","multiRNNCell");let o=r;const l=[];for(let t=0;t<e.length;t++){const n=e[t](o,a[t],i[t]);l.push(n[0]),l.push(n[1]),o=n[1]}const u=[],c=[];for(let e=0;e<l.length;e+=2)u.push(l[e]),c.push(l[e+1]);return[u,c]}});const Jh=Za({multinomial_:function(e,t,n,s=!1){const r=Ka(e,"logits","multinomial"),a=r.size,i=r.rank;if(a<2)throw new Error(`Error in multinomial: you need at least 2 outcomes, but got ${a}.`);if(i>2)throw new Error(`Rank of probabilities must be 1 or 2, but is ${i}`);n=n||Math.random();const o={logits:1===i?sc(r,[1,-1]):r},l={numSamples:t,seed:n,normalized:s},u=za.runKernel(Yn,o,l);return 1===i?sc(u,[u.size]):u}});const Qh=Za({notEqual_:function(e,t){let n=Ka(e,"a","notEqual","string_or_numeric"),s=Ka(t,"b","notEqual","string_or_numeric");[n,s]=Ea(n,s),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(Qn,r)}});const ep=Za({onesLike_:function(e){const t={x:Ka(e,"x","onesLike")};return za.runKernel(ss,t)}});const tp=Za({outerProduct_:function(e,t){const n=Ka(e,"v1","outerProduct"),s=Ka(t,"v2","outerProduct");ie(1===n.rank&&1===s.rank,(()=>`Error in outerProduct: inputs must be rank 1, but got ranks ${n.rank} and ${s.rank}.`));const r=sc(n,[-1,1]),a=sc(s,[1,-1]);return $l(r,a)}});const np=Za({pad_:function(e,t,n=0){const s=Ka(e,"x","pad");if(0===s.rank)throw new Error("pad(scalar) is not defined. Pass non-scalar to pad");const r={paddings:t,constantValue:n},a={x:s};return za.runKernel(is,a,r)}});const sp=Za({pad1d_:function(e,t,n=0){return ie(2===t.length,(()=>"Invalid number of paddings. Must be length of 2.")),np(e,[t],n)}});const rp=Za({pad2d_:function(e,t,n=0){return ie(2===t.length&&2===t[0].length&&2===t[1].length,(()=>"Invalid number of paddings. Must be length of 2 each.")),np(e,t,n)}});const ap=Za({pad3d_:function(e,t,n=0){return ie(3===t.length&&2===t[0].length&&2===t[1].length&&2===t[2].length,(()=>"Invalid number of paddings. Must be length of 2 each.")),np(e,t,n)}});const ip=Za({pad4d_:function(e,t,n=0){return ie(4===t.length&&2===t[0].length&&2===t[1].length&&2===t[2].length&&2===t[3].length,(()=>"Invalid number of paddings. Must be length of 2 each.")),np(e,t,n)}});const op=Za({spaceToBatchND_:function(e,t,n){const s=Ka(e,"x","spaceToBatchND");ie(s.rank>=1+t.length,(()=>`input rank ${s.rank} should be > than [blockShape] ${t.length}`)),ie(n.length===t.length,(()=>`paddings.shape[0] ${n.length} must be equal to [blockShape] ${t.length}`)),ie(s.shape.reduce(((e,s,r)=>r>0&&r<=t.length?e&&(s+n[r-1][0]+n[r-1][1])%t[r-1]==0:e),!0),(()=>`input spatial dimensions ${s.shape.slice(1)} with paddings ${n.toString()} must be divisible by blockShapes ${t.toString()}`));const r={x:s},a={blockShape:t,paddings:n};return za.runKernel(Bs,r,a)}});const lp=Za({pool_:function(e,t,n,s,r,a,i){null==r&&(r=[1,1]),null==a&&(a=1),0===s&&(s="valid");const o=Ka(e,"x","maxPool");let l=o,u=!1;3===o.rank&&(u=!0,l=sc(o,[1,o.shape[0],o.shape[1],o.shape[2]])),ie(Qu(a,r),(()=>`Error in pool: Either strides or dilations must be 1. Got strides ${a} and dilations '${r}'`));const c=Uu(l.shape,t,a,r,s),h=[c.dilationHeight,c.dilationWidth];let p;p="same"===s?function(e,t){const n=e.map(((e,n)=>e+(e-1)*(t[n]-1))),s=n.map((e=>e-1)),r=s.map((e=>Math.floor(e/2))),a=s.map(((e,t)=>e-r[t]));return s.map(((e,t)=>[r[t],a[t]]))}([c.filterHeight,c.filterWidth],h):[[0,0],[0,0]];const d=1===h[0]&&1===h[1],[f,m]=function(e,t,n){const s=n.map((e=>e[0])),r=n.map((e=>e[1])),a=e.concat(s,r),i=t.map(((e,t)=>(e-a[t]%e)%e)),o=r.map(((e,t)=>e+i[t])),l=t.map(((e,t)=>[s[t],o[t]])),u=t.map(((e,t)=>[0,i[t]]));return[l,u]}([c.inHeight,c.inWidth],h,p),g=d?s:"valid",y=d?l:op(l,h,f),b=("avg"===n?()=>rc(y,t,a,g,i):()=>Bh(y,t,a,g,i))(),x=d?b:hc(b,h,m);return u?sc(x,[x.shape[1],x.shape[2],x.shape[3]]):x}});const up=Za({prelu_:function(e,t){const n={x:Ka(e,"x","prelu"),alpha:Ka(t,"alpha","prelu")};return za.runKernel(us,n)}});const cp=Za({prod_:function(e,t=null,n=!1){let s=Ka(e,"x","prod");"bool"===s.dtype&&(s=no(s,"int32"));const r={x:s},a={axis:t,keepDims:n};return za.runKernel(cs,r,a)}});const hp=Za({raggedGather_:function(e,t,n,s){const r={paramsNestedSplits:e.map(((e,t)=>Ka(e,`tensors${t}`,"raggedGather","int32"))),paramsDenseValues:Ka(t,"paramsDenseValues","raggedGather"),indices:Ka(n,"indices","raggedGather","int32")},a={outputRaggedRank:s},i=za.runKernel(hs,r,a);return{outputNestedSplits:i.slice(0,i.length-1),outputDenseValues:i[i.length-1]}}});const pp=Za({raggedRange_:function(e,t,n){const s=Ka(e,"starts","raggedRange"),r={starts:s,limits:Ka(t,"limits","raggedRange",s.dtype),deltas:Ka(n,"deltas","raggedRange",s.dtype)},a=za.runKernel(ps,r);return{rtNestedSplits:a[0],rtDenseValues:a[1]}}});const dp=Za({raggedTensorToTensor_:function(e,t,n,s,r){const a=Ka(e,"shape","raggedTensorToTensor","int32"),i=Ka(t,"values","raggedTensorToTensor"),o={shape:a,values:i,defaultValue:Ka(n,"defaultValue","raggedTensorToTensor",i.dtype),rowPartitionTensors:s.map(((e,t)=>Ka(e,`tensors${t}`,"raggedTensorToTensor","int32")))},l={rowPartitionTypes:r};return za.runKernel(ds,o,l)}});const fp=Za({rand_:function(e,t,n){Ve(e);const s=ue(e);let r=null;if(null==n||"float32"===n)r=new Float32Array(s);else if("int32"===n)r=new Int32Array(s);else{if("bool"!==n)throw new Error(`Unknown data type ${n}`);r=new Uint8Array(s)}for(let e=0;e<s;e++)r[e]=t();return za.makeTensor(r,e,n)}});var mp=n(377);class gp{constructor(e,t,n,s,r){this.mean=e,this.stdDev=t,this.dtype=n,this.nextVal=NaN,this.truncated=s,this.truncated&&(this.upper=this.mean+2*this.stdDev,this.lower=this.mean-2*this.stdDev);const a=r||Math.random();this.random=mp.alea(a.toString())}nextValue(){if(!isNaN(this.nextVal)){const e=this.nextVal;return this.nextVal=NaN,e}let e,t,n=!1;for(;!n;){let s,r,a;do{s=2*this.random()-1,r=2*this.random()-1,a=s*s+r*r}while(a>=1||0===a);const i=Math.sqrt(-2*Math.log(a)/a);e=this.mean+this.stdDev*s*i,t=this.mean+this.stdDev*r*i,this.truncated&&!this.isValidTruncated(e)||(n=!0)}return this.truncated&&!this.isValidTruncated(t)||(this.nextVal=this.convertValue(t)),this.convertValue(e)}convertValue(e){return null==this.dtype||"float32"===this.dtype?e:Math.round(e)}isValidTruncated(e){return e<=this.upper&&e>=this.lower}}class yp{constructor(e,t,n,s){this.alpha=e,this.beta=1/t,this.dtype=n;const r=s||Math.random();this.randu=mp.alea(r.toString()),this.randn=new gp(0,1,n,!1,this.randu()),this.d=e<1?e+2/3:e-1/3,this.c=1/Math.sqrt(9*this.d)}nextValue(){let e,t,n,s,r,a;for(;;){do{s=this.randn.nextValue(),a=1+this.c*s}while(a<=0);if(a*=a*a,e=s*s,t=1-.331*e*e,n=.5*e+this.d*(1-a+Math.log(a)),r=this.randu(),r<t||Math.log(r)<n)break}return a=1/this.beta*this.d*a,this.alpha<1&&(a*=Math.pow(this.randu(),1/this.alpha)),this.convertValue(a)}convertValue(e){return"float32"===this.dtype?e:Math.round(e)}}class bp{constructor(e=0,t=1,n,s){if(this.canReturnFloat=()=>null==this.dtype||"float32"===this.dtype,this.min=e,this.range=t-e,this.dtype=n,null==s&&(s=Math.random()),"number"==typeof s&&(s=s.toString()),!this.canReturnFloat()&&this.range<=1)throw new Error(`The difference between ${e} - ${t} <= 1 and dtype is not float`);this.random=mp.alea(s)}convertValue(e){return this.canReturnFloat()?e:Math.round(e)}nextValue(){return this.convertValue(this.min+this.range*this.random())}}const xp=Za({randomGamma_:function(e,t,n=1,s="float32",r){if(Ve(e),null==n&&(n=1),null==s&&(s="float32"),"float32"!==s&&"int32"!==s)throw new Error(`Unsupported data type ${s}`);const a=new yp(t,n,s,r),i=to(e,s);for(let e=0;e<i.values.length;e++)i.values[e]=a.nextValue();return i.toTensor()}});const wp=Za({randomNormal_:function(e,t=0,n=1,s,r){if(Ve(e),null!=s&&"bool"===s)throw new Error(`Unsupported data type ${s}`);const a=new gp(t,n,s,!1,r),i=to(e,s);for(let e=0;e<i.values.length;e++)i.values[e]=a.nextValue();return i.toTensor()}});const vp=Za({randomStandardNormal_:function(e,t,n){if(null!=t&&"bool"===t)throw new Error(`Unsupported data type ${t}`);return wp(e,0,1,t,n)}});const kp=Za({randomUniform_:function(e,t=0,n=1,s="float32",r){Ve(e);const a=to(e,s),i=new bp(t,n,null,r);for(let e=0;e<a.values.length;e++)a.values[e]=i.nextValue();return a.toTensor()}});const Ip=Za({randomUniformInt_:function(e,t,n,s){return kp(e,t,n,"int32",s)}});function Np(e,t,n=1,s="float32"){if(0===n)throw new Error("Cannot have a step of zero");const r={start:e,stop:t,step:n,dtype:s};return za.runKernel(fs,{},r)}const Sp=Za({reciprocal_:function(e){const t={x:Ka(e,"x","reciprocal")};return za.runKernel(gs,t)}});const Tp=Za({relu_:function(e){const t={x:Ka(e,"x","relu")};return za.runKernel(ys,t)}});const Cp=Za({relu6_:function(e){const t={x:Ka(e,"x","relu6")};return za.runKernel(Is,t)}});const $p=Za({reverse_:function(e,t){const n={x:Ka(e,"x","reverse")},s={dims:t};return za.runKernel(Ns,n,s)}});const Ep=Za({reverse1d_:function(e){const t=Ka(e,"x","reverse");return ie(1===t.rank,(()=>`Error in reverse1D: x must be rank 1 but got rank ${t.rank}.`)),$p(t,0)}});const Ap=Za({reverse2d_:function(e,t){const n=Ka(e,"x","reverse");return ie(2===n.rank,(()=>`Error in reverse2D: x must be rank 2 but got rank ${n.rank}.`)),$p(n,t)}});const Rp=Za({reverse3d_:function(e,t){const n=Ka(e,"x","reverse");return ie(3===n.rank,(()=>`Error in reverse3D: x must be rank 3 but got rank ${n.rank}.`)),$p(n,t)}});const Fp=Za({reverse4d_:function(e,t){const n=Ka(e,"x","reverse");return ie(4===n.rank,(()=>`Error in reverse4D: x must be rank 4 but got rank ${n.rank}.`)),$p(n,t)}});const _p=Za({round_:function(e){const t={x:Ka(e,"x","round")};return za.runKernel(Ss,t)}});const Dp=Za({rsqrt_:function(e){const t={x:Ka(e,"x","rsqrt","float32")};return za.runKernel(Ts,t)}});const Op=Za({selu_:function(e){const t={x:Ka(e,"x","selu")};return za.runKernel(Rs,t)}});const Mp=Za({separableConv2d_:function(e,t,n,s,r,a=[1,1],i="NHWC"){const o=Ka(e,"x","separableConv2d"),l=Ka(t,"depthwiseFilter","separableConv2d"),u=Ka(n,"pointwiseFilter","separableConv2d");let c=o,h=!1;if(3===o.rank&&(h=!0,c=sc(o,[1,o.shape[0],o.shape[1],o.shape[2]])),"NCHW"===i)throw new Error("separableConv2d currently does not support dataFormat NCHW; only NHWC is supported");ie(4===c.rank,(()=>`Error in separableConv2d: input must be rank 4, but got rank ${c.rank}.`)),ie(4===l.rank,(()=>`Error in separableConv2d: depthwise filter must be rank 4, but got rank ${l.rank}.`)),ie(4===u.rank,(()=>`Error in separableConv2d: pointwise filter must be rank 4, but got rank ${l.rank}.`)),ie(1===u.shape[0],(()=>`Error in separableConv2d: the first dimension of pointwise filter  must be 1, but got ${u.shape[0]}.`)),ie(1===u.shape[1],(()=>`Error in separableConv2d: the second dimension of pointwise filter must be 1, but got ${u.shape[1]}.`));const p=l.shape[2],d=l.shape[3];ie(u.shape[2]===p*d,(()=>`Error in separableConv2d: the third dimension of pointwise filter must be ${p*d}, but got ${u.shape[2]}.`));const f=Pc(c,l,s,r,i,a),m=Tc(f,u,1,"valid",i);return h?sc(m,[m.shape[1],m.shape[2],m.shape[3]]):m}});const Lp=async function(e,t){const n=Ka(e,"x","setdiff1d"),s=Ka(t,"y","setdiff1d");ie(n.dtype===s.dtype,(()=>`x and y should have the same dtype, but got x (${n.dtype}) and y (${s.dtype}).`)),ie(1===n.rank,(()=>`x should be 1D tensor, but got x (${n.shape}).`)),ie(1===s.rank,(()=>`y should be 1D tensor, but got y (${s.shape}).`));const r=await n.data(),a=await s.data(),i=new Set(a);let o=0;for(let e=0;e<r.length;e++)i.has(r[e])||o++;const l=new pa([o],n.dtype),u=new pa([o],"int32");for(let e=0,t=0;e<r.length;e++)i.has(r[e])||(l.values[t]=r[e],u.values[t]=e,t++);return[l.toTensor(),u.toTensor()]};const zp=Za({sign_:function(e){const t={x:Ka(e,"x","sign")};return za.runKernel(Os,t)}});const Pp=Za({sin_:function(e){const t={x:Ka(e,"x","sin","float32")};return za.runKernel(_s,t)}});const Bp=Za({sinh_:function(e){const t={x:Ka(e,"x","sinh")};return za.runKernel(Ds,t)}});const Wp=Za({slice1d_:function(e,t,n){const s=Ka(e,"x","slice1d");return ie(1===s.rank,(()=>`slice1d expects a rank-1 tensor, but got a rank-${s.rank} tensor`)),lc(s,[t],[n])}});const Vp=Za({slice2d_:function(e,t,n){const s=Ka(e,"x","slice2d");return ie(2===s.rank,(()=>`slice2d expects a rank-2 tensor, but got a rank-${s.rank} tensor`)),lc(s,t,n)}});const Up=Za({slice3d_:function(e,t,n){const s=Ka(e,"x","slice3d");return ie(3===s.rank,(()=>`slice3d expects a rank-3 tensor, but got a rank-${s.rank} tensor`)),lc(s,t,n)}});const Gp=Za({slice4d_:function(e,t,n){const s=Ka(e,"x","slice4d");return ie(4===s.rank,(()=>`slice4d expects a rank-4 tensor, but got a rank-${s.rank} tensor`)),lc(s,t,n)}});const Hp=Za({softmax_:function(e,t=-1){const n=Ka(e,"logits","softmax","float32");if(-1===t&&(t=n.rank-1),t!==n.rank-1)throw Error(`Softmax along a non-last dimension is not yet supported. Logits was rank ${n.rank} and dim was ${t}`);const s={logits:n},r={dim:t};return za.runKernel(Vs,s,r)}});const jp=Za({fft_:function(e){ie("complex64"===e.dtype,(()=>`The dtype for tf.spectral.fft() must be complex64 but got ${e.dtype}.`));const t={input:e};return za.runKernel(on,t)}});const qp=Za({ifft_:function(e){ie("complex64"===e.dtype,(()=>`The dtype for tf.spectral.ifft() must be complex64 but got ${e.dtype}.`));const t={input:e};return za.runKernel(bn,t)}});const Kp=Za({irfft_:function(e){const t=e.shape[e.shape.length-1],n=e.size/t;let s;if(t<=2){const r=sc(e,[n,t]);s=qp(r)}else{const r=[n,2*(t-1)],a=sc(Fl(e),[n,t]),i=sc(Al(e),[n,t]),o=$p(lc(a,[0,1],[n,t-2]),1),l=Ao($p(lc(i,[0,1],[n,t-2]),1),Wo(-1)),u=ic([a,o],1),c=ic([i,l],1),h=sc(Ja(u,c),[r[0],r[1]]);s=qp(h)}if(s=Fl(s),3===e.rank&&0!==e.shape[0]){const t=s,n=e.shape[0];s=sc(s,[n,s.shape[0]/n,s.shape[1]]),t.dispose()}return s}});const Xp=Za({split_:function(e,t,n=0){const s={x:Ka(e,"x","split")},r={numOrSizeSplits:t,axis:n};return za.runKernel(Ws,s,r)}});const Yp=Za({rfft_:function(e,t){ie("float32"===e.dtype,(()=>`The dtype for rfft() must be real value but got ${e.dtype}`));let n=e.shape[e.shape.length-1];const s=e.size/n;let r;if(null!=t&&t<n){const s=e.shape.map((e=>0)),a=e.shape.map((e=>e));a[e.shape.length-1]=t,r=lc(e,s,a),n=t}else if(null!=t&&t>n){const s=e.shape.map((e=>e));s[e.shape.length-1]=t-n,r=ic([e,Gh(s)],e.shape.length-1),n=t}else r=e;const a=_o(r),i=sc(Ja(r,a),[s,n]),o=jp(i),l=Math.floor(n/2)+1,u=Fl(o),c=Al(o),h=Xp(u,[l,n-l],u.shape.length-1),p=Xp(c,[l,n-l],c.shape.length-1),d=r.shape.slice();return d[r.shape.length-1]=l,sc(Ja(h[0],p[0]),d)}});const Zp=Za({squaredDifference_:function(e,t){let n=Ka(e,"a","squaredDifference"),s=Ka(t,"b","squaredDifference");[n,s]=Ea(n,s),tl(n.shape,s.shape);const r={a:n,b:s};return za.runKernel(Ks,r,{})}});const Jp=Za({squeeze_:function(e,t){const n=Ka(e,"x","squeeze","string_or_numeric");return sc(n,ve(n.shape,t).newShape)}});const Qp=Za({stack_:function(e,t=0){const n=Xa(e,"tensors","stack","string_or_numeric");ie(n.length>=1,(()=>"Pass at least one tensor to tf.stack")),n.length>0&&ie(t<=n[0].rank,(()=>"Axis must be <= rank of the tensor"));const s=n,r={axis:t};return za.runKernel(as,s,r)}});const ed=Za({step_:function(e,t=0){const n={x:Ka(e,"x","step")},s={alpha:t};return za.runKernel(dr,n,s)}});const td=Za({stridedSlice_:function(e,t,n,s,r=0,a=0,i=0,o=0,l=0){const u={x:Ka(e,"x","stridedSlice","string_or_numeric")},c={begin:t,end:n,strides:s,beginMask:r,endMask:a,ellipsisMask:i,newAxisMask:o,shrinkAxisMask:l};return za.runKernel(Zs,u,c)}});const nd=Za({tan_:function(e){const t={x:Ka(e,"x","tan","float32")};return za.runKernel(nr,t)}});function sd(e,t){le(e);const n=Ha(e,t);if(1!==n.length)throw new Error("tensor1d() requires values to be a flat/TypedArray");return Qa(e,null,n,t)}function rd(e,t,n){if(le(e),null!=t&&2!==t.length)throw new Error("tensor2d() requires shape to have two numbers");const s=Ha(e,n);if(2!==s.length&&1!==s.length)throw new Error("tensor2d() requires values to be number[][] or flat/TypedArray");if(1===s.length&&null==t)throw new Error("tensor2d() requires shape to be provided when `values` are a flat/TypedArray");return Qa(e,t,s,n)}function ad(e,t,n){if(le(e),null!=t&&4!==t.length)throw new Error("tensor4d() requires shape to have four numbers");const s=Ha(e,n);if(4!==s.length&&1!==s.length)throw new Error("tensor4d() requires values to be number[][][][] or flat/TypedArray");if(1===s.length&&null==t)throw new Error("tensor4d() requires shape to be provided when `values` are a flat array");return Qa(e,t,s,n)}function id(e,t,n){if(le(e),null!=t&&5!==t.length)throw new Error("tensor5d() requires shape to have five numbers");const s=Ha(e,n);if(5!==s.length&&1!==s.length)throw new Error("tensor5d() requires values to be number[][][][][] or flat/TypedArray");if(1===s.length&&null==t)throw new Error("tensor5d() requires shape to be provided when `values` are a flat array");return Qa(e,t,s,n)}function od(e,t,n){if(le(e),null!=t&&6!==t.length)throw new Error("tensor6d() requires shape to have six numbers");const s=Ha(e,n);if(6!==s.length&&1!==s.length)throw new Error("tensor6d() requires values to be number[][][][][][] or flat/TypedArray");if(1===s.length&&null==t)throw new Error("tensor6d() requires shape to be provided when `values` are a flat array");return Qa(e,t=t||s,s,n)}const ld=Za({tensorScatterUpdate_:function(e,t,n){const s=Ka(e,"tensor","tensorScatterupdate"),r=Ka(t,"indices","tensorScatterupdate","int32"),a=Ka(n,"updates","tensorScatterupdate");if(ql(a,r,s.shape),s.dtype!==a.dtype)throw new Error(`tensor and updates must have the same dtype, instead they are ${s.dtype} and ${a.dtype}.`);const i={tensor:s,indices:r,updates:a};return za.runKernel($s,i,{})}});const ud=Za({topk_:function(e,t=1,n=!0){const s=Ka(e,"x","topk");if(0===s.rank)throw new Error("topk() expects the input to be of rank 1 or higher");const r=s.shape[s.shape.length-1];if(t<0)throw new Error(`'k' passed to topk() must be >= 0 but got ${t}`);if(t>r)throw new Error(`'k' passed to topk() must be <= the last dimension (${r}) but got ${t}`);const a={x:s},i={k:t,sorted:n},[o,l]=za.runKernel(ar,a,i);return{values:o,indices:l}}});const cd=Za({truncatedNormal_:function(e,t=0,n=1,s,r){if(Ve(e),null!=s&&"bool"===s)throw new Error("Unsupported data type $ { dtype }");const a=new gp(t,n,s,!0,r),i=to(e,s);for(let e=0;e<i.values.length;e++)i.values[e]=a.nextValue();return i.toTensor()}});const hd=Za({unique_:function(e,t=0){const n=Ka(e,"x","unique","string_or_numeric");ie(n.rank>0,(()=>"The input tensor must be at least 1D"));const s={x:n},r={axis:t},[a,i]=za.runKernel(lr,s,r);return{values:a,indices:i}}});const pd=Za({unsortedSegmentSum_:function(e,t,n){const s=Ka(e,"x","unsortedSegmentSum"),r=Ka(t,"segmentIds","unsortedSegmentSum","int32");ie(de(n),(()=>"numSegments must be of dtype int"));const a={x:s,segmentIds:r},i={numSegments:n};return za.runKernel(cr,a,i)}});const dd=Za({unstack_:function(e,t=0){const n=Ka(e,"x","unstack","string_or_numeric");ie(t>=-n.shape.length&&t<n.shape.length,(()=>`Axis = ${t} is not in [-${n.shape.length}, ${n.shape.length})`));const s={value:n},r={axis:t};return za.runKernel(ur,s,r)}});function fd(e,t){return zh(e,t,"right")}function md(e,t=!0,n,s){return za.makeVariable(e,t,n,s)}function gd(e,t){const n=[];for(let e=0;e<t.length;e++)t[e]&&n.push(e);const s=to(e,"int32"),r=to([n.length,e.length],"int32");for(let t=0;t<n.length;t++){const a=s.indexToLoc(n[t]),i=t*e.length;r.values.set(a,i)}return r.toTensor()}const yd=async function(e){const t=Ka(e,"condition","whereAsync","bool"),n=await t.data(),s=gd(t.shape,n);return e!==t&&t.dispose(),s};const bd=async function(e,t,n){const s=Ka(e,"tensor","boolMask"),r=Ka(t,"mask","boolMask","bool"),a=null==n?0:n,i=r.rank,o=s.shape;ie(i>0,(()=>"mask cannot be scalar")),oe(o.slice(a,a+i),r.shape,"mask's shape must match the first K dimensions of tensor's shape,");let l=1;for(let e=a;e<a+i;e++)l*=o[e];const u=o.slice(0,a).concat([l],o.slice(a+i)),c=sc(s,u),h=sc(r,[-1]),p=await yd(h),d=Jp(p,[1]),f=gh(c,d,a);return e!==s&&s.dispose(),t!==r&&r.dispose(),d.dispose(),c.dispose(),h.dispose(),p.dispose(),f};const xd=Za({movingAverage_:function(e,t,n,s,r=!0){const a=Ka(e,"v","movingAverage"),i=Ka(t,"x","movingAverage"),o=Ka(n,"decay","movingAverage");Aa(a,i),ie(pe(a.shape,i.shape),(()=>"Shape mismatch in v and x"));const l=Wo(1),u=Yo(l,o);let c=Ao(Yo(i,a),u);if(r){ie(null!=s,(()=>"When using zeroDebias: true, step is required."));const e=Ka(s,"step","movingAverage");c=Eo(c,Yo(l,Xo(o,e)))}return Co(a,c)}});const wd=Za({scatterND_:function(e,t,n){Ve(n);const s=Ka(e,"indices","scatterND","int32"),r=Ka(t,"updates","scatterND");ql(r,s,n);const a={indices:s,updates:r},i={shape:n};return za.runKernel(Cs,a,i)}});const vd=Za({sparseToDense_:function(e,t,n,s=0){Ve(n);const r=Ka(e,"sparseIndices","sparseToDense","int32"),a=Ka(t,"sparseValues","sparseToDense","string_or_numeric"),i=Ka(s,"defaultValue","sparseToDense",a.dtype);!function(e,t,n,s){if("int32"!==e.dtype)throw new Error(`tf.sparseToDense() expects the indices to be int32 type, but the dtype was ${e.dtype}.`);if(e.rank>2)throw new Error(`sparseIndices should be a scalar, vector, or matrix, but got shape ${e.shape}.`);const r=e.rank>0?e.shape[0]:1,a=e.rank>1?e.shape[1]:1;if(n.length!==a)throw new Error(`outputShape has incorrect number of elements:, ${n.length}, should be: ${a}.`);const i=t.size;if(0!==t.rank&&(1!==t.rank||i!==r))throw new Error(`sparseValues has incorrect shape ${t.shape}, should be [] or [${r}]`);if(t.dtype!==s.dtype)throw new Error("sparseValues.dtype must match defaultValues.dtype")}(r,a,n,i);const o={sparseIndices:r,sparseValues:a,defaultValue:i},l={outputShape:n};return za.runKernel(qs,o,l)}});const kd=Za({gatherND_:function(e,t){const n=Ka(t,"indices","gatherND","int32"),s={params:Ka(e,"x","gatherND","string_or_numeric"),indices:n};return za.runKernel(fn,s)}});const Id=Za({dropout_:function(e,t,n,s){const r=Ka(e,"x","dropout");if(ie("float32"===r.dtype,(()=>`x has to be a floating point tensor since it's going to be scaled, but got a ${r.dtype} tensor instead.`)),ie(t>=0&&t<1,(()=>`rate must be a float in the range [0, 1), but got ${t}.`)),0===t)return e instanceof ga?r.clone():r;const a=function(e,t){if(null==t)return e.shape.slice();if(pe(e.shape,t))return t;if(e.shape.length===t.length){const n=[];for(let s=0;s<e.shape.length;s++)null==t[s]&&null!=e.shape[s]?n.push(e.shape[s]):n.push(t[s]);return n}return t}(r,n),i=1-t,o=Eo(mh(Co(kp(a,0,1,"float32",s),i)),i);return Ao(r,o)}});function Nd(e){return Math.floor(Math.pow(2,Math.ceil(Math.log(e)/Math.log(2))))}function Sd(e,t,n){const s=1-e%2,r=new Float32Array(e);for(let a=0;a<e;++a){const i=2*Math.PI*a/(e+s-1);r[a]=t-n*Math.cos(i)}return sd(r,"float32")}const Td=async function(e,t,n=1){const s=Ka(e,"predictions","inTopK"),r=Ka(t,"targets","inTopK");ie(s.rank>1,(()=>`inTopK() expects the predictions to be of rank 2 or higher, but got ${s.rank}`)),ie(s.rank-1===r.rank,(()=>`predictions rank should be 1 larger than targets rank, but got predictions rank ${s.rank} and targets rank ${r.rank}`)),oe(s.shape.slice(0,s.shape.length-1),r.shape,"predictions's shape should be align with the targets' shape, except the last dimension.");const a=s.shape[s.shape.length-1];ie(n>0&&n<=a,(()=>`'k' passed to inTopK() must be > 0 && <= the predictions last dimension (${a}), but got ${n}`));const i=await s.data(),o=await r.data(),[l,u]=[i.length/a,a],c=ke("bool",l);for(let e=0;e<l;e++){const t=e*u,s=i.subarray(t,t+u),r=[];for(let e=0;e<s.length;e++)r.push({value:s[e],index:e});r.sort(((e,t)=>t.value-e.value)),c[e]=0;for(let t=0;t<n;t++)if(r[t].index===o[e]){c[e]=1;break}}return e!==s&&s.dispose(),t!==r&&r.dispose(),ei(c,r.shape,"bool")};const Cd=Za({conv2DBackpropFilter_:function(e,t,n,s,r,a="NHWC",i){let o=e;3===e.rank&&(o=sc(e,[1,e.shape[0],e.shape[1],e.shape[2]]));let l=t;3===l.rank&&(l=sc(t,[1,t.shape[0],t.shape[1],t.shape[2]])),ie(4===o.rank,(()=>`Error in conv2dDerFilter: input must be rank 4, but got shape ${o.shape}.`)),ie(4===l.rank,(()=>`Error in conv2dDerFilter: dy must be rank 4, but got shape ${l.shape}.`)),ie(4===n.length,(()=>`Error in conv2dDerFilter: filterShape must be length 4, but got ${n}.`));const u="NHWC"===a?o.shape[3]:o.shape[1],c="NHWC"===a?l.shape[3]:l.shape[1];ie(u===n[2],(()=>`Error in conv2dDerFilter: depth of input ${u}) must match input depth in filter (${n[2]}.`)),ie(c===n[3],(()=>`Error in conv2dDerFilter: depth of dy (${c}) must match output depth for filter (${n[3]}).`)),nc("conv2dDerFilter",r,i);const h={x:o,dy:l},p={strides:s,pad:r,dataFormat:a,dimRoundingMode:i,filterShape:n};return za.runKernel(Rt,h,p)}});function $d(e,t,n){if(null==n||"linear"===n)return e;if("relu"===n)return Ao(e,ed(t));throw new Error(`Cannot compute gradient for fused activation ${n}.`)}function Ed(e,t){let n=t;const s=el(e.shape,t.shape);return s.length>0&&(n=ih(n,s)),sc(n,e.shape)}function Ad(e,t,n,s){if("linear"===t)return e;if("relu"===t)return Tp(e);if("elu"===t)return qc(e);if("relu6"===t)return Cp(e);if("prelu"===t)return up(e,n);if("leakyrelu"===t)return kh(e,s);if("sigmoid"===t)return oc(e);throw new Error(`Unknown fused activation ${t}.`)}const Rd=(e,t)=>!(e>0)||"linear"===t;const Fd=Za({fusedConv2d_:function({x:e,filter:t,strides:n,pad:s,dataFormat:r="NHWC",dilations:a=[1,1],dimRoundingMode:i,bias:o,activation:l="linear",preluActivationWeights:u,leakyreluAlpha:c}){if(l=l||"linear",!1===Rd(za.state.gradientDepth,l)){ie("NHWC"===r,(()=>`Error in fused conv2d: got dataFormat of ${r} but only NHWC is currently supported for the case of gradient depth is 0 and the activation is not linear.`));let h=Tc(e,t,n,s,r,a,i);return null!=o&&(h=Co(h,o)),Ad(h,l,u,c)}const h=Ka(e,"x","conv2d","float32"),p=Ka(t,"filter","conv2d","float32");let d=h,f=!1;3===h.rank&&(f=!0,d=sc(h,[1,h.shape[0],h.shape[1],h.shape[2]])),ie(4===d.rank,(()=>`Error in fused conv2d: input must be rank 4, but got rank ${d.rank}.`)),ie(4===p.rank,(()=>`Error in fused conv2d: filter must be rank 4, but got rank ${p.rank}.`)),nc("fused conv2d",s,i);const m="NHWC"===r?d.shape[3]:d.shape[1];ie(p.shape[2]===m,(()=>`Error in conv2d: depth of input (${m}) must match input depth for filter ${p.shape[2]}.`)),ie(Qu(n,a),(()=>`Error in conv2D: Either strides or dilations must be 1. Got strides ${n} and dilations '${a}'`));const g=Hu(d.shape,p.shape,n,a,s,i);let y,b;if(null!=o&&(y=Ka(o,"bias","fused conv2d"),[y]=Ea(y,h),"NHWC"===r?tl(g.outShape,y.shape):(ie(y.shape.length<=1,(()=>`Error in fused conv2d: only supports scalar or 1-D Tensor bias for NCHW format but got the bias of rank-${y.shape.length}.`)),ie(0===y.shape.length||y.shape[0]===g.outChannels||1===y.shape[0],(()=>`Error in fused conv2d: bias shape (${y.shape}) is not compatible with the number of output channels (${g.outChannels})`)))),null!=u){const e=u.shape;if(ie(e.length<=1||3===e.length,(()=>`Error in fused conv2d: only supports scalar, 1-D Tensor or 3-D Tensor PReLU activation weights but got a tensor of rank-${e.length}.`)),1===e.length)ie(1===e[0]||e[0]===g.outChannels,(()=>`Error in fused conv2d: PReLU activation weights (${e}) is not compatible with the number of output channels (${g.outChannels}).`));else if(3===e.length)try{tl(e,g.outShape)}catch(t){const n=`Error in fused conv2d: PReLU activation weights (${e}) is not compatible with the output shape of the conv2d (${g.outShape}).`;throw Error(n)}b=Ka(u,"prelu weights","fused conv2d")}const x=(e,t)=>{ie("NHWC"===r,(()=>`Error in gradient of fused conv2D: got dataFormat of ${r} but only NHWC is currently supported.`));const[i,o,u,c]=t,h=$d(e,u,l);ie(Ju(a),(()=>`Error in gradient of fused conv2D: dilation rates greater than 1 are not yet supported in gradients. Got dilations '${a}'`));const p=[$c(o.shape,h,i,n,s),Cd(o,h,i.shape,n,s)];if(null!=c){const e=Ed(c,h);p.push(e)}return p},w={x:d,filter:p,bias:y,preluActivationWeights:b},v={strides:n,pad:s,dataFormat:r,dilations:a,dimRoundingMode:i,activation:l,leakyreluAlpha:c};if(null==o){const e=Po(((e,t,n)=>{let s=za.runKernel(yr,w,v);return n([t,e,s]),f&&(s=sc(s,[s.shape[1],s.shape[2],s.shape[3]])),{value:s,gradFunc:x}}));return e(d,p)}{const e=Po(((e,t,n,s)=>{let r=za.runKernel(yr,w,v);return s([t,e,r,n]),f&&(r=sc(r,[r.shape[1],r.shape[2],r.shape[3]])),{value:r,gradFunc:x}}));return e(d,p,y)}}});const _d=Za({depthwiseConv2dNativeBackpropFilter_:function(e,t,n,s,r,a=[1,1],i){let o=e;3===e.rank&&(o=sc(e,[1,e.shape[0],e.shape[1],e.shape[2]]));let l=t;3===l.rank&&(l=sc(t,[1,t.shape[0],t.shape[1],t.shape[2]]));const u={x:o,dy:l},c={strides:s,pad:r,dimRoundingMode:i,dilations:a,filterShape:n};return za.runKernel(Gt,u,c)}});const Dd=Za({depthwiseConv2dNativeBackpropInput_:function(e,t,n,s,r,a=[1,1],i){let o=t,l=!1;3===t.rank&&(l=!0,o=sc(t,[1,t.shape[0],t.shape[1],t.shape[2]]));const u={dy:o,filter:n},c={strides:s,pad:r,dimRoundingMode:i,dilations:a,inputShape:e},h=za.runKernel(Ht,u,c);return l?sc(h,[h.shape[1],h.shape[2],h.shape[3]]):h}});const Od=Za({fusedDepthwiseConv2d_:function({x:e,filter:t,strides:n,pad:s,dataFormat:r="NHWC",dilations:a=[1,1],dimRoundingMode:i,bias:o,activation:l="linear",preluActivationWeights:u,leakyreluAlpha:c}){if(!1===Rd(za.state.gradientDepth,l)){let h=Pc(e,t,n,s,r,a,i);return null!=o&&(h=Co(h,o)),Ad(h,l,u,c)}const h=Ka(e,"x","depthwiseConv2d","float32"),p=Ka(t,"filter","depthwiseConv2d","float32");let d=h,f=!1;3===h.rank&&(f=!0,d=sc(h,[1,h.shape[0],h.shape[1],h.shape[2]])),ie(4===d.rank,(()=>`Error in fused depthwiseConv2d: input must be rank 4, but got rank ${d.rank}.`)),ie(4===p.rank,(()=>`Error in fused depthwiseConv2d: filter must be rank 4, but got rank ${p.rank}.`)),ie(d.shape[3]===p.shape[2],(()=>`Error in fused depthwiseConv2d: number of input channels (${d.shape[3]}) must match the inChannels dimension in filter ${p.shape[2]}.`)),null==a&&(a=[1,1]),ie(Qu(n,a),(()=>`Error in fused depthwiseConv2d: Either strides or dilations must be 1. Got strides ${n} and dilations '${a}'`)),nc("fused depthwiseConv2d",s,i);const m=Hu(d.shape,p.shape,n,a,s,i,!0);let g,y;null!=o&&(g=Ka(o,"bias","fused conv2d"),[g]=Ea(g,h),tl(m.outShape,g.shape)),null!=u&&(y=Ka(u,"prelu weights","fused depthwiseConv2d"));const b=(e,t)=>{ie(Ju(a),(()=>`Error in gradient of fused depthwiseConv2d: dilation rates greater than 1 are not yet supported. Got dilations '${a}'`));const[r,o,u,c]=t,h=$d(e,u,l),p=Dd(o.shape,h,r,n,s,a,i),d=_d(o,h,r.shape,n,s,a,i);if(null!=c){return[p,d,Ed(g,h)]}return[p,d]},x={x:d,filter:p,bias:g,preluActivationWeights:y},w={strides:n,pad:s,dataFormat:r,dilations:a,dimRoundingMode:i,activation:l,leakyreluAlpha:c};if(null==o){const e=Po(((e,t,n)=>{let s=za.runKernel(br,x,w);return n([t,e,s]),f&&(s=sc(s,[s.shape[1],s.shape[2],s.shape[3]])),{value:s,gradFunc:b}}));return e(d,p)}{const e=Po(((e,t,n,s)=>{let r=za.runKernel(br,x,w);return s([t,e,r,n]),f&&(r=sc(r,[r.shape[1],r.shape[2],r.shape[3]])),{value:r,gradFunc:b}}));return e(d,p,g)}}});const Md=Za({fusedMatMul_:function({a:e,b:t,transposeA:n=!1,transposeB:s=!1,bias:r,activation:a="linear",preluActivationWeights:i,leakyreluAlpha:o=.2}){if(!1===Rd(za.state.gradientDepth,a)){let l=$l(e,t,n,s);return null!=r&&(l=Co(l,r)),Ad(l,a,i,o)}let l=Ka(e,"a","fused matMul"),u=Ka(t,"b","fused matMul");[l,u]=Ea(l,u);const c=n?l.shape[l.rank-2]:l.shape[l.rank-1],h=s?u.shape[u.rank-1]:u.shape[u.rank-2],p=n?l.shape[l.rank-1]:l.shape[l.rank-2],d=s?u.shape[u.rank-2]:u.shape[u.rank-1],f=l.shape.slice(0,-2),m=u.shape.slice(0,-2),g=ue(f),y=ue(m);ie(c===h,(()=>`Error in fused matMul: inner shapes (${c}) and (${h}) of Tensors with shapes ${l.shape} and ${u.shape} and transposeA=${n} and transposeB=${s} must match.`));const b=tl(l.shape.slice(0,-2),u.shape.slice(0,-2)).concat([p,d]),x=sc(l,n?[g,c,p]:[g,p,c]),w=sc(u,s?[y,d,h]:[y,h,d]);let v,k;null!=r&&(v=Ka(r,"bias","fused matMul"),[v]=Ea(v,l),tl(b,v.shape)),null!=i&&(k=Ka(i,"prelu weights","fused matMul"));const I=(e,t)=>{const[i,o,l,u]=t,c=$d(sc(e,l.shape),l,a);let h,p;if(n||s?!n&&s?(h=$l(c,o,!1,!1),p=$l(c,i,!0,!1)):n&&!s?(h=$l(o,c,!1,!0),p=$l(i,c,!1,!1)):(h=$l(o,c,!0,!0),p=$l(c,i,!0,!0)):(h=$l(c,o,!1,!0),p=$l(i,c,!0,!1)),null!=r){return[h,p,Ed(u,c)]}return[h,p]},N={a:x,b:w,bias:v,preluActivationWeights:k},S={transposeA:n,transposeB:s,activation:a,leakyreluAlpha:o};if(null==r){const e=Po(((e,t,n)=>{const s=za.runKernel(gr,N,S);return n([e,t,s]),{value:sc(s,b),gradFunc:I}}));return e(x,w)}{const e=Po(((e,t,n,s)=>{const r=za.runKernel(gr,N,S);return s([e,t,r,n]),{value:sc(r,b),gradFunc:I}}));return e(x,w,v)}}});const Ld=Za({hammingWindow_:function(e){return Sd(e,.54,.46)}});const zd=Za({hannWindow_:function(e){return Sd(e,.5,.5)}});const Pd=Za({frame_:function(e,t,n,s=!1,r=0){let a=0;const i=[];for(;a+t<=e.size;)i.push(lc(e,a,t)),a+=n;if(s)for(;a<e.size;){const s=a+t-e.size,o=ic([lc(e,a,t-s),qo([s],r)]);i.push(o),a+=n}return 0===i.length?rd([],[0,t]):sc(ic(i),[i.length,t])}});const Bd=Za({stft_:function(e,t,n,s,r=zd){null==s&&(s=Nd(t));const a=Pd(e,t,n),i=Ao(a,r(t));return Yp(i,s)}});const Wd=Za({cropAndResize_:function(e,t,n,s,r="bilinear",a=0){const i=Ka(e,"image","cropAndResize"),o=Ka(t,"boxes","cropAndResize","float32"),l=Ka(n,"boxInd","cropAndResize","int32"),u=o.shape[0];ie(4===i.rank,(()=>`Error in cropAndResize: image must be rank 4,but got rank ${i.rank}.`)),ie(2===o.rank&&4===o.shape[1],(()=>`Error in cropAndResize: boxes must be have size [${u},4] but had shape ${o.shape}.`)),ie(1===l.rank&&l.shape[0]===u,(()=>`Error in cropAndResize: boxInd must be have size [${u}] but had shape ${o.shape}.`)),ie(2===s.length,(()=>`Error in cropAndResize: cropSize must be of length 2, but got length ${s.length}.`)),ie(s[0]>=1&&s[1]>=1,(()=>`cropSize must be atleast [1,1], but was ${s}`)),ie("bilinear"===r||"nearest"===r,(()=>`method must be bilinear or nearest, but was ${r}`));const c={image:i,boxes:o,boxInd:l},h={method:r,extrapolationValue:a,cropSize:s};return za.runKernel(Bt,c,h)}});const Vd=Za({flipLeftRight_:function(e){const t=Ka(e,"image","flipLeftRight","float32");ie(4===t.rank,(()=>`Error in flipLeftRight: image must be rank 4,but got rank ${t.rank}.`));const n={image:t};return za.runKernel(un,n,{})}});const Ud=Za({grayscaleToRGB_:function(e){const t=Ka(e,"image","grayscaleToRGB"),n=t.rank-1,s=t.shape[n];ie(t.rank>=2,(()=>`Error in grayscaleToRGB: images must be at least rank 2, but got rank ${t.rank}.`)),ie(1===s,(()=>`Error in grayscaleToRGB: last dimension of a grayscale image should be size 1, but got size ${s}.`));const r=new Array(t.rank);return r.fill(1,0,n),r[n]=3,dh(t,r)}});const Gd=Za({rotateWithOffset_:function(e,t,n=0,s=.5){const r=Ka(e,"image","rotateWithOffset","float32");ie(4===r.rank,(()=>`Error in rotateWithOffset: image must be rank 4,but got rank ${r.rank}.`));const a={image:r},i={radians:t,fillValue:n,center:s};return za.runKernel(mr,a,i)}});function Hd(e,t,n,s,r,a){null==s&&(s=.5),null==r&&(r=Number.NEGATIVE_INFINITY),null==a&&(a=0);const i=e.shape[0];return n=Math.min(n,i),ie(0<=s&&s<=1,(()=>`iouThreshold must be in [0, 1], but was '${s}'`)),ie(2===e.rank,(()=>`boxes must be a 2D tensor, but was of rank '${e.rank}'`)),ie(4===e.shape[1],(()=>`boxes must have 4 columns, but 2nd dimension was ${e.shape[1]}`)),ie(1===t.rank,(()=>"scores must be a 1D tensor")),ie(t.shape[0]===i,(()=>`scores has incompatible shape with boxes. Expected ${i}, but was ${t.shape[0]}`)),ie(0<=a&&a<=1,(()=>`softNmsSigma must be in [0, 1], but was '${a}'`)),{maxOutputSize:n,iouThreshold:s,scoreThreshold:r,softNmsSigma:a}}const jd=Za({nonMaxSuppression_:function(e,t,n,s=.5,r=Number.NEGATIVE_INFINITY){const a=Ka(e,"boxes","nonMaxSuppression","float32"),i=Ka(t,"scores","nonMaxSuppression","float32"),o=Hd(a,i,n,s,r),l={maxOutputSize:n=o.maxOutputSize,iouThreshold:s=o.iouThreshold,scoreThreshold:r=o.scoreThreshold};return za.runKernel(es,{boxes:a,scores:i},l)}});function qd(e,t,n){const s=function(e,t,n){return function(e,t,n){let s=0,r=e.length,a=0,i=!1;for(;s<r;){a=s+(r-s>>>1);const o=n(t,e[a]);o>0?s=a+1:(r=a,i=!o)}return i?s:-s-1}(e,t,n||Kd)}(e,t,n),r=s<0?-(s+1):s;e.splice(r,0,t)}function Kd(e,t){return e>t?1:e<t?-1:0}function Xd(e,t,n,s,r){return Jd(e,t,n,s,r,0)}function Yd(e,t,n,s,r,a){return Jd(e,t,n,s,r,0,!1,a,!0)}function Zd(e,t,n,s,r,a){return Jd(e,t,n,s,r,a,!0)}function Jd(e,t,n,s,r,a,i=!1,o=!1,l=!1){const u=[];for(let e=0;e<t.length;e++)t[e]>r&&u.push({score:t[e],boxIndex:e,suppressBeginIndex:0});u.sort(tf);const c=a>0?-.5/a:0,h=[],p=[];for(;h.length<n&&u.length>0;){const t=u.pop(),{score:n,boxIndex:a,suppressBeginIndex:i}=t;if(n<r)break;let o=!1;for(let n=h.length-1;n>=i;--n){const i=Qd(e,a,h[n]);if(i>=s){o=!0;break}if(t.score=t.score*ef(s,c,i),t.score<=r)break}t.suppressBeginIndex=h.length,o||(t.score===n?(h.push(a),p.push(t.score)):t.score>r&&qd(u,t,tf))}const d=h.length,f=n-d;o&&f>0&&(h.push(...new Array(f).fill(0)),p.push(...new Array(f).fill(0)));const m={selectedIndices:h};return i&&(m.selectedScores=p),l&&(m.validOutputs=d),m}function Qd(e,t,n){const s=e.subarray(4*t,4*t+4),r=e.subarray(4*n,4*n+4),a=Math.min(s[0],s[2]),i=Math.min(s[1],s[3]),o=Math.max(s[0],s[2]),l=Math.max(s[1],s[3]),u=Math.min(r[0],r[2]),c=Math.min(r[1],r[3]),h=Math.max(r[0],r[2]),p=Math.max(r[1],r[3]),d=(o-a)*(l-i),f=(h-u)*(p-c);if(d<=0||f<=0)return 0;const m=Math.max(a,u),g=Math.max(i,c),y=Math.min(o,h),b=Math.min(l,p),x=Math.max(y-m,0)*Math.max(b-g,0);return x/(d+f-x)}function ef(e,t,n){const s=Math.exp(t*n*n);return n<=e?s:0}function tf(e,t){return e.score-t.score||e.score===t.score&&t.boxIndex-e.boxIndex}const nf=async function(e,t,n,s=.5,r=Number.NEGATIVE_INFINITY){const a=Ka(e,"boxes","nonMaxSuppressionAsync"),i=Ka(t,"scores","nonMaxSuppressionAsync"),o=Hd(a,i,n,s,r);n=o.maxOutputSize,s=o.iouThreshold,r=o.scoreThreshold;const l=await Promise.all([a.data(),i.data()]),u=l[0],c=l[1],{selectedIndices:h}=Xd(u,c,n,s,r);return a!==e&&a.dispose(),i!==t&&i.dispose(),sd(h,"int32")};const sf=Za({nonMaxSuppressionWithScore_:function(e,t,n,s=.5,r=Number.NEGATIVE_INFINITY,a=0){const i=Ka(e,"boxes","nonMaxSuppression"),o=Ka(t,"scores","nonMaxSuppression"),l=Hd(i,o,n,s,r,a),u={boxes:i,scores:o},c={maxOutputSize:n=l.maxOutputSize,iouThreshold:s=l.iouThreshold,scoreThreshold:r=l.scoreThreshold,softNmsSigma:a=l.softNmsSigma},h=za.runKernel(ns,u,c);return{selectedIndices:h[0],selectedScores:h[1]}}});const rf=async function(e,t,n,s=.5,r=Number.NEGATIVE_INFINITY,a=0){const i=Ka(e,"boxes","nonMaxSuppressionAsync"),o=Ka(t,"scores","nonMaxSuppressionAsync"),l=Hd(i,o,n,s,r,a);n=l.maxOutputSize,s=l.iouThreshold,r=l.scoreThreshold,a=l.softNmsSigma;const u=await Promise.all([i.data(),o.data()]),c=u[0],h=u[1],{selectedIndices:p,selectedScores:d}=Zd(c,h,n,s,r,a);return i!==e&&i.dispose(),o!==t&&o.dispose(),{selectedIndices:sd(p,"int32"),selectedScores:sd(d)}};const af=Za({nonMaxSuppressionPadded_:function(e,t,n,s=.5,r=Number.NEGATIVE_INFINITY,a=!1){const i=Ka(e,"boxes","nonMaxSuppression"),o=Ka(t,"scores","nonMaxSuppression"),l=Hd(i,o,n,s,r,null),u={boxes:i,scores:o},c={maxOutputSize:l.maxOutputSize,iouThreshold:l.iouThreshold,scoreThreshold:l.scoreThreshold,padToMaxOutputSize:a},h=za.runKernel(ts,u,c);return{selectedIndices:h[0],validOutputs:h[1]}}});const of=async function(e,t,n,s=.5,r=Number.NEGATIVE_INFINITY,a=!1){const i=Ka(e,"boxes","nonMaxSuppressionAsync"),o=Ka(t,"scores","nonMaxSuppressionAsync"),l=Hd(i,o,n,s,r,null),u=l.maxOutputSize,c=l.iouThreshold,h=l.scoreThreshold,[p,d]=await Promise.all([i.data(),o.data()]),{selectedIndices:f,validOutputs:m}=Yd(p,d,u,c,h,a);return i!==e&&i.dispose(),o!==t&&o.dispose(),{selectedIndices:sd(f,"int32"),validOutputs:Wo(m,"int32")}};const lf=Za({resizeBilinear_:function(e,t,n=!1,s=!1){const r=Ka(e,"images","resizeBilinear");ie(3===r.rank||4===r.rank,(()=>`Error in resizeBilinear: x must be rank 3 or 4, but got rank ${r.rank}.`)),ie(2===t.length,(()=>`Error in resizeBilinear: new shape must 2D, but got shape ${t}.`)),ie(!1===s||!1===n,(()=>"Error in resizeBilinear: If halfPixelCenters is true, alignCorners must be false."));let a=r,i=!1;3===r.rank&&(i=!0,a=sc(r,[1,r.shape[0],r.shape[1],r.shape[2]]));const[]=t,o={images:a},l={alignCorners:n,halfPixelCenters:s,size:t},u=za.runKernel(vs,o,l);return i?sc(u,[u.shape[1],u.shape[2],u.shape[3]]):u}});const uf=Za({resizeNearestNeighbor_:function(e,t,n=!1,s=!1){const r=Ka(e,"images","resizeNearestNeighbor");ie(3===r.rank||4===r.rank,(()=>`Error in resizeNearestNeighbor: x must be rank 3 or 4, but got rank ${r.rank}.`)),ie(2===t.length,(()=>`Error in resizeNearestNeighbor: new shape must 2D, but got shape ${t}.`)),ie("float32"===r.dtype||"int32"===r.dtype,(()=>"`images` must have `int32` or `float32` as dtype")),ie(!1===s||!1===n,(()=>"Error in resizeNearestNeighbor: If halfPixelCenters is true, alignCorners must be false."));let a=r,i=!1;3===r.rank&&(i=!0,a=sc(r,[1,r.shape[0],r.shape[1],r.shape[2]]));const[]=t,o={images:a},l={alignCorners:n,halfPixelCenters:s,size:t},u=za.runKernel(xs,o,l);return i?sc(u,[u.shape[1],u.shape[2],u.shape[3]]):u}});const cf=Za({threshold_:function(e,t="binary",n=!1,s=.5){const r=Ka(e,"image","threshold"),a=r.shape[0]*r.shape[1];let i,o,l,u,c=Ao(sd([s]),255);if(ie(3===r.rank,(()=>`Error in threshold: image must be rank 3,but got rank ${r.rank}.`)),ie(3===r.shape[2]||1===r.shape[2],(()=>`Error in threshold: image color channel must be equal to 3 or 1but got ${r.shape[2]}.`)),ie("int32"===r.dtype||"float32"===r.dtype,(()=>`Error in dtype: image dtype must be int32 or float32,but got dtype ${r.dtype}.`)),ie("otsu"===t||"binary"===t,(()=>`Method must be binary or otsu, but was ${t}`)),3===r.shape[2]){[i,o,l]=Xp(r,[1,1,1],-1);const e=Ao(i,.2989),t=Ao(o,.587),n=Ao(l,.114);u=Co(Co(e,t),n)}else u=e;if("otsu"===t){c=function(e,t){let n,s,r,a,i,o,l=sd([-1]),u=sd([0]),c=sd([0]);for(let h=0;h<e.size-1;h++){n=lc(e,0,h+1),s=lc(e,h+1),i=Eo(ih(n),t),o=Eo(ih(s),t);const p=ih(Ao(n,Np(0,n.size)));r=Eo(p,ih(n));const d=qo(s.shape,n.size),f=Co(Np(0,s.size),d),m=Ao(s,f);a=Eo(ih(m),ih(s));const g=Yo(r,a),y=Yo(r,a),b=Ao(i,o);c=Ao(Ao(b,g),y);const x=yh(c,u);u=Uc(x,c,u),l=Uc(x,sd([h]),l)}return l}(gc(no(_p(u),"int32"),ei([]),256),a)}const h=n?Nh(u,c):yh(u,c);return no(Ao(h,255),"int32")}});const hf=Za({transform_:function(e,t,n="nearest",s="constant",r=0,a){const i=Ka(e,"image","transform","float32"),o=Ka(t,"transforms","transform","float32");ie(4===i.rank,(()=>`Error in transform: image must be rank 4,but got rank ${i.rank}.`)),ie(2===o.rank&&(o.shape[0]===i.shape[0]||1===o.shape[0])&&8===o.shape[1],(()=>"Error in transform: Input transform should be batch x 8 or 1 x 8")),ie(null==a||2===a.length,(()=>`Error in transform: outputShape must be [height, width] or null, but got ${a}.`));const l={image:i,transforms:o},u={interpolation:n,fillMode:s,fillValue:r,outputShape:a};return za.runKernel(ir,l,u)}});const pf=Za({bandPart_:function(e,t,n){const s=Ka(e,"a","bandPart");ie(s.rank>=2,(()=>`bandPart(): Rank must be at least 2, got ${s.rank}.`));const r=s.shape,[a,i]=s.shape.slice(-2);let o,l;"number"==typeof t?(ie(t%1==0,(()=>`bandPart(): numLower must be an integer, got ${t}.`)),ie(t<=a,(()=>`bandPart(): numLower (${t}) must not be greater than the number of rows (${a}).`)),o=Ka(t<0?a:t,"numLower","bandPart")):(ie("int32"===t.dtype,(()=>"bandPart(): numLower's dtype must be an int32.")),o=Uc(Ih(t,0),a,qh(t,a))),"number"==typeof n?(ie(n%1==0,(()=>`bandPart(): numUpper must be an integer, got ${n}.`)),ie(n<=i,(()=>`bandPart(): numUpper (${n}) must not be greater than the number of columns (${i}).`)),l=Ka(n<0?i:n,"numUpper","bandPart")):(ie("int32"===n.dtype,(()=>"bandPart(): numUpper's dtype must be an int32.")),l=Uc(Ih(n,0),i,qh(n,i)));const u=sc(Np(0,a,1,"int32"),[-1,1]),c=Np(0,i,1,"int32"),h=Yo(u,c),p=_h(Nh(h,o),bh(h,Rl(l))),d=Gh([a,i],s.dtype);return sc(Qp(dd(sc(s,[-1,a,i])).map((e=>Uc(p,e,d)))),r)}});const df=Za({gramSchmidt_:function(e){let t;if(Array.isArray(e)){t=!1,ie(null!=e&&e.length>0,(()=>"Gram-Schmidt process: input must not be null, undefined, or empty"));const n=e[0].shape[0];for(let t=1;t<e.length;++t)ie(e[t].shape[0]===n,(()=>`Gram-Schmidt: Non-unique lengths found in the input vectors: (${e[t].shape[0]} vs. ${n})`))}else t=!0,e=Xp(e,e.shape[0],0).map((e=>Jp(e,[0])));ie(e.length<=e[0].shape[0],(()=>`Gram-Schmidt: Number of vectors (${e.length}) exceeds number of dimensions (${e[0].shape[0]}).`));const n=[],s=e;for(let t=0;t<e.length;++t)n.push(za.tidy((()=>{let e=s[t];if(t>0)for(let s=0;s<t;++s){const t=Ao(ih(Ao(n[s],e)),n[s]);e=Yo(e,t)}return Eo(e,lh(e,"euclidean"))})));return t?Qp(n,0):n}});function ff(e,t=!1){return za.tidy((()=>{ie(2===e.shape.length,(()=>`qr2d() requires a 2D Tensor, but got a ${e.shape.length}D Tensor.`));const n=e.shape[0],s=e.shape[1];let r=fh(n),a=so(e);const i=rd([[1]],[1,1]);let o=so(i);const l=n>=s?s:n;for(let e=0;e<l;++e){const t=a,l=o,u=r;[o,a,r]=za.tidy((()=>{const t=lc(a,[e,e],[n-e,1]),l=lh(t),u=lc(a,[e,e],[1,1]),c=Uc(yh(u,0),rd([[-1]]),rd([[1]])),h=Yo(u,Ao(c,l)),p=Eo(t,h);o=1===p.shape[0]?so(i):ic([i,lc(p,[1,0],[p.shape[0]-1,p.shape[1]])],0);const d=Rl(Eo($l(c,h),l)),f=lc(a,[e,0],[n-e,s]),m=Ao(d,o),g=_l(o);if(0===e)a=Yo(f,$l(m,$l(g,f)));else{const t=Yo(f,$l(m,$l(g,f)));a=ic([lc(a,[0,0],[e,s]),t],0)}const y=_l(m),b=lc(r,[0,e],[n,r.shape[1]-e]);if(0===e)r=Yo(b,$l($l(b,o),y));else{const t=Yo(b,$l($l(b,o),y));r=ic([lc(r,[0,0],[n,e]),t],1)}return[o,a,r]})),mo([t,l,u])}return!t&&n>s&&(r=lc(r,[0,0],[n,s]),a=lc(a,[0,0],[s,s])),[r,a]}))}const mf=Za({qr_:function(e,t=!1){if(ie(e.rank>=2,(()=>`qr() requires input tensor to have a rank >= 2, but got rank ${e.rank}`)),2===e.rank)return ff(e,t);{const n=e.shape.slice(0,e.shape.length-2).reduce(((e,t)=>e*t)),s=dd(sc(e,[n,e.shape[e.shape.length-2],e.shape[e.shape.length-1]]),0),r=[],a=[];s.forEach((e=>{const[n,s]=ff(e,t);r.push(n),a.push(s)}));return[sc(Qp(r,0),e.shape),sc(Qp(a,0),e.shape)]}}});var gf;!function(e){e[e.NONE=0]="NONE",e[e.MEAN=1]="MEAN",e[e.SUM=2]="SUM",e[e.SUM_BY_NONZERO_WEIGHTS=3]="SUM_BY_NONZERO_WEIGHTS"}(gf||(gf={}));const yf=Za({computeWeightedLoss_:function(e,t,n=gf.SUM_BY_NONZERO_WEIGHTS){const s=Ka(e,"losses","computeWeightedLoss");let r=null;null!=t&&(r=Ka(t,"weights","computeWeightedLoss"));const a=null==r?s:Ao(s,r);if(n===gf.NONE)return a;if(n===gf.SUM)return ih(a);if(n===gf.MEAN){if(null==r)return Uh(a);{const e=s.size/r.size,t=Eo(ih(a),ih(r));return e>1?Eo(t,Wo(e)):t}}if(n===gf.SUM_BY_NONZERO_WEIGHTS){if(null==r)return Eo(ih(a),Wo(s.size));{const e=Ao(r,Hh(s.shape)),t=no(ih(Qh(e,Wo(0))),"float32");return Eo(ih(a),t)}}throw Error(`Unknown reduction: ${n}`)}});const bf=Za({absoluteDifference_:function(e,t,n,s=gf.SUM_BY_NONZERO_WEIGHTS){const r=Ka(e,"labels","absoluteDifference"),a=Ka(t,"predictions","absoluteDifference");let i=null;null!=n&&(i=Ka(n,"weights","absoluteDifference")),oe(r.shape,a.shape,"Error in absoluteDifference: ");const o=Jo(Yo(r,a));return yf(o,i,s)}});const xf=Za({cosineDistance_:function(e,t,n,s,r=gf.SUM_BY_NONZERO_WEIGHTS){const a=Ka(e,"labels","cosineDistance"),i=Ka(t,"predictions","cosineDistance");let o=null;null!=s&&(o=Ka(s,"weights","cosineDistance")),oe(a.shape,i.shape,"Error in cosineDistance: ");const l=Wo(1),u=Yo(l,ih(Ao(a,i),n,!0));return yf(u,o,r)}});const wf=Za({hingeLoss_:function(e,t,n,s=gf.SUM_BY_NONZERO_WEIGHTS){let r=Ka(e,"labels","hingeLoss");const a=Ka(t,"predictions","hingeLoss");let i=null;null!=n&&(i=Ka(n,"weights","hingeLoss")),oe(r.shape,a.shape,"Error in hingeLoss: ");const o=Wo(1);r=Yo(Ao(Wo(2),r),o);const l=Tp(Yo(o,Ao(r,a)));return yf(l,i,s)}});const vf=Za({huberLoss_:function(e,t,n,s=1,r=gf.SUM_BY_NONZERO_WEIGHTS){const a=Ka(e,"labels","huberLoss"),i=Ka(t,"predictions","huberLoss");let o=null;null!=n&&(o=Ka(n,"weights","huberLoss")),oe(a.shape,i.shape,"Error in huberLoss: ");const l=Wo(s),u=Jo(Yo(i,a)),c=qh(u,l),h=Yo(u,c),p=Co(Ao(Wo(.5),Fo(c)),Ao(l,h));return yf(p,o,r)}});const kf=Za({logLoss_:function(e,t,n,s=1e-7,r=gf.SUM_BY_NONZERO_WEIGHTS){const a=Ka(e,"labels","logLoss"),i=Ka(t,"predictions","logLoss");let o=null;null!=n&&(o=Ka(n,"weights","logLoss")),oe(a.shape,i.shape,"Error in logLoss: ");const l=Wo(1),u=Wo(s),c=Rl(Ao(a,Ch(Co(i,u)))),h=Ao(Yo(l,a),Ch(Co(Yo(l,i),u))),p=Yo(c,h);return yf(p,o,r)}});const If=Za({meanSquaredError_:function(e,t,n,s=gf.SUM_BY_NONZERO_WEIGHTS){const r=Ka(e,"labels","meanSquaredError"),a=Ka(t,"predictions","meanSquaredError");let i=null;null!=n&&(i=Ka(n,"weights","meanSquaredError")),oe(r.shape,a.shape,"Error in meanSquaredError: ");const o=Zp(r,a);return yf(o,i,s)}});const Nf=Za({sigmoidCrossEntropy_:function(e,t,n,s=0,r=gf.SUM_BY_NONZERO_WEIGHTS){let a=Ka(e,"multiClassLabels","sigmoidCrossEntropy");const i=Ka(t,"logits","sigmoidCrossEntropy");let o=null;if(null!=n&&(o=Ka(n,"weights","sigmoidCrossEntropy")),oe(a.shape,i.shape,"Error in sigmoidCrossEntropy: "),s>0){const e=Wo(s),t=Wo(1),n=Wo(.5);a=Co(Ao(a,Yo(t,e)),Ao(n,e))}const l=function(e,t){const n=Ka(e,"labels","sigmoidCrossEntropyWithLogits"),s=Ka(t,"logits","sigmoidCrossEntropyWithLogits");oe(n.shape,s.shape,"Error in sigmoidCrossEntropyWithLogits: ");const r=Tp(s),a=Ao(s,n),i=$h(ch(Rl(Jo(s))));return Co(Yo(r,a),i)}(a,i);return yf(l,o,r)}});const Sf=Za({softmaxCrossEntropy_:function(e,t,n,s=0,r=gf.SUM_BY_NONZERO_WEIGHTS){let a=Ka(e,"onehotLabels","softmaxCrossEntropy");const i=Ka(t,"logits","softmaxCrossEntropy");let o=null;if(null!=n&&(o=Ka(n,"weights","softmaxCrossEntropy")),oe(a.shape,i.shape,"Error in softmaxCrossEntropy: "),s>0){const e=Wo(s),t=Wo(1),n=Wo(a.shape[1]);a=Co(Ao(a,Yo(t,e)),Eo(e,n))}const l=function(e,t,n=-1){if(-1===n&&(n=t.rank-1),n!==t.rank-1)throw Error(`Softmax cross entropy along a non-last dimension is not yet supported. Labels / logits was rank ${t.rank} and dim was ${n}`);const s=Po(((e,t,s)=>{const r=Fh(t,[n],!0),a=Yo(no(t,"float32"),r);s([e,a]);const i=Rl(Ao(a,e));return{value:ih(i,[n]),gradFunc:(e,t)=>{const[s,r]=t,a=Qc(e.shape,[n]);return[Ao(sc(e,a),Yo(no(s,"float32"),ch(r))),Ao(sc(e,a),Yo(ch(r),no(s,"float32")))]}}}));return s(e,t)}(a,i);return yf(l,o,r)}});const Tf=Za({sparseFillEmptyRows_:function(e,t,n,s){const r=Ka(e,"indices","sparseFillEmptyRows","int32"),a=Ka(t,"values","sparseFillEmptyRows"),i=Ka(n,"denseShape","sparseFillEmptyRows","int32"),o=Ka(s,"defaultValue","sparseFillEmptyRows",a.dtype);if(2!==r.rank)throw new Error(`Indices should be Tensor2D but received shape\n        ${r.shape}`);if(1!==a.rank)throw new Error(`Values should be Tensor1D but received shape ${a.shape}`);if(1!==i.rank)throw new Error(`Dense shape should be Tensor1D but received shape ${i.shape}`);if(0!==o.rank)throw new Error(`Default value should be a scalar but received shape ${o.shape}`);const l={indices:r,values:a,denseShape:i,defaultValue:o},u=za.runKernel(Us,l);return{outputIndices:u[0],outputValues:u[1],emptyRowIndicator:u[2],reverseIndexMap:u[3]}}});const Cf=Za({sparseReshape_:function(e,t,n){const s=Ka(e,"inputIndices","sparseReshape","int32"),r=Ka(t,"inputShape","sparseReshape","int32"),a=Ka(n,"newShape","sparseReshape","int32");if(2!==s.rank)throw new Error(`Input indices should be Tensor2D but received shape\n        ${s.shape}`);if(1!==r.rank)throw new Error(`Input shape should be Tensor1D but received shape ${r.shape}`);if(1!==a.rank)throw new Error(`New shape should be Tensor1D but received shape ${a.shape}`);const i={inputIndices:s,inputShape:r,newShape:a},o=za.runKernel(Gs,i);return{outputIndices:o[0],outputShape:o[1]}}});const $f=Za({sparseSegmentMean_:function(e,t,n){const s=Ka(e,"data","sparseSegmentMean"),r=Ka(t,"indices","sparseSegmentMean","int32"),a=Ka(n,"segmentIds","sparseSegmentMean","int32");if(s.rank<1)throw new Error("Data should be at least 1 dimensional but received scalar");if(1!==r.rank)throw new Error(`Indices should be Tensor1D but received shape\n          ${r.shape}`);if(1!==a.rank)throw new Error(`Segment ids should be Tensor1D but received shape\n          ${a.shape}`);const i={data:s,indices:r,segmentIds:a};return za.runKernel(Hs,i)}});const Ef=Za({sparseSegmentSum_:function(e,t,n){const s=Ka(e,"data","sparseSegmentSum"),r=Ka(t,"indices","sparseSegmentSum","int32"),a=Ka(n,"segmentIds","sparseSegmentSum","int32");if(s.rank<1)throw new Error("Data should be at least 1 dimensional but received scalar");if(1!==r.rank)throw new Error(`Indices should be Tensor1D but received shape\n         ${r.shape}`);if(1!==a.rank)throw new Error(`Segment ids should be Tensor1D but received shape\n         ${a.shape}`);const i={data:s,indices:r,segmentIds:a};return za.runKernel(js,i)}});const Af=Za({stringNGrams_:function(e,t,n,s,r,a,i,o){const l=Ka(e,"data","stringNGrams","string");if("string"!==l.dtype)throw new Error("Data must be of datatype string");if(1!==l.shape.length)throw new Error(`Data must be a vector, saw: ${l.shape}`);const u=Ka(t,"dataSplits","stringNGrams");if("int32"!==u.dtype)throw new Error("Data splits must be of datatype int32");const c={separator:n,nGramWidths:s,leftPad:r,rightPad:a,padWidth:i,preserveShortSequences:o},h={data:l,dataSplits:u},p=za.runKernel(Js,h,c);return{nGrams:p[0],nGramsSplits:p[1]}}});const Rf=Za({stringSplit_:function(e,t,n=!0){const s=Ka(e,"input","stringSplit","string"),r=Ka(t,"delimiter","stringSplit","string");if(1!==s.rank)throw new Error(`Input should be Tensor1D but received shape ${s.shape}`);if(0!==r.rank)throw new Error(`Delimiter should be a scalar but received shape ${r.shape}`);const a={skipEmpty:n},i={input:s,delimiter:r},o=za.runKernel(Qs,i,a);return{indices:o[0],values:o[1],shape:o[2]}}});const Ff=Za({stringToHashBucketFast_:function(e,t){const n=Ka(e,"input","stringToHashBucketFast","string"),s={numBuckets:t};if(t<=0)throw new Error("Number of buckets must be at least 1");const r={input:n};return za.runKernel(er,r,s)}});const _f=Za({staticRegexReplace_:function(e,t,n,s=!0){const r=Ka(e,"input","staticRegexReplace","string"),a={pattern:t,rewrite:n,replaceGlobal:s};return za.runKernel(Ys,{x:r},a)}}),Df={fft:jp,ifft:qp,rfft:Yp,irfft:Kp},Of={hammingWindow:Ld,hannWindow:zd,frame:Pd,stft:Bd},Mf={flipLeftRight:Vd,grayscaleToRGB:Ud,resizeNearestNeighbor:uf,resizeBilinear:lf,rotateWithOffset:Gd,cropAndResize:Wd,nonMaxSuppression:jd,nonMaxSuppressionAsync:nf,nonMaxSuppressionWithScore:sf,nonMaxSuppressionWithScoreAsync:rf,nonMaxSuppressionPadded:af,nonMaxSuppressionPaddedAsync:of,threshold:cf,transform:hf},Lf={bandPart:pf,gramSchmidt:df,qr:mf},zf={absoluteDifference:bf,computeWeightedLoss:yf,cosineDistance:xf,hingeLoss:wf,huberLoss:vf,logLoss:kf,meanSquaredError:If,sigmoidCrossEntropy:Nf,softmaxCrossEntropy:Sf},Pf={sparseFillEmptyRows:Tf,sparseReshape:Cf,sparseSegmentMean:$f,sparseSegmentSum:Ef},Bf={stringNGrams:Af,stringSplit:Rf,stringToHashBucketFast:Ff,staticRegexReplace:_f},Wf=Eu,Vf="undefined"!=typeof requestAnimationFrame?requestAnimationFrame:"undefined"!=typeof setImmediate?setImmediate:e=>e();function Uf(){return new Promise((e=>Vf((()=>e()))))}function Gf(e,t){const n=e[0].length;e.forEach(((e,t)=>{ie(e.length===n,(()=>`Error in concat${n}D: rank of tensors[${t}] must be the same as the rank of the rest (${n})`))})),ie(t>=0&&t<n,(()=>`Error in concat${n}D: axis must be between 0 and ${n-1}.`));const s=e[0];e.forEach(((e,r)=>{for(let a=0;a<n;a++)ie(a===t||e[a]===s[a],(()=>`Error in concat${n}D: Shape of tensors[${r}] (${e}) does not match the shape of the rest (${s}) along the non-concatenated axis ${r}.`))}))}function Hf(e,t){const n=e[0].slice();for(let s=1;s<e.length;s++)n[t]+=e[s][t];return n}var jf;function qf(e,t,n){let s=new Array;if(null==n&&null==t)return s;if(null==t)for(;s.length<e+n.length;)s.push(-1);else s=t.slice();if(null==n)return s;if(e+n.length!==s.length)throw new Error(`rt input.shape and shape=${t} are incompatible: rt input.rank = ${e+n.length}, but shape.rank = ${s.length}`);for(let r=1;r<n.length;++r){const a=n[r],i=s[s.length-n.length+r],o=s[i];if(a>=0)if(o>=0){if(o!==a)throw new Error(`rt input.shape and shape=${t} are incompatible: rt input.shape[${r+e}] = ${a} but shape[${r+e}] = ${o}`)}else s[i]=a}return s}function Kf(e){const t={FIRST_DIM_SIZE:jf.FIRST_DIM_SIZE,VALUE_ROWIDS:jf.VALUE_ROWIDS,ROW_LENGTHS:jf.ROW_LENGTHS,ROW_SPLITS:jf.ROW_SPLITS,ROW_LIMITS:jf.ROW_LIMITS,ROW_STARTS:jf.ROW_STARTS},n=[];for(const s of e){if(!(s in t))break;n.push(t[s])}return n}function Xf(e){return 0===e.length?0:e[0]===jf.FIRST_DIM_SIZE?e.length-1:e.length}function Yf(e,t){if(null==e||null==t)return;const n=e.length,s=t.length;if(n>=s)throw new Error(`defaultValue.shape=${e} and ragged tensor flatValues.shape=${t}, are incompatible: defaultValue.rank = ${n} must be less than ragged tensor input flatValues.rank = ${s})`);for(let r=0;r<Math.min(n,s-1);++r){const n=e[r],s=t[r+1];if(n>=0&&s>=0&&1!==n&&n!==s)throw new Error(`defaultValue.shape=${e}, and ragged tensor input flatValues.shape=${t} are incompatible: defaultValue.shape[${r-e.length}] = ${n} but ragged tensor input.flatValues.shape[${r-e.length}] = ${s}`)}}!function(e){e[e.FIRST_DIM_SIZE=0]="FIRST_DIM_SIZE",e[e.VALUE_ROWIDS=1]="VALUE_ROWIDS",e[e.ROW_LENGTHS=2]="ROW_LENGTHS",e[e.ROW_SPLITS=3]="ROW_SPLITS",e[e.ROW_LIMITS=4]="ROW_LIMITS",e[e.ROW_STARTS=5]="ROW_STARTS"}(jf||(jf={}));const Zf=30;function Jf(e){return e<=Zf?e:De(e,Math.floor(Math.sqrt(e)))}function Qf(e,t,n){return[n*("number"==typeof e?e:e[0]),t*("number"==typeof e?e:e[1])]}function em(e,t,n,s=!0){let r=[];if(s)r=r.concat(t.slice(0)),r.push(e[0]/n),r=r.concat(e.slice(1));else{r=r.concat(e[0]);const n=t.length;for(let s=0;s<n;++s)r=r.concat([e[s+1]/t[s],t[s]]);r=r.concat(e.slice(n+1))}return r}function tm(e,t,n=!0){const s=[];if(n){s.push(t);for(let n=t+1;n<e;++n)n<=2*t?(s.push(n),s.push(n-(t+1))):s.push(n)}else{const n=[],r=[];for(let s=1;s<e;++s)s>=2*t+1||s%2==1?r.push(s):n.push(s);s.push(...n),s.push(0),s.push(...r)}return s}function nm(e,t,n,s=!0){const r=[];s?r.push(e[0]/n):r.push(e[0]*n);for(let n=1;n<e.length;++n)n<=t.length?s?r.push(t[n-1]*e[n]):r.push(e[n]/t[n-1]):r.push(e[n]);return r}function sm(e,t){const n=[0];for(let s=0;s<t;++s)n.push(e[s][0]);return n}function rm(e,t,n){const s=e.slice(0,1);for(let r=0;r<n;++r)s.push(e[r+1]-t[r][0]-t[r][1]);return s}const am=1.7580993408473768,im=1.0507009873554805,om=.3275911,lm=.254829592,um=-.284496736,cm=1.421413741,hm=-1.453152027,pm=1.061405429;function dm(e,t){if(e.length!==t.length)throw new Error(`Cannot merge real and imag arrays of different lengths. real:${e.length}, imag: ${t.length}.`);const n=new Float32Array(2*e.length);for(let s=0;s<n.length;s+=2)n[s]=e[s/2],n[s+1]=t[s/2];return n}function fm(e){const t=new Float32Array(e.length/2),n=new Float32Array(e.length/2);for(let s=0;s<e.length;s+=2)t[s/2]=e[s],n[s/2]=e[s+1];return{real:t,imag:n}}function mm(e){const t=Math.ceil(e.length/4),n=new Float32Array(t),s=new Float32Array(t);for(let t=0;t<e.length;t+=4)n[Math.floor(t/4)]=e[t],s[Math.floor(t/4)]=e[t+1];return{real:n,imag:s}}function gm(e){const t=Math.floor(e.length/4),n=new Float32Array(t),s=new Float32Array(t);for(let t=2;t<e.length;t+=4)n[Math.floor(t/4)]=e[t],s[Math.floor(t/4)]=e[t+1];return{real:n,imag:s}}function ym(e,t){return{real:e[2*t],imag:e[2*t+1]}}function bm(e,t,n,s){e[2*s]=t,e[2*s+1]=n}function xm(e,t){const n=new Float32Array(e/2),s=new Float32Array(e/2);for(let r=0;r<Math.ceil(e/2);r++){const a=(t?2:-2)*Math.PI*(r/e);n[r]=Math.cos(a),s[r]=Math.sin(a)}return{real:n,imag:s}}function wm(e,t,n){const s=(n?2:-2)*Math.PI*(e/t);return{real:Math.cos(s),imag:Math.sin(s)}}const vm="->",km=/->/g,Im=",",Nm="...";function Sm(e,t){const n=((e=e.replace(/\s/g,"")).length-e.replace(km,"").length)/vm.length;if(n<1)throw new Error("Equations without an arrow are not supported.");if(n>1)throw new Error(`Equation must contain exactly one arrow ("${vm}").`);const[s,r]=e.split(vm);ie(-1===s.indexOf(Nm),(()=>`The ellipsis notation ("${Nm}") is not supported yet.`));const a=s.split(Im),i=a.length;if(t!==i)throw new Error(`Expected ${i} input tensors, received ${t}`);if(i>2)throw new Error("Support for more than 2 input tensors is not implemented yet.");const o=[];for(let e=0;e<r.length;++e){const t=r[e];if(!a.some((e=>-1!==e.indexOf(t))))throw new Error(`Output subscripts contain the label ${t} not present in the input subscripts.`);-1===o.indexOf(t)&&o.push(t)}for(let e=0;e<s.length;++e){const t=s[e];-1===o.indexOf(t)&&t!==Im&&o.push(t)}const l=new Array(a.length);for(let e=0;e<i;++e){if(new Set(a[e].split("")).size!==a[e].length)throw new Error(`Found duplicate axes in input component ${a[e]}. Support for duplicate axes in input is not implemented yet.`);l[e]=[];for(let t=0;t<a[e].length;++t)l[e].push(o.indexOf(a[e][t]))}const u=o.length,c=[];for(let e=r.length;e<u;++e)c.push(e);return{allDims:o,summedDims:c,idDims:l}}function Tm(e,t){let n=new Array(e);n.fill(-1);for(let e=0;e<t.length;++e)n[t[e]]=e;const s=[];for(let t=0;t<e;++t)-1===n[t]&&s.push(t);return n=n.filter((e=>-1!==e)),{permutationIndices:n,expandDims:s}}function Cm(e,t,n){const s=new Array(e);for(let e=0;e<n.length;++e){const r=n[e].shape;for(let n=0;n<t[e].length;++n)void 0===s[t[e][n]]?s[t[e][n]]=r[n]:ie(s[t[e][n]]===r[n],(()=>`Expected dimension ${s[t[e][n]]} at axis ${n} of input shaped ${JSON.stringify(r)}, but got dimension ${r[n]}`))}}function $m(e,t){const n=e,s=[];let r=0;0===e.length&&n.push(-1),r=e.length+1;for(let e=0;e<r;++e)s.push([]);const a=[];for(let e=0;e<n.length;++e){const r=Am(t,n[e]);for(const t of r)-1===a.indexOf(t)&&(s[e].push(t),a.push(t))}return{path:n,steps:s}}function Em(e){return e.every(((e,t)=>e===t))}function Am(e,t){const n=[];for(let s=0;s<e.length;++s)0!==e[s].length&&-1===e[s].indexOf(t)&&-1!==t||n.push(s);return n}function Rm(e,t,n=0){let s=[];if("number"==typeof t)ie(e.shape[n]%t==0,(()=>"Number of splits must evenly divide the axis.")),s=new Array(t).fill(e.shape[n]/t);else{const r=t.reduce(((e,t)=>(-1===t&&(e+=1),e)),0);ie(r<=1,(()=>"There should be only one negative value in split array."));const a=t.indexOf(-1);if(-1!==a){const s=t.reduce(((e,t)=>t>0?e+t:e));t[a]=e.shape[n]-s}ie(e.shape[n]===t.reduce(((e,t)=>e+t)),(()=>"The sum of sizes must match the size of the axis dimension.")),s=t}return s}function Fm(e){return`Received SparseTensor with denseShape[0] = 0 but\n  indices.shape[0] = ${e}`}function _m(e,t){return`indices(${e}, 0) is invalid: ${t} < 0`}function Dm(e,t,n){return`indices(${e}, 0) is invalid: ${t} >= ${n}`}function Om(e,t){return`only one output dimension may be -1, not both ${e} and ${t}`}function Mm(e,t){return`size ${e} must be non-negative, not ${t}`}function Lm(){return"reshape cannot infer the missing input size for an empty tensor unless all specified input sizes are non-zero"}function zm(e,t){return`Input to reshape is a SparseTensor with ${ue(e)}\n  dense values, but the requested shape requires a multiple of ${ue(t)}. inputShape=${e} outputShape= ${t}`}function Pm(e,t){return`Input to reshape is a tensor with ${ue(e)} dense values, but the requested shape has ${ue(t)}. inputShape=${e} outputShape=${t}`}function Bm(){return"segment ids must be >= 0"}function Wm(){return"segment ids are not increasing"}function Vm(e,t){return`Segment id ${e} out of range [0, ${t}), possibly because segmentIds input is not sorted.`}function Um(e,t,n){return`Bad: indices[${e}] == ${t} out of range [0, ${n})`}function Gm(e,t){let n,s=!1;for(e<=Zf?(n=e,s=!0):n=De(e,Math.floor(Math.sqrt(e)));!s;)n>t||n===e?s=!0:n=De(e,n+1);return n}function Hm(e,t,n){const s=[],r=e.length;for(let a=0;a<r;a++)a!==t?s.push(e[a]):s.push(n);return s}function jm(e,t,n,s){const r=t.shape.length,a=e.shape.length;if(0!==s&&(s<-r||s>r))throw new Error(`Expect batchDims in the range of [-${r}, ${r}], but got ${s}`);if(s<0&&(s+=r),s>a)throw new Error(`batchDims (${s}) must be less than rank(x) (\n    ${a}).`);if(n<s)throw new Error(`batchDims (${s}) must be less than or equal to axis (${n}).`);for(let n=0;n<s;++n)if(e.shape[n]!==t.shape[n])throw new Error(`x.shape[${n}]: ${e.shape[n]} should be equal to indices.shape[${n}]: ${t.shape[n]}.`);const i=e.shape[n],o=[];let l=1,u=1,c=1;for(let t=0;t<s;++t)o.push(e.shape[t]),l*=e.shape[t];for(let t=s;t<n;t++)o.push(e.shape[t]),u*=e.shape[t];for(let e=s;e<r;e++)o.push(t.shape[e]);for(let t=n+1;t<a;t++)o.push(e.shape[t]),c*=e.shape[t];return{batchSize:l,sliceSize:c,outerSize:u,dimSize:i,outputShape:o}}function qm(e){try{return e.map((e=>Jr(e)))}catch(e){throw new Error(`Failed to decode encoded string bytes into utf-8, error: ${e}`)}}function Km(e){return e.map((e=>Zr(e)))}!function(){for(const e of ol)Go(e)}();const Xm={kernelName:et,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(e,ed(no(n,"float32"),-1))}}},Ym={kernelName:tt,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>{const t=Fo(no(n,"float32")),s=Ro(Yo(Wo(1),t));return Rl(Eo(e,s))}}}},Zm={kernelName:nt,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>{const t=Ro(Yo(Fo(no(n,"float32")),1));return Eo(e,t)}}}},Jm={kernelName:st,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=tl(n.shape,s.shape);return{a:()=>{let t=e;const s=el(n.shape,r);return s.length>0&&(t=ih(t,s)),sc(t,n.shape)},b:()=>{let t=e;const n=el(s.shape,r);return n.length>0&&(t=ih(t,n)),sc(t,s.shape)}}}},Qm={kernelName:rt,saveAllInputs:!0,gradFunc:(e,t)=>{const n={};return t.forEach(((t,s)=>{n[s]=()=>e.clone()})),n}},eg={kernelName:ot,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>_o(n)}}},tg={kernelName:lt,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>_o(n)}}},ng={kernelName:ut,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,Ro(Yo(Wo(1),Fo(no(n,"float32")))))}}},sg={kernelName:ct,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>{const t=Ro(Co(Wo(1),Fo(no(n,"float32"))));return Eo(e,t)}}}},rg={kernelName:dt,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=tl(n.shape,s.shape);return{a:()=>{const t=Co(Fo(n),Fo(s));let a=Ao(e,Eo(s,t));const i=el(n.shape,r);return i.length>0&&(a=ih(a,i)),sc(a,n.shape)},b:()=>{const t=Co(Fo(n),Fo(s));let a=Rl(Ao(e,Eo(n,t)));const i=el(s.shape,r);return i.length>0&&(a=ih(a,i)),sc(a,s.shape)}}}},ag={kernelName:ht,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,Co(Fo(no(n,"float32")),1))}}},ig={kernelName:pt,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,Yo(Wo(1),Fo(no(n,"float32"))))}}};const og=Za({avgPool3dGrad_:function(e,t,n,s,r,a){const i=Ka(e,"dy","avgPool3dGrad"),o=Ka(t,"input","avgPool3dGrad");let l=i,u=o,c=!1;4===o.rank&&(c=!0,l=sc(i,[1,i.shape[0],i.shape[1],i.shape[2],i.shape[3]]),u=sc(o,[1,o.shape[0],o.shape[1],o.shape[2],o.shape[3]])),ie(5===l.rank,(()=>`Error in avgPool3dGrad: dy must be rank 5 but got rank ${l.rank}.`)),ie(5===u.rank,(()=>`Error in avgPool3dGrad: input must be rank 5 but got rank ${u.rank}.`)),nc("avgPool3dGrad",r,a);const h={dy:l,input:u},p={filterSize:n,strides:s,pad:r,dimRoundingMode:a},d=za.runKernel(yt,h,p);return c?sc(d,[d.shape[1],d.shape[2],d.shape[3],d.shape[4]]):d}}),lg={kernelName:gt,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{filterSize:r,strides:a,pad:i,dimRoundingMode:o}=n;return{x:()=>og(e,s,r,a,i,o)}}};const ug=Za({avgPoolGrad_:function(e,t,n,s,r){const a=Ka(e,"dy","avgPoolGrad"),i=Ka(t,"input","avgPoolGrad");ie(i.rank===a.rank,(()=>`Rank of input (${i.rank}) does not match rank of dy (${a.rank})`));let o=i,l=a,u=!1;3===i.rank&&(u=!0,o=sc(i,[1,i.shape[0],i.shape[1],i.shape[2]]),l=sc(a,[1,a.shape[0],a.shape[1],a.shape[2]])),ie(4===l.rank,(()=>`Error in avgPoolGrad: dy must be rank 4 but got rank ${l.rank}.`)),ie(4===o.rank,(()=>`Error in avgPoolGrad: input must be rank 4 but got rank ${o.rank}.`));const c={dy:l,input:o},h={filterSize:n,strides:s,pad:r},p=za.runKernel(mt,c,h);return u?sc(p,[p.shape[1],p.shape[2],p.shape[3]]):p}}),cg={kernelName:ft,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{filterSize:r,strides:a,pad:i}=n;return{x:()=>ug(e,s,r,a,i)}}},hg={kernelName:bt,inputsToSave:["a","b"],gradFunc:(e,t,n)=>{const[s,r]=t,{transposeA:a,transposeB:i}=n;return a||i?!a&&i?{a:()=>$l(e,r,!1,!1),b:()=>$l(e,s,!0,!1)}:a&&!i?{a:()=>$l(r,e,!1,!0),b:()=>$l(s,e,!1,!1)}:{a:()=>$l(r,e,!0,!0),b:()=>$l(e,s,!0,!0)}:{a:()=>$l(e,r,!1,!0),b:()=>$l(s,e,!0,!1)}}},pg={kernelName:xt,gradFunc:(e,t,n)=>{const{blockShape:s,crops:r}=n;return{x:()=>op(e,s,r)}}},dg={kernelName:kt,gradFunc:(e,t,n)=>{const s=n,r=s.inputShape,a=s.shape,i=Array.from(a);for(let e=r.length-1;e>=0;e--)if(r[e]===a[e])i[e]=1;else if(1!==r[e])throw new Error(`broadcastTo(): [${r}] cannot be broadcast to [${a}].`);const o=[];for(let e=0;e<i.length;e++)i[e]>1&&o.push(e);return{x:()=>ih(e,o,!0)}}},fg={kernelName:Nt,gradFunc:e=>({x:()=>e.clone()})},mg={kernelName:St,gradFunc:e=>({x:()=>_o(e)})},gg={kernelName:Tt,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{clipValueMin:r,clipValueMax:a}=n;return{x:()=>Uc(_h(bh(s,r),Nh(s,a)),e,_o(e))}}},yg={kernelName:$t,inputsToSave:["x"],gradFunc:Xm.gradFunc},bg={kernelName:Et,saveAllInputs:!0,gradFunc:(e,t,n)=>{const s=t.map((e=>e.shape)),{axis:r}=n,a=we(r,t[0].shape)[0],i=s.map((e=>e[a]));return Xp(e,i,a).map((e=>()=>e))}},xg={kernelName:At,inputsToSave:["x","filter"],gradFunc:(e,t,n)=>{const[s,r]=t,{dilations:a,strides:i,pad:o,dataFormat:l}=n;return ie(Ju(a),(()=>`Error in gradient of conv2D: dilation rates greater than 1 are not yet supported in gradients. Got dilations '${a}'`)),{x:()=>$c(s.shape,e,r,i,o,l),filter:()=>Cd(s,e,r.shape,i,o,l)}}},wg={kernelName:Ft,inputsToSave:["dy","filter"],gradFunc:(e,t,n)=>{const[s,r]=t,{strides:a,pad:i,dataFormat:o,dimRoundingMode:l}=n;return{dy:()=>Tc(e,r,a,i,o,1,l),filter:()=>Cd(e,s,r.shape,a,i,o,l)}}};const vg=Za({conv3DBackpropFilter_:function(e,t,n,s,r){let a=e;4===e.rank&&(a=sc(e,[1,e.shape[0],e.shape[1],e.shape[2],e.shape[3]]));let i=t;4===i.rank&&(i=sc(t,[1,t.shape[0],t.shape[1],t.shape[2],t.shape[3]])),ie(5===a.rank,(()=>`Error in conv3dDerFilter: input must be rank 5, but got shape ${a.shape}.`)),ie(5===i.rank,(()=>`Error in conv3dDerFilter: dy must be rank 5, but got shape ${i.shape}.`)),ie(5===n.length,(()=>`Error in conv3dDerFilter: filterShape must be length 5, but got ${n}.`)),ie(a.shape[4]===n[3],(()=>`Error in conv3dDerFilter: depth of input ${a.shape[4]}) must match input depth in filter (${n[3]}.`)),ie(i.shape[4]===n[4],(()=>`Error in conv3dDerFilter: depth of dy (${i.shape[4]}) must match output depth for filter (${n[4]}).`));const o={x:a,dy:i},l={strides:s,pad:r,filterShape:n};return za.runKernel(Dt,o,l)}}),kg={kernelName:_t,inputsToSave:["x","filter"],gradFunc:(e,t,n)=>{const{dilations:s,strides:r,pad:a}=n;ie(Ju(s),(()=>`Error in gradient of conv3D: dilation rates greater than 1 are not yet supported in gradients. Got dilations '${s}'`));const[i,o]=t;return{x:()=>Rc(i.shape,e,o,r,a),filter:()=>vg(i,e,o.shape,r,a)}}},Ig={kernelName:Mt,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(Rl(Pp(no(n,"float32"))),e)}}},Ng={kernelName:Lt,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(Bp(no(n,"float32")),e)}}},Sg={kernelName:Pt,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{axis:r,exclusive:a,reverse:i}=n;return{x:()=>{const t=th([r],s.rank);let n=Mc(e,r,a,!i);return null!=t&&(n=_l(n,t)),n}}}},Tg={kernelName:Ut,inputsToSave:["x","filter"],gradFunc:(e,t,n)=>{const{dilations:s,strides:r,pad:a,dimRoundingMode:i}=n,o=null==s?[1,1]:s;ie(Ju(o),(()=>`Error in gradient of depthwiseConv2dNative: dilation rates greater than 1 are not yet supported. Got dilations '${o}'`));const[l,u]=t;return ie(4===l.rank,(()=>`Error in gradient of depthwiseConv2dNative: input must be rank 4, but got rank ${l.rank}.`)),ie(4===u.rank,(()=>`Error in gradient of depthwiseConv2dNative: filter must be rank 4, but got rank ${u.rank}.`)),ie(l.shape[3]===u.shape[2],(()=>`Error in gradient of depthwiseConv2d: number of input channels (${l.shape[3]}) must match the inChannels dimension in filter ${u.shape[2]}.`)),ie(Qu(r,o),(()=>`Error in gradient of depthwiseConv2d: Either strides or dilations must be  1. Got strides ${r} and dilations '${o}'.`)),nc("depthwiseConv2d",a,i),{x:()=>Dd(l.shape,e,u,r,a,o,i),filter:()=>_d(l,e,u.shape,r,a,o,i)}}},Cg={kernelName:qt,inputsToSave:["x","filter"],gradFunc:(e,t,n)=>{const[s,r]=t,a={x:s,filter:r,dy:e},i={x:s,filter:r,dy:e};return{x:()=>za.runKernel(Kt,a,n),filter:()=>za.runKernel(Xt,i,n)}}},$g={kernelName:Qt,outputsToSave:[!0],gradFunc:(e,t)=>{const[n]=t,s={dy:e,y:n};return{x:()=>za.runKernel(en,s)}}},Eg={kernelName:tn,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t,s=Ao(ch(Rl(Fo(n))),2/Math.sqrt(Math.PI));return{x:()=>Ao(e,s)}}},Ag={kernelName:sn,outputsToSave:[!0],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(e,n)}}},Rg={kernelName:rn,inputsToSave:["input"],gradFunc:(e,t)=>{const[n]=t;return{input:()=>sc(e,n.shape)}}},Fg={kernelName:an,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(e,ch(n))}}},_g={kernelName:cn,gradFunc:e=>({x:()=>_o(e)})},Dg={kernelName:hn,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=tl(n.shape,s.shape);return{a:()=>{const t=Eo(e,no(s,"float32")),a=el(n.shape,r);return a.length>0?sc(ih(t,a),n.shape):t},b:()=>{let t=Ao(e,no(n,"float32"));const a=el(s.shape,r);a.length>0&&(t=sc(ih(t,a),s.shape));const i=Fo(s);return Rl(Eo(t,no(i,"float32")))}}}},Og={kernelName:pn,inputsToSave:["x","mean","variance","scale"],gradFunc:(e,t,n)=>{const{varianceEpsilon:s}=n,[r,a,i,o]=t,l=null==o?Wo(1):o,u=el(a.shape,r.shape),c=[];if(1===a.rank){for(let e=0;e<r.shape.length-1;++e)c.push(r.shape[e]);c.push(1)}const h=Yo(r,a),p=Ao(e,l),d=Dp(Co(i,Wo(s))),f=Ao(Ao(Ao(d,d),d),Wo(-.5));return{x:()=>1===a.rank?sc(Ao(Ao(e,dh(sc(d,[1,1,1,a.shape[0]]),c)),l),r.shape):sc(Ao(Ao(e,d),l),r.shape),mean:()=>{let e=Ao(Ao(d,Wo(-1)),p);return 1===a.rank&&(e=ih(e,u)),sc(e,a.shape)},variance:()=>{let e=Ao(Ao(f,h),p);return 1===a.rank&&(e=ih(e,u)),sc(e,a.shape)},scale:()=>{const t=Ao(h,d);let n=Ao(e,t);return 1===a.rank&&(n=ih(n,u)),sc(n,a.shape)},offset:()=>{let t=e;return 1===a.rank&&(t=ih(t,u)),sc(t,a.shape)}}}},Mg={kernelName:dn,inputsToSave:["x","indices"],gradFunc:(e,t,n)=>{const[s,r]=t,{axis:a}=n,i=we(a,s.shape)[0];return{x:()=>{const t=s.shape,n=r.size,o=t.slice(0,i),l=o.length,u=t.slice(a,t.length).slice(1),c=u.length,h=Lg(0,l),p=Lg(l+1,l+1+c),d=zg([o,[n],u]),f=sc(e,d),m=sc(r,[n]),g=zg([[l],h,p]),y=_l(f,g);let b=pd(y,m,s.shape[i]);const x=nh(g);return b=_l(b,x),b},indices:()=>r}}};function Lg(e,t){const n=[];for(let s=e;s<t;++s)n.push(s);return n}function zg(e){const t=[];for(let n=0;n<e.length;++n)for(let s=0;s<e[n].length;++s)t.push(e[n][s]);return t}const Pg={kernelName:gn,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t;return{a:()=>_o(n),b:()=>_o(s)}}},Bg={kernelName:yn,gradFunc:e=>({x:()=>no(e,"float32")})},Wg={kernelName:wn,gradFunc:e=>({x:()=>_o(e)})},Vg={kernelName:vn,gradFunc:e=>({x:()=>_o(e)})},Ug={kernelName:kn,gradFunc:e=>({x:()=>_o(e)})},Gg={kernelName:In,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{alpha:r}=n,a=yh(s,0);return{x:()=>Uc(a,e,Ao(e,r))}}},Hg={kernelName:$n,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,Co(n,1))}}},jg={kernelName:Cn,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,no(n,"float32"))}}},qg={kernelName:_n,inputsToSave:[],outputsToSave:[!0],gradFunc:(e,t,n)=>{const[s]=t,{axis:r}=n;return{logits:()=>{const t=ch(s);return Yo(e,Ao(ih(e,r,!0),t))}}}};const Kg=Za({localResponseNormalizationBackprop_:function(e,t,n,s=5,r=1,a=1,i=.5){const o={x:e,y:t,dy:n},l={depthRadius:s,bias:r,alpha:a,beta:i};return za.runKernel(Mn,o,l)}}),Xg={kernelName:On,inputsToSave:["x"],outputsToSave:[!0],gradFunc:(e,t,n)=>{const[s,r]=t,{depthRadius:a,bias:i,alpha:o,beta:l}=n;return{x:()=>Kg(s,r,e,a,i,o,l)}}};function Yg(e,t,n,s){return t.rank<n.rank&&(t=sc(t,Qc(t.shape,s))),e.rank<n.rank&&(e=sc(e,Qc(e.shape,s))),{x:()=>Ao(e,no(Vc(n,t),e.dtype))}}const Zg={kernelName:zn,inputsToSave:["x"],outputsToSave:[!0],gradFunc:(e,t,n)=>{const s=n,{reductionIndices:r}=s,a=t[0],i=Yg(e,t[1],a,we(r,a.shape));return{x:()=>i.x()}}},Jg={kernelName:Pn,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t;return{a:()=>Ao(e,no(bh(n,s),"float32")),b:()=>Ao(e,no(Ih(n,s),"float32"))}}};const Qg=Za({maxPool3dGrad_:function(e,t,n,s,r,a,i){const o=Ka(e,"dy","maxPool3dGrad"),l=Ka(t,"input","maxPool3dGrad"),u=Ka(n,"output","maxPool3dGrad");let c=o,h=l,p=u,d=!1;4===l.rank&&(d=!0,c=sc(o,[1,o.shape[0],o.shape[1],o.shape[2],o.shape[3]]),h=sc(l,[1,l.shape[0],l.shape[1],l.shape[2],l.shape[3]]),p=sc(u,[1,u.shape[0],u.shape[1],u.shape[2],u.shape[3]])),ie(5===c.rank,(()=>`Error in maxPool3dGrad: dy must be rank 5 but got rank ${c.rank}.`)),ie(5===h.rank,(()=>`Error in maxPool3dGrad: input must be rank 5 but got rank ${h.rank}.`)),ie(5===p.rank,(()=>`Error in maxPool3dGrad: output must be rank 5 but got rank ${p.rank}.`)),nc("maxPool3dGrad",a,i);const f={dy:c,input:h,output:p},m={filterSize:s,strides:r,pad:a,dimRoundingMode:i},g=za.runKernel(Un,f,m);return d?sc(g,[g.shape[1],g.shape[2],g.shape[3],g.shape[4]]):g}}),ey={kernelName:Vn,inputsToSave:["x"],outputsToSave:[!0],gradFunc:(e,t,n)=>{const[s,r]=t,{filterSize:a,strides:i,pad:o,dimRoundingMode:l}=n;return{x:()=>Qg(e,s,r,a,i,o,l)}}};const ty=Za({maxPoolGrad_:function(e,t,n,s,r,a,i){const o=Ka(e,"dy","maxPoolGrad"),l=Ka(t,"input","maxPoolGrad"),u=Ka(n,"output","maxPoolGrad");ie(l.rank===o.rank,(()=>`Rank of input (${l.rank}) does not match rank of dy (${o.rank})`)),ie(4===o.rank,(()=>`Error in maxPoolGrad: dy must be rank 4 but got rank ${o.rank}.`)),ie(4===l.rank,(()=>`Error in maxPoolGrad: input must be rank 4 but got rank ${l.rank}.`)),nc("maxPoolGrad",a,i);const c={dy:o,input:l,output:u},h={filterSize:s,strides:r,pad:a,dimRoundingMode:i};return za.runKernel(Wn,c,h)}}),ny={kernelName:Bn,inputsToSave:["x"],outputsToSave:[!0],gradFunc:(e,t,n)=>{const[s,r]=t,{filterSize:a,strides:i,pad:o}=n;return{x:()=>ty(e,s,r,a,i,o)}}},sy={kernelName:Kn,inputsToSave:["x"],gradFunc:(e,t,n)=>{const s=t[0],{paddings:r}=n,a=r.map((e=>e[0]));return{x:()=>lc(e,a,s.shape)}}},ry={kernelName:is,inputsToSave:["x"],gradFunc:(e,t,n)=>{const s=t[0],{paddings:r}=n,a=r.map((e=>e[0]));return{x:()=>lc(e,a,s.shape)}}},ay={kernelName:ls,inputsToSave:["a","b"],outputsToSave:[!0],gradFunc:(e,t)=>{const[n,s,r]=t,a=n,i=s,o=tl(a.shape,i.shape);return{a:()=>{const t=no(i,"float32");let n=Ao(e,Ao(t,Xo(a,Yo(t,Wo(1)))));const s=el(a.shape,o);return s.length>0&&(n=ih(n,s)),sc(n,a.shape)},b:()=>{const t=yh(a,0),n=Uc(t,Ch(a),_o(a));let s=Ao(e,Ao(r,n));const l=el(i.shape,o);return l.length>0&&(s=ih(s,l)),sc(s,i.shape)}}}};function iy(e,t,n){const s=e.shape.length,r=s-n.length,a=th(n,s);let i=e;null!=a&&(i=_l(e,a));const o=i.shape.slice(),l=o.splice(s-n.length,n.length).reduce(((e,t)=>e*t),1);o.push(l);let u=function(e,t,n){const s=e.shape.slice();s[n]=1;const r=sc(t,s),a=Oc(e,n,!0,!1),i=Oc(e,n,!0,!0),o=Ao(a,i);return Ao(r,o)}(i.reshape(o),t,r);if(u=u.reshape(i.shape),null!=a){const e=nh(a);u=_l(u,e)}return u}const oy={kernelName:Rs,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>{const t=yh(n,Wo(0)),s=Wo(am),r=Wo(im),a=Ao(e,r),i=Ao(Ao(e,s),ch(no(n,"float32")));return Uc(t,a,i)}}}},ly={kernelName:Bs,gradFunc:(e,t,n)=>{const{blockShape:s,paddings:r}=n;return{x:()=>hc(e,s,r)}}},uy={kernelName:Ws,gradFunc:(e,t,n)=>{const{axis:s}=n;return{x:()=>ic(e,s)}}};const cy=[Xm,Ym,Zm,Jm,Qm,eg,tg,ng,sg,rg,ag,ig,lg,cg,hg,pg,dg,fg,mg,gg,yg,bg,wg,xg,kg,Ig,Ng,Sg,Tg,Cg,{kernelName:Zt,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=tl(n.shape,s.shape);return{a:()=>{const t=Eo(e,no(s,"float32")),a=el(n.shape,r);return a.length>0?sc(ih(t,a),n.shape):t},b:()=>{let t=Ao(e,no(n,"float32"));const a=el(s.shape,r);a.length>0&&(t=sc(ih(t,a),s.shape));const i=Fo(s);return Rl(Eo(t,no(i,"float32")))}}}},$g,Eg,Ag,Rg,Fg,Dg,_g,Og,Mg,Pg,Bg,Wg,Vg,Ug,Gg,Hg,jg,qg,Xg,Zg,Zg,Jg,ey,ny,{kernelName:Hn,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{axis:r}=n,a=we(r,s.shape),i=ue(Jc(s.shape,a)[1]);return{x:()=>{const t=s.shape.slice();a.forEach((e=>{t[e]=1}));const n=sc(e,t);return Eo(Ao(n,Hh(s.shape,"float32")),i)}}}},{kernelName:jn,inputsToSave:["x"],outputsToSave:[!0],gradFunc:(e,t,n)=>{const s=n,{axis:r}=s,[a,i]=t,o=Yg(e,i,a,we(r,a.shape));return{x:()=>o.x()}}},{kernelName:qn,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t;return{a:()=>Ao(e,no(Nh(n,s),"float32")),b:()=>Ao(e,no(yh(n,s),"float32"))}}},sy,{kernelName:Xn,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=tl(n.shape,s.shape);return{a:()=>{const t=el(n.shape,r);return t.length>0?sc(ih(e,t),n.shape):e},b:()=>{const t=Ao(e,Rl(mh(Eo(n,s)))),a=el(s.shape,r);return a.length>0?sc(ih(t,a),s.shape):t}}}},{kernelName:Zn,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=tl(n.shape,s.shape);return{a:()=>{const t=Ao(e,no(s,"float32")),a=el(n.shape,r);return a.length>0?sc(ih(t,a),n.shape):t},b:()=>{const t=Ao(e,no(n,"float32")),a=el(s.shape,r);return a.length>0?sc(ih(t,a),s.shape):t}}}},{kernelName:Jn,gradFunc:e=>({x:()=>Rl(e)})},{kernelName:rs,inputsToSave:["indices"],gradFunc:(e,t)=>{const n=t[0];return{indices:()=>Gh(n.shape,"float32")}}},{kernelName:ss,gradFunc:e=>({x:()=>_o(e)})},{kernelName:as,saveAllInputs:!0,gradFunc:(e,t,n)=>{const{axis:s}=n;return dd(e,s).map((e=>()=>e))}},ry,ry,ay,{kernelName:us,inputsToSave:["x","alpha"],gradFunc:(e,t)=>{const[n,s]=t,r=yh(n,0);return{x:()=>Uc(r,e,Ao(e,s)),alpha:()=>{let t=Uc(r,_o(e),Ao(e,n));const a=el(s.shape,e.shape);return a.length>0&&(t=ih(t,a)),sc(t,s.shape)}}}},{kernelName:cs,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{axis:r}=n;let a=[];return a=null==r?s.shape.map(((e,t)=>t)):"number"==typeof r?[r]:r,{x:()=>iy(s,e,a)}}},{kernelName:gs,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,Rl(Fo(n)))}}},{kernelName:Is,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t,s=Ao(Nh(n,6),ed(n));return{x:()=>Ao(e,no(s,"float32"))}}},{kernelName:ys,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(e,no(ed(n),"float32"))}}},{kernelName:bs,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>sc(e,n.shape)}}},{kernelName:vs,inputsToSave:["images"],gradFunc:(e,t,n)=>{const[s]=t,r={dy:e,images:s};return{images:()=>za.runKernel(ks,r,n)}}},{kernelName:xs,inputsToSave:["images"],gradFunc:(e,t,n)=>{const[s]=t,r={dy:e,images:s};return{images:()=>za.runKernel(ws,r,n)}}},{kernelName:Ns,gradFunc:(e,t,n)=>{const{dims:s}=n,r=we(s,e.shape);return{x:()=>$p(e,r)}}},{kernelName:Ss,gradFunc:e=>({x:()=>_o(e)})},{kernelName:Ts,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Rl(Eo(e,Ao(Xo(n,1.5),2)))}}},{kernelName:As,inputsToSave:["condition"],gradFunc:(e,t)=>{const[n]=t;return{condition:()=>no(_o(n),"float32"),t:()=>Ao(e,no(n,e.dtype)),e:()=>Ao(e,no(Dh(n),e.dtype))}}},oy,{kernelName:Ms,outputsToSave:[!0],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(e,Ao(n,Yo(Wo(1),n)))}}},{kernelName:Os,gradFunc:e=>({x:()=>_o(e)})},{kernelName:_s,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(_c(no(n,"float32")),e)}}},{kernelName:Ds,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(Dc(no(n,"float32")),e)}}},{kernelName:Fs,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{begin:r,size:a}=n,i=s.shape,[o,l]=hu(s,r,a),u=[];for(let t=0;t<e.rank;t++)u.push([o[t],i[t]-o[t]-l[t]]);return{x:()=>np(e,u)}}},{kernelName:Vs,outputsToSave:[!0],gradFunc:(e,t,n)=>{const[s]=t,{dim:r}=n,a=Ao(e,s);return{logits:()=>Yo(a,Ao(ih(a,[r],true),s))}}},{kernelName:Ls,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(e,oc(n))}}},ly,ly,uy,uy,{kernelName:zs,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,Ao(Ro(no(n,"float32")),2))}}},{kernelName:Ks,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=Wo(2);return{a:()=>Ao(e,Ao(r,Yo(n,s))),b:()=>Ao(e,Ao(r,Yo(s,n)))}}},{kernelName:Xs,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(e,Ao(no(n,"float32"),2))}}},{kernelName:dr,gradFunc:e=>({x:()=>_o(e)})},{kernelName:tr,inputsToSave:["a","b"],gradFunc:(e,t)=>{const[n,s]=t,r=tl(n.shape,s.shape);return{a:()=>{let t=e;const s=el(n.shape,r);return s.length>0&&(t=ih(t,s)),sc(t,n.shape)},b:()=>{let t=e;const n=el(s.shape,r);return n.length>0&&(t=ih(t,n)),sc(Rl(t),s.shape)}}}},{kernelName:Ps,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,r=s.shape.slice(),{axis:a}=n;we(a,s.shape).forEach((e=>{r[e]=1}));const i=sc(e,r),o=Ao(i,Hh(s.shape,"float32"));return{x:()=>o}}},{kernelName:nr,inputsToSave:["x"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Eo(e,Fo(_c(n)))}}},{kernelName:sr,outputsToSave:[!0],gradFunc:(e,t)=>{const[n]=t;return{x:()=>Ao(Yo(Wo(1),Fo(n)),e)}}},{kernelName:rr,inputsToSave:["x"],gradFunc:(e,t,n)=>{const[s]=t,{reps:r}=n;return{x:()=>{let t=_o(s);if(1===s.rank)for(let n=0;n<r[0];++n)t=Co(t,lc(e,[n*s.shape[0]],[s.shape[0]]));else if(2===s.rank)for(let n=0;n<r[0];++n)for(let a=0;a<r[1];++a)t=Co(t,lc(e,[n*s.shape[0],a*s.shape[1]],[s.shape[0],s.shape[1]]));else if(3===s.rank)for(let n=0;n<r[0];++n)for(let a=0;a<r[1];++a)for(let i=0;i<r[2];++i)t=Co(t,lc(e,[n*s.shape[0],a*s.shape[1],i*s.shape[2]],[s.shape[0],s.shape[1],s.shape[2]]));else{if(4!==s.rank)throw new Error(`Gradient for tile operation is not implemented for rank-${s.rank} tensors yet.`);for(let n=0;n<r[0];++n)for(let a=0;a<r[1];++a)for(let i=0;i<r[2];++i)for(let o=0;o<r[3];++o)t=Co(t,lc(e,[n*s.shape[0],a*s.shape[1],i*s.shape[2],o*s.shape[3]],[s.shape[0],s.shape[1],s.shape[2],s.shape[3]]))}return t}}}},{kernelName:or,gradFunc:(e,t,n)=>{const s=n,{perm:r}=s,a=nh(r);return{x:()=>_l(e,a)}}},{kernelName:ur,gradFunc:(e,t,n)=>{const s=n,{axis:r}=s;return{value:()=>Qp(e,r)}}},{kernelName:cr,inputsToSave:["segmentIds"],gradFunc:(e,t)=>{const[n]=t;return{x:()=>function(e,t){const n=nl(t,_o(t)),s=gh(e,n);let r=bh(t,Wo(0,"int32"));const a=s.rank-r.rank;for(let e=0;e<a;++e)r=hh(r,e+1);r=_h(r,Hh(s.shape,"bool"));const i=_o(s);return Uc(r,s,i)}(e,n)}}},{kernelName:pr,gradFunc:e=>({x:()=>_o(e)})}];for(const e of cy)Cr(e);ya().prototype.abs=function(){return this.throwIfDisposed(),Jo(this)},ya().prototype.acos=function(){return this.throwIfDisposed(),Au(this)},ya().prototype.acosh=function(){return this.throwIfDisposed(),Ru(this)},ya().prototype.add=function(e){return this.throwIfDisposed(),Co(this,e)},ya().prototype.all=function(e,t){return this.throwIfDisposed(),_u(this,e,t)},ya().prototype.any=function(e,t){return this.throwIfDisposed(),Du(this,e,t)},ya().prototype.argMax=function(e){return this.throwIfDisposed(),Ou(this,e)},ya().prototype.argMin=function(e){return this.throwIfDisposed(),Mu(this,e)},ya().prototype.asScalar=function(){return this.throwIfDisposed(),ie(1===this.size,(()=>"The array must have only 1 element.")),sc(this,[])},ya().prototype.asType=function(e){return this.throwIfDisposed(),no(this,e)},ya().prototype.as1D=function(){return this.throwIfDisposed(),sc(this,[this.size])},ya().prototype.as2D=function(e,t){return this.throwIfDisposed(),sc(this,[e,t])},ya().prototype.as3D=function(e,t,n){return this.throwIfDisposed(),sc(this,[e,t,n])},ya().prototype.as4D=function(e,t,n,s){return this.throwIfDisposed(),sc(this,[e,t,n,s])},ya().prototype.as5D=function(e,t,n,s,r){return this.throwIfDisposed(),sc(this,[e,t,n,s,r])},ya().prototype.asin=function(){return this.throwIfDisposed(),Lu(this)},ya().prototype.asinh=function(){return this.throwIfDisposed(),zu(this)},ya().prototype.atan=function(){return this.throwIfDisposed(),Pu(this)},ya().prototype.atan2=function(e){return this.throwIfDisposed(),Bu(this,e)},ya().prototype.atanh=function(){return this.throwIfDisposed(),Wu(this)},ya().prototype.avgPool=function(e,t,n,s){return this.throwIfDisposed(),rc(this,e,t,n,s)},ya().prototype.batchToSpaceND=function(e,t){return this.throwIfDisposed(),hc(this,e,t)},ya().prototype.batchNorm=function(e,t,n,s,r){return this.throwIfDisposed(),pc(this,e,t,n,s,r)},ya().prototype.broadcastTo=function(e){return this.throwIfDisposed(),xc(this,e)},ya().prototype.cast=function(e){return this.throwIfDisposed(),no(this,e)},ya().prototype.ceil=function(){return this.throwIfDisposed(),wc(this)},ya().prototype.clipByValue=function(e,t){return this.throwIfDisposed(),vc(this,e,t)},ya().prototype.concat=function(e,t){return this.throwIfDisposed(),e instanceof ga&&(e=[e]),ic([this,...e],t)},ya().prototype.conv1d=function(e,t,n,s,r,a){return this.throwIfDisposed(),Cc(this,e,t,n,s,r,a)},ya().prototype.conv2dTranspose=function(e,t,n,s,r){return this.throwIfDisposed(),Ec(this,e,t,n,s,r)},ya().prototype.conv2d=function(e,t,n,s,r,a){return this.throwIfDisposed(),Tc(this,e,t,n,s,r,a)},ya().prototype.cos=function(){return this.throwIfDisposed(),_c(this)},ya().prototype.cosh=function(){return this.throwIfDisposed(),Dc(this)},ya().prototype.cumprod=function(e,t,n){return this.throwIfDisposed(),Oc(this,e,t,n)},ya().prototype.cumsum=function(e,t,n){return this.throwIfDisposed(),Mc(this,e,t,n)},ya().prototype.depthToSpace=function(e,t){return this.throwIfDisposed(),zc(this,e,t)},ya().prototype.depthwiseConv2d=function(e,t,n,s,r,a){return this.throwIfDisposed(),Pc(this,e,t,n,s,r,a)},ya().prototype.dilation2d=function(e,t,n,s,r){return this.throwIfDisposed(),Wc(this,e,t,n,s,r)},ya().prototype.divNoNan=function(e){return this.throwIfDisposed(),Gc(this,e)},ya().prototype.div=function(e){return this.throwIfDisposed(),Eo(this,e)},ya().prototype.dot=function(e){return this.throwIfDisposed(),Hc(this,e)},ya().prototype.elu=function(){return this.throwIfDisposed(),qc(this)},ya().prototype.equal=function(e){return this.throwIfDisposed(),Vc(this,e)},ya().prototype.erf=function(){return this.throwIfDisposed(),Xc(this)},ya().prototype.euclideanNorm=function(e,t){return this.throwIfDisposed(),uh(this,e,t)},ya().prototype.exp=function(){return this.throwIfDisposed(),ch(this)},ya().prototype.expandDims=function(e){return this.throwIfDisposed(),hh(this,e)},ya().prototype.expm1=function(){return this.throwIfDisposed(),ph(this)},ya().prototype.fft=function(){return this.throwIfDisposed(),jp(this)},ya().prototype.flatten=function(){return this.throwIfDisposed(),sc(this,[this.size])},ya().prototype.floor=function(){return this.throwIfDisposed(),mh(this)},ya().prototype.floorDiv=function(e){return this.throwIfDisposed(),$o(this,e)},ya().prototype.gather=function(e,t,n){return this.throwIfDisposed(),gh(this,e,t,n)},ya().prototype.greaterEqual=function(e){return this.throwIfDisposed(),bh(this,e)},ya().prototype.greater=function(e){return this.throwIfDisposed(),yh(this,e)},ya().prototype.ifft=function(){return this.throwIfDisposed(),qp(this)},ya().prototype.irfft=function(){return this.throwIfDisposed(),Kp(this)},ya().prototype.isFinite=function(){return this.throwIfDisposed(),xh(this)},ya().prototype.isInf=function(){return this.throwIfDisposed(),wh(this)},ya().prototype.isNaN=function(){return this.throwIfDisposed(),vh(this)},ya().prototype.leakyRelu=function(e){return this.throwIfDisposed(),kh(this,e)},ya().prototype.lessEqual=function(e){return this.throwIfDisposed(),Nh(this,e)},ya().prototype.less=function(e){return this.throwIfDisposed(),Ih(this,e)},ya().prototype.localResponseNormalization=function(e,t,n,s){return this.throwIfDisposed(),Th(this,e,t,n,s)},ya().prototype.logSigmoid=function(){return this.throwIfDisposed(),Ah(this)},ya().prototype.logSoftmax=function(e){return this.throwIfDisposed(),Rh(this,e)},ya().prototype.logSumExp=function(e,t){return this.throwIfDisposed(),Fh(this,e,t)},ya().prototype.log=function(){return this.throwIfDisposed(),Ch(this)},ya().prototype.log1p=function(){return this.throwIfDisposed(),$h(this)},ya().prototype.logicalAnd=function(e){return this.throwIfDisposed(),_h(this,e)},ya().prototype.logicalNot=function(){return this.throwIfDisposed(),Dh(this)},ya().prototype.logicalOr=function(e){return this.throwIfDisposed(),Oh(this,e)},ya().prototype.logicalXor=function(e){return this.throwIfDisposed(),Mh(this,e)},ya().prototype.matMul=function(e,t,n){return this.throwIfDisposed(),$l(this,e,t,n)},ya().prototype.maxPool=function(e,t,n,s){return this.throwIfDisposed(),Bh(this,e,t,n,s)},ya().prototype.max=function(e,t){return this.throwIfDisposed(),rh(this,e,t)},ya().prototype.maximum=function(e){return this.throwIfDisposed(),nl(this,e)},ya().prototype.mean=function(e,t){return this.throwIfDisposed(),Uh(this,e,t)},ya().prototype.min=function(e,t){return this.throwIfDisposed(),ah(this,e,t)},ya().prototype.minimum=function(e){return this.throwIfDisposed(),qh(this,e)},ya().prototype.mirrorPad=function(e,t){return this.throwIfDisposed(),Kh(this,e,t)},ya().prototype.mod=function(e){return this.throwIfDisposed(),Xh(this,e)},ya().prototype.mul=function(e){return this.throwIfDisposed(),Ao(this,e)},ya().prototype.neg=function(){return this.throwIfDisposed(),Rl(this)},ya().prototype.norm=function(e,t,n){return this.throwIfDisposed(),lh(this,e,t,n)},ya().prototype.notEqual=function(e){return this.throwIfDisposed(),Qh(this,e)},ya().prototype.oneHot=function(e,t=1,n=0){return this.throwIfDisposed(),El(this,e,t,n)},ya().prototype.onesLike=function(){return this.throwIfDisposed(),ep(this)},ya().prototype.pad=function(e,t){return this.throwIfDisposed(),np(this,e,t)},ya().prototype.pool=function(e,t,n,s,r,a){return this.throwIfDisposed(),lp(this,e,t,n,s,r,a)},ya().prototype.pow=function(e){return this.throwIfDisposed(),Xo(this,e)},ya().prototype.prelu=function(e){return this.throwIfDisposed(),up(this,e)},ya().prototype.prod=function(e,t){return this.throwIfDisposed(),cp(this,e,t)},ya().prototype.reciprocal=function(){return this.throwIfDisposed(),Sp(this)},ya().prototype.relu=function(){return this.throwIfDisposed(),Tp(this)},ya().prototype.relu6=function(){return this.throwIfDisposed(),Cp(this)},ya().prototype.reshapeAs=function(e){return this.throwIfDisposed(),sc(this,e.shape)},ya().prototype.reshape=function(e){return this.throwIfDisposed(),sc(this,e)},ya().prototype.resizeBilinear=function(e,t,n){return this.throwIfDisposed(),lf(this,e,t,n)},ya().prototype.resizeNearestNeighbor=function(e,t,n){return this.throwIfDisposed(),uf(this,e,t,n)},ya().prototype.reverse=function(e){return this.throwIfDisposed(),$p(this,e)},ya().prototype.rfft=function(){return this.throwIfDisposed(),Yp(this)},ya().prototype.round=function(){return this.throwIfDisposed(),_p(this)},ya().prototype.rsqrt=function(){return this.throwIfDisposed(),Dp(this)},ya().prototype.selu=function(){return this.throwIfDisposed(),Op(this)},ya().prototype.separableConv2d=function(e,t,n,s,r,a){return this.throwIfDisposed(),Mp(this,e,t,n,s,r,a)},ya().prototype.sigmoid=function(){return this.throwIfDisposed(),oc(this)},ya().prototype.sign=function(){return this.throwIfDisposed(),zp(this)},ya().prototype.sin=function(){return this.throwIfDisposed(),Pp(this)},ya().prototype.sinh=function(){return this.throwIfDisposed(),Bp(this)},ya().prototype.slice=function(e,t){return this.throwIfDisposed(),lc(this,e,t)},ya().prototype.softmax=function(e){return this.throwIfDisposed(),Hp(this,e)},ya().prototype.softplus=function(){return this.throwIfDisposed(),Eh(this)},ya().prototype.spaceToBatchND=function(e,t){return this.throwIfDisposed(),op(this,e,t)},ya().prototype.split=function(e,t){return this.throwIfDisposed(),Xp(this,e,t)},ya().prototype.sqrt=function(){return this.throwIfDisposed(),Ro(this)},ya().prototype.square=function(){return this.throwIfDisposed(),Fo(this)},ya().prototype.squaredDifference=function(e){return this.throwIfDisposed(),Zp(this,e)},ya().prototype.squeeze=function(e){return this.throwIfDisposed(),Jp(this,e)},ya().prototype.stack=function(e,t){this.throwIfDisposed();const n=e instanceof ga?[this,e]:[this,...e];return Qp(n,t)},ya().prototype.step=function(e){return this.throwIfDisposed(),ed(this,e)},ya().prototype.stridedSlice=function(e,t,n,s,r,a,i,o){return this.throwIfDisposed(),td(this,e,t,n,s,r,a,i,o)},ya().prototype.sub=function(e){return this.throwIfDisposed(),Yo(this,e)},ya().prototype.sum=function(e,t){return this.throwIfDisposed(),ih(this,e,t)},ya().prototype.tan=function(){return this.throwIfDisposed(),nd(this)},ya().prototype.tanh=function(){return this.throwIfDisposed(),uc(this)},ya().prototype.tile=function(e){return this.throwIfDisposed(),dh(this,e)},ya().prototype.toBool=function(){return this.throwIfDisposed(),no(this,"bool")},ya().prototype.toFloat=function(){return this.throwIfDisposed(),no(this,"float32")},ya().prototype.toInt=function(){return this.throwIfDisposed(),no(this,"int32")},ya().prototype.topk=function(e,t){return this.throwIfDisposed(),ud(this,e,t)},ya().prototype.transpose=function(e){return this.throwIfDisposed(),_l(this,e)},ya().prototype.unique=function(e){return this.throwIfDisposed(),hd(this,e)},ya().prototype.unsortedSegmentSum=function(e,t){return this.throwIfDisposed(),pd(this,e,t)},ya().prototype.unstack=function(e){return this.throwIfDisposed(),dd(this,e)},ya().prototype.where=function(e,t){return this.throwIfDisposed(),Uc(e,this,t)},ya().prototype.zerosLike=function(){return this.throwIfDisposed(),_o(this)};class hy extends Error{constructor(e){super(e),Object.setPrototypeOf(this,hy.prototype)}}class py extends Error{constructor(e){super(e),Object.setPrototypeOf(this,py.prototype)}}class dy extends Error{constructor(e){super(e),Object.setPrototypeOf(this,dy.prototype)}}class fy extends Error{constructor(e){super(e),Object.setPrototypeOf(this,fy.prototype)}}class my extends Error{constructor(e){super(e),Object.setPrototypeOf(this,my.prototype)}}class gy{constructor(e){this.maxEntries=e||100,this.cache=new Map}get(e){let t;return this.cache.has(e)&&(t=this.cache.get(e),this.cache.delete(e),this.cache.set(e,t)),t}put(e,t){if(this.cache.has(e))this.cache.delete(e);else if(this.cache.size>=this.maxEntries){const e=this.cache.keys().next().value;this.cache.delete(e)}this.cache.set(e,t)}getMaxEntries(){return this.maxEntries}setMaxEntries(e){if(e<0)throw new Error(`The maxEntries of LRU caches must be at least 0, but got ${e}.`);if(this.maxEntries>e)for(let t=0;t<this.maxEntries-e;t++){const e=this.cache.keys().next().value;this.cache.delete(e)}this.maxEntries=e}}function yy(e,t){if(Array.isArray(e)){let n=[];for(let s=0;s<t;s++)n=n.concat(e);return n}{const n=new Array(t);return n.fill(e),n}}function by(e,t){if(!e)throw new my(t)}function xy(e,t){let n=0;for(const s of e)s===t&&n++;return n}function wy(e){return 1===e.length?e[0]:e}function vy(e){return Array.isArray(e)?e:[e]}function ky(e){const t=e.replace(/(.)([A-Z][a-z0-9]+)/g,"$1_$2").replace(/([a-z])([A-Z])/g,"$1_$2").toLowerCase();return"_"!==t[0]?t:"private"+t}function Iy(e){return e.length<=1||-1===e.indexOf("_")?e:e.replace(/[_]+(\w|$)/g,((e,t)=>t.toUpperCase()))}let Ny={};function Sy(e){if(null==e)return null;const t={};return t.className=e.getClassName(),t.config=e.getConfig(),t}function Ty(e){if(null!=e&&"object"==typeof e)if(Array.isArray(e))e.forEach((e=>Ty(e)));else{const t=Object.keys(e);for(const n of t){const t=e[n];null!=t&&"object"==typeof t&&(Array.isArray(t)||"ndarray"!==t.type||"number"!=typeof t.value?Ty(t):e[n]=t.value)}}}function Cy(e,t={},n={},s="object",r=!1){if("string"==typeof e){const r=e;let a;if(r in n)a=n[r];else if(r in Ny)a=Ny[r];else if(a=t[r],null==a)throw new dy(`Unknown ${s}: ${e}. This may be due to one of the following reasons:\n1. The ${s} is defined in Python, in which case it needs to be ported to TensorFlow.js or your JavaScript code.\n2. The custom ${s} is defined in JavaScript, but is not registered properly with tf.serialization.registerClass().`);return a}{const a=e;if(null==a.className||null==a.config)throw new dy(`${s}: Improper config format: ${JSON.stringify(a)}.\n'className' and 'config' must set.`);const i=a.className;let o,l;if(i in n?[o,l]=n[i]:i in Ny?[o,l]=Ny.className:i in t&&([o,l]=t[i]),null==o)throw new dy(`Unknown ${s}: ${i}. This may be due to one of the following reasons:\n1. The ${s} is defined in Python, in which case it needs to be ported to TensorFlow.js or your JavaScript code.\n2. The custom ${s} is defined in JavaScript, but is not registered properly with tf.serialization.registerClass().`);if(null!=l){const e={};for(const t of Object.keys(Ny))e[t]=Ny[t];for(const t of Object.keys(n))e[t]=n[t];a.config.customObjects=e;const t=Object.assign({},Ny);for(const e of Object.keys(n))Ny[e]=n[e];Ty(a.config);const s=l(o,a.config,n,r);return Ny=Object.assign({},t),s}{const e=Object.assign({},Ny);for(const e of Object.keys(n))Ny[e]=n[e];const t=new o(a.config);return Ny=Object.assign({},e),t}}}function $y(e,t){return-1*function(e,t){return e<t?-1:e>t?1:0}(e,t)}function Ey(e){if(null==e)return e;const t=[];for(const n of e)-1===t.indexOf(n)&&t.push(n);return t}function Ay(e){if(null==e)throw new dy(`Invalid value in obj: ${JSON.stringify(e)}`);for(const t in e)if(e.hasOwnProperty(t))return!1;return!0}function Ry(e,t,n){if(null!=n&&e.indexOf(n)<0)throw new dy(`${n} is not a valid ${t}.  Valid values are ${e} or null/undefined.`)}function Fy(e,t,n=0,s=1/0){return by(n>=0),by(s>=n),Array.isArray(e)&&e.length>=n&&e.length<=s&&e.every((e=>typeof e===t))}function _y(e,t){Array.isArray(e)?(ie(e.length>0,(()=>`${t} is unexpectedly an empty array.`)),e.forEach(((e,n)=>_y(e,`element ${n+1} of ${t}`)))):ie(Number.isInteger(e)&&e>0,(()=>`Expected ${t} to be a positive integer, but got ${Dy(e)}.`))}function Dy(e){return null===e?"null":Array.isArray(e)?"["+e.map((e=>Dy(e))).join(",")+"]":"string"==typeof e?`"${e}"`:`${e}`}function Oy(e){return"relu"===e?"relu":"linear"===e?"linear":"elu"===e?"elu":null}let My=0;function Ly(){return My++}const zy={};function Py(e=""){return e in zy||(zy[e]=0),zy[e]+=1,e+zy[e].toString()}const By=["channelsFirst","channelsLast"],Wy=["nearest","bilinear"],Vy=["valid","same","causal"],Uy=["max","avg"],Gy=["sum","mul","concat","ave"],Hy=new Map;function jy(e){Ry(By,"DataFormat",e)}function qy(e){Ry(Vy,"PaddingMode",e)}function Ky(e){Ry(Uy,"PoolMode",e)}const Xy=[],Yy="/";function Zy(e,t){Xy.push(e);try{const e=t();return Xy.pop(),e}catch(e){throw Xy.pop(),e}}function Jy(e){if(!tb(e))throw new Error("Not a valid tensor name: '"+e+"'");return(0===Xy.length?"":Xy.join(Yy)+Yy)+e}function Qy(e){if(!tb(e))throw new Error("Not a valid tensor name: '"+e+"'");Hy.has(e)||Hy.set(e,0);const t=Hy.get(e);if(Hy.set(e,Hy.get(e)+1),t>0){const n=`${e}_${t}`;return Hy.set(n,1),n}return e}const eb=new RegExp(/^[A-Za-z0-9][-A-Za-z0-9\._\/]*$/);function tb(e){return!!e.match(eb)}function nb(e,t,n){null==t&&(t=0),null==n&&(n=e.length);let s=1;for(let r=t;r<n;++r)s*=e[r];return s}function sb(e){if(0===e.length)return Number.NaN;let t=Number.POSITIVE_INFINITY;for(let n=0;n<e.length;n++){const s=e[n];s<t&&(t=s)}return t}function rb(e){if(0===e.length)return Number.NaN;let t=Number.NEGATIVE_INFINITY;for(let n=0;n<e.length;n++){const s=e[n];s>t&&(t=s)}return t}function ab(e,t){if(t<e)throw new dy(`end (${t}) < begin (${e}) is forbidden.`);const n=[];for(let s=e;s<t;++s)n.push(s);return n}let ib;function ob(){return null==ib&&(ib=So().epsilon()),ib}function lb(e,t){return no(e,t)}function ub(e,t=-1){const n=e.shape.slice();return t<0&&(t=n.length+t+1),n.splice(t,0,1),sc(e,n)}function cb(e,t,n){return fo((()=>{switch(e.rank){case 1:return Wp(e,t,n);case 2:return Vp(e,[t,0],[n,e.shape[1]]);case 3:return Up(e,[t,0,0],[n,e.shape[1],e.shape[2]]);case 4:return Gp(e,[t,0,0,0],[n,e.shape[1],e.shape[2],e.shape[3]]);case 5:return lc(e,[t,0,0,0,0],[n,e.shape[1],e.shape[2],e.shape[3],e.shape[4]]);case 6:return lc(e,[t,0,0,0,0,0],[n,e.shape[1],e.shape[2],e.shape[3],e.shape[4],e.shape[5]]);default:throw new dy(`sliceAlongFirstAxis() received an unsupported tensor rank: ${e.rank}`)}}))}function hb(e,t,n){return fo((()=>{switch(e.rank){case 1:return Wp(e,t,n);case 2:return Vp(e,[0,t],[e.shape[0],n]);case 3:return Up(e,[0,0,t],[e.shape[0],e.shape[1],n]);case 4:return Gp(e,[0,0,0,t],[e.shape[0],e.shape[1],e.shape[2],n]);default:throw new dy(`sliceAlongLastAxis() received an unsupported tensor rank: ${e.rank}`)}}))}function pb(e,t,n,s){return fo((()=>{switch(e.rank){case 1:return Wp(e,t,n);case 2:switch(s){case 1:return cb(e,t,n);case 2:return hb(e,t,n);default:throw new dy(`The axis is not within the rank of the tensor ${s}`)}case 3:switch(s){case 1:return cb(e,t,n);case 2:return Up(e,[0,t,0],[e.shape[0],n,e.shape[2]]);case 3:return hb(e,t,n);default:throw new dy(`The axis is not within the rank of the tensor ${s}`)}case 4:switch(s){case 1:return cb(e,t,n);case 2:return Gp(e,[0,t,0,0],[e.shape[0],n,e.shape[2],e.shape[3]]);case 3:return Gp(e,[0,0,t,0],[e.shape[0],e.shape[1],n,e.shape[3]]);case 4:return hb(e,t,n);default:throw new dy(`The axis is not within the rank of the tensor ${s}`)}default:throw new dy(`sliceAlongLastAxis() received an unsupported tensor rank: ${e.rank}`)}}))}function db(e,t=-1){let n;return t<0&&(n=e[0].rank,t=0!==n?n:0),t===e[0].rank&&(t=-1),ic(e,t)}function fb(e,t){switch(e.rank){case 1:return kc([e,t]);case 2:return Ic([e,t],0);case 3:return Nc([e,t],0);case 4:return Sc([e,t],0);default:throw new dy(`concatAlongFirstAxis() received an unsupported tensor rank: ${e.rank}`)}}function mb(e,t){if(Array.isArray(t)||(t=[t]),e.rank!==t.length)throw new dy(`The length of input n (${t.length}) does not match the number of dimensions in input x (${e.rank})`);return dh(e,t)}function gb(e,t=0,n=1,s,r){return wp(e,t,n,s,r)}function yb(e,t,n,s){if(e.rank<2||t.rank<2)throw new fy(`dot requires both inputs to be rank >= 2 but got x shape = ${e.shape} and y shape = ${t.shape}`);if(t.rank>=3){if(e.shape.slice(-1)[0]!==t.shape.slice(-2)[0])throw new fy(`If rank y >= 3, then the second last dim of y must equal the last dim of x but got x shape = ${e.shape} and  y shape = ${t.shape}`)}if(2===e.rank&&2===t.rank){return Md({a:e,b:t,transposeA:!1,transposeB:!1,bias:s?wb(e.rank,s,"channelsLast"):null,activation:n})}{const r=e.shape.slice(),a=r.pop();e=sc(e,[-1,a]);const i=t.shape.slice(),o=i.pop(),l=i.pop(),u=[...i,o],c=Array.from({length:t.rank},((e,n)=>0===n?t.rank-2:n<=t.rank-2?n-1:n));t=sc(_l(t,c),[l,-1]);const h=[...r,...u];return sc(Md({a:e,b:t,transposeA:!1,transposeB:!1,bias:s?wb(e.rank,s,"channelsLast"):null,activation:n}),h)}}function bb(e,t,n){return fo((()=>(t=Array.isArray(t)?sd(t,"int32"):no(t,"int32"),gh(e,t,n))))}function xb(e){return Ao(e,e)}function wb(e,t,n){const s=t.shape;if(1!==t.rank&&t.rank!==e)throw new dy(`Unexpected bias dimensions: ${t.rank}; expected it to be 1 or ${e}`);if(5===e){if("channelsFirst"===n)return 1===s.length?sc(t,[1,s[0],1,1,1]):sc(t,[1,s[3],s[0],s[1],s[2]]);if("channelsLast"===n)return 1===s.length?sc(t,[1,1,1,1,s[0]]):sc(t,[1].concat(s))}else if(4===e){if("channelsFirst"===n)return 1===s.length?sc(t,[1,s[0],1,1]):sc(t,[1,s[2],s[0],s[1]]);if("channelsLast"===n)return 1===s.length?sc(t,[1,1,1,s[0]]):sc(t,[1].concat(s))}else if(3===e){if("channelsFirst"===n)return 1===s.length?sc(t,[1,s[0],1]):sc(t,[1,s[1],s[0]]);if("channelsLast"===n)return 1===s.length?sc(t,[1,1,s[0]]):sc(t,[1].concat(s))}else if(e<3)return t;throw new dy(`Unsupported input rank by biasAdd: ${t.rank}`)}function vb(e,t,n){return fo((()=>(null==n&&(n="channelsLast"),jy(n),Co(e,wb(e.rank,t,n)))))}function kb(e,t,n,s){return fo((()=>Id(e,t,n,s)))}function Ib(e,t,n=!1){return n?e():t()}const Nb=["fanIn","fanOut","fanAvg"],Sb=["normal","uniform","truncatedNormal"];class Tb extends Vo{fromConfigUsesCustomObjects(){return!1}getConfig(){return{}}}class Cb extends Tb{apply(e,t){return Gh(e,t)}}Cb.className="Zeros",Go(Cb);class $b extends Tb{apply(e,t){return Hh(e,t)}}$b.className="Ones",Go($b);class Eb extends Tb{constructor(e){if(super(),"object"!=typeof e)throw new dy(`Expected argument of type ConstantConfig but got ${e}`);if(void 0===e.value)throw new dy(`config must have value set but got ${e}`);this.value=e.value}apply(e,t){return fo((()=>Ao(Wo(this.value),Hh(e,t))))}getConfig(){return{value:this.value}}}Eb.className="Constant",Go(Eb);class Ab extends Tb{constructor(e){super(),this.DEFAULT_MINVAL=-.05,this.DEFAULT_MAXVAL=.05,this.minval=e.minval||this.DEFAULT_MINVAL,this.maxval=e.maxval||this.DEFAULT_MAXVAL,this.seed=e.seed}apply(e,t){return kp(e,this.minval,this.maxval,t,this.seed)}getConfig(){return{minval:this.minval,maxval:this.maxval,seed:this.seed}}}Ab.className="RandomUniform",Go(Ab);class Rb extends Tb{constructor(e){super(),this.DEFAULT_MEAN=0,this.DEFAULT_STDDEV=.05,this.mean=e.mean||this.DEFAULT_MEAN,this.stddev=e.stddev||this.DEFAULT_STDDEV,this.seed=e.seed}apply(e,t){if("float32"!==(t=t||"float32")&&"int32"!==t)throw new fy(`randomNormal does not support dType ${t}.`);return gb(e,this.mean,this.stddev,t,this.seed)}getConfig(){return{mean:this.mean,stddev:this.stddev,seed:this.seed}}}Rb.className="RandomNormal",Go(Rb);class Fb extends Tb{constructor(e){super(),this.DEFAULT_MEAN=0,this.DEFAULT_STDDEV=.05,this.mean=e.mean||this.DEFAULT_MEAN,this.stddev=e.stddev||this.DEFAULT_STDDEV,this.seed=e.seed}apply(e,t){if("float32"!==(t=t||"float32")&&"int32"!==t)throw new fy(`truncatedNormal does not support dType ${t}.`);return cd(e,this.mean,this.stddev,t,this.seed)}getConfig(){return{mean:this.mean,stddev:this.stddev,seed:this.seed}}}Fb.className="TruncatedNormal",Go(Fb);class _b extends Tb{constructor(e){super(),this.gain=null!=e.gain?e.gain:1}apply(e,t){return fo((()=>{if(2!==e.length||e[0]!==e[1])throw new dy("Identity matrix initializer can only be used for 2D square matrices.");return Ao(this.gain,fh(e[0]))}))}getConfig(){return{gain:this.gain}}}_b.className="Identity",Go(_b);class Db extends Tb{constructor(e){if(super(),e.scale<0)throw new dy(`scale must be a positive float. Got: ${e.scale}`);var t;this.scale=null==e.scale?1:e.scale,this.mode=null==e.mode?"fanIn":e.mode,t=this.mode,Ry(Nb,"FanMode",t),this.distribution=null==e.distribution?"normal":e.distribution,function(e){Ry(Sb,"Distribution",e)}(this.distribution),this.seed=e.seed}apply(e,t){const n=function(e,t="channelsLast"){let n,s;if(jy(t),2===e.length)n=e[0],s=e[1];else if(-1!==[3,4,5].indexOf(e.length)){if("channelsFirst"===t){const t=nb(e,2);n=e[1]*t,s=e[0]*t}else if("channelsLast"===t){const t=nb(e,0,e.length-2);n=e[e.length-2]*t,s=e[e.length-1]*t}}else{const t=nb(e);n=Math.sqrt(t),s=Math.sqrt(t)}return[n,s]}(e),s=n[0],r=n[1];let a=this.scale;if("fanIn"===this.mode?a/=Math.max(1,s):"fanOut"===this.mode?a/=Math.max(1,r):a/=Math.max(1,(s+r)/2),"normal"===this.distribution){const n=Math.sqrt(a);if("float32"!==(t=t||"float32")&&"int32"!==t)throw new fy(`${this.getClassName()} does not support dType ${t}.`);return cd(e,0,n,t,this.seed)}{const n=Math.sqrt(3*a);return kp(e,-n,n,t,this.seed)}}getConfig(){return{scale:this.scale,mode:this.mode,distribution:this.distribution,seed:this.seed}}}Db.className="VarianceScaling",Go(Db);class Ob extends Db{constructor(e){super({scale:1,mode:"fanAvg",distribution:"uniform",seed:null==e?null:e.seed})}getClassName(){return Db.className}}Ob.className="GlorotUniform",Go(Ob);class Mb extends Db{constructor(e){super({scale:1,mode:"fanAvg",distribution:"normal",seed:null==e?null:e.seed})}getClassName(){return Db.className}}Mb.className="GlorotNormal",Go(Mb);class Lb extends Db{constructor(e){super({scale:2,mode:"fanIn",distribution:"normal",seed:null==e?null:e.seed})}getClassName(){return Db.className}}Lb.className="HeNormal",Go(Lb);class zb extends Db{constructor(e){super({scale:2,mode:"fanIn",distribution:"uniform",seed:null==e?null:e.seed})}getClassName(){return Db.className}}zb.className="HeUniform",Go(zb);class Pb extends Db{constructor(e){super({scale:1,mode:"fanIn",distribution:"normal",seed:null==e?null:e.seed})}getClassName(){return Db.className}}Pb.className="LeCunNormal",Go(Pb);class Bb extends Db{constructor(e){super({scale:1,mode:"fanIn",distribution:"uniform",seed:null==e?null:e.seed})}getClassName(){return Db.className}}Bb.className="LeCunUniform",Go(Bb);class Wb extends Tb{constructor(e){super(),this.DEFAULT_GAIN=1,this.ELEMENTS_WARN_SLOW=2e3,this.gain=null==e.gain?this.DEFAULT_GAIN:e.gain,this.seed=e.seed}apply(e,t){return fo((()=>{if(e.length<2)throw new fy("Shape must be at least 2D.");if("int32"!==t&&"float32"!==t&&void 0!==t)throw new TypeError(`Unsupported data type ${t}.`);const n=ue(e.slice(0,-1)),s=e[e.length-1],r=n*s;r>this.ELEMENTS_WARN_SLOW&&console.warn(`Orthogonal initializer is being called on a matrix with more than ${this.ELEMENTS_WARN_SLOW} (${r}) elements: Slowness may result.`);const a=gb([Math.max(s,n),Math.min(s,n)],0,1,t,this.seed),i=Lf.qr(a,!1);let o=i[0];const l=i[1].flatten().stridedSlice([0],[Math.min(s,n)*Math.min(s,n)],[Math.min(s,n)+1]);return o=Ao(o,l.sign()),n<s&&(o=o.transpose()),Ao(Wo(this.gain),o.reshape(e))}))}getConfig(){return{gain:this.gain,seed:this.seed}}}Wb.className="Orthogonal",Go(Wb);const Vb={constant:"Constant",glorotNormal:"GlorotNormal",glorotUniform:"GlorotUniform",heNormal:"HeNormal",heUniform:"HeUniform",identity:"Identity",leCunNormal:"LeCunNormal",leCunUniform:"LeCunUniform",ones:"Ones",orthogonal:"Orthogonal",randomNormal:"RandomNormal",randomUniform:"RandomUniform",truncatedNormal:"TruncatedNormal",varianceScaling:"VarianceScaling",zeros:"Zeros"};function Ub(e,t={}){return Cy(e,Uo.getMap().classNameMap,t,"initializer")}function Gb(e){return Sy(e)}function Hb(e){if("string"==typeof e){const t=e in Vb?Vb[e]:e;if("GlorotNormal"===t)return new Mb;if("GlorotUniform"===t)return new Ob;if("HeNormal"===t)return new Lb;if("HeUniform"===t)return new zb;if("LeCunNormal"===t)return new Pb;if("LeCunUniform"===t)return new Bb;{const e={};return e.className=t,e.config={},Ub(e)}}return e instanceof Tb?e:Ub(e)}function jb(e){return Array.isArray(e)&&Array.isArray(e[0])}function qb(e){return 0===e.length?[]:Array.isArray(e[0])?e:[e]}function Kb(e){let t;if(Array.isArray(e)){if(1!==e.length)throw new dy(`Expected Tensor length to be 1; got ${e.length}`);t=e[0]}else t=e;return t}function Xb(e){if(Array.isArray(e)&&Array.isArray(e[0])){if(1===e.length)return e[0];throw new dy(`Expected exactly 1 Shape; got ${e.length}`)}return e}function Yb(e){let t=0;for(const n of e)0===n.shape.length?t+=1:t+=n.shape.reduce(((e,t)=>e*t));return t}const Zb="Variable";class Jb{constructor(e,t="float32",n=Zb,s=!0,r=null){this.dtype=null==t?"float32":t,this.shape=e.shape,this.id=Ly(),n=null==n?Zb:n,this.originalName=Jy(n),this.name=Qy(this.originalName),this.trainable_=s,this.constraint=r,this.val=md(e,this.trainable_,this.name,this.dtype)}read(){return this.assertNotDisposed(),this.val}write(e){return this.assertNotDisposed(),function(e,t){if(e.shape.toString()!==t.shape.toString())throw new Error("Shape mismatch: "+JSON.stringify(e.shape)+" vs. "+JSON.stringify(t.shape))}(this.val,e),this.val.id!==e.id&&(this.val.assign(e),null!=this.constraint&&this.val.assign(this.constraint.apply(this.val))),this}dispose(){this.assertNotDisposed(),this.val.dispose()}assertNotDisposed(){if(this.val.isDisposed)throw new Error(`LayersVariable ${this.name} is already disposed.`)}get trainable(){return this.trainable_}set trainable(e){this.trainable_=e,this.val.trainable=e}}function Qb(e){return e.map((e=>e.read()))}function ex(e){e.forEach((e=>{e[0].write(e[1])}))}class tx{constructor(e){this.dtype=e.dtype,this.shape=e.shape,null!=e.shape?this.ndim=e.shape.length:this.ndim=e.ndim,this.maxNDim=e.maxNDim,this.minNDim=e.minNDim,this.axes=e.axes||{}}}class nx{constructor(e,t,n,s,r,a,i){this.dtype=e,this.shape=t,this.sourceLayer=n,this.inputs=s,this.callArgs=r,this.outputTensorIndex=i,this.id=Ly(),null!=a&&(this.originalName=Jy(a),this.name=Qy(this.originalName)),this.rank=t.length}}let sx=0;class rx{constructor(e,t){this.callArgs=t,this.id=sx++,this.outboundLayer=e.outboundLayer,this.inboundLayers=e.inboundLayers,this.nodeIndices=e.nodeIndices,this.tensorIndices=e.tensorIndices,this.inputTensors=e.inputTensors,this.outputTensors=e.outputTensors,this.inputMasks=e.inputMasks,this.outputMasks=e.outputMasks,this.inputShapes=e.inputShapes,this.outputShapes=e.outputShapes;for(const t of e.inboundLayers)null!=t&&t.outboundNodes.push(this);e.outboundLayer.inboundNodes.push(this)}getConfig(){const e=[];for(const t of this.inboundLayers)null!=t?e.push(t.name):e.push(null);return{outboundLayer:this.outboundLayer?this.outboundLayer.name:null,inboundLayers:e,nodeIndices:this.nodeIndices,tensorIndices:this.tensorIndices}}}let ax=0;class ix extends Vo{constructor(e={}){super(),this._callHook=null,this._addedWeightNames=[],this._stateful=!1,this.id=ax++,this.activityRegularizer=null,this.inputSpec=null,this.supportsMasking=!1,this._trainableWeights=[],this._nonTrainableWeights=[],this._losses=[],this._updates=[],this._built=!1,this.inboundNodes=[],this.outboundNodes=[];let t=e.name;if(!t){const e=this.getClassName();t=ky(e)+"_"+Py(e)}if(this.name=t,this.trainable_=null==e.trainable||e.trainable,null!=e.inputShape||null!=e.batchInputShape){let t;if(null!=e.batchInputShape)t=e.batchInputShape;else if(null!=e.inputShape){let n=null;null!=e.batchSize&&(n=e.batchSize),t=[n].concat(e.inputShape)}this.batchInputShape=t;let n=e.dtype;null==n&&(n=e.inputDType),null==n&&(n="float32"),this.dtype=n}null!=e.weights?this.initialWeights=e.weights:this.initialWeights=null,this._refCount=null,this.fastWeightInitDuringBuild=!1}static nodeKey(e,t){return e.name+"_ib-"+t.toString()}getNodeAtIndex(e,t){if(0===this.inboundNodes.length)throw new py(`The layer has never been called and thus has no defined ${t}.`);if(this.inboundNodes.length<=e)throw new dy(`Asked to get ${t} at node ${e}, but the layer has only ${this.inboundNodes.length} inbound nodes.`);return this.inboundNodes[e]}getInputAt(e){return wy(this.getNodeAtIndex(e,"input").inputTensors)}getOutputAt(e){return wy(this.getNodeAtIndex(e,"output").outputTensors)}get input(){if(this.inboundNodes.length>1)throw new hy(`Layer ${this.name} has multiple inbound nodes, hence the notion of "layer input" is ill-defined. Use \`getInputAt(nodeIndex)\` instead.`);if(0===this.inboundNodes.length)throw new hy(`Layer ${this.name} is not connected, no input to return.`);return wy(this.getNodeAtIndex(0,"input").inputTensors)}get output(){if(0===this.inboundNodes.length)throw new hy(`Layer ${this.name} has no inbound nodes.`);if(this.inboundNodes.length>1)throw new hy(`Layer ${this.name} has multiple inbound nodes, hence the notion of "layer output" is ill-defined. Use \`getOutputAt(nodeIndex)\` instead.`);return wy(this.getNodeAtIndex(0,"output").outputTensors)}get losses(){return this._losses}calculateLosses(){return this.losses.map((e=>e()))}get updates(){return this._updates}get built(){return this._built}set built(e){this._built=e}get trainable(){return this.trainable_}set trainable(e){this._trainableWeights.forEach((t=>t.trainable=e)),this.trainable_=e}get trainableWeights(){return this.trainable_?this._trainableWeights.filter((e=>e.trainable)):[]}set trainableWeights(e){this._trainableWeights=e}get nonTrainableWeights(){return this.trainable?this._trainableWeights.filter((e=>!e.trainable)).concat(this._nonTrainableWeights):this._trainableWeights.concat(this._nonTrainableWeights)}set nonTrainableWeights(e){this._nonTrainableWeights=e}get weights(){return this.trainableWeights.concat(this.nonTrainableWeights)}get stateful(){return this._stateful}resetStates(){if(!this.stateful)throw new Error("Cannot call the resetStates() method of a non-stateful Layer object.")}assertInputCompatibility(e){if(e=vy(e),null==this.inputSpec||0===this.inputSpec.length)return;const t=vy(this.inputSpec);if(e.length!==t.length)throw new dy(`Layer ${this.name} expects ${t.length} inputs, but it received ${e.length} input tensors. Input received: ${e}`);for(let n=0;n<e.length;n++){const s=e[n],r=t[n];if(null==r)continue;const a=s.rank;if(null!=r.ndim&&a!==r.ndim)throw new dy(`Input ${n} is incompatible with layer ${this.name}: expected ndim=${r.ndim}, found ndim=${a}`);if(null!=r.maxNDim&&a>r.maxNDim)throw new dy(`Input ${n} is incompatible with layer ${this.name}: expected max_ndim=${r.maxNDim}, found ndim=${a}`);if(null!=r.minNDim&&a<r.minNDim)throw new dy(`Input ${n} is incompatible with layer ${this.name}: expected min_ndim=${r.minNDim}, found ndim=${a}.`);if(null!=r.dtype&&s.dtype!==r.dtype)throw new dy(`Input ${n} is incompatible with layer ${this.name} : expected dtype=${r.dtype}, found dtype=${s.dtype}.`);if(r.axes){const e=s.shape;for(const t in r.axes){const s=Number(t),a=r.axes[t],i=s>=0?e[s]:e[e.length+s];if(null!=a&&-1===[a,null].indexOf(i))throw new dy(`Input ${n} is incompatible with layer ${this.name}: expected axis ${s} of input shape to have value ${a} but got shape ${e}.`)}}if(null!=r.shape)for(let e=0;e<r.shape.length;++e){const t=r.shape[e],a=s.shape[e];if(null!=t&&null!=a&&t!==a)throw new dy(`Input ${n} is incompatible with layer ${this.name}: expected shape=${r.shape}, found shape=${s.shape}.`)}}}call(e,t){return e}invokeCallHook(e,t){null!=this._callHook&&this._callHook(e,t)}setCallHook(e){this._callHook=e}clearCallHook(){this._callHook=null}apply(e,t){t=t||{},this.assertNotDisposed();const n=vy(e);let s=!0;for(const e of n)if(!(e instanceof nx)){s=!1;break}let r=!0;for(const e of n)if(e instanceof nx){r=!1;break}if(s===r)throw new dy("Arguments to apply() must be all SymbolicTensors or all Tensors");return Zy(this.name,(()=>{if(!this.built){this.assertInputCompatibility(e);const t=[];for(const n of vy(e))t.push(n.shape);this.build(wy(t)),this.built=!0,this.initialWeights&&this.setWeights(this.initialWeights),null===this._refCount&&r&&(this._refCount=1)}if(this.assertInputCompatibility(e),r){let s=this.call(e,t);const r=vy(s),a=[];for(let e of r)-1!==n.indexOf(e)&&(e=e.clone()),a.push(e);if(s=wy(a),null!=this.activityRegularizer)throw new fy("Layer invocation in the presence of activity regularizer(s) is not supported yet.");return s}{const n=function(e){e=vy(e);const t=[];for(const n of e)t.push(n.shape);return wy(t)}(e),s=this.computeOutputShape(n);let r;const a="float32";if(this.warnOnIncompatibleInputShape(Array.isArray(e)?n[0]:n),r=null!=s&&s.length>0&&Array.isArray(s[0])?s.map(((n,s)=>new nx(a,n,this,vy(e),t,this.name,s))):new nx(a,s,this,vy(e),t,this.name),this.addInboundNode(e,r,null,null,n,s,t),this._refCount++,null!=this.activityRegularizer)throw new fy("Layer invocation in the presence of activity regularizer(s) is not supported yet.");return r}}))}warnOnIncompatibleInputShape(e){if(null!=this.batchInputShape)if(e.length!==this.batchInputShape.length)console.warn(`The rank of the input tensor provided (shape: ${JSON.stringify(e)}) does not match that of the batchInputShape (${JSON.stringify(this.batchInputShape)}) of the layer ${this.name}`);else{let t=!1;this.batchInputShape.forEach(((n,s)=>{null!=n&&null!=e[s]&&e[s]!==n&&(t=!0)})),t&&console.warn(`The shape of the input tensor (${JSON.stringify(e)}) does not match the expectation of layer ${this.name}: ${JSON.stringify(this.batchInputShape)}`)}}get outputShape(){if(null==this.inboundNodes||0===this.inboundNodes.length)throw new hy(`The layer ${this.name} has never been called and thus has no defined output shape.`);const e=[];for(const t of this.inboundNodes){const n=JSON.stringify(t.outputShapes);-1===e.indexOf(n)&&e.push(n)}if(1===e.length){const e=this.inboundNodes[0].outputShapes;return Array.isArray(e)&&Array.isArray(e[0])&&1===e.length?e[0]:e}throw new hy(`The layer ${this.name} has multiple inbound nodes with different output shapes. Hence the notion of "output shape" is ill-defined for the layer.`)}countParams(){if(!this.built)throw new py(`You tried to call countParams() on ${this.name}, but the layer is not built yet. Build it first by calling build(batchInputShape).`);return Yb(this.weights)}build(e){this.built=!0}getWeights(e=!1){return Qb(e?this.trainableWeights:this.weights)}setWeights(e){fo((()=>{const t=this.weights;if(t.length!==e.length)throw new dy(`You called setWeights(weights) on layer "${this.name}" with a weight list of length ${e.length}, but the layer was expecting ${t.length} weights. Provided weights: ${e}...`);if(0===t.length)return;const n=[],s=Qb(t);for(let r=0;r<s.length;++r){const a=s[r],i=t[r],o=e[r];if(!pe(a.shape,o.shape))throw new dy(`Layer weight shape ${a.shape} not compatible with provided weight shape ${o.shape}`);n.push([i,o])}ex(n)}))}addWeight(e,t,n,s,r,a,i,o){if(-1!==this._addedWeightNames.indexOf(e))throw new dy(`Duplicate weight name ${e} for layer ${this.name}`);this._addedWeightNames.push(e),null==n&&(n="float32"),this.fastWeightInitDuringBuild&&(s=null!=o?o():Hb("zeros"));const l=s.apply(t,n),u=new Jb(l,n,e,a,i);return l.dispose(),null!=r&&this.addLoss((()=>r.apply(u.read()))),null==a&&(a=!0),a?this._trainableWeights.push(u):this._nonTrainableWeights.push(u),u}setFastWeightInitDuringBuild(e){this.fastWeightInitDuringBuild=e}addLoss(e){null==e||Array.isArray(e)&&0===e.length||(e=vy(e),void 0!==this._losses&&null!==this._losses&&this.losses.push(...e))}computeOutputShape(e){return e}computeMask(e,t){if(!this.supportsMasking){if(null!=t){if(!Array.isArray(t))throw new TypeError(`Layer ${this.name} does not support masking, but was passed an inputMask.`);t.forEach((e=>{if(null!=e)throw new TypeError(`Layer ${this.name} does not support masking, but was passed an inputMask.`)}))}return null}return t}addInboundNode(e,t,n,s,r,a,i=null){const o=vy(e);t=vy(t),n=vy(n),s=vy(s),r=qb(r),a=qb(a);const l=[],u=[],c=[];for(const e of o)l.push(e.sourceLayer),u.push(e.nodeIndex),c.push(e.tensorIndex);new rx({outboundLayer:this,inboundLayers:l,nodeIndices:u,tensorIndices:c,inputTensors:o,outputTensors:t,inputMasks:n,outputMasks:s,inputShapes:r,outputShapes:a},i);for(let e=0;e<t.length;e++)t[e].sourceLayer=this,t[e].nodeIndex=this.inboundNodes.length-1,t[e].tensorIndex=e}getConfig(){const e={name:this.name,trainable:this.trainable};return null!=this.batchInputShape&&(e.batchInputShape=this.batchInputShape),null!=this.dtype&&(e.dtype=this.dtype),e}disposeWeights(){return this.weights.forEach((e=>e.dispose())),this.weights.length}assertNotDisposed(){if(0===this._refCount)throw new Error(`Layer '${this.name}' is already disposed.`)}dispose(){if(!this.built)throw new Error(`Cannot dispose Layer ${this.name} because it has not been built yet.`);if(null===this._refCount)throw new Error(`Cannot dispose Layer ${this.name} because it has not been used yet.`);this.assertNotDisposed();let e=0;return 0==--this._refCount&&(e=this.disposeWeights()),{refCountAfterDispose:this._refCount,numDisposedVariables:e}}}function ox(e,t,n){if((null==t||null!=n&&n>0)&&(t=e.sourceLayer,n=e.nodeIndex),0===t.inboundNodes.length)return[e];{const e=t.inboundNodes[n];if(0===e.inboundLayers.length)return e.inputTensors;{const t=[];for(let n=0;n<e.inboundLayers.length;n++){const s=ox(e.inputTensors[n],e.inboundLayers[n],e.nodeIndices[n]);for(const e of s)-1===t.indexOf(e)&&t.push(e)}return t}}}class lx extends ix{constructor(e){if(super({dtype:e.dtype,name:null!=e.name?e.name:Py("input").toString()}),null==e.batchSize&&(e.batchSize=null),null==e.sparse&&(e.sparse=!1),this.trainable=!1,this.built=!0,this.sparse=e.sparse,null!=e.inputShape&&null!=e.batchInputShape)throw new dy("Only provide the inputShape OR batchInputShape argument to inputLayer, not both at the same time.");let t=e.batchInputShape;if(null==t){if(null==e.inputShape)throw new dy("An InputLayer should be passed either a `batchInputShape` or an `inputShape`.");t=[e.batchSize].concat(e.inputShape)}else if(null!=e.batchSize)throw new dy("Cannot specify batchSize if batchInputShape is specified when creating an InputLayer.");const n=e.dtype||"float32";this.batchInputShape=t,this.dtype=n,this.inputSpec=[{shape:t}];const s=new nx(this.dtype,this.batchInputShape,this,[],{},this.name);s.nodeIndex=0,s.tensorIndex=0,new rx({outboundLayer:this,inboundLayers:[],nodeIndices:[],tensorIndices:[],inputTensors:[s],outputTensors:[s],inputMasks:[null],outputMasks:[null],inputShapes:[t],outputShapes:[t]})}apply(e,t){throw new dy(`Cannot pass any input to an InputLayer's apply() method. InputLayer name: ${this.name}`)}dispose(){return{refCountAfterDispose:this._refCount,numDisposedVariables:0}}getConfig(){return{batchInputShape:this.batchInputShape,dtype:this.dtype,sparse:this.sparse,name:this.name}}}function ux(e){if(null==e.batchShape&&null==e.shape)throw new Error("Please provide to Input either a `shape` or a `batchShape` argument. Note that `shape` does not include the batch dimension.");if(null!=e.batchShape&&null!=e.shape)throw new dy("Please provide either a `shape` or `batchShape` argument to Input, but not both.");let t=e.batchShape;null!=e.shape&&null==t&&(t=[null].concat(e.shape));let n=e.dtype;null==n&&(n="float32");return new lx({batchInputShape:t,name:e.name,dtype:n,sparse:e.sparse}).inboundNodes[0].outputTensors[0]}lx.className="InputLayer",Go(lx);class cx{constructor(e){if(this.id2Value={},this.id2Mask={},this.name2Id={},e instanceof cx)for(const t in e.id2Value)this.id2Value[t]=e.id2Value[t],t in e.id2Mask&&(this.id2Mask[t]=e.id2Mask[t]);else{if(null==e)return;for(const t of e)this.add(t.key,t.value)}}add(e,t,n){if(null!=this.id2Value[e.id])throw new dy(`Duplicate key: name=${e.name}, id=${e.id}`);return this.id2Value[e.id]=function(e,t){if(null==e.dtype||e.dtype===t.dtype)return t;try{return no(t,e.dtype)}catch(n){throw new dy(`The dtype of the feed (${t.dtype}) can not be cast to the dtype of the key '${e.name}' (${e.dtype}).`)}}(e,t),this.name2Id[e.name]=e.id,null!=n&&(this.id2Mask[e.id]=n),this}addFeed(e){this.add(e.key,e.value)}hasKey(e){return null!=this.id2Value[e.id]}names(){return Object.keys(this.name2Id)}getValue(e){if(e instanceof nx){if(null==this.id2Value[e.id])throw new dy(`Nonexistent key: ${e.name}`);return this.id2Value[e.id]}{const t=this.name2Id[e];if(null==t)throw new dy(`Feed dict has no SymbolicTensor name: ${e}`);return this.id2Value[t]}}getMask(e){if(e instanceof nx){if(null==this.id2Value[e.id])throw new dy(`Nonexistent key: ${e.name}`);return this.id2Mask[e.id]}{const t=this.name2Id[e];if(null==t)throw new dy(`Feed dict has no SymbolicTensor name: ${e}`);return this.id2Mask[t]}}disposeMasks(){null!=this.id2Mask&&mo(this.id2Mask)}}const hx=new gy,px=new gy;function dx(e,t,n,s){const r=null!=n&&n.training,a=Array.isArray(e),i=a?e:[e],o=i.map((e=>e.name)),l=[],u=t.names();for(const e of o)-1!==u.indexOf(e)?l.push(t.getValue(e)):l.push(null);null!=s&&(s.maxNumTensors=-1/0,s.minNumTensors=1/0);const c=o.join(",")+"|"+t.names().sort().join(",");let h,p=hx.get(c);if(null==p){const e=function(e,t){ie(null!=e&&e.length>0,(()=>"Expected at least one fetch, got none"));let n=[],s={};if(1===e.length){const r=mx(e[0],t);n=r.sorted,s=r.recipientMap}else{const r=new Set;for(const a of e){const{sorted:e,recipientMap:i}=mx(a,t);for(const t of e)r.has(t.name)||(n.push(t),r.add(t.name));for(const e in i)null==s[e]&&(s[e]=new Set),i[e].forEach((t=>s[e].add(t)))}}return{sorted:n,recipientCounts:fx(s)}}(i,t);p=e.sorted,h=e.recipientCounts,hx.put(c,p),px.put(c,h)}h={},r||Object.assign(h,px.get(c));const d=new cx(t);for(let e=0;e<p.length;++e){if(null!=s){const e=ho().numTensors;e>s.maxNumTensors&&(s.maxNumTensors=e),e<s.minNumTensors&&(s.minNumTensors=e)}const a=p[e],i=a.sourceLayer;if(i instanceof lx)continue;const u=[],c=[],f=[];let m=!1;for(const e of a.inputs){const n=d.getValue(e),s=d.getMask(e);u.push(n),c.push(s),null!=s&&(m=!0),r||(h[e.name]--,0!==h[e.name]||t.hasKey(e)||-1!==o.indexOf(e.name)||n.isDisposed||!0===e.sourceLayer.stateful||f.push(n))}m&&((n=n||{}).mask=c[0]);const g=vy(i.apply(u,n));let y=null;i.supportsMasking&&(y=i.computeMask(u,c));const b=gx(a),x=Array.isArray(b)?b:[b];for(let e=0;e<x.length;++e){d.hasKey(x[e])||d.add(x[e],g[e],Array.isArray(y)?y[0]:y);const t=o.indexOf(x[e].name);-1!==t&&(l[t]=g[e])}r||mo(f)}return d.disposeMasks(),a?l:l[0]}function fx(e){const t={};for(const n in e)t[n]=e[n].size;return t}function mx(e,t){const n=new Set,s=[],r={};for(const e of t.names())n.add(e);const a=[],i=[];for(a.push(e);a.length>0;){const e=a[a.length-1];if(n.has(e.name)){a.pop();continue}const t=i[i.length-1]===a.length-1;if(0===e.inputs.length||t)a.pop(),s.push(e),n.add(e.name),t&&i.pop();else{i.push(a.length-1);for(const t of e.inputs)null==r[t.name]&&(r[t.name]=new Set),r[t.name].add(e.name),n.has(t.name)||a.push(t)}}return{sorted:s,recipientMap:r}}function gx(e){let t;if(1===e.sourceLayer.inboundNodes.length)t=e.sourceLayer.output;else{let n=null;for(let t=0;t<e.sourceLayer.inboundNodes.length;++t)for(const s of e.sourceLayer.inboundNodes[t].outputTensors)if(s.id===e.id){n=t;break}t=e.sourceLayer.getOutputAt(n)}return t}function yx(e,t){return fo((()=>Ro(ih(Ao(e,e),t,!0))))}Xe().registerFlag("TOPOLOGICAL_SORT_CACHE_MAX_ENTRIES",(()=>100),(function(e){null!=hx&&hx.setMaxEntries(e),null!=px&&px.setMaxEntries(e)}));class bx extends Vo{getConfig(){return{}}}class xx extends bx{constructor(e){super(),this.defaultMaxValue=2,this.defaultAxis=0,this.maxValue=null!=e.maxValue?e.maxValue:this.defaultMaxValue,this.axis=null!=e.axis?e.axis:this.defaultAxis}apply(e){return fo((()=>{const t=yx(e,this.axis),n=vc(t,0,this.maxValue);return Ao(e,Eo(n,Co(ob(),t)))}))}getConfig(){return{maxValue:this.maxValue,axis:this.axis}}}xx.className="MaxNorm",Go(xx);class wx extends bx{constructor(e){super(),this.defaultAxis=0,this.axis=null!=e.axis?e.axis:this.defaultAxis}apply(e){return fo((()=>Eo(e,Co(ob(),yx(e,this.axis)))))}getConfig(){return{axis:this.axis}}}wx.className="UnitNorm",Go(wx);class vx extends bx{apply(e){return Tp(e)}}vx.className="NonNeg",Go(vx);class kx extends bx{constructor(e){super(),this.defaultMinValue=0,this.defaultMaxValue=1,this.defaultRate=1,this.defaultAxis=0,this.minValue=null!=e.minValue?e.minValue:this.defaultMinValue,this.maxValue=null!=e.maxValue?e.maxValue:this.defaultMaxValue,this.rate=null!=e.rate?e.rate:this.defaultRate,this.axis=null!=e.axis?e.axis:this.defaultAxis}apply(e){return fo((()=>{const t=yx(e,this.axis),n=Co(Ao(this.rate,vc(t,this.minValue,this.maxValue)),Ao(1-this.rate,t));return Ao(e,Eo(n,Co(ob(),t)))}))}getConfig(){return{minValue:this.minValue,maxValue:this.maxValue,rate:this.rate,axis:this.axis}}}kx.className="MinMaxNorm",Go(kx);const Ix={maxNorm:"MaxNorm",minMaxNorm:"MinMaxNorm",nonNeg:"NonNeg",unitNorm:"UnitNorm"};function Nx(e){return Sy(e)}function Sx(e,t={}){return Cy(e,Uo.getMap().classNameMap,t,"constraint")}function Tx(e){if(null==e)return null;if("string"==typeof e){return Sx({className:e in Ix?Ix[e]:e,config:{}})}return e instanceof bx?e:Sx(e)}function Cx(e){return new xx(e)}function $x(e){return new wx(e)}function Ex(){return new vx}function Ax(e){return new kx(e)}function Rx(){return new Cb}function Fx(){return new $b}function _x(e){return new Eb(e)}function Dx(e){return new Ab(e)}function Ox(e){return new Rb(e)}function Mx(e){return new Fb(e)}function Lx(e){return new _b(e)}function zx(e){return new Db(e)}function Px(e){return new Ob(e)}function Bx(e){return new Mb(e)}function Wx(e){return new Lb(e)}function Vx(e){return new zb(e)}function Ux(e){return new Pb(e)}function Gx(e){return new Bb(e)}function Hx(e){return new Wb(e)}async function jx(e){if(null==e)return;const t=[],n=[],s=[];for(const r in e){const a=e[r];if("number"!=typeof a){const e=a;t.push(e.data()),n.push(r),s.push(e)}}if(t.length>0){const r=await Promise.all(t);for(let t=0;t<r.length;++t)e[n[t]]=r[t][0];mo(s)}}function qx(e){if(null!=e)for(const t in e){const n=e[t];"number"!=typeof n&&n.dispose()}}var Kx;!function(e){e[e.SILENT=0]="SILENT",e[e.VERBOSE=1]="VERBOSE"}(Kx||(Kx={}));class Xx{constructor(){this.validationData=null}setParams(e){this.params=e}async onEpochBegin(e,t){}async onEpochEnd(e,t){}async onBatchBegin(e,t){}async onBatchEnd(e,t){}async onTrainBegin(e){}async onTrainEnd(e){}setModel(e){}}class Yx{constructor(e,t=10){null==e&&(e=[]),this.callbacks=e,this.queueLength=t}append(e){this.callbacks.push(e)}setParams(e){for(const t of this.callbacks)t.setParams(e)}setModel(e){for(const t of this.callbacks)t.setModel(e)}async onEpochBegin(e,t){null==t&&(t={});for(const n of this.callbacks)await n.onEpochBegin(e,t)}async onEpochEnd(e,t){null==t&&(t={});for(const n of this.callbacks)await n.onEpochEnd(e,t)}async onBatchBegin(e,t){null==t&&(t={});for(const n of this.callbacks)await n.onBatchBegin(e,t)}async onBatchEnd(e,t){null==t&&(t={});for(const n of this.callbacks)await n.onBatchEnd(e,t)}async onTrainBegin(e){null==e&&(e={});for(const t of this.callbacks)await t.onTrainBegin(e)}async onTrainEnd(e){null==e&&(e={});for(const t of this.callbacks)await t.onTrainEnd(e)}}class Zx extends Xx{constructor(){super()}async onEpochBegin(e){this.seen=0,this.totals={}}async onBatchEnd(e,t){null==t&&(t={});const n=null==t.size?0:t.size;this.seen+=n;for(const e in t){const s=t[e];if("number"==typeof s)this.totals.hasOwnProperty(e)||(this.totals[e]=0),this.totals[e]=this.totals[e]+s*n;else{let t;e in this.totals?t=this.totals[e]:this.totals[e]=0;const r=fo((()=>Co(this.totals[e],Ao(s,n))));this.totals[e]=r,null!=t&&t.dispose()}}}async onEpochEnd(e,t){if(null!=t)for(const e of this.params.metrics)null!=this.totals[e]&&("number"==typeof this.totals[e]?t[e]=this.totals[e]/this.seen:fo((()=>{const n=Ao(Eo(1,this.seen),this.totals[e]);t[e]=n,this.totals[e].dispose(),go(t[e])})))}}class Jx extends Xx{async onTrainBegin(e){this.epoch=[],this.history={}}async onEpochEnd(e,t){null==t&&(t={}),this.epoch.push(e);for(const e in t)null==this.history[e]&&(this.history[e]=[]),this.history[e].push(t[e])}async syncData(){const e=[],t=[],n=[];for(const s in this.history){const r=this.history[s];for(let a=0;a<r.length;++a)if("number"!=typeof r[a]){const i=r[a];e.push(i.data()),t.push(s),n.push(a)}}const s=await Promise.all(e);for(let e=0;e<s.length;++e){this.history[t[e]][n[e]].dispose(),this.history[t[e]][n[e]]=s[e][0]}}}class Qx extends Xx{constructor(e,t){if(super(),this.currentEpoch=0,this.nowFunc=e.nowFunc,this.nextFrameFunc=e.nextFrameFunc||Uf,this.yieldEvery=t||"auto","auto"===this.yieldEvery&&(this.yieldEvery=125),"never"===this.yieldEvery&&null!=e.onYield)throw new Error("yieldEvery is `never` but you provided an `onYield` callback. Either change `yieldEvery` or remove the callback");Re(this.yieldEvery)&&(this.maybeWait=function(e,t,n){let s,r=null!=n?n():Xr();return(...a)=>{const i=null!=n?n():Xr();return i-r<t||(r=i,s=e(...a)),s}}(this.maybeWait.bind(this),this.yieldEvery,this.nowFunc)),this.trainBegin=e.onTrainBegin,this.trainEnd=e.onTrainEnd,this.epochBegin=e.onEpochBegin,this.epochEnd=e.onEpochEnd,this.batchBegin=e.onBatchBegin,this.batchEnd=e.onBatchEnd,this.yield=e.onYield}async maybeWait(e,t,n){const s=[];null!=this.yield&&(await jx(n),s.push(this.yield(e,t,n))),s.push(this.nextFrameFunc()),await Promise.all(s)}async onEpochBegin(e,t){this.currentEpoch=e,null!=this.epochBegin&&(await jx(t),await this.epochBegin(e,t))}async onEpochEnd(e,t){const n=[];null!=this.epochEnd&&(await jx(t),n.push(this.epochEnd(e,t))),"epoch"===this.yieldEvery&&n.push(this.nextFrameFunc()),await Promise.all(n)}async onBatchBegin(e,t){null!=this.batchBegin&&(await jx(t),await this.batchBegin(e,t))}async onBatchEnd(e,t){const n=[];null!=this.batchEnd&&(await jx(t),n.push(this.batchEnd(e,t))),"batch"===this.yieldEvery?n.push(this.nextFrameFunc()):Re(this.yieldEvery)&&n.push(this.maybeWait(this.currentEpoch,e,t)),await Promise.all(n)}async onTrainBegin(e){null!=this.trainBegin&&(await jx(e),await this.trainBegin(e))}async onTrainEnd(e){null!=this.trainEnd&&(await jx(e),await this.trainEnd(e))}}function ew(e,t){if(null==e&&(e={}),e instanceof Xx)return[e];if(Array.isArray(e)&&e[0]instanceof Xx)return e;return vy(e).map((e=>new Qx(e,t)))}class tw{constructor(){}static registerCallbackConstructor(e,t){ie(e>=0&&Number.isInteger(e),(()=>`Verbosity level is expected to be an integer >= 0, but got ${e}`)),tw.checkForDuplicate(t),null==tw.constructors[e]&&(tw.constructors[e]=[]),tw.constructors[e].push(t)}static checkForDuplicate(e){for(const t in tw.constructors){tw.constructors[+t].forEach((t=>{if(t===e)throw new dy("Duplicate callback constructor.")}))}}static clear(){tw.constructors={}}static createCallbacks(e){const t=[];for(const n in tw.constructors){const s=+n;e>=s&&t.push(...tw.constructors[s])}return t.map((e=>new e))}}function nw(e,t,n,s,r,a,i,o,l){const u=new Jx,c=[new Zx,...tw.createCallbacks(t)];null!=e&&c.push(...e),c.push(u);const h=new Yx(c);return h.setParams({epochs:n,initialEpoch:s,samples:r,steps:a,batchSize:i,verbose:t,doValidation:o,metrics:l}),{callbackList:h,history:u}}function sw(e,t={},n=!1){return Cy(e,Uo.getMap().classNameMap,t,"layer",n)}function rw(e,t){return fo((()=>{"float32"!==e.dtype&&(e=no(e,"float32"));const n=ih(xb(e),t,!0),s=qo(n.shape,ob()),r=Ro(nl(n,s));return Eo(e,r)}))}function aw(e,t){return fo((()=>Uh(xb(Yo(t,e)),-1)))}function iw(e,t){return fo((()=>Uh(Jo(Yo(t,e)),-1)))}function ow(e,t){return fo((()=>{const n=Yo(e,t),s=vc(Jo(e),ob(),Number.MAX_VALUE),r=Jo(Eo(n,s));return Ao(100,Uh(r,-1))}))}function lw(e,t){return fo((()=>{const n=vc(t,ob(),Number.MAX_VALUE),s=Ch(Co(1,n)),r=vc(e,ob(),Number.MAX_VALUE),a=Ch(Co(1,r));return Uh(xb(Yo(s,a)),-1)}))}function uw(e,t,n=!1){return fo((()=>{if(n)t=Hp(t);else{const e=ih(t,t.shape.length-1,!0);t=Eo(t,e)}return t=vc(t,ob(),1-ob()),Rl(ih(Ao(no(e,"float32"),Ch(t)),t.shape.length-1))}))}function cw(e,t,n=!1){return fo((()=>{const s=no(mh(function(e){const t=[nb(e.shape)];return sc(e,t)}(e)),"int32"),r=(t=vc(t,ob(),1-ob())).shape;return uw(sc(El(s,r[r.length-1]),r),t,n)}))}function hw(e,t){return fo((()=>{let n;return n=vc(t,ob(),1-ob()),n=Ch(Eo(n,Yo(1,n))),Uh(function(e,t){if(!pe(e.shape,t.shape))throw new dy(`logits and labels must have the same shape, but got shapes ${JSON.stringify(e.shape)} and ${JSON.stringify(t.shape)}`);return fo((()=>{const n=Tp(t),s=Rl(Jo(t));return Co(Yo(n,Ao(t,e)),$h(ch(s)))}))}(e,n),-1)}))}function pw(e,t){return fo((()=>{const n=vc(e,ob(),1),s=vc(t,ob(),1);return ih(Ao(e,Ch(Eo(n,s))),-1)}))}function dw(e,t){return fo((()=>{const n=rw(e,-1),s=rw(t,-1),r=Ao(n,s);return Rl(ih(r,-1))}))}tw.constructors={};const fw={meanSquaredError:aw,meanAbsoluteError:iw,meanAbsolutePercentageError:ow,meanSquaredLogarithmicError:lw,squaredHinge:function(e,t){return fo((()=>{const n=nl(0,Yo(1,Ao(e,t)));return Uh(xb(n),-1)}))},hinge:function(e,t){return fo((()=>{const n=nl(0,Yo(1,Ao(e,t)));return Uh(n,-1)}))},categoricalHinge:function(e,t){return fo((()=>{const n=ih(Ao(e,t),-1),s=rh(Ao(Yo(1,e),t),-1);return nl(0,Co(1,Yo(s,n)))}))},logcosh:function(e,t){return fo((()=>{const n=Math.log(2),s=Yo(t,e),r=Yo(Co(s,Eh(Ao(-2,s))),n);return Uh(r,-1)}))},categoricalCrossentropy:uw,sparseCategoricalCrossentropy:cw,binaryCrossentropy:hw,kullbackLeiblerDivergence:pw,poisson:function(e,t){return fo((()=>{const n=Ch(Co(ob(),t));return Uh(Yo(t,Ao(e,n)),-1)}))},cosineProximity:dw};function mw(e){if("string"==typeof e){if(e in fw)return fw[e];let t=`Unknown loss ${e}`;throw e.toLowerCase().includes("softmaxcrossentropy")&&(t=`Unknown loss ${e}. Use "categoricalCrossentropy" as the string name for tf.losses.softmaxCrossEntropy`),new dy(t)}return e}function gw(e,t){return fo((()=>{const n=Ao(.5,ep(t)),s=lb(yh(t,n),e.dtype);return Uh(Vc(e,s),-1)}))}function yw(e,t){return fo((()=>lb(Vc(Ou(e,-1),Ou(t,-1)),"float32")))}function bw(e,t){return fo((()=>no(ih(_h(Vc(e,1),Vc(t,1))),"float32")))}function xw(e,t){return fo((()=>{const n=bw(e,t),s=function(e,t){return fo((()=>no(ih(_h(Vc(e,0),Vc(t,1))),"float32")))}(e,t),r=Co(n,s);return no(Uc(yh(r,0),Eo(n,r),0),"float32")}))}function ww(e,t){return fo((()=>{const n=bw(e,t),s=function(e,t){return fo((()=>no(ih(_h(Vc(e,1),Vc(t,0))),"float32")))}(e,t),r=Co(n,s);return no(Uc(yh(r,0),Eo(n,r),0),"float32")}))}function vw(e,t){return hw(e,t)}function kw(e,t){return e.rank===t.rank&&(e=Jp(e,[e.rank-1])),(t=Ou(t,-1)).dtype!==e.dtype&&(t=no(t,e.dtype)),no(Vc(e,t),"float32")}const Iw=uw,Nw=cw,Sw={binaryAccuracy:gw,categoricalAccuracy:yw,precision:xw,categoricalCrossentropy:Iw,sparseCategoricalCrossentropy:Nw,mse:aw,MSE:aw,mae:iw,MAE:iw,mape:ow,MAPE:ow,cosine:dw};function Tw(e){if("string"==typeof e&&e in Sw)return Sw[e];if("string"!=typeof e&&null!=e)return e;throw new dy(`Unknown metric ${e}`)}function Cw(e){if(by(null!==e,`Unknown LossOrMetricFn ${e}`),"string"==typeof e)return e;{let t;for(const n of Object.keys(fw))if(fw[n]===e){t=n;break}if(void 0!==t)return t;for(const n of Object.keys(Sw))if(Sw[n]===e){t=n;break}return void 0!==t?t:e.name}}const $w=1048576;function Ew(e,t,n=!1){if(null==e||"object"!=typeof e||Object.getPrototypeOf(e)!==Object.prototype||!Aw(e))throw new Error("User-defined metadata is expected to be a JSON object, but is not.");if(n){const n=JSON.stringify(e);n.length>$w&&console.warn(`User-defined metadata of model "${t}" is too large in size (length=${n.length} when serialized). It is not recommended to store such large objects in user-defined metadata. Please make sure its serialized length is <= 1048576.`)}}function Aw(e){if(null===e)return!0;if("object"==typeof e){if(Object.getPrototypeOf(e)===Object.prototype){const t=Object.keys(e);for(const n of t){if("string"!=typeof n)return!1;if(!Aw(e[n]))return!1}return!0}if(Array.isArray(e)){for(const t of e)if(!Aw(t))return!1;return!0}return!1}{const t=typeof e;return"string"===t||"number"===t||"boolean"===t}}function Rw(e,t,n,s=console.log){const r=function(e){let t=!0;const n=[],s=[];for(const t in e.nodesByDepth)n.push(e.nodesByDepth[t]);for(const e of n){if(e.length>1||1===e.length&&e[0].inboundLayers.length>1){t=!1;break}s.push(...e)}if(t)for(const n of e.layers){let e=!1;for(const r of n.inboundNodes)if(-1!==s.indexOf(r)){if(e){t=!1;break}e=!0}if(!t)break}return t}(e),a=["Layer (type)","Input Shape","Output shape","Param #"];let i;if(r?(t=t||90,n=n||[.32,.61,.89,1]):(t=t||115,n=n||[.24,.48,.7,.8,1]),n[n.length-1]<=1&&(n=n.map((e=>Math.floor(t*e)))),!r){a.push("Receives inputs"),i=[];for(const t in e.nodesByDepth)i.push(...e.nodesByDepth[t])}s("_".repeat(t)),Fw(a,n,s),s("=".repeat(t));const o=e.layers;for(let e=0;e<o.length;++e)r?_w(o[e],n,s):Dw(o[e],n,i,s),s((e===o.length-1?"=":"_").repeat(t));e.checkTrainableWeightsConsistency();const l=function(e){let t;t=null!=e.collectedTrainableWeights?Yb(e.collectedTrainableWeights):Yb(e.trainableWeights);return t}(e),u=Yb(e.nonTrainableWeights);s(`Total params: ${l+u}`),s(`Trainable params: ${l}`),s(`Non-trainable params: ${u}`),s("_".repeat(t))}function Fw(e,t,n=console.log){let s="";for(let n=0;n<e.length;++n)n>0&&(s=s.slice(0,s.length-1)+" "),s+=e[n],s=s.slice(0,t[n]),s+=" ".repeat(t[n]-s.length);n(s)}function _w(e,t,n){let s,r;try{r=e.inboundNodes.map((e=>JSON.stringify(e.inputShapes))).join(",")}catch(e){r="multiple"}try{s=JSON.stringify(e.outputShape)}catch(e){s="multiple"}Fw([`${e.name} (${e.getClassName()})`,r,s,e.countParams().toString()],t,n)}function Dw(e,t,n,s){let r,a;try{a=e.inboundNodes.map((e=>JSON.stringify(e.inputShapes))).join(",")}catch(e){a="multiple"}try{r=JSON.stringify(e.outputShape)}catch(e){r="multiple"}const i=[];for(const t of e.inboundNodes)if(!(null!=n&&n.length>0&&-1===n.indexOf(t)))for(let e=0;e<t.inboundLayers.length;++e){const n=t.inboundLayers[e].name,s=t.nodeIndices[e],r=t.tensorIndices[e];i.push(`${n}[${s}][${r}]`)}const o=e.name,l=e.getClassName(),u=0===i.length?"":i[0];Fw([`${o} (${l})`,a,r,e.countParams().toString(),u],t,s);for(let e=1;e<i.length;++e)Fw(["","","","",i[e]],t,s)}function Ow(e,t,n){return("inboundNodes"===e||"outputLayers"===e||"inputLayers"===e)&&0===t&&"string"==typeof n}function Mw(e,t){if(null===e)return null;if("string"==typeof e)return Iy(e);if("number"==typeof e||"boolean"==typeof e)return e;if(e instanceof Array){const n=[],s=e.length;for(let r=0;r<s;++r){const s=e[r];Ow(t,r,s)?n.push(s):n.push(Mw(s,t))}return n}{const t={};for(const n of Object.keys(e)){const s=e[n];if("name"===n&&"string"==typeof s)t[n]=s;else{const e=Iy(n);t[e]=Mw(s,e)}}return t}}function Lw(e,t){if(null==e)return null;if("string"==typeof e)return ky(e);if("number"==typeof e||"boolean"==typeof e)return e;if(e instanceof Array){const n=[],s=e.length;for(let r=0;r<s;++r){const s=e[r];Ow(t,r,s)?n.push(s):n.push(Lw(s,t))}return n}{const t={};for(const n of Object.keys(e)){const s=e[n],r=ky(n);t[r]="name"!==n&&"className"!==n||"string"!=typeof s?Lw(s,n):s}return t}}const zw="4.6.0";class Pw extends ix{constructor(e){if(super({}),this.containerNodes=new Set,this.name=e.name,null==this.name){const e=this.getClassName().toLowerCase();this.name=Py(e)}if(this.supportsMasking=!1,this.trainable_=!0,Array.isArray(e.inputs)?this.inputs=e.inputs.slice():this.inputs=[e.inputs],Array.isArray(e.outputs)?this.outputs=e.outputs.slice():this.outputs=[e.outputs],Ey(this.inputs).length!==this.inputs.length)throw new dy(`The list of inputs passed to the model is redundant. All inputs should only appear once. Found: ${this.inputs.map((e=>e.name))}`);Ey(this.outputs).length!==this.outputs.length&&console.warn(`The list of outputs passed to the model is redundant. All outputs should only appear once. Found: ${this.outputs.map((e=>e.name))}`),this.inputLayers=[],this.inputLayersNodeIndices=[],this.inputLayersTensorIndices=[],this.outputLayers=[],this.outputLayersNodeIndices=[],this.outputLayersTensorIndices=[],this.layers=[],this.internalContainerRefs=[];for(const e of this.outputs){const t=e.sourceLayer,n=e.nodeIndex,s=e.tensorIndex;this.outputLayers.push(t),this.outputLayersNodeIndices.push(n),this.outputLayersTensorIndices.push(s)}for(const e of this.inputs){const t=e.sourceLayer,n=e.nodeIndex,s=e.tensorIndex;by(0===n,"input layer has >1 nodes"),by(0===s,"input layer has >1 tensors"),this.inputLayers.push(t),this.inputLayersNodeIndices.push(n),this.inputLayersTensorIndices.push(s)}this.inputNames=[],this.outputNames=[],this.feedInputShapes=[],this.feedInputNames=[],this.feedOutputNames=[];for(let t=0;t<this.inputLayers.length;t++){const n=this.inputLayers[t];if(!(n instanceof lx))throw new TypeError(`Input layers to a LayersModel must be InputLayer objects. Received inputs: ${e.inputs}. Input ${t} (0-based) originates from layer type ${n.getClassName()}.`);this.inputNames.push(n.name),this.feedInputShapes.push(n.batchInputShape),this.feedInputNames.push(n.name)}for(const e of this.outputLayers)this.outputNames.push(e.name);this.internalInputShapes=this.inputs.map((e=>e.shape)),this.internalOutputShapes=this.outputs.map((e=>e.shape));const t={},n={},s={},r={},a={},i=[],o=(e,t,n,s,r,l)=>{null!=s&&null!=r&&null!=l||(s=e.sourceLayer,r=e.nodeIndex,l=e.tensorIndex);const u=s.inboundNodes[r];if(-1!==n.indexOf(u))throw new py(`The tensor ${e.name} at layer "${s.name}" is part of a cycle.`);if(-1!==t.indexOf(u))return;this.containerNodes.add(Pw.nodeKey(s,r)),s.id in a||(a[s.id]=Object.keys(a).length),-1===n.indexOf(u)&&n.push(u);const c=u.inboundLayers.length;for(let e=0;e<c;e++){const s=u.inputTensors[e],r=u.inboundLayers[e],a=u.nodeIndices[e],i=u.tensorIndices[e];o(s,t,n,r,a,i)}for(t.push(u);n.indexOf(u)>=0;)n.splice(n.indexOf(u),1);i.push(u)},l=[],u=[];for(const e of this.outputs)o(e,l,u);const c=i.slice().reverse();for(const e of c){n[e.id]=e,e.id in t||(t[e.id]=0);let a=t[e.id];const i=null==s[e.outboundLayer.id]?0:s[e.outboundLayer.id];a=Math.max(a,i),s[e.outboundLayer.id]=a,r[e.outboundLayer.id]=e.outboundLayer,t[e.id]=a;for(let s=0;s<e.inboundLayers.length;s++){const r=e.inboundLayers[s],i=e.nodeIndices[s],o=r.inboundNodes[i],l=null==t[o.id]?0:t[o.id];t[o.id]=Math.max(a+1,l),n[o.id]=o}}const h={};for(const e in t){const s=t[e];s in h||(h[s]=[]),h[s].push(n[e])}const p={};for(const e in s){const t=s[e];t in p||(p[t]=[]),p[t].push(r[e])}let d=Object.keys(p).map((e=>parseInt(e,10))).sort($y);this.layers=[];for(const e of d){const t=p[e];t.sort(((e,t)=>{const n=a[e.id],s=a[t.id];return n<s?-1:n>s?1:0}));for(const e of t)e instanceof Pw&&this.internalContainerRefs.push(e),this.layers.push(e)}this.layersByDepth=p,d=Object.keys(h).map((e=>parseInt(e,10))).sort($y);const f=this.inputs.slice(),m=[];for(const e of d)for(const t of h[e]){const e=t.outboundLayer;if(null!=e){for(const n of t.inputTensors)if(-1===f.indexOf(n))throw new py(`Graph disconnected: cannot obtain value for tensor ${n} at layer "${e.name}". The following previous layers were accessed without issue: ${m}`);for(const e of t.outputTensors)f.push(e);m.push(e.name)}}this.nodesByDepth=h;const g=this.layers.map((e=>e.name));for(const e of g){const t=g.filter((t=>t===e)).length;if(1!==t)throw new py(`The name "${e}" is used ${t} times in the model. All layer names should be unique. Layer names: `+JSON.stringify(g))}this.outboundNodes=[],this.inboundNodes=[],new rx({outboundLayer:this,inboundLayers:[],nodeIndices:[],tensorIndices:[],inputTensors:this.inputs,outputTensors:this.outputs,inputMasks:this.inputs.map((e=>null)),outputMasks:this.outputs.map((e=>null)),inputShapes:this.inputs.map((e=>e.shape)),outputShapes:this.outputs.map((e=>e.shape))}),this.built=!0,this._refCount=1}assertNotDisposed(){if(0===this._refCount)throw new Error(`Container '${this.name}' is already disposed.`)}dispose(){this.assertNotDisposed();const e={refCountAfterDispose:null,numDisposedVariables:0};if(0==--this._refCount){for(const t of this.layers)e.numDisposedVariables+=t.dispose().numDisposedVariables;for(const t of this.internalContainerRefs)e.numDisposedVariables+=t.dispose().numDisposedVariables}return e.refCountAfterDispose=this._refCount,e}get trainable(){return this.trainable_}set trainable(e){this.layers.forEach((t=>{t._trainableWeights.forEach((t=>t.trainable=e))})),this.trainable_=e}get trainableWeights(){if(this._trainableWeights.length>0)throw new dy("Container instance unexpectedly contains _trainableWeights.The trainable weights of a Container are a union of the trainable weights of its consituent Layers. Its own _trainableWeights must remain an empty Array.");if(!this.trainable)return[];let e=[];for(const t of this.layers)e=e.concat(t.trainableWeights);return e}get nonTrainableWeights(){const e=[];for(const t of this.layers)e.push(...t.nonTrainableWeights);if(!this.trainable){const t=[];for(const e of this.layers)t.push(...e.trainableWeights);return t.concat(e)}return e}get weights(){return this.trainableWeights.concat(this.nonTrainableWeights)}loadWeights(e,t=!0){const n={};let s=0;for(const e of this.layers)for(const t of e.weights){if(null!=n[t.originalName])throw new dy(`Duplicate weight name: ${t.originalName}`);n[t.originalName]=t,s++}const r=[];for(const s in e){let a=s;if(null==n[s]){const e=s.split("/");a=e.slice(0,-2).concat([e[e.length-1]]).join("/")}if(null!=n[a])r.push([n[a],e[s]]);else if(t)throw new dy(`Provided weight data has no target variable: ${s}`);delete n[a]}if(t){const e=[];for(const t in n)e.push(t);if(e.length>0)throw new dy(`${e.length} of ${s} weights are not set: ${e}`)}ex(r)}updatedConfig(){const e=this.getConfig(),t={};return t.className=this.getClassName(),t.config=e,t.kerasVersion=`tfjs-layers ${zw}`,t.backend="TensorFlow.js",t}toJSON(e,t=!0){const n=Lw(this.updatedConfig());return t?JSON.stringify(n):n}call(e,t){return fo((()=>{e=vy(e);const n=new cx;for(let t=0;t<this.inputs.length;++t)n.add(this.inputs[t],e[t]);return dx(this.outputs,n,t)}))}computeMask(e,t){return fo((()=>{let n;return e=vy(e),n=null==t?yy(null,e.length):vy(t),this.runInternalGraph(e,n)[1]}))}computeOutputShape(e){const t=qb(e);if(t.length!==this.inputLayers.length)throw new dy(`Invalid inputShape argument ${e}: model has ${this.inputLayers.length} tensor inputs.`);const n={};for(let e=0;e<t.length;e++){const s=this.inputLayers[e],r=t[e];n[s.name+"_0_0"]=r}const s=Object.keys(this.nodesByDepth).map((e=>parseInt(e,10))).sort($y);if(s.length>1)for(const e of s){const t=this.nodesByDepth[e];for(const e of t){const t=e.outboundLayer;if(-1!==this.inputLayers.map((e=>e.id)).indexOf(t.id))continue;const s=[];for(let t=0;t<e.inboundLayers.length;t++){const r=e.inboundLayers[t],a=e.nodeIndices[t],i=e.tensorIndices[t],o=n[`${r.name}_${a}_${i}`];s.push(o)}const r=qb(t.computeOutputShape(wy(s))),a=t.inboundNodes.indexOf(e);for(let e=0;e<r.length;e++){n[`${t.name}_${a}_${e}`]=r[e]}}}const r=[],a=[];for(let e=0;e<this.outputLayers.length;e++){const t=this.outputLayers[e],n=this.outputLayersNodeIndices[e],s=this.outputLayersTensorIndices[e],r=`${t.name}_${n}_${s}`;a.push(r)}for(let e=0;e<a.length;e++){const t=a[e];by(t in n),r.push(n[t])}return wy(r)}runInternalGraph(e,t){null==t&&(t=yy(null,e.length));const n={};for(let s=0;s<this.inputs.length;++s){const r=this.inputs[s],a=e[s],i=t[s];n[r.id]=[a,i]}const s=Object.keys(this.nodesByDepth).map((e=>parseInt(e,10))).sort($y);for(const e of s){const t=this.nodesByDepth[e];for(const e of t){const t=e.outboundLayer,s=e.inputTensors,r=e.outputTensors,a=new Array;for(const e of s)e.id in n&&a.push(n[e.id]);if(a.length===s.length){let s,i,o,l,u={};if(null!=e.callArgs&&(u=e.callArgs),1===a.length){const[e,n]=a[0];null==u.mask&&(u.mask=n),o=vy(t.call(e,u)),l=vy(t.computeMask(e,n)),s=[e],i=[n]}else s=a.map((e=>e[0])),i=a.map((e=>e[1])),null==u.mask&&(u.mask=i),o=vy(t.call(s,u)),l=vy(t.computeMask(s,i));if(t.activityRegularizer)throw new fy("LayersModel invocation with concrete Tensor value(s) in the presence of activity regularizer(s) is not supported yet.");for(let e=0;e<r.length;++e){const t=r[e],s=o[e],a=l[e];n[t.id]=[s,a]}}}}const r=[],a=[],i=[];for(const e of this.outputs){by(e.id in n,`Could not compute output ${e.name} : ${e.id}`);const[t,s]=n[e.id];i.push(t.shape),r.push(t),a.push(s)}return[r,a,i]}buildNodeConversionMap(e){const t={};let n;for(const e of this.layers){n=e instanceof Pw?1:0;for(let s=0;s<e.inboundNodes.length;s++){const r=Pw.nodeKey(e,s);this.containerNodes.has(r)&&(t[r]=n,n+=1)}}return t}getLayer(e,t){if(null!=t){if(this.layers.length<=t)throw new dy(`Was asked to retrieve layer at index ${t}, but model only has ${this.layers.length} layer(s).`);return this.layers[t]}if(null==e)throw new dy("Provide either a layer name or layer index");for(const t of this.layers)if(t.name===e)return t;throw new dy(`No such layer: ${e}`)}calculateLosses(){return fo((()=>{const e=[];for(const t of this.layers)for(let n=0;n<t.inboundNodes.length;++n){const s=Pw.nodeKey(t,n);this.containerNodes.has(s)&&e.push(...t.calculateLosses())}return e}))}getConfig(){const e={name:this.name},t=this.buildNodeConversionMap(this.layers),n=[];for(const e of this.layers){const s=e.getClassName(),r=e.getConfig(),a=[];for(let n=0;n<e.inboundNodes.length;n++){const s=e.inboundNodes[n],r=Pw.nodeKey(e,n);let i={};if(this.containerNodes.has(r)){if(s.callArgs)try{JSON.stringify(s.callArgs),i=s.callArgs}catch(t){console.warn(`Layer ${e.name} was passed non-serializable keyword arguments: ${s.callArgs}. They will not be included in the serialized model (and thus will be missing at deserialization time).`),i={}}if(s.inboundLayers.length>0){const e=[];for(let n=0;n<s.inboundLayers.length;n++){const r=s.inboundLayers[n],a=s.nodeIndices[n],o=s.tensorIndices[n];let l=t[Pw.nodeKey(r,a)];null==l&&(l=0),e.push([r.name,l,o,i])}a.push(e)}}}const i={};i.name=e.name,i.className=s,i.config=r,i.inboundNodes=a,n.push(i)}e.layers=n;const s=[];for(let e=0;e<this.inputLayers.length;e++){const n=this.inputLayers[e],r=this.inputLayersNodeIndices[e],a=Pw.nodeKey(n,r);if(!this.containerNodes.has(a))continue;let i=t[a];null==i&&(i=0);const o=this.inputLayersTensorIndices[e];s.push([n.name,i,o])}e.inputLayers=s;const r=[];for(let e=0;e<this.outputLayers.length;e++){const n=this.outputLayers[e],s=this.outputLayersNodeIndices[e],a=Pw.nodeKey(n,s);if(!this.containerNodes.has(a))continue;let i=t[a];null==i&&(i=0);const o=this.outputLayersTensorIndices[e];r.push([n.name,i,o])}return e.outputLayers=r,e}static fromConfig(e,t,n={},s=!1){const r={},a={};function i(e,t){e.name in a?a[e.name].push(t):a[e.name]=[t]}function o(e,t){const n=[];let s;for(const a of t){const o=a[0],l=a[1],u=a[2];if(s=null==a[3]?{}:a[3],!(o in r))return void i(e,t);const c=r[o];if(c.inboundNodes.length<=l)return void i(e,t);const h=c.inboundNodes[l];n.push(h.outputTensors[u])}n.length>0&&e.apply(wy(n),s)}function l(e){const n=e.name,a=sw(e,null!=t.customObjects?t.customObjects:{});a.setFastWeightInitDuringBuild(s),r[n]=a;e.inboundNodes.forEach((e=>{if(!(e instanceof Array))throw new dy(`Corrupted configuration, expected array for nodeData: ${e}`);i(a,e)}))}const u=t.name,c=t.layers;for(const e of c)l(e);for(;!Ay(a);)for(const e of c){const t=r[e.name];if(t.name in a){const e=a[t.name];delete a[t.name];for(const n of e)o(t,n)}}const h=[],p=[],d=t.inputLayers;for(const e of d){const t=e[0],n=e[1],s=e[2];by(t in r);const a=r[t].inboundNodes[n].outputTensors;h.push(a[s])}const f=t.outputLayers;for(const e of f){const t=e[0],n=e[1],s=e[2];by(t in r);const a=r[t].inboundNodes[n].outputTensors;p.push(a[s])}return new e({inputs:h,outputs:p,name:u})}get stateful(){if(this._stateful)throw new dy("Container instance unexpectedly has _stateful = true. The statefulness of a Container is determined by the Layers it contains. Its _stateful property must remain the default false.");for(const e of this.layers)if(e.stateful)return!0;return!1}resetStates(){fo((()=>{this.layers.forEach((e=>{e.stateful&&e.resetStates()}))}))}}function Bw(e,t,n){const s=t.length;if(null==e||Array.isArray(e)&&0===e.length)return t.map((e=>null));if(1===s)return Array.isArray(e)&&1===e.length?e:"object"==typeof e&&t[0]in e?[e[t[0]]]:[e];if(Array.isArray(e)){if(e.length!==s)throw new Error(`Provided ${n} is an array of ${e.length} element(s), but the model has ${s} outputs. Make sure a set of weights is provided for each model output.`);return e}if("object"==typeof e&&Object.keys(e).length>0&&"object"==typeof e[Object.keys(e)[0]]){const n=[];return t.forEach((t=>{t in e?n.push(e[t]):n.push(null)})),n}throw new Error(`The model has multiple (${s}) outputs, so ${n} must be either an array with ${s} elements or an object with ${t} keys. Provided ${n} not understood: ${JSON.stringify(e)}`)}function Ww(e,t){return Bw(e,t,"classWeight")}async function Vw(e,t,n,s){if(null!=t||null!=s)throw new Error("Support sampleWeight is not implemented yet");if(null!=n){const t=fo((()=>{if(1===e.shape.length)return so(e);if(2===e.shape.length){if(e.shape[1]>1){return Ou(e,1)}if(1===e.shape[1])return sc(e,[e.shape[0]]);throw new Error(`Encountered unexpected last-dimension size (${e.shape[1]}) during handling of class weights. The size is expected to be >= 1.`)}throw new Error(`Unexpected rank of target (y) tensor (${e.rank}) during handling of class weights. The rank is expected to be 1 or 2.`)})),s=Array.from(await t.data());mo(t);const r=[];return s.forEach((e=>{if(null==n[e])throw new Error(`classWeight must contain all classes in the training data. The class ${e} exists in the data but not in classWeight`);r.push(n[e])})),sd(r,"float32")}return null}function Uw(e,t){return Ao(e,t)}function Gw(e,t){let n,s;const r=t;n=r.xs,s=r.ys,ie(null!=n&&null!=s,(()=>`A Dataset iterator for fitDataset() is expected to generate objects of the form \`{xs: xVal, ys: yVal}\`, where the two values may be \`tf.Tensor\`, an array of Tensors, or a map of string to Tensor.  The provided Dataset instead generates ${t}`));const a=Hw("input",e.inputNames,n),i=Hw("output",e.outputNames,s),o=a[0].shape[0];ie(a.length===e.inputs.length,(()=>`LayersModel has ${e.inputs.length} inputs, but the dataset provides ${a.length} inputs.  (Expected input keys: ${JSON.stringify(e.inputNames)})`)),ie(i.length===e.outputs.length,(()=>`LayersModel has ${e.outputs.length} outputs, but the dataset provides ${i.length} outputs.  (Expected output keys: ${JSON.stringify(e.outputNames)})`));for(let t=0;t<a.length;t++)ie(a[t].shape[0]===o,(()=>`Batch size mismatch: input ${e.inputNames[t]} has ${a[t].shape[0]}; expected  ${o} based on input ${e.inputNames[0]}.`));for(let t=0;t<i.length;t++)ie(i[t].shape[0]===o,(()=>`Batch size mismatch: output ${e.outputNames[t]} has ${i[t].shape[0]}; expected  ${o} based on input ${e.inputNames[0]}.`));return{xs:a,ys:i}}function Hw(e,t,n){if(n instanceof ga)return[n];if(Array.isArray(n))return ie(n.length===t.length,(()=>`Received an array of ${n.length} Tensors, but expected ${t.length} to match the ${e} keys ${t}.`)),n;{const s=[];for(const r of t){if(null==n[r])throw new dy(`The feature data generated by the dataset lacks the required ${e} key '${r}'.`);s.push(n[r])}return s}}async function jw(e,t,n){const s=null!=n.batchesPerEpoch;if(ie(null!=e.optimizer,(()=>"You must compile a model before training/testing. Use LayersModel.compile(modelCompileConfig).")),ie(null!=n,(()=>"For fitDataset(), the 2nd argument (config) is required, but it is not provided in this call.")),ie(null!=n.epochs&&n.epochs>0&&Number.isInteger(n.epochs),(()=>`For fitDataset(), config.epochs is expected to be a positive integer, but got ${n.epochs}`)),ie(!s||n.batchesPerEpoch>0&&Number.isInteger(n.batchesPerEpoch),(()=>`For fitDataset(), config.batchesPerEpoch is expected to be a positive integer if specified, but got ${n.batchesPerEpoch}`)),ie(null==n.validationSplit,(()=>"`validationSplit` is not supported by `fitDataset()`. Use validationData instead.")),e.isTraining)throw new Error("Cannot start training because another fit() call is ongoing.");e.isTraining=!0;try{const r=null!=n.validationData;let a,i;if(r)if(qw(n.validationData))ie(null==n.validationBatches||n.validationBatches>0&&Number.isInteger(n.validationBatches),(()=>`For fitDataset() with dataset-based validation, config.validationBatches is expected not to be provided, or to be a positive integer, but got ${n.validationBatches}`));else{const e=function(e){if(3===e.length)throw new fy("Validation with sample weights is not implemented yet.");return{xs:e[0],ys:e[1]}}(n.validationData);a=e.xs,i=e.ys}const o=e.makeTrainFunction(),l=e.getDedupedMetricsNames();let u;u=r?l.slice().concat(l.map((e=>"val_"+e))):l.slice();const c=ew(n.callbacks,n.yieldEvery),h=null==n.verbose?1:n.verbose,{callbackList:p,history:d}=nw(c,h,n.epochs,null,null,function(e,t){let n=null;null!=t.batchesPerEpoch?n=t.batchesPerEpoch:Number.isFinite(e.size)&&(n=e.size);return n}(t,n),null,r,u);p.setModel(e),e.history=d,await p.onTrainBegin(),e.stopTraining_=!1;let f=null==n.initialEpoch?0:n.initialEpoch,m=await t.iterator();for(;f<n.epochs;){const u={};await p.onEpochBegin(f);let c=0,h=0;for(s||(m=await t.iterator());!s||c<n.batchesPerEpoch;){const t=await m.next();if(s&&t.done){console.warn(`You provided \`batchesPerEpoch\` as ${n.batchesPerEpoch}, but your dataset iterator ran out of data after ${c} batches; interrupting training. Make sure that your dataset can generate at least \`batchesPerEpoch * epochs\` batches (in this case, `+n.batchesPerEpoch*n.epochs+" batches). You may need to use the repeat() function when building your dataset.");break}if(null!=t.value){const{xs:s,ys:r}=Gw(e,t.value),a={};a.batch=h,a.size=s[0].shape[0],await p.onBatchBegin(h,a);const i=[];if(null!=n.classWeight){const t=Ww(n.classWeight,e.outputNames);for(let e=0;e<t.length;++e)i.push(await Vw(r[e],null,t[e]))}const u=s.concat(r).concat(i),d=o(u);mo(u);for(let e=0;e<l.length;++e){const t=l[e],n=d[e];a[t]=n,go(n)}await p.onBatchEnd(h,a),qx(a),h++,c++}if(s?c>=n.batchesPerEpoch:t.done){if(r){let t;t=qw(n.validationData)?vy(await e.evaluateDataset(n.validationData,{batches:n.validationBatches})):vy(e.evaluate(a,i,{batchSize:null==n.validationBatchSize?32:n.validationBatchSize,verbose:0}));for(let n=0;n<e.metricsNames.length;++n)u[`val_${e.metricsNames[n]}`]=t[n]}break}if(e.stopTraining_)break}if(await p.onEpochEnd(f,u),f++,e.stopTraining_)break}return await p.onTrainEnd(),await e.history.syncData(),e.history}finally{e.isTraining=!1}}function qw(e){return"function"==typeof e.iterator}function Kw(e){ie(e>0&&Number.isInteger(e),(()=>`batchSize is required to be a positive integer, but got ${e}`))}function Xw(e,t,n){return null==e?[null]:Array.isArray(e)?e.map((e=>cb(e,t,n-t))):cb(e,t,n-t)}function Yw(e,t){return fo((()=>null==e?null:Array.isArray(e)?e.map((e=>Yw(e,t))):bb(e,"int32"===t.dtype?t:no(t,"int32"))))}function Zw(e,t){const n=[];let s=0,r=null;for(;s<e;)r=s+t,r>=e&&(r=e),n.push([s,r]),s=r;return n}function Jw(e){const t=[];e instanceof ga&&(e=[e]);for(let n=0;n<e.length;++n){const s=e[n];if(1===s.rank)t.push(ub(s,1));else{if(0===s.rank)throw new Error("Expected tensor to be at least 1D, but received a 0D tensor (scalar).");t.push(s)}}return t}function Qw(e,t){if(null==e)return;const n=[];if(t instanceof ga)n.push(t.id);else if(Array.isArray(t))t.forEach((e=>n.push(e.id)));else if(null!=t)for(const e in t){const s=t[e];n.push(s.id)}const s=[];if(e instanceof ga)-1===n.indexOf(e.id)&&s.push(e);else if(Array.isArray(e))e.forEach((e=>{-1===n.indexOf(e.id)&&s.push(e)}));else if(null!=e)for(const t in e){const r=e[t];-1===n.indexOf(r.id)&&s.push(r)}s.forEach((e=>{e.isDisposed||e.dispose()}))}function ev(e){return Array.isArray(e)}function tv(e){return!function(e){return e instanceof ga}(e)&&!ev(e)}function nv(e,t,n,s=!0,r=""){if(null==t||0===t.length){if(null!=e){let t=!1;if(ev(e)&&e.length>0)t=!0;else if(tv(e)){for(const n in e)if(e.hasOwnProperty(n)){t=!0;break}}else t=!0;if(t)throw new dy(`Error when checking model ${r} expected no data, but got ${e}`)}return[]}if(null==e)return t.map((e=>null));let a;if(tv(e)){a=[];for(const n of t){if(null==e[n])throw new dy(`No data provided for "${n}". Need data for each key in: ${t}`);a.push(e[n])}}else if(ev(e)){if(e.length!==t.length)throw new dy(`Error when checking model ${r}: the Array of Tensors that you are passing to your model is not the size the model expected. Expected to see ${t.length} Tensor(s), but instead got the following list of Tensor(s): ${e}`);a=e}else{if(t.length>1)throw new dy(`The model ${r} expects ${t.length} Tensor(s), but only received one Tensor. Found: Tensor with shape ${e.shape}`);a=[e]}if(a=Jw(a),null!=n)for(let e=0;e<t.length;++e){if(null==n[e])continue;const i=a[e];if(i.shape.length!==n[e].length)throw new dy(`Error when checking ${r}: expected ${t[e]} to have ${n[e].length} dimension(s). but got array with shape ${i.shape}`);for(let t=0;t<n[e].length;++t){if(0===t&&!s)continue;const a=i.shape[t],o=n[e][t];if(null!=o&&o>=0&&a!==o)throw new dy(`${r} expected a batch of elements where each example has shape [${n[e].slice(1,n[e].length)}] (i.e.,tensor shape [*,${n[e].slice(1,n[e].length)}]) but the ${r} received an input with ${i.shape[0]} examples, each with shape [${i.shape.slice(1,i.shape.length)}] (tensor shape [${i.shape}])`)}}return a}function sv(e,t,n,s=!0,r=""){let a;if(Array.isArray(e)){if(e.length!==t.length)throw new dy(`Error when checking model ${r}: the Array of Tensors that you are passing to your model is not the size the the model expected. Expected to see ${t.length} Tensor(s), but instead got ${e.length} Tensors(s).`);a=e}else{if(t.length>1)throw new dy(`The model expects ${t.length} ${r} Tensors, but only received one Tensor. Found: array with shape ${JSON.stringify(e.shape)}.`);a=[e]}if(null!=n)for(let e=0;e<t.length;++e){if(null==n[e])continue;const i=a[e];if(i.shape.length!==n[e].length)throw new dy(`Error when checking ${r}: expected ${t[e]} to have ${n[e].length} dimension(s), but got array with shape ${JSON.stringify(i.shape)}`);for(let a=0;a<n[e].length;++a){if(0===a&&!s)continue;const o=i.shape[a],l=n[e][a];if(null!=l&&l!==o)throw new dy(`Error when checking ${r}: expected ${t[e]} to have shape ${JSON.stringify(n[e])} but got array with shape ${JSON.stringify(i.shape)}.`)}}}class rv extends Pw{constructor(e){super(e),this.isTraining=!1}summary(e,t,n=console.log){if(!this.built)throw new dy("This model has never been called, thus its weights have not been created yet. So no summary can be displayed. Build the model first (e.g., by calling it on some test data).");Rw(this,e,t,n)}compile(e){if(null==e.loss&&(e.loss=[]),this.loss=e.loss,"string"==typeof e.optimizer)this.optimizer_=function(e){const t={Adagrad:()=>Wf.adagrad(.01),Adadelta:()=>Wf.adadelta(1,.95,ob()),Adam:()=>Wf.adam(.001,.9,.999,ob()),Adamax:()=>Wf.adamax(.002,.9,.999,ob(),0),RMSProp:()=>Wf.rmsprop(.001,.9,0,ob()),SGD:()=>Wf.sgd(.01)};if(t.adagrad=t.Adagrad,t.adadelta=t.Adadelta,t.adam=t.Adam,t.adamax=t.Adamax,t.rmsprop=t.RMSProp,t.sgd=t.SGD,e in t)return t[e]();throw new dy(`Unknown Optimizer ${e}`)}(e.optimizer),this.isOptimizerOwned=!0;else{if(!(e.optimizer instanceof Ho))throw new dy("User-defined optimizer must be an instance of tf.Optimizer.");this.optimizer_=e.optimizer,this.isOptimizerOwned=!1}let t=[];if(Array.isArray(e.loss)||"string"==typeof e.loss||"function"==typeof e.loss)if(Array.isArray(e.loss)){if(e.loss.length!==this.outputs.length)throw new dy(`When passing an Array as loss, it should have one entry per model output. The model has ${this.outputs.length} output(s), but you passed loss=${e.loss}.`);const n=e.loss;t=n.map((e=>mw(e)))}else{const n=mw(e.loss);this.outputs.forEach((e=>{t.push(n)}))}else{e.loss=e.loss;for(const t in e.loss)if(-1===this.outputNames.indexOf(t))throw new dy(`Unknown entry in loss dictionary: "${t}". Only expected the following keys: ${this.outputNames}`);for(const n of this.outputNames)null==e.loss[n]&&console.warn(`Output "${n}" is missing from loss dictionary. We assume this was done on purpose, and we will not be expecting data to be passed to ${n} during training`),t.push(mw(e.loss[n]))}this.lossFunctions=t,this.feedOutputNames=[],this.feedOutputShapes=[],this.feedLossFns=[];for(let e=0;e<this.outputs.length;++e){const t=this.internalOutputShapes[e],n=this.outputNames[e];this.feedOutputNames.push(n),this.feedOutputShapes.push(t),this.feedLossFns.push(this.lossFunctions[e])}const n=[];this.metrics=e.metrics,this.metricsNames=["loss"],this.metricsTensors=[],Zy("loss",(()=>{for(let e=0;e<this.outputs.length;++e){if(-1!==n.indexOf(e))continue;const t=this.lossFunctions[e];this.outputs.length>1&&(this.metricsTensors.push([t,e]),this.metricsNames.push(this.outputNames[e]+"_loss"))}}));const s=function(e,t){if(null==e||Array.isArray(e)&&0===e.length)return t.map((e=>[]));let n;if("string"==typeof e||"function"==typeof e)n=[e];else{if(!Array.isArray(e)&&"object"!=typeof e)throw new TypeError(`Type of metrics argument not understood. Expected an string,function, Array, or Object, found: ${e}`);n=e}if(Array.isArray(n))return t.map((e=>n));{const e=[];for(const s of t){let t=n.hasOwnProperty(s)?n[s]:[];Array.isArray(t)||(t=[t]),e.push(t)}return e}}(e.metrics,this.outputNames),r=(e,t,n)=>{this.outputNames.length>1&&(t=this.outputNames[e]+"_"+t),this.metricsNames.push(t),this.metricsTensors.push([n,e])};Zy("metric",(()=>{for(let e=0;e<this.outputs.length;++e){if(-1!==n.indexOf(e))continue;(t=>{let n,s,a;for(const i of t){if("string"==typeof i&&-1!==["accuracy","acc","crossentropy","ce"].indexOf(i)){const t=this.internalOutputShapes[e];let r;1===t[t.length-1]||this.lossFunctions[e]===hw?-1!==["accuracy","acc"].indexOf(i)?s=gw:-1!==["crossentropy","ce"].indexOf(i)&&(s=vw):this.lossFunctions[e]===cw?-1!==["accuracy","acc"].indexOf(i)?s=kw:-1!==["crossentropy","ce"].indexOf(i)&&(s=Nw):-1!==["accuracy","acc"].indexOf(i)?s=yw:-1!==["crossentropy","ce"].indexOf(i)&&(s=Iw),-1!==["accuracy","acc"].indexOf(i)?r="acc":-1!==["crossentropy","ce"].indexOf(i)&&(r="ce"),a=s,n=""+r}else{const e=Tw(i);a=e,n=""+Cw(i)}let t;Zy(n,(()=>{t=a})),r(e,n,t)}})(s[e])}})),this.collectedTrainableWeights=this.trainableWeights}checkTrainableWeightsConsistency(){null!=this.collectedTrainableWeights&&this.trainableWeights.length!==this.collectedTrainableWeights.length&&console.warn("Discrepancy between trainableweights and collected trainable weights. Did you set `model.trainable` without calling `model.compile()` afterwards?")}evaluate(e,t,n={}){const s=null==n.batchSize?32:n.batchSize;Kw(s);const r=this.standardizeUserDataXY(e,t,!0,s);try{const e=r[0].concat(r[1]);this.makeTestFunction();const t=this.testFunction;return wy(this.testLoop(t,e,s,n.verbose,n.steps))}finally{Qw(r[0],e),Qw(r[1],t)}}async evaluateDataset(e,t){return this.makeTestFunction(),async function(e,t,n){const s=null!=(n=n||{}).batches,r=e.testFunction;let a=[];if(n.verbose>0)throw new fy("Verbose mode is not implemented yet.");ie(!s||n.batches>0&&Number.isInteger(n.batches),(()=>`Test loop expects \`batches\` to be a positive integer, but received ${JSON.stringify(n.batches)}`));const i="function"==typeof t.next?t:await t.iterator();let o=0,l=0;for(;!s||l<n.batches;){const t=await i.next();if(a=fo((()=>{if(t.value){const{xs:n,ys:s}=Gw(e,t.value),i=n.concat(s),u=fo((()=>r(i)));if(mo(i),0===l)for(let e=0;e<u.length;++e)a.push(Wo(0));const c=i[0].shape[0];for(let e=0;e<u.length;++e){const t=u[e],n=a[e];a[e]=fo((()=>Co(a[e],Ao(c,t)))),l>0&&mo(n)}mo(u),o+=c,++l}return a})),t.done){s&&console.warn(`Your dataset iterator ran out of data during evaluateDataset(). Interrupting evalution. Make sure that your dataset can generate at least \`batches\` batches (in this case, ${n.batches} batches). You may need to use the repeat() function when building your dataset.`);break}}for(let e=0;e<a.length;++e){const t=a[e];a[e]=Eo(a[e],o),mo(t)}return wy(a)}(this,e,t)}checkNumSamples(e,t,n,s="steps"){let r;if(null!=n){if(r=null,null!=t)throw new dy(`If ${s} is set, batchSize must be null or undefined.Got batchSize = ${t}`)}else{if(null==e)throw new dy(`Either the input data should have a defined shape, or ${s} shoud be specified.`);r=Array.isArray(e)?e[0].shape[0]:e.shape[0]}return r}execute(e,t){if(Array.isArray(t)&&0===t.length)throw new dy("`outputs` is an empty Array, which is not allowed.");const n=Array.isArray(t),s=n?t:[t],r=this.retrieveSymbolicTensors(s),a=new cx;if(e instanceof ga&&(e=[e]),Array.isArray(e)){if(e.length!==this.inputs.length)throw new dy(`The number of inputs provided (${e.length}) does not match the number of inputs of this model (${this.inputs.length}).`);for(let t=0;t<this.inputs.length;++t)a.add(this.inputs[t],e[t])}else for(const t of this.inputs){const n=e[t.name];if(null==n)throw new dy(`No value is provided for the model's input ${t.name}`);a.add(t,n)}const i=dx(r,a);return n?i:i[0]}retrieveSymbolicTensors(e){const t=yy(null,e.length);let n=e.length;for(const s of this.layers){const r=Array.isArray(s.output)?s.output:[s.output],a=r.map((e=>e.name));for(let s=0;s<e.length;++s){const i=a.indexOf(e[s]);if(-1!==i&&(t[s]=r[i],n--),0===n)break}if(0===n)break}if(n>0){const n=[];throw t.forEach(((t,s)=>{null==t&&n.push(e[s])})),new dy(`Cannot find SymbolicTensors for output name(s): ${JSON.stringify(n)}`)}return t}predictLoop(e,t=32,n=!1){return fo((()=>{const s=this.checkNumSamples(e);if(n)throw new fy("Verbose predictLoop() is not implemented yet.");const r=Zw(s,t),a=this.outputs.map((e=>[]));for(let t=0;t<r.length;++t){fo((()=>{const n=r[t][0],s=r[t][1],a=Xw(e,n,s),i=[];if(Array.isArray(a))for(let e=0;e<a.length;++e)i.push({key:this.inputs[e],value:a[e]});else i.push({key:this.inputs[0],value:a});const o=new cx(i);return dx(this.outputs,o)})).forEach(((e,t)=>a[t].push(e)))}return wy(a.map((e=>ic(e,0))))}))}predict(e,t={}){const n=Jw(e);sv(n,this.inputNames,this.feedInputShapes,!1);try{const e=null==t.batchSize?32:t.batchSize;return Kw(e),this.predictLoop(n,e)}finally{Qw(n,e)}}predictOnBatch(e){sv(e,this.inputNames,this.feedInputShapes,!0);const t=(Array.isArray(e)?e[0]:e).shape[0];return this.predictLoop(e,t)}standardizeUserDataXY(e,t,n=!0,s){if(null==this.optimizer_)throw new py("You must compile a model before training/testing. Use LayersModel.compile(modelCompileArgs).");const r=[];for(let e=0;e<this.feedOutputShapes.length;++e){const t=this.feedOutputShapes[e];this.feedLossFns[e]===cw?r.push(t.slice(0,t.length-1).concat([1])):r.push(t)}if(function(e,t,n){const s=Ey(e.map((e=>e.shape[0])));s.sort();const r=Ey(t.map((e=>e.shape[0])));if(r.sort(),s.length>1)throw new dy(`All input Tensors (x) should have the same number of samples. Got array shapes: ${JSON.stringify(e.map((e=>e.shape)))}`);if(r.length>1)throw new dy(`All target Tensors (y) should have the same number of samples. Got array shapes: ${JSON.stringify(t.map((e=>e.shape)))}`);if(s.length>0&&r.length>0&&!pe(s,r))throw new dy(`Input Tensors should have the same number of samples as target Tensors. Found ${s[0]} input sample(s) and ${r[0]} target sample(s).`)}(e=nv(e,this.feedInputNames,this.feedInputShapes,!1,"input"),t=nv(t,this.feedOutputNames,r,!1,"target")),function(e,t,n){const s=[aw,hw,uw];for(let r=0;r<e.length;++r){const a=e[r],i=t[r],o=n[r];if(null!=i){if(i===uw&&1===a.shape[a.shape.length-1])throw new dy(`You are passing a target array of shape ${a.shape} while using a loss 'categorical_crossentropy'. 'categorical_crossentropy'expects targets to be binary matrices (1s and 0s) of shape [samples, classes].`);if(-1!==s.indexOf(i)){const e=a.shape.slice(1),t=o.slice(1);for(let n=0;n<e.length;++n){const s=e[n],r=t[n];if(null!=r&&s!==r)throw new dy(`A target Tensor with shape ${a.shape} was passed for an output of shape ${o}, while using a loss function that expects targets to have the same shape as the output.`)}}}}}(t,this.feedLossFns,this.feedOutputShapes),this.stateful&&null!=s&&s>0&&e[0].shape[0]%s!=0)throw new dy(`In a stateful network, you should only pass inputs with a number of samples that is divisible by the batch size ${s}. Found: ${e[0].shape[0]} sample(s).`);return[e,t]}async standardizeUserData(e,t,n,s,r=!0,a){const[i,o]=this.standardizeUserDataXY(e,t,r,a);if(null!=n)throw new Error("sample weight is not supported yet.");let l=null;if(null!=s){const e=Ww(s,this.outputNames);l=[];for(let t=0;t<e.length;++t)l.push(await Vw(o[t],null,e[t]))}return[i,o,l]}testLoop(e,t,n,s=0,r){return fo((()=>{const a=this.checkNumSamples(t,n,r,"steps"),i=[];if(s>0)throw new fy("Verbose mode is not implemented yet.");if(null!=r)throw new fy("steps mode in testLoop() is not implemented yet");{const s=Zw(a,n),r=sd(ab(0,a));for(let n=0;n<s.length;++n){const a=s[n][0],o=s[n][1],l=cb(r,a,o-a),u=Yw(t,l),c=e(u);if(0===n)for(let e=0;e<c.length;++e)i.push(Wo(0));for(let e=0;e<c.length;++e){const t=c[e];i[e]=Co(i[e],Ao(o-a,t))}}for(let e=0;e<i.length;++e)i[e]=Eo(i[e],a)}return i}))}getDedupedMetricsNames(){const e=this.metricsNames,t=[];for(let n=0;n<e.length;++n){const s=e[n];let r=s;if(xy(e,s)>1){r+=`_${xy(e.slice(0,n),s)}`}t.push(r)}return t}makeTrainFunction(){return e=>{const t=[],n=e.slice(0,this.inputs.length),s=e.slice(this.inputs.length,this.inputs.length+this.outputs.length),r=e.slice(this.inputs.length+this.outputs.length,this.inputs.length+2*this.outputs.length),a=[],i=this.collectedTrainableWeights.map((e=>e.read()));return[this.optimizer_.minimize((()=>{const e=[];for(let t=0;t<this.inputs.length;++t)e.push({key:this.inputs[t],value:n[t]});const i=new cx(e),o=dx(this.outputs,i,{training:!0});let l;for(let e=0;e<this.lossFunctions.length;++e){let n=(0,this.lossFunctions[e])(s[e],o[e]);null!=r[e]&&(n=Uw(n,r[e]));const a=Uh(n);t.push(a),l=0===e?n:Co(l,n)}for(let e=0;e<this.metricsTensors.length;++e){let n;if(this.outputs.length>1&&e<this.outputs.length)n=t[e];else{const t=this.metricsTensors[e][0],r=this.metricsTensors[e][1];n=Uh(t(s[r],o[r]))}go(n),a.push(n)}return l=Uh(l),this.calculateLosses().forEach((e=>{l=Co(l,e)})),l}),!0,i)].concat(a)}}makeTestFunction(){this.testFunction=e=>fo((()=>{const t=[];let n;const s=e.slice(0,this.inputs.length),r=e.slice(this.inputs.length,this.inputs.length+this.outputs.length),a=[];for(let e=0;e<this.inputs.length;++e)a.push({key:this.inputs[e],value:s[e]});const i=new cx(a),o=dx(this.outputs,i);for(let e=0;e<this.lossFunctions.length;++e){const s=this.lossFunctions[e],a=Uh(s(r[e],o[e]));n=0===e?a:Co(n,a),t.push(n)}for(let e=0;e<this.metricsTensors.length;++e){const n=this.metricsTensors[e][0],s=this.metricsTensors[e][1],a=Uh(n(r[s],o[s]));t.push(a)}return t}))}async fit(e,t,n={}){if(this.isTraining)throw new Error("Cannot start training because another fit() call is ongoing.");let s,r,a,i,o,l,u,c,h;this.isTraining=!0;try{const p=null==n.batchSize?32:n.batchSize;Kw(p);const d=!1,f=await this.standardizeUserData(e,t,n.sampleWeight,n.classWeight,d,p);s=f[0],r=f[1],h=f[2];let m,g=!1;if(null!=n.validationData&&n.validationData.length>0){if(g=!0,2!==n.validationData.length)throw 3===n.validationData.length?new fy("validationData including sample weights is not supported yet."):new dy(`When passing validation data, it must contain 2 (valX, valY) or 3 (valX, valY, valSampleWeight) items; ${n.validationData} is invalid.`);o=n.validationData[0],l=n.validationData[1];const e=!0,t=await this.standardizeUserData(o,l,null,null,e,p);u=t[0],c=t[1],m=u.concat(c)}else if(null!=n.validationSplit&&n.validationSplit>0&&n.validationSplit<1){g=!0;const e=Math.floor(s[0].shape[0]*(1-n.validationSplit)),t=s[0].shape[0];u=Xw(s,e,t),a=s,s=Xw(s,0,e),c=Xw(r,e,t),i=r,r=Xw(r,0,e),m=u.concat(c)}else null!=n.validationSteps&&(g=!0);const y=s.concat(r).concat(h);this.checkTrainableWeightsConsistency();const b=this.makeTrainFunction(),x=this.getDedupedMetricsNames();let w,v;g?(this.makeTestFunction(),w=this.testFunction,v=x.slice().concat(x.map((e=>"val_"+e)))):(w=null,m=[],v=x.slice());const k=ew(n.callbacks,n.yieldEvery);return await this.fitLoop(b,y,x,p,n.epochs,n.verbose,k,w,m,n.shuffle,v,n.initialEpoch,null,null)}finally{this.isTraining=!1,Qw(s,e),Qw(r,t),Qw(a,e),Qw(i,t),Qw(u,o),Qw(c,l),null!=h&&mo(h)}}async fitLoop(e,t,n,s,r,a,i,o,l,u,c,h,p,d){null==s&&(s=32),null==r&&(r=1),null==u&&(u=!0),null==h&&(h=0);let f=!1;if(null!=o&&null!=l&&(f=!0),null!=d&&(f=!0,null==p))throw new dy("Can only use `validationSteps` when doing step-wise training, i.e., `stepsPerEpoch` must be set.");const m=this.checkNumSamples(t,s,p,"steps_per_epoch");let g;null!=m&&(g=ab(0,m)),null==a&&(a=1);const{callbackList:y,history:b}=nw(i,a,r,h,m,p,s,f,c);y.setModel(this),this.history=b,await y.onTrainBegin(),this.stopTraining_=!1;for(let a=h;a<r;++a){await y.onEpochBegin(a);const r={};if(null!=p)throw new fy("stepsPerEpoch mode is not implemented yet.");{if("batch"===u)throw new fy("batch shuffling is not implemneted yet");u&&J(g);const a=sd(g),i=Zw(m,s);for(let u=0;u<i.length;++u){const c={};if(await y.onBatchBegin(u,c),fo((()=>{const h=i[u][0],p=i[u][1],d=cb(a,h,p-h);c.batch=u,c.size=p-h;const m=Yw(t,d),g=e(m);for(let e=0;e<n.length;++e){const t=n[e],s=g[e];c[t]=s,go(s)}if(u===i.length-1&&f){const e=this.testLoop(o,l,s);for(let t=0;t<n.length;++t){const s=n[t],a=e[t];go(a),r["val_"+s]=a}}})),await y.onBatchEnd(u,c),qx(c),this.stopTraining_)break}a.dispose()}if(await y.onEpochEnd(a,r),this.stopTraining_)break}return await y.onTrainEnd(),await this.history.syncData(),this.history}async fitDataset(e,t){return jw(this,e,t)}async trainOnBatch(e,t){const n=await this.standardizeUserData(e,t),s=n[0],r=n[1],a=this.makeTrainFunction()(s.concat(r)),i=[];for(const e of a){const t=await e.data();i.push(t[0])}return mo(a),Qw(n[0],e),Qw(n[1],t),wy(i)}getNamedWeights(e){const t=[],n=null!=e&&e.trainableOnly,s=n?this.trainableWeights:this.weights,r=this.getWeights(n);for(let e=0;e<s.length;++e)n&&!s[e].trainable||t.push({name:s[e].originalName,tensor:r[e]});return t}set stopTraining(e){this.stopTraining_=e}get stopTraining(){return this.stopTraining_}get optimizer(){return this.optimizer_}set optimizer(e){this.optimizer_!==e&&(this.optimizer_=e,this.isOptimizerOwned=!1)}dispose(){const e=super.dispose();if(0===e.refCountAfterDispose&&null!=this.optimizer&&this.isOptimizerOwned){const t=ho().numTensors;this.optimizer_.dispose(),e.numDisposedVariables+=t-ho().numTensors}return e}getLossIdentifiers(){let e;if("string"==typeof this.loss)e=ky(this.loss);else if(Array.isArray(this.loss)){for(const e of this.loss)if("string"!=typeof e)throw new Error("Serialization of non-string loss is not supported.");e=this.loss.map((e=>ky(e)))}else{const t=Object.keys(this.loss);e={};const n=this.loss;for(const s of t){if("string"!=typeof n[s])throw new Error("Serialization of non-string loss is not supported.");e[s]=ky(n[s])}}return e}getMetricIdentifiers(){if("string"==typeof this.metrics||"function"==typeof this.metrics)return[ky(Cw(this.metrics))];if(Array.isArray(this.metrics))return this.metrics.map((e=>ky(Cw(e))));{const e={};for(const t in this.metrics)e[t]=ky(Cw(this.metrics[t]));return e}}getTrainingConfig(){return{loss:this.getLossIdentifiers(),metrics:this.getMetricIdentifiers(),optimizer_config:{class_name:this.optimizer.getClassName(),config:this.optimizer.getConfig()}}}loadTrainingConfig(e){if(null!=e.weighted_metrics)throw new Error("Loading weight_metrics is not supported yet.");if(null!=e.loss_weights)throw new Error("Loading loss_weights is not supported yet.");if(null!=e.sample_weight_mode)throw new Error("Loading sample_weight_mode is not supported yet.");const t=sw(Mw(e.optimizer_config));let n,s;if("string"==typeof e.loss)n=Iy(e.loss);else if(Array.isArray(e.loss))n=e.loss.map((e=>Iy(e)));else if(null!=e.loss){n={};for(const t in e.loss)n[t]=Iy(e.loss[t])}if(Array.isArray(e.metrics))s=e.metrics.map((e=>Iy(e)));else if(null!=e.metrics){s={};for(const t in e.metrics)s[t]=Iy(e.metrics[t])}this.compile({loss:n,metrics:s,optimizer:t})}async save(e,t){if("string"==typeof e){const t=wi(e);if(0===t.length)throw new dy(`Cannot find any save handlers for URL '${e}'`);if(t.length>1)throw new dy(`Found more than one (${t.length}) save handlers for URL '${e}'`);e=t[0]}if(null==e.save)throw new dy("LayersModel.save() cannot proceed because the IOHandler provided does not have the `save` attribute defined.");const n=await ri(this.getNamedWeights(t)),s={modelTopology:this.toJSON(null,!1),format:"layers-model",generatedBy:`TensorFlow.js tfjs-layers v${zw}`,convertedBy:null};if(null!=t&&t.includeOptimizer&&null!=this.optimizer){s.trainingConfig=this.getTrainingConfig();const e="optimizer",{data:t,specs:r}=await ri(await this.optimizer.getWeights(),e);n.specs.push(...r),n.data=ui([n.data,t])}if(null!=this.userDefinedMetadata){const e=!0;Ew(this.userDefinedMetadata,this.name,e),s.userDefinedMetadata=this.userDefinedMetadata}return s.weightData=n.data,s.weightSpecs=n.specs,e.save(s)}setUserDefinedMetadata(e){Ew(e,this.name),this.userDefinedMetadata=e}getUserDefinedMetadata(){return this.userDefinedMetadata}}rv.className="Model",Go(rv);class av extends rv{}async function iv(e,t){"modelTopology"in e||(e={modelTopology:e});let n=e.modelTopology;null!=n.model_config&&(n=n.model_config);const s=sw(Mw(n),t);if(null!=e.weightsManifest){const t=await fl(e.weightsManifest,e.pathPrefix,s.weights.map((e=>e.originalName))),n={};for(const e of s.weights)n[e.originalName]=t[e.originalName];s.loadWeights(n),mo(t)}return s}async function ov(e,t){if(null==t&&(t={}),"string"==typeof e){const n=vi(e,t);if(0===n.length)n.push(wl(e,t));else if(n.length>1)throw new dy(`Found more than one (${n.length}) load handlers for URL '${e}'`);e=n[0]}return async function(e,t,n){null==n&&(n={});if(null==e.load)throw new dy("Cannot proceed with model loading because the IOHandler provided does not have the `load` method implemented.");const s=await e.load();let r=s.modelTopology;null!=r.model_config&&(r=r.model_config);const a=null==n.strict||n.strict,i=null!=s.weightData&&null!=s.weightSpecs&&a,o=sw(Mw(r),t,i),l=s.trainingConfig;null!=l&&o.loadTrainingConfig(l);null!=s.userDefinedMetadata&&o.setUserDefinedMetadata(s.userDefinedMetadata);if(null!=s.weightData){if(null==s.weightSpecs)throw new dy("LayersModel artifacts contains weight data, but not weight specs. Therefore loading of weights cannot proceed.");const{modelWeights:e,optimizerWeights:t}=function(e,t){const n=ai(e,t),s={},r=[];return t.forEach((e=>{"optimizer"===e.group?r.push({name:e.name,tensor:n[e.name]}):s[e.name]=n[e.name]})),{modelWeights:s,optimizerWeights:r}}(s.weightData,s.weightSpecs);o.loadWeights(e,a),null!=o.optimizer&&t.length>0&&await o.optimizer.setWeights(t),mo(e),mo(t.map((e=>e.tensor)))}return o}(e,void 0,t)}av.className="Functional",Go(av);class lv extends rv{constructor(e){if(super({inputs:[],outputs:[]}),e=e||{},this.trainable=!0,this.built=!1,this.name=null!=e.name?e.name:Py("sequential_"),null!=e.layers)for(const t of e.layers)this.add(t)}checkShape(e){if(e.inboundNodes[0].outputTensors[0].shape.some((e=>e<0)))throw new dy(`Negative dimension size caused by adding layer ${e.name} with input shape [${e.inboundNodes[0].inputTensors[0].shape}]`)}add(e){const t=e instanceof lv||e instanceof rv;let n;if(t){if(n=e,1!==n.outputs.length)throw new dy("All layers in a Sequential model should have a single output tensor. For multi-output layers, use the functional API.");if(1!==n.inputs.length)throw new dy("All layers in a Sequential model should have a single input tensor. For multi-input layers, use the functional API.")}if(0===this.outputs.length){if(0===e.inboundNodes.length){if(null==e.batchInputShape)throw new dy("The first layer in a Sequential model must get an `inputShape` or `batchInputShape` argument.");const t=ux({batchShape:e.batchInputShape,dtype:e.dtype,name:e.name+"_input"});e.apply(t)}if(t)this.outputs=n.outputs,this.inputs=n.inputs;else{if(1!==e.inboundNodes.length)throw new dy(`A layer added to a Sequential model must not already be connected somewhere else. LayersModel received layer ${e.name} which has ${e.inboundNodes.length} pre-existing inbound connections.`);if(1!==e.inboundNodes[0].outputTensors.length)throw new dy("All layers in a Sequential model should have a single output tensor. For multi-output layers, use the functional API.");this.checkShape(e),this.outputs=[e.inboundNodes[0].outputTensors[0]],this.inputs=ox(this.outputs[0])}this.inboundNodes=[],new rx({outboundLayer:this,inboundLayers:[],nodeIndices:[],tensorIndices:[],inputTensors:this.inputs,outputTensors:this.outputs,inputMasks:yy(null,this.inputs.length),outputMasks:[null],inputShapes:this.inputs.map((e=>e.shape)),outputShapes:this.outputs[0].shape})}else{const t=e.apply(this.outputs[0]);if(Array.isArray(t))throw new TypeError("All layers in a Sequential model should have a single output tensor. For multi-output layers, use the functional API.");this.checkShape(e),this.outputs=[t],this.inboundNodes[0].outputTensors=this.outputs,this.inboundNodes[0].outputShapes=[this.outputs[0].shape]}this.layers.push(e),this.built=!1}pop(){if(0===this.layers.length)throw new TypeError("There are no layers in the model.");if(this.layers.pop(),0===this.layers.length)this.outputs=[],this.inboundNodes=[],this.outboundNodes=[];else{const e=this.layers.length-1;this.layers[e].outboundNodes=[],this.outputs=[this.layers[e].output],this.inboundNodes[0].outputTensors=this.outputs,this.inboundNodes[0].outputShapes=[this.outputs[0].shape]}}call(e,t){return null==this.model&&this.build(),this.model.call(e,t)}build(e){if(Xb(e),0===this.inputs.length||0===this.outputs.length)throw new TypeError("Sequential model cannot be built: model is empty. Add some layers first.");this.model=new rv({inputs:this.inputs,outputs:this.outputs[0],name:this.name+"_model"}),this.model.trainable=this.trainable,this.supportsMasking=this.model.supportsMasking,this.inputLayers=this.model.inputLayers,this.inputLayersNodeIndices=this.model.inputLayersNodeIndices,this.inputLayersTensorIndices=this.model.inputLayersTensorIndices,this.outputLayers=this.model.outputLayers,this.outputLayersNodeIndices=this.model.outputLayersNodeIndices,this.outputLayersTensorIndices=this.model.outputLayersTensorIndices,this.nodesByDepth=this.model.nodesByDepth,this.containerNodes=this.model.containerNodes,this.outputNames=this.model.outputNames,this.inputNames=this.model.inputNames,this.built=!0}countParams(){return this.built||this.build(),super.countParams()}summary(e,t,n=console.log){this.built||this.build(),super.summary(e,t,n)}setWeights(e){null==this.model&&this.build(),this.model.setWeights(e)}evaluate(e,t,n={}){if(!this.built)throw new py("The model needs to be compiled before being used.");return this.model.evaluate(e,t,n)}async evaluateDataset(e,t){if(!this.built)throw new py("The model needs to be compiled before being used.");return this.model.evaluateDataset(e,t)}predict(e,t={}){return null==this.model&&this.build(),this.model.predict(e,t)}predictOnBatch(e){return null==this.model&&this.build(),this.model.predictOnBatch(e)}compile(e){this.build(),this.model.compile(e),this.optimizer_=this.model.optimizer,this.isOptimizerOwned=this.model.isOptimizerOwned,this.loss=this.model.loss,this.metrics=this.model.metrics,this.metricsTensors=this.model.metricsTensors,this.metricsNames=this.model.metricsNames}get optimizer(){return null==this.model?void 0:this.model.optimizer}set optimizer(e){this.model.optimizer=e}async fit(e,t,n={}){if(!this.built)throw new py("The model needs to be compiled before being used.");return this.model.fit(e,t,n)}async fitDataset(e,t){if(!this.built)throw new py("The model needs to be compiled before being used.");return this.model.fitDataset(e,t)}async trainOnBatch(e,t){return this.model.trainOnBatch(e,t)}static fromConfig(e,t,n={},s=!1){let r,a={};if(t instanceof Array){if(null==t[0].className||"Merge"===t[0].className)throw new dy("Legacy serialization format not supported yet.");r=t}else ie(null!=t.layers,(()=>"When the config data for a Sequential model is not an Array, it must be an Object that contains the 'layers' field.")),r=t.layers,delete t.layers,a=t;const i=new e(a);if(!(i instanceof lv))throw new fy(`Sequential.fromConfig called on non-Sequential input: ${i}`);for(const e of r){const t=sw(e,void 0,s);s&&t.setFastWeightInitDuringBuild(!0),i.add(t)}return i}set stopTraining(e){if(null==this.model)throw new dy("Cannot set the stopTraining property of a sequential model before it is compiled.");this.model.stopTraining=e}get stopTraining(){if(null==this.model)throw new dy("Cannot get the stopTraining property of a sequential model before it is compiled.");return this.model.stopTraining}getConfig(){const e=[];for(const t of this.layers){const n={};n.className=t.getClassName(),n.config=t.getConfig(),e.push(n)}return{name:this.name,layers:e}}}function uv(e){return new rv(e)}function cv(e){return new lv(e)}function hv(e){return ux(e)}function pv(e,t){tw.registerCallbackConstructor(e,t)}lv.className="Sequential",Go(lv);class dv extends Vo{getConfig(){return{}}}class fv extends dv{apply(e,t=1){return function(e,t=1){if(1!==t)throw new fy(`Support for alpha values other than 1 (${t}) is not implemented yet.`);return qc(e)}(e,t)}}fv.className="elu",Go(fv);class mv extends dv{apply(e){return Op(e)}}mv.className="selu",Go(mv);class gv extends dv{apply(e){return Tp(e)}}gv.className="relu",Go(gv);class yv extends dv{apply(e){return fo((()=>qh(6,Tp(e))))}}yv.className="relu6",Go(yv);class bv extends dv{apply(e){return e}}bv.className="linear",Go(bv);class xv extends dv{apply(e){return oc(e)}}xv.className="sigmoid",Go(xv);class wv extends dv{apply(e){return function(e){return fo((()=>{const t=Co(.5,Ao(.2,e));return vc(t,0,1)}))}(e)}}wv.className="hardSigmoid",Go(wv);class vv extends dv{apply(e){return Eh(e)}}vv.className="softplus",Go(vv);class kv extends dv{apply(e){return function(e){return fo((()=>Eo(e,Co(Jo(e),1))))}(e)}}kv.className="softsign",Go(kv);class Iv extends dv{apply(e){return uc(e)}}Iv.className="tanh",Go(Iv);class Nv extends dv{apply(e,t=-1){return Hp(e,t)}}Nv.className="softmax",Go(Nv);class Sv extends dv{apply(e,t=-1){return Rh(e,t)}}Sv.className="logSoftmax",Go(Sv);class Tv extends dv{apply(e,t=1){return fo((()=>Ao(oc(Ao(e,t)),e)))}}Tv.className="swish",Go(Tv);class Cv extends dv{apply(e){return fo((()=>Ao(e,uc(Eh(e)))))}}function $v(e){return e.getClassName()}function Ev(e,t={}){return Cy(e,Uo.getMap().classNameMap,t,"activation")}function Av(e){if(null==e){const e={className:"linear",config:{}};return Ev(e)}if("string"==typeof e){const t={};return t.className=e,t.config={},Ev(t)}return e instanceof dv?e:Ev(e)}function Rv(e){if(null!=e&&"object"!=typeof e)throw new Error(`Argument to L1L2 regularizer's constructor is expected to be an object, but received: ${e}`)}Cv.className="mish",Go(Cv);class Fv extends Vo{}class _v extends Fv{constructor(e){super(),Rv(e),this.l1=null==e||null==e.l1?.01:e.l1,this.l2=null==e||null==e.l2?.01:e.l2,this.hasL1=0!==this.l1,this.hasL2=0!==this.l2}apply(e){return fo((()=>{let t=Gh([1]);return this.hasL1&&(t=Co(t,ih(Ao(this.l1,Jo(e))))),this.hasL2&&(t=Co(t,ih(Ao(this.l2,xb(e))))),sc(t,[])}))}getConfig(){return{l1:this.l1,l2:this.l2}}static fromConfig(e,t){return new e({l1:t.l1,l2:t.l2})}}_v.className="L1L2",Go(_v);const Dv={l1l2:"L1L2"};function Ov(e){return Sy(e)}function Mv(e,t={}){return Cy(e,Uo.getMap().classNameMap,t,"regularizer")}function Lv(e){if(null==e)return null;if("string"==typeof e){return Mv({className:e in Dv?Dv[e]:e,config:{}})}return e instanceof Fv?e:Mv(e)}class zv extends ix{constructor(e){super(null==e?{}:e),this.supportsMasking=!0,null!=e&&(this.maxValue=e.maxValue)}call(e,t){e=Kb(e);let n=Tp(e);return null!=this.maxValue&&(n=vc(n,0,this.maxValue)),n}computeOutputShape(e){return e}getConfig(){const e={maxValue:this.maxValue},t=super.getConfig();return Object.assign(e,t),e}}zv.className="ReLU",Go(zv);class Pv extends ix{constructor(e){super(null==e?{}:e),this.DEFAULT_ALPHA=.3,null==e&&(e={}),this.alpha=null==e.alpha?this.DEFAULT_ALPHA:e.alpha}call(e,t){const n=Kb(e);return kh(n,this.alpha)}computeOutputShape(e){return e}getConfig(){const e={alpha:this.alpha},t=super.getConfig();return Object.assign(e,t),e}}Pv.className="LeakyReLU",Go(Pv);class Bv extends ix{constructor(e){if(super(null==e?{}:e),this.DEFAULT_ALPHA_INITIALIZER="zeros",null==e&&(e={}),this.supportsMasking=!0,this.alphaInitializer=Hb(e.alphaInitializer||this.DEFAULT_ALPHA_INITIALIZER),this.alphaRegularizer=Lv(e.alphaRegularizer),this.alphaConstraint=Tx(e.alphaConstraint),null==e.sharedAxes)this.sharedAxes=null;else if(Array.isArray(e.sharedAxes))this.sharedAxes=e.sharedAxes;else{if("number"!=typeof e.sharedAxes)throw new dy(`Expected sharedAxes to be a number or an array of numbers, but got ${e.sharedAxes}`);this.sharedAxes=[e.sharedAxes]}}build(e){const t=(e=Xb(e)).slice(1);if(null!=this.sharedAxes)for(const e of this.sharedAxes)t[e-1]=1;this.alpha=this.addWeight("alpha",t,"float32",this.alphaInitializer,this.alphaRegularizer,!0,this.alphaConstraint);const n={};if(null!=this.sharedAxes)for(let t=1;t<e.length;++t)n[t]=e[t];this.inputSpec=[new tx({ndim:e.length,axes:n})],this.built=!0}call(e,t){return e=Kb(e),up(e,this.alpha.read())}getConfig(){const e={alphaInitializer:Gb(this.alphaInitializer),alphaRegularizer:Ov(this.alphaRegularizer),alphaConstraint:Nx(this.alphaConstraint),sharedAxes:this.sharedAxes},t=super.getConfig();return Object.assign(e,t),e}}Bv.className="PReLU",Go(Bv);class Wv extends ix{constructor(e){if(super(null==e?{}:e),this.DEFAULT_ALPHA=1,null==e&&(e={}),null!=e.alpha&&e.alpha!==this.DEFAULT_ALPHA)throw new fy(`Non-default alpha value (${e.alpha}) is not supported by the ELU layer yet.`);this.alpha=null==e.alpha?this.DEFAULT_ALPHA:e.alpha}call(e,t){const n=Kb(e);return qc(n)}computeOutputShape(e){return e}getConfig(){const e={alpha:this.alpha},t=super.getConfig();return Object.assign(e,t),e}}Wv.className="ELU",Go(Wv);class Vv extends ix{constructor(e){super(null==e?{}:e),this.DEFAULT_THETA=1,null==e&&(e={}),this.theta=null==e.theta?this.DEFAULT_THETA:e.theta}call(e,t){const n=Kb(e);return Ao(n,no(yh(n,this.theta),"float32"))}computeOutputShape(e){return e}getConfig(){const e={theta:this.theta},t=super.getConfig();return Object.assign(e,t),e}}Vv.className="ThresholdedReLU",Go(Vv);class Uv extends ix{constructor(e){super(null==e?{}:e),this.DEFAULT_AXIS=1,null==e&&(e={}),this.softmax=(new Nv).apply,this.axis=null==e.axis?this.DEFAULT_AXIS:e.axis}call(e,t){const n=Kb(e);return this.softmax(n,this.axis)}computeOutputShape(e){return e}getConfig(){const e={axis:this.axis},t=super.getConfig();return Object.assign(e,t),e}}function Gv(e,t,n){if("number"==typeof e)return yy(e,t);if(e.length!==t)throw new dy(`The ${n} argument must be an integer or tuple of ${t} integers. Received: ${e.length} elements.`);for(let r=0;r<t;++r){const a=e[r];if((s=a)!==parseInt(s.toString(),10))throw new dy(`The ${n} argument must be an integer or tuple of ${t} integers. Received: ${JSON.stringify(e)} including a non-integer number ${a}`)}return e;var s}function Hv(e,t,n,s,r=1){if(null==e)return e;let a;return a="same"===n?e:e-(t+(t-1)*(r-1))+1,Math.floor((a+s-1)/s)}function jv(e,t,n,s){if(null==e)return null;if("valid"===s)e=e*t+rb([n-t,0]);else{if("same"!==s)throw new dy(`Unsupport padding mode: ${s}.`);e*=t}return e}function qv(e,t){return fo((()=>(jy(t),"channelsFirst"===t?_l(e,[0,2,3,1]):e)))}function Kv(e,t){return fo((()=>(jy(t),"channelsFirst"===t?_l(e,[0,2,3,4,1]):e)))}function Xv(e,t,n,s=1,r="valid",a,i=1){return fo((()=>{if(null==a&&(a="channelsLast"),jy(a),3!==e.shape.length)throw new dy(`The input of a conv1dWithBias operation should be 3, but is ${e.shape.length} instead.`);if(3!==t.shape.length)throw new dy(`The kernel for a conv1dWithBias operation should be 3, but is ${t.shape.length} instead`);if(null!=n&&1!==n.shape.length)throw new dy(`The bias for a conv1dWithBias operation should be 1, but is ${t.shape.length} instead`);if("channelsFirst"===a&&(e=_l(e,[0,2,1])),"causal"===r)throw new fy("The support for CAUSAL padding mode in conv1dWithBias is not implemented yet.");let o=Cc(e,t,s,"same"===r?"same":"valid","NWC",i);return null!=n&&(o=vb(o,n)),o}))}function Yv(e,t,n,s=[1,1],r="valid",a,i,o=null){return fo((()=>{if(null==a&&(a="channelsLast"),jy(a),3!==e.rank&&4!==e.rank)throw new dy(`conv2dWithBiasActivation expects input to be of rank 3 or 4, but received ${e.rank}.`);if(3!==t.rank&&4!==t.rank)throw new dy(`conv2dWithBiasActivation expects kernel to be of rank 3 or 4, but received ${e.rank}.`);let l=qv(e,a);if("causal"===r)throw new fy("The support for CAUSAL padding mode in conv1dWithBias is not implemented yet.");return l=Fd({x:l,filter:t,strides:s,pad:"same"===r?"same":"valid",dilations:i,dataFormat:"NHWC",bias:n,activation:o}),"channelsFirst"===a&&(l=_l(l,[0,3,1,2])),l}))}function Zv(e,t,n,s=[1,1,1],r="valid",a,i){return fo((()=>{if(null==a&&(a="channelsLast"),jy(a),4!==e.rank&&5!==e.rank)throw new dy(`conv3dWithBias expects input to be of rank 4 or 5, but received ${e.rank}.`);if(4!==t.rank&&5!==t.rank)throw new dy(`conv3dWithBias expects kernel to be of rank 4 or 5, but received ${e.rank}.`);let o=Kv(e,a);if("causal"===r)throw new fy("The support for CAUSAL padding mode in conv3dWithBias is not implemented yet.");return o=Ac(o,t,s,"same"===r?"same":"valid","NDHWC",i),null!=n&&(o=vb(o,n)),"channelsFirst"===a&&(o=_l(o,[0,4,1,2,3])),o}))}Uv.className="Softmax",Go(Uv);class Jv extends ix{constructor(e,t){if(super(t),this.bias=null,this.DEFAULT_KERNEL_INITIALIZER="glorotNormal",this.DEFAULT_BIAS_INITIALIZER="zeros",Jv.verifyArgs(t),this.rank=e,_y(this.rank,"rank"),1!==this.rank&&2!==this.rank&&3!==this.rank)throw new fy(`Convolution layer for rank other than 1, 2, or 3 (${this.rank}) is not implemented yet.`);if(this.kernelSize=Gv(t.kernelSize,e,"kernelSize"),this.strides=Gv(null==t.strides?1:t.strides,e,"strides"),this.padding=null==t.padding?"valid":t.padding,qy(this.padding),this.dataFormat=null==t.dataFormat?"channelsLast":t.dataFormat,jy(this.dataFormat),this.activation=Av(t.activation),this.useBias=null==t.useBias||t.useBias,this.biasInitializer=Hb(t.biasInitializer||this.DEFAULT_BIAS_INITIALIZER),this.biasConstraint=Tx(t.biasConstraint),this.biasRegularizer=Lv(t.biasRegularizer),this.activityRegularizer=Lv(t.activityRegularizer),this.dilationRate=Gv(null==t.dilationRate?1:t.dilationRate,e,"dilationRate"),1===this.rank&&Array.isArray(this.dilationRate)&&1!==this.dilationRate.length)throw new dy(`dilationRate must be a number or an array of a single number for 1D convolution, but received ${JSON.stringify(this.dilationRate)}`);if(2===this.rank){if("number"==typeof this.dilationRate)this.dilationRate=[this.dilationRate,this.dilationRate];else if(2!==this.dilationRate.length)throw new dy(`dilationRate must be a number or array of two numbers for 2D convolution, but received ${JSON.stringify(this.dilationRate)}`)}else if(3===this.rank)if("number"==typeof this.dilationRate)this.dilationRate=[this.dilationRate,this.dilationRate,this.dilationRate];else if(3!==this.dilationRate.length)throw new dy(`dilationRate must be a number or array of three numbers for 3D convolution, but received ${JSON.stringify(this.dilationRate)}`)}static verifyArgs(e){if(by("kernelSize"in e,"required key 'kernelSize' not in config"),"number"!=typeof e.kernelSize&&!Fy(e.kernelSize,"number",1,3))throw new dy(`BaseConv expects config.kernelSize to be number or number[] with length 1, 2, or 3, but received ${JSON.stringify(e.kernelSize)}.`)}getConfig(){const e={kernelSize:this.kernelSize,strides:this.strides,padding:this.padding,dataFormat:this.dataFormat,dilationRate:this.dilationRate,activation:$v(this.activation),useBias:this.useBias,biasInitializer:Gb(this.biasInitializer),biasRegularizer:Ov(this.biasRegularizer),activityRegularizer:Ov(this.activityRegularizer),biasConstraint:Nx(this.biasConstraint)},t=super.getConfig();return Object.assign(e,t),e}}class Qv extends Jv{constructor(e,t){super(e,t),this.kernel=null,Qv.verifyArgs(t),this.filters=t.filters,_y(this.filters,"filters"),this.kernelInitializer=Hb(t.kernelInitializer||this.DEFAULT_KERNEL_INITIALIZER),this.kernelConstraint=Tx(t.kernelConstraint),this.kernelRegularizer=Lv(t.kernelRegularizer)}build(e){e=Xb(e);const t="channelsFirst"===this.dataFormat?1:e.length-1;if(null==e[t])throw new dy(`The channel dimension of the input should be defined. Found ${e[t]}`);const n=e[t],s=this.kernelSize.concat([n,this.filters]);this.kernel=this.addWeight("kernel",s,null,this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint),this.useBias&&(this.bias=this.addWeight("bias",[this.filters],null,this.biasInitializer,this.biasRegularizer,!0,this.biasConstraint)),this.inputSpec=[{ndim:this.rank+2,axes:{[t]:n}}],this.built=!0}call(e,t){return fo((()=>{let t;e=Kb(e);const n=null==this.bias?null:this.bias.read(),s=Oy(this.activation.getClassName());if(null!=s&&2===this.rank)t=Yv(e,this.kernel.read(),n,this.strides,this.padding,this.dataFormat,this.dilationRate,s);else{if(1===this.rank)t=Xv(e,this.kernel.read(),n,this.strides[0],this.padding,this.dataFormat,this.dilationRate[0]);else if(2===this.rank)t=Yv(e,this.kernel.read(),n,this.strides,this.padding,this.dataFormat,this.dilationRate);else{if(3!==this.rank)throw new fy("convolutions greater than 3D are not implemented yet.");t=Zv(e,this.kernel.read(),n,this.strides,this.padding,this.dataFormat,this.dilationRate)}null!=this.activation&&(t=this.activation.apply(t))}return t}))}computeOutputShape(e){e=Xb(e);const t=[],n="channelsLast"===this.dataFormat?e.slice(1,e.length-1):e.slice(2);for(let e=0;e<n.length;++e){const s=Hv(n[e],this.kernelSize[e],this.padding,this.strides[e],"number"==typeof this.dilationRate?this.dilationRate:this.dilationRate[e]);t.push(s)}let s=[e[0]];return"channelsLast"===this.dataFormat?(s=s.concat(t),s.push(this.filters)):(s.push(this.filters),s=s.concat(t)),s}getConfig(){const e={filters:this.filters,kernelInitializer:Gb(this.kernelInitializer),kernelRegularizer:Ov(this.kernelRegularizer),kernelConstraint:Nx(this.kernelConstraint)},t=super.getConfig();return Object.assign(e,t),e}static verifyArgs(e){if(!("filters"in e)||"number"!=typeof e.filters||e.filters<1)throw new dy(`Convolution layer expected config.filters to be a 'number' > 0 but got ${JSON.stringify(e.filters)}`)}}class ek extends Qv{constructor(e){super(2,e),ek.verifyArgs(e)}getConfig(){const e=super.getConfig();return delete e.rank,e}static verifyArgs(e){if("number"!=typeof e.kernelSize&&!Fy(e.kernelSize,"number",1,2))throw new dy(`Conv2D expects config.kernelSize to be number or number[] with length 1 or 2, but received ${JSON.stringify(e.kernelSize)}.`)}}ek.className="Conv2D",Go(ek);class tk extends Qv{constructor(e){super(3,e),tk.verifyArgs(e)}getConfig(){const e=super.getConfig();return delete e.rank,e}static verifyArgs(e){if("number"!=typeof e.kernelSize&&(!Array.isArray(e.kernelSize)||1!==e.kernelSize.length&&3!==e.kernelSize.length))throw new dy(`Conv3D expects config.kernelSize to be number or [number, number, number], but received ${JSON.stringify(e.kernelSize)}.`)}}tk.className="Conv3D",Go(tk);class nk extends ek{constructor(e){if(super(e),this.inputSpec=[new tx({ndim:4})],"same"!==this.padding&&"valid"!==this.padding)throw new dy(`Conv2DTranspose currently supports only padding modes 'same' and 'valid', but received padding mode ${this.padding}`)}build(e){if(4!==(e=Xb(e)).length)throw new dy("Input should have rank 4; Received input shape: "+JSON.stringify(e));const t="channelsFirst"===this.dataFormat?1:e.length-1;if(null==e[t])throw new dy("The channel dimension of the inputs should be defined. Found `None`.");const n=e[t],s=this.kernelSize.concat([this.filters,n]);this.kernel=this.addWeight("kernel",s,"float32",this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint),this.useBias&&(this.bias=this.addWeight("bias",[this.filters],"float32",this.biasInitializer,this.biasRegularizer,!0,this.biasConstraint)),this.inputSpec=[new tx({ndim:4,axes:{[t]:n}})],this.built=!0}call(e,t){return fo((()=>{let t=Kb(e);if(4!==t.shape.length)throw new dy(`Conv2DTranspose.call() expects input tensor to be rank-4, but received a tensor of rank-${t.shape.length}`);const n=t.shape,s=n[0];let r,a;"channelsFirst"===this.dataFormat?(r=2,a=3):(r=1,a=2);const i=n[r],o=n[a],l=this.kernelSize[0],u=this.kernelSize[1],c=this.strides[0],h=this.strides[1],p=[s,jv(i,c,l,this.padding),jv(o,h,u,this.padding),this.filters];"channelsLast"!==this.dataFormat&&(t=_l(t,[0,2,3,1]));let d=Ec(t,this.kernel.read(),p,this.strides,this.padding);return"channelsLast"!==this.dataFormat&&(d=_l(d,[0,3,1,2])),null!=this.bias&&(d=vb(d,this.bias.read(),this.dataFormat)),null!=this.activation&&(d=this.activation.apply(d)),d}))}computeOutputShape(e){const t=(e=Xb(e)).slice();let n,s,r;"channelsFirst"===this.dataFormat?(n=1,s=2,r=3):(n=3,s=1,r=2);const a=this.kernelSize[0],i=this.kernelSize[1],o=this.strides[0],l=this.strides[1];return t[n]=this.filters,t[s]=jv(t[s],o,a,this.padding),t[r]=jv(t[r],l,i,this.padding),t}getConfig(){const e=super.getConfig();return delete e.dilationRate,e}}nk.className="Conv2DTranspose",Go(nk);class sk extends tk{constructor(e){if(super(e),this.inputSpec=[new tx({ndim:5})],"same"!==this.padding&&"valid"!==this.padding)throw new dy(`Conv3DTranspose currently supports only padding modes 'same' and 'valid', but received padding mode ${this.padding}`)}build(e){if(5!==(e=Xb(e)).length)throw new dy("Input should have rank 5; Received input shape: "+JSON.stringify(e));const t="channelsFirst"===this.dataFormat?1:e.length-1;if(null==e[t])throw new dy("The channel dimension of the inputs should be defined. Found `None`.");const n=e[t],s=this.kernelSize.concat([this.filters,n]);this.kernel=this.addWeight("kernel",s,"float32",this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint),this.useBias&&(this.bias=this.addWeight("bias",[this.filters],"float32",this.biasInitializer,this.biasRegularizer,!0,this.biasConstraint)),this.inputSpec=[new tx({ndim:5,axes:{[t]:n}})],this.built=!0}call(e,t){return fo((()=>{let t=Kb(e);if(5!==t.shape.length)throw new dy(`Conv3DTranspose.call() expects input tensor to be rank-4, but received a tensor of rank-${t.shape.length}`);const n=t.shape,s=n[0];let r,a,i;"channelsFirst"===this.dataFormat?(i=2,r=3,a=4):(i=1,r=2,a=3);const o=n[i],l=n[r],u=n[a],c=this.kernelSize[0],h=this.kernelSize[1],p=this.kernelSize[2],d=this.strides[0],f=this.strides[1],m=this.strides[2],g=[s,jv(o,d,c,this.padding),jv(l,f,h,this.padding),jv(u,m,p,this.padding),this.filters];"channelsLast"!==this.dataFormat&&(t=_l(t,[0,2,3,4,1]));let y=Fc(t,this.kernel.read(),g,this.strides,this.padding);return"channelsLast"!==this.dataFormat&&(y=_l(y,[0,4,1,2,3])),null!==this.bias&&(y=vb(y,this.bias.read(),this.dataFormat)),null!==this.activation&&(y=this.activation.apply(y)),y}))}computeOutputShape(e){const t=(e=Xb(e)).slice();let n,s,r,a;"channelsFirst"===this.dataFormat?(n=1,s=2,r=3,a=4):(n=4,s=1,r=2,a=3);const i=this.kernelSize[0],o=this.kernelSize[1],l=this.kernelSize[2],u=this.strides[0],c=this.strides[1],h=this.strides[2];return t[n]=this.filters,t[s]=jv(t[s],u,i,this.padding),t[r]=jv(t[r],c,o,this.padding),t[a]=jv(t[a],h,l,this.padding),t}getConfig(){const e=super.getConfig();return delete e.dilationRate,e}}sk.className="Conv3DTranspose",Go(sk);class rk extends Qv{constructor(e,t){if(super(e,t),this.DEFAULT_DEPTHWISE_INITIALIZER="glorotUniform",this.DEFAULT_POINTWISE_INITIALIZER="glorotUniform",this.depthwiseKernel=null,this.pointwiseKernel=null,null==t.filters)throw new dy("The `filters` configuration field is required by SeparableConv, but is unspecified.");if(null!=t.kernelInitializer||null!=t.kernelRegularizer||null!=t.kernelConstraint)throw new dy("Fields kernelInitializer, kernelRegularizer and kernelConstraint are invalid for SeparableConv2D. Use depthwiseInitializer, depthwiseRegularizer, depthwiseConstraint, pointwiseInitializer, pointwiseRegularizer and pointwiseConstraint instead.");if(null!=t.padding&&"same"!==t.padding&&"valid"!==t.padding)throw new dy(`SeparableConv${this.rank}D supports only padding modes: 'same' and 'valid', but received ${JSON.stringify(t.padding)}`);this.depthMultiplier=null==t.depthMultiplier?1:t.depthMultiplier,this.depthwiseInitializer=Hb(t.depthwiseInitializer||this.DEFAULT_DEPTHWISE_INITIALIZER),this.depthwiseRegularizer=Lv(t.depthwiseRegularizer),this.depthwiseConstraint=Tx(t.depthwiseConstraint),this.pointwiseInitializer=Hb(t.depthwiseInitializer||this.DEFAULT_POINTWISE_INITIALIZER),this.pointwiseRegularizer=Lv(t.pointwiseRegularizer),this.pointwiseConstraint=Tx(t.pointwiseConstraint)}build(e){if((e=Xb(e)).length<this.rank+2)throw new dy(`Inputs to SeparableConv${this.rank}D should have rank ${this.rank+2}, but received input shape: ${JSON.stringify(e)}`);const t="channelsFirst"===this.dataFormat?1:e.length-1;if(null==e[t]||e[t]<0)throw new dy(`The channel dimension of the inputs should be defined, but found ${JSON.stringify(e[t])}`);const n=e[t],s=this.kernelSize.concat([n,this.depthMultiplier]),r=[];for(let e=0;e<this.rank;++e)r.push(1);r.push(n*this.depthMultiplier,this.filters);const a=!0;this.depthwiseKernel=this.addWeight("depthwise_kernel",s,"float32",this.depthwiseInitializer,this.depthwiseRegularizer,a,this.depthwiseConstraint),this.pointwiseKernel=this.addWeight("pointwise_kernel",r,"float32",this.pointwiseInitializer,this.pointwiseRegularizer,a,this.pointwiseConstraint),this.useBias?this.bias=this.addWeight("bias",[this.filters],"float32",this.biasInitializer,this.biasRegularizer,a,this.biasConstraint):this.bias=null,this.inputSpec=[new tx({ndim:this.rank+2,axes:{[t]:n}})],this.built=!0}call(e,t){return fo((()=>{let t;if(e=Kb(e),1===this.rank)throw new fy("1D separable convolution is not implemented yet.");return 2===this.rank&&("channelsFirst"===this.dataFormat&&(e=_l(e,[0,2,3,1])),t=Mp(e,this.depthwiseKernel.read(),this.pointwiseKernel.read(),this.strides,this.padding,this.dilationRate,"NHWC")),this.useBias&&(t=vb(t,this.bias.read(),this.dataFormat)),null!=this.activation&&(t=this.activation.apply(t)),"channelsFirst"===this.dataFormat&&(t=_l(t,[0,3,1,2])),t}))}getConfig(){const e=super.getConfig();return delete e.rank,delete e.kernelInitializer,delete e.kernelRegularizer,delete e.kernelConstraint,e.depthwiseInitializer=Gb(this.depthwiseInitializer),e.pointwiseInitializer=Gb(this.pointwiseInitializer),e.depthwiseRegularizer=Ov(this.depthwiseRegularizer),e.pointwiseRegularizer=Ov(this.pointwiseRegularizer),e.depthwiseConstraint=Nx(this.depthwiseConstraint),e.pointwiseConstraint=Nx(this.pointwiseConstraint),e}}rk.className="SeparableConv";class ak extends rk{constructor(e){super(2,e)}}ak.className="SeparableConv2D",Go(ak);class ik extends Qv{constructor(e){super(1,e),ik.verifyArgs(e),this.inputSpec=[{ndim:3}]}getConfig(){const e=super.getConfig();return delete e.rank,delete e.dataFormat,e}static verifyArgs(e){if("number"!=typeof e.kernelSize&&!Fy(e.kernelSize,"number",1,1))throw new dy(`Conv1D expects config.kernelSize to be number or number[] with length 1, but received ${JSON.stringify(e.kernelSize)}.`)}}ik.className="Conv1D",Go(ik);class ok extends ix{constructor(e){super(e),"number"==typeof e.cropping?this.cropping=[[e.cropping,e.cropping],[e.cropping,e.cropping]]:"number"==typeof e.cropping[0]?this.cropping=[[e.cropping[0],e.cropping[0]],[e.cropping[1],e.cropping[1]]]:this.cropping=e.cropping,this.dataFormat=void 0===e.dataFormat?"channelsLast":e.dataFormat,this.inputSpec=[{ndim:4}]}computeOutputShape(e){return"channelsFirst"===this.dataFormat?[e[0],e[1],e[2]-this.cropping[0][0]-this.cropping[0][1],e[3]-this.cropping[1][0]-this.cropping[1][1]]:[e[0],e[1]-this.cropping[0][0]-this.cropping[0][1],e[2]-this.cropping[1][0]-this.cropping[1][1],e[3]]}call(e,t){return fo((()=>{if(e=Kb(e),"channelsLast"===this.dataFormat){const t=pb(e,this.cropping[0][0],e.shape[1]-this.cropping[0][0]-this.cropping[0][1],2);return pb(t,this.cropping[1][0],e.shape[2]-this.cropping[1][1]-this.cropping[1][0],3)}{const t=pb(e,this.cropping[0][0],e.shape[2]-this.cropping[0][0]-this.cropping[0][1],3);return pb(t,this.cropping[1][0],e.shape[3]-this.cropping[1][1]-this.cropping[1][0],4)}}))}getConfig(){const e={cropping:this.cropping,dataFormat:this.dataFormat},t=super.getConfig();return Object.assign(e,t),e}}ok.className="Cropping2D",Go(ok);class lk extends ix{constructor(e){var t;super(e),this.DEFAULT_SIZE=[2,2],this.inputSpec=[{ndim:4}],this.size=null==e.size?this.DEFAULT_SIZE:e.size,this.dataFormat=null==e.dataFormat?"channelsLast":e.dataFormat,jy(this.dataFormat),this.interpolation=null==e.interpolation?"nearest":e.interpolation,t=this.interpolation,Ry(Wy,"InterpolationFormat",t)}computeOutputShape(e){if("channelsFirst"===this.dataFormat){const t=null==e[2]?null:this.size[0]*e[2],n=null==e[3]?null:this.size[1]*e[3];return[e[0],e[1],t,n]}{const t=null==e[1]?null:this.size[0]*e[1],n=null==e[2]?null:this.size[1]*e[2];return[e[0],t,n,e[3]]}}call(e,t){return fo((()=>{let t=Kb(e);const n=t.shape;if("channelsFirst"===this.dataFormat){t=_l(t,[0,2,3,1]);const e=this.size[0]*n[2],s=this.size[1]*n[3],r="nearest"===this.interpolation?Mf.resizeNearestNeighbor(t,[e,s]):Mf.resizeBilinear(t,[e,s]);return _l(r,[0,3,1,2])}{const e=this.size[0]*n[1],s=this.size[1]*n[2];return"nearest"===this.interpolation?Mf.resizeNearestNeighbor(t,[e,s]):Mf.resizeBilinear(t,[e,s])}}))}getConfig(){const e={size:this.size,dataFormat:this.dataFormat,interpolation:this.interpolation},t=super.getConfig();return Object.assign(e,t),e}}lk.className="UpSampling2D",Go(lk);class uk extends Jv{constructor(e){super(2,e),this.depthwiseKernel=null,this.depthMultiplier=null==e.depthMultiplier?1:e.depthMultiplier,this.depthwiseInitializer=Hb(e.depthwiseInitializer||this.DEFAULT_KERNEL_INITIALIZER),this.depthwiseConstraint=Tx(e.depthwiseConstraint),this.depthwiseRegularizer=Lv(e.depthwiseRegularizer)}build(e){if((e=Xb(e)).length<4)throw new dy(`Inputs to DepthwiseConv2D should have rank 4. Received input shape: ${JSON.stringify(e)}.`);const t="channelsFirst"===this.dataFormat?1:3;if(null==e[t]||e[t]<0)throw new dy(`The channel dimension of the inputs to DepthwiseConv2D should be defined, but is not (${e[t]}).`);const n=e[t],s=[this.kernelSize[0],this.kernelSize[1],n,this.depthMultiplier];this.depthwiseKernel=this.addWeight("depthwise_kernel",s,null,this.depthwiseInitializer,this.depthwiseRegularizer,!0,this.depthwiseConstraint),this.useBias?this.bias=this.addWeight("bias",[n*this.depthMultiplier],null,this.biasInitializer,this.biasRegularizer,!0,this.biasConstraint):this.bias=null,this.built=!0}call(e,t){return fo((()=>{let t=function(e,t,n=[1,1],s="valid",r,a){return fo((()=>{null==r&&(r="channelsLast"),jy(r);let i=qv(e,r);if(4!==e.rank)throw new dy(`Input for depthwiseConv2d is required to be 4-D, but is instead ${e.rank}-D`);if(4!==t.rank)throw new dy(`depthwiseKernel is required to be 4-D, but is instead ${t.rank}-D`);return i=Pc(i,t,n,"same"===s?"same":"valid","NHWC",a),"channelsFirst"===r&&(i=_l(i,[0,3,1,2])),i}))}(e=Kb(e),this.depthwiseKernel.read(),this.strides,this.padding,this.dataFormat,null);return this.useBias&&(t=vb(t,this.bias.read(),this.dataFormat)),null!=this.activation&&(t=this.activation.apply(t)),t}))}computeOutputShape(e){e=Xb(e);const t="channelsFirst"===this.dataFormat?e[2]:e[1],n="channelsFirst"===this.dataFormat?e[3]:e[2],s="channelsFirst"===this.dataFormat?e[1]*this.depthMultiplier:e[3]*this.depthMultiplier,r=Hv(t,this.kernelSize[0],this.padding,this.strides[0]),a=Hv(n,this.kernelSize[1],this.padding,this.strides[1]);return"channelsFirst"===this.dataFormat?[e[0],s,r,a]:[e[0],r,a,s]}getConfig(){const e=super.getConfig();return e.depthMultiplier=this.depthMultiplier,e.depthwiseInitializer=Gb(this.depthwiseInitializer),e.depthwiseRegularizer=Ov(this.depthwiseRegularizer),e.depthwiseConstraint=Nx(this.depthwiseRegularizer),e}}function ck(e,t,n,s){if(Array.isArray(e)){if(null!=t||null!=n)throw new dy("When inputs is an array, neither initialState or constants should be provided");null!=s&&(n=e.slice(e.length-s,e.length),e=e.slice(0,e.length-s)),e.length>1&&(t=e.slice(1,e.length)),e=e[0]}function r(e){return null==e||Array.isArray(e)?e:[e]}return{inputs:e,initialState:t=r(t),constants:n=r(n)}}function hk(e,t,n,s=!1,r,a,i=!1,o=!1){return fo((()=>{const l=t.shape.length;if(l<3)throw new dy(`Input should be at least 3D, but is ${l}D.`);const u=[1,0].concat(ab(2,l));if(t=_l(t,u),null!=a)throw new fy("The rnn() functoin of the deeplearn.js backend does not support constants yet.");i&&console.warn("Backend rnn(): the unroll = true option is not applicable to the imperative deeplearn.js backend."),null!=r&&((r=no(no(r,"bool"),"float32")).rank===l-1&&(r=hh(r,-1)),r=_l(r,u)),s&&(t=$p(t,0),null!=r&&(r=$p(r,0)));const c=[];let h,p=n;const d=t.shape[0],f=dd(t);let m,g;null!=r&&(m=dd(r));for(let t=0;t<d;++t){const n=f[t],s=fo((()=>e(n,p)));if(null==r)h=s[0],p=s[1];else{const e=fo((()=>{const e=m[t],n=Yo(ep(e),e);return{output:Co(Ao(s[0],e),Ao(p[0],n)),newStates:p.map(((t,r)=>Co(Ao(s[1][r],e),Ao(t,n))))}}));h=e.output,p=e.newStates}o&&c.push(h)}if(o){g=Qp(c,1)}return[h,g,p]}))}uk.className="DepthwiseConv2D",Go(uk);class pk extends ix{constructor(e){let t;if(super(e),null==e.cell)throw new dy("cell property is missing for the constructor of RNN.");if(t=Array.isArray(e.cell)?new wk({cells:e.cell}):e.cell,null==t.stateSize)throw new dy("The RNN cell should have an attribute `stateSize` (tuple of integers, one integer per RNN state).");this.cell=t,this.returnSequences=null!=e.returnSequences&&e.returnSequences,this.returnState=null!=e.returnState&&e.returnState,this.goBackwards=null!=e.goBackwards&&e.goBackwards,this._stateful=null!=e.stateful&&e.stateful,this.unroll=null!=e.unroll&&e.unroll,this.supportsMasking=!0,this.inputSpec=[new tx({ndim:3})],this.stateSpec=null,this.states_=null,this.numConstants=null,this.keptStates=[]}getStates(){if(null==this.states_){return ab(0,Array.isArray(this.cell.stateSize)?this.cell.stateSize.length:1).map((e=>null))}return this.states_}setStates(e){this.states_=e}computeOutputShape(e){jb(e)&&(e=e[0]);let t=this.cell.stateSize;Array.isArray(t)||(t=[t]);const n=t[0];let s;if(s=this.returnSequences?[e[0],e[1],n]:[e[0],n],this.returnState){const n=[];for(const s of t)n.push([e[0],s]);return[s].concat(n)}return s}computeMask(e,t){return fo((()=>{Array.isArray(t)&&(t=t[0]);const e=this.returnSequences?t:null;if(this.returnState){const t=this.states.map((e=>null));return[e].concat(t)}return e}))}get states(){if(null==this.states_){const e=Array.isArray(this.cell.stateSize)?this.cell.stateSize.length:1,t=[];for(let n=0;n<e;++n)t.push(null);return t}return this.states_}set states(e){this.states_=e}build(e){if(null!=this.numConstants)throw new fy("Constants support is not implemented in RNN yet.");jb(e)&&(e=e[0]);const t=this.stateful?e[0]:null,n=e.slice(2);this.inputSpec[0]=new tx({shape:[t,null,...n]});const s=[e[0]].concat(e.slice(2));let r;if(this.cell.build(s),r=Array.isArray(this.cell.stateSize)?this.cell.stateSize:[this.cell.stateSize],null!=this.stateSpec){if(!pe(this.stateSpec.map((e=>e.shape[e.shape.length-1])),r))throw new dy(`An initialState was passed that is not compatible with cell.stateSize. Received stateSpec=${this.stateSpec}; However cell.stateSize is ${this.cell.stateSize}`)}else this.stateSpec=r.map((e=>new tx({shape:[null,e]})));this.stateful&&this.resetStates()}resetStates(e,t=!1){fo((()=>{if(!this.stateful)throw new hy("Cannot call resetStates() on an RNN Layer that is not stateful.");const n=this.inputSpec[0].shape[0];if(null==n)throw new dy("If an RNN is stateful, it needs to know its batch size. Specify the batch size of your input tensors: \n- If using a Sequential model, specify the batch size by passing a `batchInputShape` option to your first layer.\n- If using the functional API, specify the batch size by passing a `batchShape` option to your Input layer.");if(null==this.states_)Array.isArray(this.cell.stateSize)?this.states_=this.cell.stateSize.map((e=>Gh([n,e]))):this.states_=[Gh([n,this.cell.stateSize])];else if(null==e)mo(this.states_),null!=this.keptStates&&(mo(this.keptStates),this.keptStates=[]),Array.isArray(this.cell.stateSize)?this.states_=this.cell.stateSize.map((e=>Gh([n,e]))):this.states_[0]=Gh([n,this.cell.stateSize]);else{if(Array.isArray(e)||(e=[e]),e.length!==this.states_.length)throw new dy(`Layer ${this.name} expects ${this.states_.length} state(s), but it received ${e.length} state value(s). Input received: ${e}`);!0===t?this.keptStates.push(this.states_.slice()):mo(this.states_);for(let t=0;t<this.states_.length;++t){const s=e[t],r=Array.isArray(this.cell.stateSize)?this.cell.stateSize[t]:this.cell.stateSize,a=[n,r];if(!pe(s.shape,a))throw new dy(`State ${t} is incompatible with layer ${this.name}: expected shape=${a}, received shape=${s.shape}`);this.states_[t]=s}}this.states_=this.states_.map((e=>go(e.clone())))}))}apply(e,t){let n=null==t?null:t.initialState,s=null==t?null:t.constants;null==t&&(t={});const r=ck(e,n,s,this.numConstants);e=r.inputs,n=r.initialState,s=r.constants;let a=[],i=[];if(null!=n){t.initialState=n,a=a.concat(n),this.stateSpec=[];for(const e of n)this.stateSpec.push(new tx({shape:e.shape}));i=i.concat(this.stateSpec)}null!=s&&(t.constants=s,a=a.concat(s),this.numConstants=s.length);if(a[0]instanceof nx){const n=[e].concat(a),s=this.inputSpec.concat(i),r=this.inputSpec;this.inputSpec=s;const o=super.apply(n,t);return this.inputSpec=r,o}return super.apply(e,t)}call(e,t){return fo((()=>{const n=null==t?null:t.mask,s=null==t?null:t.training;let r=null==t?null:t.initialState;e=Kb(e),null==r&&(r=this.stateful?this.states_:this.getInitialState(e));const a=Array.isArray(this.cell.stateSize)?this.cell.stateSize.length:1;if(r.length!==a)throw new dy(`RNN Layer has ${a} state(s) but was passed ${r.length} initial state(s).`);this.unroll&&console.warn("Ignoring unroll = true for RNN layer, due to imperative backend.");const i={training:s},o=hk(((e,t)=>{const n=this.cell.call([e].concat(t),i);return[n[0],n.slice(1)]}),e,r,this.goBackwards,n,null,this.unroll,this.returnSequences),l=o[0],u=o[1],c=o[2];this.stateful&&this.resetStates(c,s);const h=this.returnSequences?u:l;return this.returnState?[h].concat(c):h}))}getInitialState(e){return fo((()=>{let t=Gh(e.shape);return t=ih(t,[1,2]),t=ub(t),Array.isArray(this.cell.stateSize)?this.cell.stateSize.map((e=>e>1?mb(t,[1,e]):t)):this.cell.stateSize>1?[mb(t,[1,this.cell.stateSize])]:[t]}))}get trainableWeights(){return this.trainable?this.cell.trainableWeights:[]}get nonTrainableWeights(){return this.trainable?this.cell.nonTrainableWeights:this.cell.weights}setFastWeightInitDuringBuild(e){super.setFastWeightInitDuringBuild(e),null!=this.cell&&this.cell.setFastWeightInitDuringBuild(e)}getConfig(){const e=super.getConfig(),t={returnSequences:this.returnSequences,returnState:this.returnState,goBackwards:this.goBackwards,stateful:this.stateful,unroll:this.unroll};null!=this.numConstants&&(t.numConstants=this.numConstants);const n=this.cell.getConfig();return this.getClassName()===pk.className&&(t.cell={className:this.cell.getClassName(),config:n}),Object.assign(Object.assign(Object.assign({},n),e),t)}static fromConfig(e,t,n={}){const s=sw(t.cell,n);return new e(Object.assign(t,{cell:s}))}}pk.className="RNN",Go(pk);class dk extends ix{}class fk extends dk{constructor(e){super(e),this.DEFAULT_ACTIVATION="tanh",this.DEFAULT_KERNEL_INITIALIZER="glorotNormal",this.DEFAULT_RECURRENT_INITIALIZER="orthogonal",this.DEFAULT_BIAS_INITIALIZER="zeros",this.units=e.units,_y(this.units,"units"),this.activation=Av(null==e.activation?this.DEFAULT_ACTIVATION:e.activation),this.useBias=null==e.useBias||e.useBias,this.kernelInitializer=Hb(e.kernelInitializer||this.DEFAULT_KERNEL_INITIALIZER),this.recurrentInitializer=Hb(e.recurrentInitializer||this.DEFAULT_RECURRENT_INITIALIZER),this.biasInitializer=Hb(e.biasInitializer||this.DEFAULT_BIAS_INITIALIZER),this.kernelRegularizer=Lv(e.kernelRegularizer),this.recurrentRegularizer=Lv(e.recurrentRegularizer),this.biasRegularizer=Lv(e.biasRegularizer),this.kernelConstraint=Tx(e.kernelConstraint),this.recurrentConstraint=Tx(e.recurrentConstraint),this.biasConstraint=Tx(e.biasConstraint),this.dropout=sb([1,rb([0,null==e.dropout?0:e.dropout])]),this.recurrentDropout=sb([1,rb([0,null==e.recurrentDropout?0:e.recurrentDropout])]),this.dropoutFunc=e.dropoutFunc,this.stateSize=this.units,this.dropoutMask=null,this.recurrentDropoutMask=null}build(e){e=Xb(e),this.kernel=this.addWeight("kernel",[e[e.length-1],this.units],null,this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint),this.recurrentKernel=this.addWeight("recurrent_kernel",[this.units,this.units],null,this.recurrentInitializer,this.recurrentRegularizer,!0,this.recurrentConstraint),this.useBias?this.bias=this.addWeight("bias",[this.units],null,this.biasInitializer,this.biasRegularizer,!0,this.biasConstraint):this.bias=null,this.built=!0}call(e,t){return fo((()=>{if(2!==e.length)throw new dy(`SimpleRNNCell expects 2 input Tensors, got ${e.length}.`);let n=e[1];e=e[0];const s=null!=t.training&&t.training;let r;0<this.dropout&&this.dropout<1&&null==this.dropoutMask&&(this.dropoutMask=vk({ones:()=>ep(e),rate:this.dropout,training:s,dropoutFunc:this.dropoutFunc})),0<this.recurrentDropout&&this.recurrentDropout<1&&null==this.recurrentDropoutMask&&(this.recurrentDropoutMask=vk({ones:()=>ep(n),rate:this.recurrentDropout,training:s,dropoutFunc:this.dropoutFunc}));const a=this.dropoutMask,i=this.recurrentDropoutMask;r=yb(null!=a?Ao(e,a):e,this.kernel.read()),null!=this.bias&&(r=vb(r,this.bias.read())),null!=i&&(n=Ao(n,i));let o=Co(r,yb(n,this.recurrentKernel.read()));return null!=this.activation&&(o=this.activation.apply(o)),[o,o]}))}getConfig(){const e=super.getConfig(),t={units:this.units,activation:$v(this.activation),useBias:this.useBias,kernelInitializer:Gb(this.kernelInitializer),recurrentInitializer:Gb(this.recurrentInitializer),biasInitializer:Gb(this.biasInitializer),kernelRegularizer:Ov(this.kernelRegularizer),recurrentRegularizer:Ov(this.recurrentRegularizer),biasRegularizer:Ov(this.biasRegularizer),activityRegularizer:Ov(this.activityRegularizer),kernelConstraint:Nx(this.kernelConstraint),recurrentConstraint:Nx(this.recurrentConstraint),biasConstraint:Nx(this.biasConstraint),dropout:this.dropout,recurrentDropout:this.recurrentDropout};return Object.assign(Object.assign({},e),t)}}fk.className="SimpleRNNCell",Go(fk);class mk extends pk{constructor(e){e.cell=new fk(e),super(e)}call(e,t){return fo((()=>{null!=this.cell.dropoutMask&&(mo(this.cell.dropoutMask),this.cell.dropoutMask=null),null!=this.cell.recurrentDropoutMask&&(mo(this.cell.recurrentDropoutMask),this.cell.recurrentDropoutMask=null);const n=null==t?null:t.mask,s=null==t?null:t.training,r=null==t?null:t.initialState;return super.call(e,{mask:n,training:s,initialState:r})}))}static fromConfig(e,t){return new e(t)}}mk.className="SimpleRNN",Go(mk);class gk extends dk{constructor(e){if(super(e),this.DEFAULT_ACTIVATION="tanh",this.DEFAULT_RECURRENT_ACTIVATION="hardSigmoid",this.DEFAULT_KERNEL_INITIALIZER="glorotNormal",this.DEFAULT_RECURRENT_INITIALIZER="orthogonal",this.DEFAULT_BIAS_INITIALIZER="zeros",e.resetAfter)throw new dy("GRUCell does not support reset_after parameter set to true.");this.units=e.units,_y(this.units,"units"),this.activation=Av(void 0===e.activation?this.DEFAULT_ACTIVATION:e.activation),this.recurrentActivation=Av(void 0===e.recurrentActivation?this.DEFAULT_RECURRENT_ACTIVATION:e.recurrentActivation),this.useBias=null==e.useBias||e.useBias,this.kernelInitializer=Hb(e.kernelInitializer||this.DEFAULT_KERNEL_INITIALIZER),this.recurrentInitializer=Hb(e.recurrentInitializer||this.DEFAULT_RECURRENT_INITIALIZER),this.biasInitializer=Hb(e.biasInitializer||this.DEFAULT_BIAS_INITIALIZER),this.kernelRegularizer=Lv(e.kernelRegularizer),this.recurrentRegularizer=Lv(e.recurrentRegularizer),this.biasRegularizer=Lv(e.biasRegularizer),this.kernelConstraint=Tx(e.kernelConstraint),this.recurrentConstraint=Tx(e.recurrentConstraint),this.biasConstraint=Tx(e.biasConstraint),this.dropout=sb([1,rb([0,null==e.dropout?0:e.dropout])]),this.recurrentDropout=sb([1,rb([0,null==e.recurrentDropout?0:e.recurrentDropout])]),this.dropoutFunc=e.dropoutFunc,this.implementation=e.implementation,this.stateSize=this.units,this.dropoutMask=null,this.recurrentDropoutMask=null}build(e){const t=(e=Xb(e))[e.length-1];this.kernel=this.addWeight("kernel",[t,3*this.units],null,this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint),this.recurrentKernel=this.addWeight("recurrent_kernel",[this.units,3*this.units],null,this.recurrentInitializer,this.recurrentRegularizer,!0,this.recurrentConstraint),this.useBias?this.bias=this.addWeight("bias",[3*this.units],null,this.biasInitializer,this.biasRegularizer,!0,this.biasConstraint):this.bias=null,this.built=!0}call(e,t){return fo((()=>{if(2!==e.length)throw new dy(`GRUCell expects 2 input Tensors (inputs, h, c), got ${e.length}.`);const n=null!=t.training&&t.training;let s=e[1];e=e[0],0<this.dropout&&this.dropout<1&&null==this.dropoutMask&&(this.dropoutMask=vk({ones:()=>ep(e),rate:this.dropout,training:n,count:3,dropoutFunc:this.dropoutFunc})),0<this.recurrentDropout&&this.recurrentDropout<1&&null==this.recurrentDropoutMask&&(this.recurrentDropoutMask=vk({ones:()=>ep(s),rate:this.recurrentDropout,training:n,count:3,dropoutFunc:this.dropoutFunc}));const r=this.dropoutMask,a=this.recurrentDropoutMask;let i,o,l;0<this.dropout&&this.dropout<1&&(e=Ao(e,r[0]));let u=yb(e,this.kernel.read());this.useBias&&(u=vb(u,this.bias.read())),0<this.recurrentDropout&&this.recurrentDropout<1&&(s=Ao(s,a[0]));const c=this.recurrentKernel.read(),[h,p]=Xp(c,[2*this.units,this.units],c.rank-1),d=yb(s,h),[f,m,g]=Xp(u,3,u.rank-1),[y,b]=Xp(d,2,d.rank-1);i=this.recurrentActivation.apply(Co(f,y)),o=this.recurrentActivation.apply(Co(m,b));const x=yb(Ao(o,s),p);l=this.activation.apply(Co(g,x));const w=Co(Ao(i,s),Ao(Co(1,Rl(i)),l));return[w,w]}))}getConfig(){const e=super.getConfig(),t={units:this.units,activation:$v(this.activation),recurrentActivation:$v(this.recurrentActivation),useBias:this.useBias,kernelInitializer:Gb(this.kernelInitializer),recurrentInitializer:Gb(this.recurrentInitializer),biasInitializer:Gb(this.biasInitializer),kernelRegularizer:Ov(this.kernelRegularizer),recurrentRegularizer:Ov(this.recurrentRegularizer),biasRegularizer:Ov(this.biasRegularizer),activityRegularizer:Ov(this.activityRegularizer),kernelConstraint:Nx(this.kernelConstraint),recurrentConstraint:Nx(this.recurrentConstraint),biasConstraint:Nx(this.biasConstraint),dropout:this.dropout,recurrentDropout:this.recurrentDropout,implementation:this.implementation,resetAfter:!1};return Object.assign(Object.assign({},e),t)}}gk.className="GRUCell",Go(gk);class yk extends pk{constructor(e){0===e.implementation&&console.warn("`implementation=0` has been deprecated, and now defaults to `implementation=1`. Please update your layer call."),e.cell=new gk(e),super(e)}call(e,t){return fo((()=>{null!=this.cell.dropoutMask&&(mo(this.cell.dropoutMask),this.cell.dropoutMask=null),null!=this.cell.recurrentDropoutMask&&(mo(this.cell.recurrentDropoutMask),this.cell.recurrentDropoutMask=null);const n=null==t?null:t.mask,s=null==t?null:t.training,r=null==t?null:t.initialState;return super.call(e,{mask:n,training:s,initialState:r})}))}static fromConfig(e,t){return 0===t.implmentation&&(t.implementation=1),new e(t)}}yk.className="GRU",Go(yk);class bk extends dk{constructor(e){super(e),this.DEFAULT_ACTIVATION="tanh",this.DEFAULT_RECURRENT_ACTIVATION="hardSigmoid",this.DEFAULT_KERNEL_INITIALIZER="glorotNormal",this.DEFAULT_RECURRENT_INITIALIZER="orthogonal",this.DEFAULT_BIAS_INITIALIZER="zeros",this.units=e.units,_y(this.units,"units"),this.activation=Av(void 0===e.activation?this.DEFAULT_ACTIVATION:e.activation),this.recurrentActivation=Av(void 0===e.recurrentActivation?this.DEFAULT_RECURRENT_ACTIVATION:e.recurrentActivation),this.useBias=null==e.useBias||e.useBias,this.kernelInitializer=Hb(e.kernelInitializer||this.DEFAULT_KERNEL_INITIALIZER),this.recurrentInitializer=Hb(e.recurrentInitializer||this.DEFAULT_RECURRENT_INITIALIZER),this.biasInitializer=Hb(e.biasInitializer||this.DEFAULT_BIAS_INITIALIZER),this.unitForgetBias=e.unitForgetBias,this.kernelRegularizer=Lv(e.kernelRegularizer),this.recurrentRegularizer=Lv(e.recurrentRegularizer),this.biasRegularizer=Lv(e.biasRegularizer),this.kernelConstraint=Tx(e.kernelConstraint),this.recurrentConstraint=Tx(e.recurrentConstraint),this.biasConstraint=Tx(e.biasConstraint),this.dropout=sb([1,rb([0,null==e.dropout?0:e.dropout])]),this.recurrentDropout=sb([1,rb([0,null==e.recurrentDropout?0:e.recurrentDropout])]),this.dropoutFunc=e.dropoutFunc,this.implementation=e.implementation,this.stateSize=[this.units,this.units],this.dropoutMask=null,this.recurrentDropoutMask=null}build(e){var t;const n=(e=Xb(e))[e.length-1];let s;if(this.kernel=this.addWeight("kernel",[n,4*this.units],null,this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint),this.recurrentKernel=this.addWeight("recurrent_kernel",[this.units,4*this.units],null,this.recurrentInitializer,this.recurrentRegularizer,!0,this.recurrentConstraint),this.useBias){if(this.unitForgetBias){const e=this.biasInitializer,n=this.units;s=new((t=class extends Tb{apply(t,s){const r=e.apply([n]),a=(new $b).apply([n]),i=e.apply([2*n]);return fb(fb(r,a),i)}}).className="CustomInit",t)}else s=this.biasInitializer;this.bias=this.addWeight("bias",[4*this.units],null,s,this.biasRegularizer,!0,this.biasConstraint)}else this.bias=null;this.built=!0}call(e,t){return fo((()=>{const n=null!=t.training&&t.training;if(3!==e.length)throw new dy(`LSTMCell expects 3 input Tensors (inputs, h, c), got ${e.length}.`);let s=e[1];const r=e[2];e=e[0],0<this.dropout&&this.dropout<1&&null==this.dropoutMask&&(this.dropoutMask=vk({ones:()=>ep(e),rate:this.dropout,training:n,count:4,dropoutFunc:this.dropoutFunc})),0<this.recurrentDropout&&this.recurrentDropout<1&&null==this.recurrentDropoutMask&&(this.recurrentDropoutMask=vk({ones:()=>ep(s),rate:this.recurrentDropout,training:n,count:4,dropoutFunc:this.dropoutFunc}));const a=this.dropoutMask,i=this.recurrentDropoutMask;let o,l,u,c;0<this.dropout&&this.dropout<1&&(e=Ao(e,a[0]));let h=yb(e,this.kernel.read());0<this.recurrentDropout&&this.recurrentDropout<1&&(s=Ao(s,i[0])),h=Co(h,yb(s,this.recurrentKernel.read())),this.useBias&&(h=vb(h,this.bias.read()));const[p,d,f,m]=Xp(h,4,h.rank-1);o=this.recurrentActivation.apply(p),l=this.recurrentActivation.apply(d),u=Co(Ao(l,r),Ao(o,this.activation.apply(f))),c=this.recurrentActivation.apply(m);const g=Ao(c,this.activation.apply(u));return[g,g,u]}))}getConfig(){const e=super.getConfig(),t={units:this.units,activation:$v(this.activation),recurrentActivation:$v(this.recurrentActivation),useBias:this.useBias,kernelInitializer:Gb(this.kernelInitializer),recurrentInitializer:Gb(this.recurrentInitializer),biasInitializer:Gb(this.biasInitializer),unitForgetBias:this.unitForgetBias,kernelRegularizer:Ov(this.kernelRegularizer),recurrentRegularizer:Ov(this.recurrentRegularizer),biasRegularizer:Ov(this.biasRegularizer),activityRegularizer:Ov(this.activityRegularizer),kernelConstraint:Nx(this.kernelConstraint),recurrentConstraint:Nx(this.recurrentConstraint),biasConstraint:Nx(this.biasConstraint),dropout:this.dropout,recurrentDropout:this.recurrentDropout,implementation:this.implementation};return Object.assign(Object.assign({},e),t)}}bk.className="LSTMCell",Go(bk);class xk extends pk{constructor(e){0===e.implementation&&console.warn("`implementation=0` has been deprecated, and now defaults to `implementation=1`. Please update your layer call."),e.cell=new bk(e),super(e)}call(e,t){return fo((()=>{null!=this.cell.dropoutMask&&(mo(this.cell.dropoutMask),this.cell.dropoutMask=null),null!=this.cell.recurrentDropoutMask&&(mo(this.cell.recurrentDropoutMask),this.cell.recurrentDropoutMask=null);const n=null==t?null:t.mask,s=null==t?null:t.training,r=null==t?null:t.initialState;return super.call(e,{mask:n,training:s,initialState:r})}))}static fromConfig(e,t){return 0===t.implmentation&&(t.implementation=1),new e(t)}}xk.className="LSTM",Go(xk);class wk extends dk{constructor(e){super(e),this.cells=e.cells}get stateSize(){const e=[];for(const t of this.cells.slice().reverse())Array.isArray(t.stateSize)?e.push(...t.stateSize):e.push(t.stateSize);return e}call(e,t){return fo((()=>{let n=e.slice(1);const s=[];for(const e of this.cells.slice().reverse())Array.isArray(e.stateSize)?s.push(n.splice(0,e.stateSize.length)):s.push(n.splice(0,1));s.reverse();const r=[];let a;for(let i=0;i<this.cells.length;++i){const o=this.cells[i];n=s[i],a=0===i?[e[0]].concat(n):[a[0]].concat(n),a=o.call(a,t),r.push(a.slice(1))}n=[];for(const e of r.slice().reverse())n.push(...e);return[a[0]].concat(n)}))}build(e){let t;jb(e)&&(e=e[0]),this.cells.forEach(((n,s)=>{Zy(`RNNCell_${s}`,(()=>{n.build(e),t=Array.isArray(n.stateSize)?n.stateSize[0]:n.stateSize,e=[e[0],t]}))})),this.built=!0}getConfig(){const e=super.getConfig(),t={cells:this.cells.map((e=>({className:e.getClassName(),config:e.getConfig()})))};return Object.assign(Object.assign({},e),t)}static fromConfig(e,t,n={}){const s=[];for(const e of t.cells)s.push(sw(e,n));return new e({cells:s})}get trainableWeights(){if(!this.trainable)return[];const e=[];for(const t of this.cells)e.push(...t.trainableWeights);return e}get nonTrainableWeights(){const e=[];for(const t of this.cells)e.push(...t.nonTrainableWeights);if(!this.trainable){const t=[];for(const e of this.cells)t.push(...e.trainableWeights);return t.concat(e)}return e}getWeights(){const e=[];for(const t of this.cells)e.push(...t.weights);return Qb(e)}setWeights(e){const t=[];for(const n of this.cells){const s=n.weights.length,r=e.splice(s);for(let e=0;e<n.weights.length;++e)t.push([n.weights[e],r[e]])}ex(t)}}function vk(e){const{ones:t,rate:n,training:s=!1,count:r=1,dropoutFunc:a}=e,i=()=>null!=a?a(t(),n):kb(t(),n),o=()=>Ib(i,t,s);if(!r||r<=1)return go(o().clone());return Array(r).fill(void 0).map(o).map((e=>go(e.clone())))}wk.className="StackedRNNCells",Go(wk);var kk=function(e,t){var n={};for(var s in e)Object.prototype.hasOwnProperty.call(e,s)&&t.indexOf(s)<0&&(n[s]=e[s]);if(null!=e&&"function"==typeof Object.getOwnPropertySymbols){var r=0;for(s=Object.getOwnPropertySymbols(e);r<s.length;r++)t.indexOf(s[r])<0&&Object.prototype.propertyIsEnumerable.call(e,s[r])&&(n[s[r]]=e[s[r]])}return n};class Ik extends pk{constructor(e){if(e.unroll)throw new fy("Unrolling is not possible with convolutional RNNs.");if(Array.isArray(e.cell))throw new fy("It is not possible at the moment to stack convolutional cells.");super(e),this.inputSpec=[new tx({ndim:5})]}call(e,t){return fo((()=>{if(null!=this.cell.dropoutMask&&(mo(this.cell.dropoutMask),this.cell.dropoutMask=null),null!=this.cell.recurrentDropoutMask&&(mo(this.cell.recurrentDropoutMask),this.cell.recurrentDropoutMask=null),t&&t.constants)throw new dy("ConvRNN2D cell does not support constants");const n=null==t?null:t.mask,s=null==t?null:t.training,r=null==t?null:t.initialState;return super.call(e,{mask:n,training:s,initialState:r})}))}computeOutputShape(e){let t=this.computeSingleOutputShape(e);return this.returnSequences||(t=[t[0],...t.slice(2)]),this.returnState&&(t=[t,...Array(2).fill([e[0],...t.slice(-3)])]),t}getInitialState(e){return fo((()=>{const{stateSize:t}=this.cell,n=e.shape,s=this.computeSingleOutputShape(n),r=Gh([s[0],...s.slice(2)]);return Array.isArray(t)?Array(t.length).fill(r):[r]}))}resetStates(e,t=!1){fo((()=>{if(!this.stateful)throw new hy("Cannot call resetStates() on an RNN Layer that is not stateful.");const n=this.inputSpec[0].shape,s=this.computeSingleOutputShape(n),r=[s[0],...s.slice(2)];if(null==n[0])throw new dy("If an RNN is stateful, it needs to know its batch size. Specify the batch size of your input tensors: \n- If using a Sequential model, specify the batch size by passing a `batchInputShape` option to your first layer.\n- If using the functional API, specify the batch size by passing a `batchShape` option to your Input layer.");if(null==this.getStates())Array.isArray(this.cell.stateSize)?this.states_=this.cell.stateSize.map((()=>Gh(r))):this.states_=[Gh(r)];else if(null==e)mo(this.states_),null!=this.keptStates&&(mo(this.keptStates),this.keptStates=[]),Array.isArray(this.cell.stateSize)?this.states_=this.cell.stateSize.map((()=>Gh(r))):this.states_[0]=Gh(r);else{if(Array.isArray(e)||(e=[e]),e.length!==this.states_.length)throw new dy(`Layer ${this.name} expects ${this.states_.length} state(s), but it received ${e.length} state value(s). Input received: ${e}`);t?this.keptStates.push(this.states_.slice()):mo(this.states_);for(let t=0;t<this.states_.length;++t){const n=e[t],s=r;if(!pe(n.shape,s))throw new dy(`State ${t} is incompatible with layer ${this.name}: expected shape=${s}, received shape=${n.shape}`);this.states_[t]=n}}this.states_=this.states_.map((e=>go(e.clone())))}))}computeSingleOutputShape(e){const{dataFormat:t,filters:n,kernelSize:s,padding:r,strides:a,dilationRate:i}=this.cell,o="channelsFirst"===t,l=e[o?3:2],u=e[o?4:3],c=Hv(l,s[0],r,a[0],i[0]),h=Hv(u,s[1],r,a[1],i[1]);return[...e.slice(0,2),...o?[n,c,h]:[c,h,n]]}}Ik.className="ConvRNN2D";class Nk extends bk{constructor(e){const{filters:t,kernelSize:n,strides:s,padding:r,dataFormat:a,dilationRate:i}=e;super(Object.assign(Object.assign({},e),{units:t})),this.filters=t,_y(this.filters,"filters"),this.kernelSize=Gv(n,2,"kernelSize"),this.kernelSize.forEach((e=>_y(e,"kernelSize"))),this.strides=Gv(s||1,2,"strides"),this.strides.forEach((e=>_y(e,"strides"))),this.padding=r||"valid",qy(this.padding),this.dataFormat=a||"channelsLast",jy(this.dataFormat),this.dilationRate=Gv(i||1,2,"dilationRate"),this.dilationRate.forEach((e=>_y(e,"dilationRate")))}build(e){var t;e=Xb(e);const n="channelsFirst"===this.dataFormat?1:e.length-1;if(null==e[n])throw new dy(`The channel dimension of the input should be defined. Found ${e[n]}`);const s=e[n],r=this.kernelSize.concat([s,4*this.filters]);this.kernel=this.addWeight("kernel",r,null,this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint);const a=this.kernelSize.concat([this.filters,4*this.filters]);if(this.recurrentKernel=this.addWeight("recurrent_kernel",a,null,this.recurrentInitializer,this.recurrentRegularizer,!0,this.recurrentConstraint),this.useBias){let e;if(this.unitForgetBias){const n=this.biasInitializer,s=this.filters;e=new((t=class extends Tb{apply(e,t){return db([n.apply([s]),Hh([s]),n.apply([2*s])])}}).className="CustomInit",t)}else e=this.biasInitializer;this.bias=this.addWeight("bias",[4*this.filters],null,e,this.biasRegularizer,!0,this.biasConstraint)}this.built=!0}call(e,t){return fo((()=>{if(3!==e.length)throw new dy(`ConvLSTM2DCell expects 3 input Tensors (inputs, h, c), got ${e.length}.`);const n=t.training||!1,s=e[0],r=e[1],a=e[2];0<this.dropout&&this.dropout<1&&null==this.dropoutMask&&(this.dropoutMask=vk({ones:()=>ep(s),rate:this.dropout,training:n,count:4,dropoutFunc:this.dropoutFunc}));const i=this.dropoutMask,o=(e,t,n)=>t&&t[n]?Ao(t[n],e):e;let l=o(s,i,0),u=o(s,i,1),c=o(s,i,2),h=o(s,i,3);0<this.recurrentDropout&&this.recurrentDropout<1&&null==this.recurrentDropoutMask&&(this.recurrentDropoutMask=vk({ones:()=>ep(r),rate:this.recurrentDropout,training:n,count:4,dropoutFunc:this.dropoutFunc}));const p=this.recurrentDropoutMask;let d=o(r,p,0),f=o(r,p,1),m=o(r,p,2),g=o(r,p,3);const[y,b,x,w]=Xp(this.kernel.read(),4,3),[v,k,I,N]=this.useBias?Xp(this.bias.read(),4):[null,null,null,null];l=this.inputConv(l,y,v,this.padding),u=this.inputConv(u,b,k,this.padding),c=this.inputConv(c,x,I,this.padding),h=this.inputConv(h,w,N,this.padding);const[S,T,C,$]=Xp(this.recurrentKernel.read(),4,3);d=this.recurrentConv(d,S),f=this.recurrentConv(f,T),m=this.recurrentConv(m,C),g=this.recurrentConv(g,$);const E=this.recurrentActivation.apply(Co(l,d)),A=this.recurrentActivation.apply(Co(u,f)),R=Co(Ao(A,a),Ao(E,this.activation.apply(Co(c,m)))),F=Ao(this.recurrentActivation.apply(Co(h,g)),this.activation.apply(R));return[F,F,R]}))}getConfig(){const e=super.getConfig(),{units:t}=e,n=kk(e,["units"]),s={filters:this.filters,kernelSize:this.kernelSize,padding:this.padding,dataFormat:this.dataFormat,dilationRate:this.dilationRate,strides:this.strides};return Object.assign(Object.assign({},n),s)}inputConv(e,t,n,s){const r=Tc(e,t,this.strides,s||"valid","channelsFirst"===this.dataFormat?"NCHW":"NHWC",this.dilationRate);return n?vb(r,n,this.dataFormat):r}recurrentConv(e,t){return Tc(e,t,1,"same","channelsFirst"===this.dataFormat?"NCHW":"NHWC")}}Nk.className="ConvLSTM2DCell",Go(Nk);class Sk extends Ik{constructor(e){const t=new Nk(e);super(Object.assign(Object.assign({},e),{cell:t}))}static fromConfig(e,t){return new e(t)}}Sk.className="ConvLSTM2D",Go(Sk);class Tk extends ix{constructor(e){super(e),this.rate=Math.max(Math.min(e.rate,1),0),this.noiseShape=e.noiseShape,this.seed=e.seed,this.supportsMasking=!0}getNoiseShape(e){if(null==this.noiseShape)return this.noiseShape;const t=e.shape,n=[];for(let e=0;e<this.noiseShape.length;++e)n.push(null==this.noiseShape[e]?t[e]:this.noiseShape[e]);return n}call(e,t){return fo((()=>{this.invokeCallHook(e,t);const n=Kb(e);if(0<this.rate&&this.rate<1){const e=null!=t.training&&t.training,s=this.getNoiseShape(n);return Ib((()=>kb(n,this.rate,s,this.seed)),(()=>n),e)}return e}))}getConfig(){const e={rate:this.rate,noiseShape:this.noiseShape,seed:this.seed},t=super.getConfig();return Object.assign(e,t),e}dispose(){return super.dispose()}}Tk.className="Dropout",Go(Tk);class Ck extends Tk{constructor(e){super(e),this.inputSpec=[{ndim:3}]}getNoiseShape(e){const t=e.shape;return[t[0],1,t[2]]}}Ck.className="SpatialDropout1D",Go(Ck);class $k extends ix{constructor(e){if(super(e),this.activation=null,this.useBias=!0,this.kernel=null,this.bias=null,this.DEFAULT_KERNEL_INITIALIZER="glorotNormal",this.DEFAULT_BIAS_INITIALIZER="zeros",null==e.batchInputShape&&null==e.inputShape&&null!=e.inputDim){let t=null;null!=e.batchSize&&(t=e.batchSize),this.batchInputShape=[t,e.inputDim]}this.units=e.units,_y(this.units,"units"),this.activation=Av(e.activation),null!=e.useBias&&(this.useBias=e.useBias),this.kernelInitializer=Hb(e.kernelInitializer||this.DEFAULT_KERNEL_INITIALIZER),this.biasInitializer=Hb(e.biasInitializer||this.DEFAULT_BIAS_INITIALIZER),this.kernelConstraint=Tx(e.kernelConstraint),this.biasConstraint=Tx(e.biasConstraint),this.kernelRegularizer=Lv(e.kernelRegularizer),this.biasRegularizer=Lv(e.biasRegularizer),this.activityRegularizer=Lv(e.activityRegularizer),this.supportsMasking=!0,this.inputSpec=[{minNDim:2}]}build(e){const t=(e=Xb(e))[e.length-1];null==this.kernel&&(this.kernel=this.addWeight("kernel",[t,this.units],null,this.kernelInitializer,this.kernelRegularizer,!0,this.kernelConstraint),this.useBias&&(this.bias=this.addWeight("bias",[this.units],null,this.biasInitializer,this.biasRegularizer,!0,this.biasConstraint))),this.inputSpec=[{minNDim:2,axes:{[-1]:t}}],this.built=!0}computeOutputShape(e){const t=(e=Xb(e)).slice();return t[t.length-1]=this.units,t}call(e,t){return fo((()=>{this.invokeCallHook(e,t);const n=Kb(e),s=Oy(this.activation.getClassName());let r;return null!=s?r=yb(n,this.kernel.read(),s,this.bias?this.bias.read():null):(r=yb(n,this.kernel.read()),null!=this.bias&&(r=vb(r,this.bias.read())),null!=this.activation&&(r=this.activation.apply(r))),r}))}getConfig(){const e={units:this.units,activation:$v(this.activation),useBias:this.useBias,kernelInitializer:Gb(this.kernelInitializer),biasInitializer:Gb(this.biasInitializer),kernelRegularizer:Ov(this.kernelRegularizer),biasRegularizer:Ov(this.biasRegularizer),activityRegularizer:Ov(this.activityRegularizer),kernelConstraint:Nx(this.kernelConstraint),biasConstraint:Nx(this.biasConstraint)},t=super.getConfig();return Object.assign(e,t),e}}$k.className="Dense",Go($k);class Ek extends ix{constructor(e){super(e=e||{}),this.inputSpec=[{minNDim:3}],this.dataFormat=e.dataFormat}computeOutputShape(e){e=Xb(e);for(const t of e.slice(1))if(null==t)throw new dy(`The shape of the input to "Flatten" is not fully defined (got ${e.slice(1)}). Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model.`);return[e[0],nb(e,1)]}call(e,t){return fo((()=>{this.invokeCallHook(e,t);let n=Kb(e);if("channelsFirst"===this.dataFormat&&n.rank>1){const e=[0];for(let t=2;t<n.rank;++t)e.push(t);e.push(1),n=_l(n,e)}return function(e){if(e.rank<=1)throw new dy(`batchFlatten requires a minimum rank of 2. Got rank: ${e.rank}.`);const t=[e.shape[0],nb(e.shape,1)];return sc(e,t)}(n)}))}getConfig(){const e={};null!=this.dataFormat&&(e.dataFormat=this.dataFormat);const t=super.getConfig();return Object.assign(e,t),e}}Ek.className="Flatten",Go(Ek);class Ak extends ix{constructor(e){super(e),this.supportsMasking=!0,this.activation=Av(e.activation)}call(e,t){return fo((()=>{this.invokeCallHook(e,t);const n=Kb(e);return this.activation.apply(n)}))}getConfig(){const e={activation:$v(this.activation)},t=super.getConfig();return Object.assign(e,t),e}}Ak.className="Activation",Go(Ak);class Rk extends ix{constructor(e){super(e),this.n=e.n,this.inputSpec=[{ndim:2}]}computeOutputShape(e){return[e[0],this.n,e[1]]}call(e,t){return fo((()=>{return e=Kb(e),t=e,n=this.n,fo((()=>{if(2!==t.shape.length)throw new dy(`repeat() expects a rank-2 tensor, but received a rank-${t.shape.length} tensor.`);return mb(ub(t,1),[1,n,1])}));var t,n}))}getConfig(){const e={n:this.n},t=super.getConfig();return Object.assign(e,t),e}}Rk.className="RepeatVector",Go(Rk);class Fk extends ix{constructor(e){super(e),this.targetShape=e.targetShape;for(let e=0;e<this.targetShape.length;++e)this.isUnknown(this.targetShape[e])&&(this.targetShape[e]=null)}isUnknown(e){return e<0||null==e}fixUnknownDimension(e,t){const n="Total size of new array must be unchanged.",s=t.slice();let r=1,a=null;for(let e=0;e<s.length;++e){const t=s[e];if(this.isUnknown(t)){if(null!==a)throw new dy("Can only specifiy one unknown dimension.");a=e}else r*=t}const i=nb(e);if(null!==a){if(0===r||i%r!=0)throw new dy(n);s[a]=i/r}else if(i!==r)throw new dy(n);return s}computeOutputShape(e){let t=!1;for(let n=0;n<e.length;++n)if(this.isUnknown(e[n])){t=!0;break}return t?e.slice(0,1).concat(this.targetShape):e.slice(0,1).concat(this.fixUnknownDimension(e.slice(1),this.targetShape))}call(e,t){return fo((()=>{this.invokeCallHook(e,t);const n=Kb(e),s=n.shape,r=s.slice(0,1).concat(this.fixUnknownDimension(s.slice(1),this.targetShape));return sc(n,r)}))}getConfig(){const e={targetShape:this.targetShape},t=super.getConfig();return Object.assign(e,t),e}}Fk.className="Reshape",Go(Fk);class _k extends ix{constructor(e){if(super(e),null==e.dims)throw new Error("Required configuration field `dims` is missing during Permute constructor call.");if(!Array.isArray(e.dims))throw new Error(`Permute constructor requires \`dims\` to be an Array, but received ${e.dims} instead.`);const t=ab(1,e.dims.length+1);if(!pe(e.dims.slice().sort(),t))throw new Error("Invalid permutation `dims`: "+JSON.stringify(e.dims)+" `dims` must contain consecutive integers starting from 1.");this.dims=e.dims,this.dimsIncludingBatch=[0].concat(this.dims),this.inputSpec=[new tx({ndim:this.dims.length+1})]}computeOutputShape(e){const t=(e=Xb(e)).slice();return this.dims.forEach(((n,s)=>{t[s+1]=e[n]})),t}call(e,t){return _l(Kb(e),this.dimsIncludingBatch)}getConfig(){const e={dims:this.dims},t=super.getConfig();return Object.assign(e,t),e}}_k.className="Permute",Go(_k);class Dk extends ix{constructor(e){super(null==e?{}:e),this.supportsMasking=!0,this.maskValue=null!=e?null==e.maskValue?0:e.maskValue:0}computeOutputShape(e){return e}getConfig(){const e=super.getConfig(),t={maskValue:this.maskValue};return Object.assign(t,e),t}computeMask(e,t){const n=Kb(e);return Du(Qh(n,this.maskValue),-1)}call(e,t){return fo((()=>{this.invokeCallHook(e,t);const n=Kb(e),s=Du(Qh(n,this.maskValue),-1,!0);return Ao(n,no(s,n.dtype))}))}}Dk.className="Masking",Go(Dk);class Ok extends ix{constructor(e){if(super(e),this.embeddings=null,this.DEFAULT_EMBEDDINGS_INITIALIZER="randomUniform",null==e.batchInputShape&&null==e.inputShape){let t=null;null!=e.batchSize&&(t=e.batchSize),null==e.inputLength?this.batchInputShape=[t,null]:this.batchInputShape=[t].concat(vy(e.inputLength))}this.inputDim=e.inputDim,_y(this.inputDim,"inputDim"),this.outputDim=e.outputDim,_y(this.outputDim,"outputDim"),this.embeddingsInitializer=Hb(e.embeddingsInitializer||this.DEFAULT_EMBEDDINGS_INITIALIZER),this.embeddingsRegularizer=Lv(e.embeddingsRegularizer),this.activityRegularizer=Lv(e.activityRegularizer),this.embeddingsConstraint=Tx(e.embeddingsConstraint),this.maskZero=e.maskZero,this.supportsMasking=e.maskZero,this.inputLength=e.inputLength}build(e){this.embeddings=this.addWeight("embeddings",[this.inputDim,this.outputDim],this.dtype,this.embeddingsInitializer,this.embeddingsRegularizer,!0,this.embeddingsConstraint),this.built=!0}warnOnIncompatibleInputShape(e){}computeMask(e,t){return fo((()=>this.maskZero?(e=Kb(e),Qh(e,_o(e))):null))}computeOutputShape(e){if(e=Xb(e),null==this.inputLength)return[...e,this.outputDim];const t=vy(this.inputLength);if(t.length!==e.length-1)throw new dy(`"inputLength" is ${this.inputLength}, but received input shape has shape ${e}`);{let n=0;for(let s=0;s<t.length;++s){const r=t[s],a=e[s+1];if(null!=r&&null!=a&&r!==a)throw new dy(`"inputLength" is ${this.inputLength}, but received input shape has shape ${e}`);null==r&&(t[n]=a),n++}}return[e[0],...t,this.outputDim]}call(e,t){return fo((()=>{this.invokeCallHook(e,t);let n=Kb(e);"int32"!==n.dtype&&(n=lb(n,"int32"));const s=bb(this.embeddings.read(),sc(n,[n.size]));return sc(s,Xb(this.computeOutputShape(n.shape)))}))}getConfig(){const e={inputDim:this.inputDim,outputDim:this.outputDim,embeddingsInitializer:Gb(this.embeddingsInitializer),embeddingsRegularizer:Ov(this.embeddingsRegularizer),activityRegularizer:Ov(this.activityRegularizer),embeddingsConstraint:Nx(this.embeddingsConstraint),maskZero:this.maskZero,inputLength:this.inputLength},t=super.getConfig();return Object.assign(e,t),e}}Ok.className="Embedding",Go(Ok);class Mk extends ix{constructor(e){super(e||{}),this.supportsMasking=!0}mergeFunction(e){throw new fy}computeElementwiseOpOutputShape(e,t){if(null==e||null==t)return null;if(e.length<t.length)return this.computeElementwiseOpOutputShape(t,e);if(0===t.length)return e;const n=e.slice(0,e.length-t.length);for(let s=0;s<t.length;++s){const r=e[e.length-t.length+s],a=t[s];if(null==r||null==a||r<0||a<0)n.push(null);else if(1===r)n.push(a);else if(1===a)n.push(r);else{if(r!==a)throw new dy("Operands could not be broadcast together with shapes "+JSON.stringify(e)+" "+JSON.stringify(t));n.push(r)}}return n}build(e){if(Array.isArray(e)&&!Array.isArray(e[0])&&(e=[Xb(e)]),e.length<2)throw new dy(`A merge layer should be called on an Array of at least 2 inputs. Got ${e.length} input(s).`);let t=[];for(const n of e)null!=n&&null!==n[0]&&t.push(n[0]);if(t=Ey(t),t.length>1)throw new dy(`Can not merge tensors with different batch sizes. Got tensors with shapes: ${JSON.stringify(e)}.`);let n=null==e[0]?null:e[0].slice(1);for(let t=1;t<e.length;++t){const s=null==e[t]?null:e[t].slice(1);n=this.computeElementwiseOpOutputShape(n,s)}const s=e.map((e=>e.length));-1===e.indexOf(null)&&1===Ey(s).length?this.reshapeRequired=!1:this.reshapeRequired=!0}call(e,t){return fo((()=>{if(this.reshapeRequired){const t=[],n=e.map((e=>e.rank));if(-1===n.indexOf(null)){const s=rb(n);for(let n of e){const e=n.rank;for(let t=0;t<s-e;++t)n=ub(n,1);t.push(n)}return this.mergeFunction(t)}{let n=!1;for(const s of e){const e=s.rank;if(null==e){const e=s.shape,r=e[0],a=e.slice(1).concat([r]);let i=sc(s,[r].concat(nb(e.slice(1))));i=_l(i,[1,0]),i=sc(i,a),t.push(i),n=!0}else if(e>1){const r=ab(1,e).concat([0]);t.push(_l(s,r)),n=!0}else t.push(s)}let s=this.mergeFunction(t);const r=s.rank;if(n)if(null==r){const e=s.shape,t=e[e.length-1],n=[t].concat(e.slice(0,e.length-1));s=sc(_l(sc(s,[-1,t]),[1,0]),n)}else if(r>1){const e=[r-1].concat(ab(0,r-1));s=_l(s,e)}return s}}return this.mergeFunction(e)}))}computeOutputShape(e){let t;t=null==e[0]?null:e[0].slice(1);for(let n=1;n<e.length;++n){const s=null==e[n]?null:e[n].slice(1);t=this.computeElementwiseOpOutputShape(t,s)}let n=[];for(const t of e)null!=t&&null!==t[0]&&n.push(t[0]);return n=Ey(n),t=1===n.length?n.concat(t):[null].concat(t),t}computeMask(e,t){return fo((()=>{if(null==t)return null;if(!Array.isArray(t))throw new dy("`mask` should be an Array");if(!Array.isArray(e))throw new dy("`inputs` should be an Array");if(t.length!==e.length)throw new dy(`The Array 'inputs' and 'mask' are expected to have the same length, but have different lengths (${e.length} vs ${t.length})`);if(t.every((e=>null==e)))return null;let n=(t=t.map((e=>null==e?e:hh(e,0))))[0];for(let e=1;e<t.length-1;++e)n=_h(n,t[e]);return n}))}}class Lk extends Mk{constructor(e){super(e)}mergeFunction(e){return fo((()=>{let t=e[0].clone();for(let n=1;n<e.length;++n)t=Co(t,e[n]);return t}))}}Lk.className="Add",Go(Lk);class zk extends Mk{constructor(e){super(e)}mergeFunction(e){return fo((()=>{let t=e[0].clone();for(let n=1;n<e.length;++n)t=Ao(t,e[n]);return t}))}}zk.className="Multiply",Go(zk);class Pk extends Mk{constructor(e){super(e)}mergeFunction(e){return fo((()=>{let t=e[0].clone();for(let n=1;n<e.length;++n)t=Co(t,e[n]);return Ao(1/e.length,t)}))}}Pk.className="Average",Go(Pk);class Bk extends Mk{constructor(e){super(e)}mergeFunction(e){return fo((()=>{let t=e[0];for(let n=1;n<e.length;++n)t=nl(t,e[n]);return t}))}}Bk.className="Maximum",Go(Bk);class Wk extends Mk{constructor(e){super(e)}mergeFunction(e){return fo((()=>{let t=e[0];for(let n=1;n<e.length;++n)t=qh(t,e[n]);return t}))}}Wk.className="Minimum",Go(Wk);class Vk extends Mk{constructor(e){super(e),this.DEFAULT_AXIS=-1,null==e&&(e={}),this.axis=null==e.axis?this.DEFAULT_AXIS:e.axis,this.supportsMasking=!0,this.reshapeRequired=!1}build(e){if(!Array.isArray(e)||!Array.isArray(e[0])||1===e.length)throw new dy("A `Concatenate` layer should be called on a list of at least 2 inputs");let t=!0;for(const n of e)if(null!=n){t=!1;break}if(t)return;const n=[];for(let t=0;t<e.length;++t){const s=e[t].slice();s.splice(this.axis,1);let r=!1;for(const e of n)if(pe(e,s)){r=!0;break}r||n.push(s)}if(n.length>1)throw new dy("A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got input shapes: "+JSON.stringify(e))}mergeFunction(e){return fo((()=>db(e,this.axis)))}computeOutputShape(e){if(!Array.isArray(e)||!Array.isArray(e[0]))throw new dy("A `Concatenate` layer should be called on a list of inputs.");const t=e,n=t[0].slice(),s=this.axis<0?n.length+this.axis:this.axis;for(const e of t.slice(1)){if(null==n[s]||null==e[s]){n[s]=null;break}n[s]+=e[s]}return n}computeMask(e,t){if(null==t)return null;if(!Array.isArray(t))throw new dy("`mask` should be an array for Concatenate");if(!Array.isArray(e))throw new dy("`inputs` should be an array for Concatenate");if(t.length!==e.length)throw new dy(`Mismatch in the length of mask (${t.length}) and the legnth of inputs (${e.length})`);return fo((()=>{let n=!0;if(t.forEach((e=>{null==e||(n=!1)})),n)return null;const s=[];for(let n=0;n<e.length;++n)null==t[n]?s.push(no(ep(e[n]),"bool")):t[n].rank<e[n].rank?s.push(hh(t[n],-1)):s.push(t[n]);const r=ic(s,this.axis);return _u(r,-1,!1)}))}getConfig(){const e={axis:this.axis},t=super.getConfig();return Object.assign(e,t),e}}function Uk(e,t){for(;e<0;)e+=t;return e}Vk.className="Concatenate",Go(Vk);class Gk extends Mk{constructor(e){super(e),this.axes=e.axes,this.normalize=null!=e.normalize&&e.normalize,this.supportsMasking=!0,this.reshapeRequired=!1}build(e){ie(Array.isArray(e)&&2===e.length&&Array.isArray(e[0])&&Array.isArray(e[1]),(()=>"A `Dot` layer should be called on a list of exactly 2 inputs."));const t=e[0],n=e[1];if(t.length>3||n.length>3)throw new fy("Dot layer does not support tensors of 4D or higher rank yet.");const s=this.interpretAxes(t,n);if(t[s[0]]!==n[s[1]])throw new dy(`Dimension incompatibility: ${t[s[0]]} !== ${n[s[1]]}`)}mergeFunction(e){if(2!==e.length)throw new dy(`A \`Dot\` layer must be called on exactly 2 inputs, but received ${e.length} input(s).`);let t,n=e[0],s=e[1];return t=Array.isArray(this.axes)?this.axes.map(((t,n)=>Uk(t,e[n].shape.length))):[Uk(this.axes,n.shape.length),Uk(this.axes,s.shape.length)],this.normalize&&(n=rw(n,t[0]),s=rw(s,t[1])),function(e,t,n){if(e.shape.length>3||t.shape.length>3)throw new fy("batchDot is not implemented for tensors of 4D or higher rank yet");if(ie(e.shape.length>=2,(()=>`batchDot requires the rank of x to be >= 2, but got ${e.shape.length}`)),ie(e.shape.length>=2,(()=>`batchDot requires the rank of y to be >= 2, but got ${t.shape.length}`)),"number"==typeof n&&(n=[n,n]),"complex64"===e.dtype||"complex64"===t.dtype)throw new fy("batchDot is not implemented for complex64-type Tensors yet.");const s=e.shape.length,r=t.shape.length;null==n&&(n=[s-1,r-2]);const a=n;return fo((()=>{let n,i;if(s>r){n=s-r;const e=[];for(let t=0;t<n;++t)e.push(1);t=sc(t,t.shape.concat(e))}else if(r>s){n=r-s;const t=[];for(let e=0;e<n;++e)t.push(1);e=sc(e,e.shape.concat(t))}else n=0;if(2===e.shape.length&&2===t.shape.length)i=a[0]===a[1]?ih(Ao(e,t),a[0]):ih(Ao(_l(e,[1,0]),t),a[1]);else{const n=a[0]!==e.shape.length-1,s=a[1]===t.shape.length-1;i=$l(e,t,n,s)}if(n>0){let e;e=s>r?s+r-3:s-1;const t=[];for(let s=e;s<e+n;++s)t.push(s);i=Jp(i,t)}return 1===i.shape.length&&(i=hh(i,1)),i}))}(n,s,t)}interpretAxes(e,t){let n;return n=Array.isArray(this.axes)?this.axes:[Uk(this.axes,e.length),Uk(this.axes,t.length)],n}computeOutputShape(e){ie(Array.isArray(e)&&2===e.length&&Array.isArray(e[0])&&Array.isArray(e[1]),(()=>"A `Dot` layer should be called on a list of exactly 2 inputs."));const t=e[0].slice(),n=e[1].slice();if(t.length>3||n.length>3)throw new fy("Dot layer does not support tensors of 4D or higher rank yet.");const s=this.interpretAxes(t,n);t.splice(s[0],1),n.splice(s[1],1),n.splice(0,1);const r=t.concat(n);return 1===r.length&&r.push(1),r}computeMask(e,t){return null}getConfig(){const e={axes:this.axes,normalize:this.normalize},t=super.getConfig();return Object.assign(e,t),e}}Gk.className="Dot",Go(Gk);class Hk extends ix{constructor(e){super(e),this.supportsMasking=!0,this.stddev=e.stddev}computeOutputShape(e){return e}getConfig(){const e=super.getConfig(),t={stddev:this.stddev};return Object.assign(t,e),t}call(e,t){return fo((()=>{this.invokeCallHook(e,t);const n=Kb(e);return Ib((()=>Co(gb(n.shape,0,this.stddev),n)),(()=>n),t.training||!1)}))}}Hk.className="GaussianNoise",Go(Hk);class jk extends ix{constructor(e){super(e),this.supportsMasking=!0,this.rate=e.rate}computeOutputShape(e){return e}getConfig(){const e=super.getConfig(),t={rate:this.rate};return Object.assign(t,e),t}call(e,t){return fo((()=>{this.invokeCallHook(e,t);const n=Kb(e);if(this.rate>0&&this.rate<1){return Ib((()=>{const e=Math.sqrt(this.rate/(1-this.rate));return Ao(n,gb(n.shape,1,e))}),(()=>n),t.training||!1)}return n}))}}jk.className="GaussianDropout",Go(jk);class qk extends ix{constructor(e){super(e),this.supportsMasking=!0,this.rate=e.rate,this.noiseShape=e.noiseShape}_getNoiseShape(e){return this.noiseShape||Kb(e).shape}computeOutputShape(e){return e}getConfig(){const e=super.getConfig(),t={rate:this.rate};return Object.assign(t,e),t}call(e,t){return fo((()=>{if(this.rate<1&&this.rate>0){const n=this._getNoiseShape(e),s=()=>{const t=Kb(e),s=-1.7580993408473766;let r=bh(kp(n),this.rate);r=lb(r,"float32");const a=((1-this.rate)*(1+this.rate*s**2))**-.5,i=-a*s*this.rate,o=Co(Ao(t,r),Ao(Co(r,-1),s));return Co(Ao(o,a),i)};return Ib(s,(()=>Kb(e)),t.training||!1)}return e}))}}function Kk(e,t,n,s,r,a=.001){let i;if(2===e.rank)i=dc(e,t,n,s,r,a);else if(3===e.rank)i=fc(e,t,n,s,r,a);else{if(4!==e.rank)throw new fy(`batchNormalization is not implemented for array of rank ${e.rank} yet`);i=mc(e,t,n,s,r,a)}return i}function Xk(e,t,n,s,r=.001){return pe(s.slice().sort(),ab(0,e.rank-1))?function(e,t,n,s,r=.001){return fo((()=>{const a=Yh(e,s),i=a.mean,o=a.variance;return[Kk(e,i,o,n,t,r),i,o]}))}(e,t,n,s,r):function(e,t,n,s,r=.001){return fo((()=>{const a=Yh(e,s),i=a.mean,o=a.variance,l=[];for(const t of ab(0,e.rank))-1!==s.indexOf(t)?l.push(1):l.push(e.shape[t]);const u=sc(i,l),c=sc(o,l),h=null==t?null:sc(t,l),p=null==n?null:sc(n,l);return[Kk(e,u,c,p,h,r),i,o]}))}(e,t,n,s,r)}qk.className="AlphaDropout",Go(qk);class Yk extends ix{constructor(e){null==e&&(e={}),super(e),this.supportsMasking=!0,this.axis=null==e.axis?-1:e.axis,this.momentum=null==e.momentum?.99:e.momentum,this.epsilon=null==e.epsilon?.001:e.epsilon,this.center=null==e.center||e.center,this.scale=null==e.scale||e.scale,this.betaInitializer=Hb(e.betaInitializer||"zeros"),this.gammaInitializer=Hb(e.gammaInitializer||"ones"),this.movingMeanInitializer=Hb(e.movingMeanInitializer||"zeros"),this.movingVarianceInitializer=Hb(e.movingVarianceInitializer||"ones"),this.betaConstraint=Tx(e.betaConstraint),this.gammaConstraint=Tx(e.gammaConstraint),this.betaRegularizer=Lv(e.betaRegularizer),this.gammaRegularizer=Lv(e.gammaRegularizer)}build(e){e=Xb(e);const t=this.axis>=0?this.axis:this.axis+e.length,n=e[t];if(null==n)throw new dy(`Axis ${t} of input tensor should have a defined dimension but the layer received an input with shape ${JSON.stringify(e)}.`);this.inputSpec=[new tx({ndim:e.length,axes:{[t]:n}})];const s=[n];this.scale&&(this.gamma=this.addWeight("gamma",s,null,this.gammaInitializer,this.gammaRegularizer,!0,this.gammaConstraint)),this.center&&(this.beta=this.addWeight("beta",s,null,this.betaInitializer,this.betaRegularizer,!0,this.betaConstraint)),this.movingMean=this.addWeight("moving_mean",s,null,this.movingMeanInitializer,null,!1),this.movingVariance=this.addWeight("moving_variance",s,null,this.movingVarianceInitializer,null,!1),this.built=!0}call(e,t){return fo((()=>{const n=null!=t.training&&t.training,s=Kb(e),r=s.shape,a=r.length,i=ab(0,a),o=this.axis>=0?this.axis:this.axis+a;i.splice(o,1);const l=yy(1,a);l[o]=r[o];const u=i.slice();u.sort();const c=!pe(u,ab(0,a).slice(0,a-1));if(!n)return(()=>{if(c){const e=sc(this.movingMean.read(),l),t=sc(this.movingVariance.read(),l),n=this.center?sc(this.beta.read(),l):null,r=this.scale?sc(this.gamma.read(),l):null;return Kk(s,e,t,n,r,this.epsilon)}return Kk(s,this.movingMean.read(),this.movingVariance.read(),null==this.beta?null:this.beta.read(),null==this.gamma?null:this.gamma.read(),this.epsilon)})();const[h,p,d]=Xk(s,this.gamma.read(),this.beta.read(),i,this.epsilon),f=(e,t,n)=>{fo((()=>{const s=1-n,r=e.read(),a=Ao(Yo(r,t),s);e.write(Yo(r,a))}))};return(()=>{f(this.movingMean,p,this.momentum),f(this.movingVariance,d,this.momentum)})(),h}))}getConfig(){const e={axis:this.axis,momentum:this.momentum,epsilon:this.epsilon,center:this.center,scale:this.scale,betaInitializer:Gb(this.betaInitializer),gammaInitializer:Gb(this.gammaInitializer),movingMeanInitializer:Gb(this.movingMeanInitializer),movingVarianceInitializer:Gb(this.movingVarianceInitializer),betaRegularizer:Ov(this.betaRegularizer),gammaRegularizer:Ov(this.gammaRegularizer),betaConstraint:Nx(this.betaConstraint),gammaConstraint:Nx(this.gammaConstraint)},t=super.getConfig();return Object.assign(e,t),e}}Yk.className="BatchNormalization",Go(Yk);class Zk extends ix{constructor(e){if(null==e&&(e={}),super(e),this.axis=null==e.axis?-1:e.axis,"number"==typeof this.axis){if(!Number.isInteger(this.axis))throw new Error(`Expected axis to be an integer, but received ${this.axis}`)}else{if(!Array.isArray(this.axis))throw new Error(`Expected axis to be an integer or an array of integers, but received ${JSON.stringify(this.axis)}`);for(const e of this.axis)if(!Number.isInteger(e))throw new Error(`Expected axis to be an array of integers, but received ${JSON.stringify(this.axis)}`)}this.epsilon=null==e.epsilon?.001:e.epsilon,this.center=null==e.center||e.center,this.scale=null==e.scale||e.scale,this.betaInitializer=Hb(e.betaInitializer||"zeros"),this.gammaInitializer=Hb(e.gammaInitializer||"ones"),this.betaRegularizer=Lv(e.betaRegularizer),this.gammaRegularizer=Lv(e.gammaRegularizer),this.supportsMasking=!0}build(e){const t=(e=Xb(e)).length;"number"==typeof this.axis&&(this.axis=[this.axis]);for(let e=0;e<this.axis.length;++e)this.axis[e]<0&&(this.axis[e]+=t);for(const e of this.axis)if(e<0||e>=t)throw new Error(`Invalid axis: ${e}`);if(this.axis.length!==Ey(this.axis).length)throw new Error(`Found duplicate axes in: ${this.axis}`);const n=this.axis.map((t=>e[t]));this.scale?this.gamma=this.addWeight("gamma",n,"float32",this.gammaInitializer,this.gammaRegularizer,true):this.gamma=null,this.center?this.beta=this.addWeight("beta",n,"float32",this.betaInitializer,this.betaRegularizer,true):this.beta=null,this.built=!0}call(e,t){const n=Kb(e),s=n.shape,r=s.length;return fo((()=>{let{mean:e,variance:t}=Yh(n,this.axis,!0);const a=yy(1,r);for(const e of this.axis)a[e]=s[e];const i=e=>null!=e&&e.shape.length!==r?sc(e,a):e;let o=this.scale?i(this.gamma.read()):null,l=this.center?i(this.beta.read()):null;const u=[],c=[];for(let e=0;e<r;++e)-1!==this.axis.indexOf(e)?(u.push(s[e]),c.push(1)):(u.push(1),c.push(s[e]));return e=dh(e,u),t=dh(t,u),null!=o&&(o=dh(o,c)),null!=l&&(l=dh(l,c)),Kk(n,e,t,l,o,this.epsilon)}))}getConfig(){const e={axis:this.axis,epsilon:this.epsilon,center:this.center,scale:this.scale,betaInitializer:Gb(this.betaInitializer),gammaInitializer:Gb(this.gammaInitializer),betaRegularizer:Ov(this.betaRegularizer),gammaRegularizer:Ov(this.gammaRegularizer)},t=super.getConfig();return Object.assign(e,t),e}}Zk.className="LayerNormalization",Go(Zk);class Jk extends ix{constructor(e){if(null==e&&(e={}),super(e),this.dataFormat=null==e.dataFormat?"channelsLast":e.dataFormat,null==e.padding)this.padding=[[1,1],[1,1]];else if("number"==typeof e.padding)this.padding=[[e.padding,e.padding],[e.padding,e.padding]];else{if(e.padding=e.padding,2!==e.padding.length)throw new dy(`ZeroPadding2D expects padding to be a length-2 array, but received a length-${e.padding.length} array.`);let t,n;if("number"==typeof e.padding[0])t=[e.padding[0],e.padding[0]],n=[e.padding[1],e.padding[1]];else{if(e.padding=e.padding,2!==e.padding[0].length)throw new dy(`ZeroPadding2D expects height padding to be a length-2 array, but received a length-${e.padding[0].length} array.`);if(t=e.padding[0],2!==e.padding[1].length)throw new dy(`ZeroPadding2D expects width padding to be a length-2 array, but received a length-${e.padding[1].length} array.`);n=e.padding[1]}this.padding=[t,n]}this.inputSpec=[new tx({ndim:4})]}computeOutputShape(e){let t,n;return e=Xb(e),"channelsFirst"===this.dataFormat?(t=null!=e[2]&&e[2]>=0?e[2]+this.padding[0][0]+this.padding[0][1]:null,n=null!=e[3]&&e[3]>=0?e[3]+this.padding[1][0]+this.padding[1][1]:null,[e[0],e[1],t,n]):(t=null!=e[1]&&e[1]>=0?e[1]+this.padding[0][0]+this.padding[0][1]:null,n=null!=e[2]&&e[2]>=0?e[2]+this.padding[1][0]+this.padding[1][1]:null,[e[0],t,n,e[3]])}call(e,t){return fo((()=>{return t=Kb(e),n=this.padding,s=this.dataFormat,fo((()=>{if(4!==t.rank)throw new dy(`temporalPadding expects input tensor to be 4-D, but received a ${t.rank}-D tensor.`);if(null==n&&(n=[[1,1],[1,1]]),2!==n.length||2!==n[0].length||2!==n[1].length)throw new dy("spatial2dPadding expects `padding` to be an Array of two Arrays, each of which is an Array of two integers.");if(null==s&&(s="channelsLast"),"channelsLast"!==s&&"channelsFirst"!==s)throw new dy(`Unknown data format: ${s}. Supported data formats are 'channelsLast' and 'channelsFirst.`);let e;return e="channelsFirst"===s?[[0,0],[0,0],n[0],n[1]]:[[0,0],n[0],n[1],[0,0]],np(t,e)}));var t,n,s}))}getConfig(){const e={padding:this.padding,dataFormat:this.dataFormat},t=super.getConfig();return Object.assign(e,t),e}}function Qk(e,t,n,s,r,a){return fo((()=>{let i;jy(r),Ky(a),qy(s),null==n&&(n=[1,1]),null==s&&(s="valid"),null==r&&(r="channelsLast"),null==a&&(a="max"),e=qv(e,r);const o="same"===s?"same":"valid";return i="max"===a?Bh(e,t,n,o):rc(e,t,n,o),"channelsFirst"===r&&(i=_l(i,[0,3,1,2])),i}))}function eI(e,t,n,s,r,a){return fo((()=>{let i;jy(r),Ky(a),qy(s),null==n&&(n=[1,1,1]),null==s&&(s="valid"),null==r&&(r="channelsLast"),null==a&&(a="max"),e=Kv(e,r);const o="same"===s?"same":"valid";return i="max"===a?Wh(e,t,n,o):ac(e,t,n,o),"channelsFirst"===r&&(i=_l(i,[0,4,1,2,3])),i}))}Jk.className="ZeroPadding2D",Go(Jk);class tI extends ix{constructor(e){if(null==e.poolSize&&(e.poolSize=2),super(e),"number"==typeof e.poolSize)this.poolSize=[e.poolSize];else{if(!Array.isArray(e.poolSize)||1!==e.poolSize.length||"number"!=typeof e.poolSize[0])throw new dy(`poolSize for 1D convolutional layer must be a number or an Array of a single number, but received ${JSON.stringify(e.poolSize)}`);this.poolSize=e.poolSize}if(_y(this.poolSize,"poolSize"),null==e.strides)this.strides=this.poolSize;else if("number"==typeof e.strides)this.strides=[e.strides];else{if(!Array.isArray(e.strides)||1!==e.strides.length||"number"!=typeof e.strides[0])throw new dy(`strides for 1D convolutional layer must be a number or an Array of a single number, but received ${JSON.stringify(e.strides)}`);this.strides=e.strides}_y(this.strides,"strides"),this.padding=null==e.padding?"valid":e.padding,qy(this.padding),this.inputSpec=[new tx({ndim:3})]}computeOutputShape(e){const t=Hv((e=Xb(e))[1],this.poolSize[0],this.padding,this.strides[0]);return[e[0],t,e[2]]}call(e,t){return fo((()=>{this.invokeCallHook(e,t),e=ub(Kb(e),2);const n=this.poolingFunction(Kb(e),[this.poolSize[0],1],[this.strides[0],1],this.padding,"channelsLast");return Jp(n,[2])}))}getConfig(){const e={poolSize:this.poolSize,padding:this.padding,strides:this.strides},t=super.getConfig();return Object.assign(e,t),e}}class nI extends tI{constructor(e){super(e)}poolingFunction(e,t,n,s,r){return jy(r),qy(s),Qk(e,t,n,s,r,"max")}}nI.className="MaxPooling1D",Go(nI);class sI extends tI{constructor(e){super(e)}poolingFunction(e,t,n,s,r){return jy(r),qy(s),Qk(e,t,n,s,r,"avg")}}sI.className="AveragePooling1D",Go(sI);class rI extends ix{constructor(e){if(null==e.poolSize&&(e.poolSize=[2,2]),super(e),this.poolSize=Array.isArray(e.poolSize)?e.poolSize:[e.poolSize,e.poolSize],null==e.strides)this.strides=this.poolSize;else if(Array.isArray(e.strides)){if(2!==e.strides.length)throw new dy(`If the strides property of a 2D pooling layer is an Array, it is expected to have a length of 2, but received length ${e.strides.length}.`);this.strides=e.strides}else this.strides=[e.strides,e.strides];_y(this.poolSize,"poolSize"),_y(this.strides,"strides"),this.padding=null==e.padding?"valid":e.padding,this.dataFormat=null==e.dataFormat?"channelsLast":e.dataFormat,jy(this.dataFormat),qy(this.padding),this.inputSpec=[new tx({ndim:4})]}computeOutputShape(e){e=Xb(e);let t="channelsFirst"===this.dataFormat?e[2]:e[1],n="channelsFirst"===this.dataFormat?e[3]:e[2];return t=Hv(t,this.poolSize[0],this.padding,this.strides[0]),n=Hv(n,this.poolSize[1],this.padding,this.strides[1]),"channelsFirst"===this.dataFormat?[e[0],e[1],t,n]:[e[0],t,n,e[3]]}call(e,t){return fo((()=>(this.invokeCallHook(e,t),this.poolingFunction(Kb(e),this.poolSize,this.strides,this.padding,this.dataFormat))))}getConfig(){const e={poolSize:this.poolSize,padding:this.padding,strides:this.strides,dataFormat:this.dataFormat},t=super.getConfig();return Object.assign(e,t),e}}class aI extends rI{constructor(e){super(e)}poolingFunction(e,t,n,s,r){return jy(r),qy(s),Qk(e,t,n,s,r,"max")}}aI.className="MaxPooling2D",Go(aI);class iI extends rI{constructor(e){super(e)}poolingFunction(e,t,n,s,r){return jy(r),qy(s),Qk(e,t,n,s,r,"avg")}}iI.className="AveragePooling2D",Go(iI);class oI extends ix{constructor(e){if(null==e.poolSize&&(e.poolSize=[2,2,2]),super(e),this.poolSize=Array.isArray(e.poolSize)?e.poolSize:[e.poolSize,e.poolSize,e.poolSize],null==e.strides)this.strides=this.poolSize;else if(Array.isArray(e.strides)){if(3!==e.strides.length)throw new dy(`If the strides property of a 3D pooling layer is an Array, it is expected to have a length of 3, but received length ${e.strides.length}.`);this.strides=e.strides}else this.strides=[e.strides,e.strides,e.strides];_y(this.poolSize,"poolSize"),_y(this.strides,"strides"),this.padding=null==e.padding?"valid":e.padding,this.dataFormat=null==e.dataFormat?"channelsLast":e.dataFormat,jy(this.dataFormat),qy(this.padding),this.inputSpec=[new tx({ndim:5})]}computeOutputShape(e){e=Xb(e);let t="channelsFirst"===this.dataFormat?e[2]:e[1],n="channelsFirst"===this.dataFormat?e[3]:e[2],s="channelsFirst"===this.dataFormat?e[4]:e[3];return t=Hv(t,this.poolSize[0],this.padding,this.strides[0]),n=Hv(n,this.poolSize[1],this.padding,this.strides[1]),s=Hv(s,this.poolSize[2],this.padding,this.strides[2]),"channelsFirst"===this.dataFormat?[e[0],e[1],t,n,s]:[e[0],t,n,s,e[4]]}call(e,t){return fo((()=>(this.invokeCallHook(e,t),this.poolingFunction(Kb(e),this.poolSize,this.strides,this.padding,this.dataFormat))))}getConfig(){const e={poolSize:this.poolSize,padding:this.padding,strides:this.strides,dataFormat:this.dataFormat},t=super.getConfig();return Object.assign(e,t),e}}class lI extends oI{constructor(e){super(e)}poolingFunction(e,t,n,s,r){return jy(r),qy(s),eI(e,t,n,s,r,"max")}}lI.className="MaxPooling3D",Go(lI);class uI extends oI{constructor(e){super(e)}poolingFunction(e,t,n,s,r){return jy(r),qy(s),eI(e,t,n,s,r,"avg")}}uI.className="AveragePooling3D",Go(uI);class cI extends ix{constructor(e){super(e),this.inputSpec=[new tx({ndim:3})]}computeOutputShape(e){return[e[0],e[2]]}call(e,t){throw new fy}}class hI extends cI{constructor(e){super(e||{})}call(e,t){return fo((()=>{const t=Kb(e);return Uh(t,1)}))}}hI.className="GlobalAveragePooling1D",Go(hI);class pI extends cI{constructor(e){super(e||{})}call(e,t){return fo((()=>{const t=Kb(e);return rh(t,1)}))}}pI.className="GlobalMaxPooling1D",Go(pI);class dI extends ix{constructor(e){super(e),this.dataFormat=null==e.dataFormat?"channelsLast":e.dataFormat,jy(this.dataFormat),this.inputSpec=[new tx({ndim:4})]}computeOutputShape(e){return"channelsLast"===this.dataFormat?[e[0],e[3]]:[e[0],e[1]]}call(e,t){throw new fy}getConfig(){const e={dataFormat:this.dataFormat},t=super.getConfig();return Object.assign(e,t),e}}class fI extends dI{call(e,t){return fo((()=>{const t=Kb(e);return"channelsLast"===this.dataFormat?Uh(t,[1,2]):Uh(t,[2,3])}))}}fI.className="GlobalAveragePooling2D",Go(fI);class mI extends dI{call(e,t){return fo((()=>{const t=Kb(e);return"channelsLast"===this.dataFormat?rh(t,[1,2]):rh(t,[2,3])}))}}mI.className="GlobalMaxPooling2D",Go(mI);class gI extends ix{constructor(e){super(e),this.layer=e.layer}build(e){this.built=!0}get trainable(){return null!=this.layer&&this.layer.trainable}set trainable(e){null!=this.layer&&(this.layer.trainable=e)}get trainableWeights(){return this.layer.trainableWeights}get nonTrainableWeights(){return this.layer.nonTrainableWeights}get updates(){return this.layer._updates}get losses(){return this.layer.losses}getWeights(){return this.layer.getWeights()}setWeights(e){this.layer.setWeights(e)}getConfig(){const e={layer:{className:this.layer.getClassName(),config:this.layer.getConfig()}},t=super.getConfig();return Object.assign(e,t),e}setFastWeightInitDuringBuild(e){super.setFastWeightInitDuringBuild(e),null!=this.layer&&this.layer.setFastWeightInitDuringBuild(e)}static fromConfig(e,t,n={}){const s=sw(t.layer,n);delete t.layer;const r={layer:s};return Object.assign(r,t),new e(r)}}class yI extends gI{constructor(e){super(e),this.supportsMasking=!0}build(e){if((e=Xb(e)).length<3)throw new dy(`TimeDistributed layer expects an input shape >= 3D, but received input shape ${JSON.stringify(e)}`);this.inputSpec=[{shape:e}];const t=[e[0]].concat(e.slice(2));this.layer.built||(this.layer.build(t),this.layer.built=!0),super.build(e)}computeOutputShape(e){const t=[(e=Xb(e))[0]].concat(e.slice(2)),n=this.layer.computeOutputShape(t),s=e[1];return[n[0],s].concat(n.slice(1))}call(e,t){return fo((()=>hk(((e,n)=>[Kb(this.layer.call(e,t)),[]]),e=Kb(e),[],!1,null,null,!1,!0)[1]))}}yI.className="TimeDistributed",Go(yI);class bI extends gI{constructor(e){super(e);const t=e.layer.getConfig(),n={};n.className=e.layer.getClassName(),n.config=t,this.forwardLayer=sw(n),t.goBackwards=!0!==t.goBackwards;const s={};var r;if(s.className=e.layer.getClassName(),s.config=t,this.backwardLayer=sw(s),this.forwardLayer.name="forward_"+this.forwardLayer.name,this.backwardLayer.name="backward_"+this.backwardLayer.name,this.mergeMode=void 0===e.mergeMode?"concat":e.mergeMode,r=this.mergeMode,Ry(Gy,"BidirectionalMergeMode",r),e.weights)throw new fy("weights support is not implemented for Bidirectional layer yet.");this._stateful=e.layer.stateful,this.returnSequences=e.layer.returnSequences,this.returnState=e.layer.returnState,this.supportsMasking=!0,this._trainable=!0,this.inputSpec=e.layer.inputSpec,this.numConstants=null}get trainable(){return this._trainable}set trainable(e){this._trainable=e,null!=this.forwardLayer&&(this.forwardLayer.trainable=e),null!=this.backwardLayer&&(this.backwardLayer.trainable=e)}getWeights(){return this.forwardLayer.getWeights().concat(this.backwardLayer.getWeights())}setWeights(e){const t=e.length,n=Math.floor(t/2);this.forwardLayer.setWeights(e.slice(0,n)),this.backwardLayer.setWeights(e.slice(n))}computeOutputShape(e){let t,n,s,r=this.forwardLayer.computeOutputShape(e);return Array.isArray(r)&&Array.isArray(r[0])||(r=[r]),this.returnState?(s=r.slice(1),t=r[0]):t=r[0],"concat"===this.mergeMode?(t[t.length-1]*=2,n=[t]):n=null==this.mergeMode?[t,t.slice()]:[t],this.returnState?null==this.mergeMode?n.concat(s).concat(s.slice()):[t].concat(s).concat(s.slice()):wy(n)}apply(e,t){let n=null==t?null:t.initialState,s=null==t?null:t.constants;null==t&&(t={});const r=ck(e,n,s,this.numConstants);if(e=r.inputs,n=r.initialState,s=r.constants,Array.isArray(e)&&(n=e.slice(1),e=e[0]),(null==n||0===n.length)&&null==s)return super.apply(e,t);const a=[],i=[];if(null!=n){const e=n.length;if(e%2>0)throw new dy("When passing `initialState` to a Bidrectional RNN, the state should be an Array containing the states of the underlying RNNs.");t.initialState=n,a.push(...n);const s=n.map((e=>new tx({shape:e.shape})));this.forwardLayer.stateSpec=s.slice(0,e/2),this.backwardLayer.stateSpec=s.slice(e/2),i.push(...s)}if(null!=s)throw new fy("Support for constants in Bidirectional layers is not implemented yet.");const o=a[0]instanceof nx;for(const e of a)if(e instanceof nx!==o)throw new dy("The initial state of a Bidirectional layer cannot be specified as a mix of symbolic and non-symbolic tensors");if(o){const n=[e].concat(a),s=this.inputSpec.concat(i),r=this.inputSpec;this.inputSpec=s;const o=super.apply(n,t);return this.inputSpec=r,o}return super.apply(e,t)}call(e,t){return fo((()=>{const n=t.initialState;let s,r,a,i;if(null==n)s=this.forwardLayer.call(e,t),r=this.backwardLayer.call(e,t);else{const a=n.slice(0,n.length/2),i=n.slice(n.length/2);s=this.forwardLayer.call(e,Object.assign(t,{initialState:a})),r=this.backwardLayer.call(e,Object.assign(t,{initialState:i}))}return this.returnState&&(Array.isArray(s)&&(a=s.slice(1).concat(r.slice(1))),s=s[0],r=r[0]),this.returnSequences&&(r=$p(r,1)),"concat"===this.mergeMode?i=db([s,r]):"sum"===this.mergeMode?i=Co(s,r):"ave"===this.mergeMode?i=Ao(.5,Co(s,r)):"mul"===this.mergeMode?i=Ao(s,r):null==this.mergeMode&&(i=[s,r]),this.returnState?null==this.mergeMode?i.concat(a):[i].concat(a):i}))}resetStates(e){this.forwardLayer.resetStates(),this.backwardLayer.resetStates()}build(e){Zy(this.forwardLayer.name,(()=>{this.forwardLayer.build(e)})),Zy(this.backwardLayer.name,(()=>{this.backwardLayer.build(e)})),this.built=!0}computeMask(e,t){let n;if(Array.isArray(t)&&(t=t[0]),n=this.returnSequences?null==this.mergeMode?[t,t]:t:null==this.mergeMode?[null,null]:null,this.returnState){const e=this.forwardLayer.states.map((e=>null));return Array.isArray(n)?n.concat(e).concat(e):[n].concat(e).concat(e)}return n}get trainableWeights(){return this.forwardLayer.trainableWeights.concat(this.backwardLayer.trainableWeights)}get nonTrainableWeights(){return this.forwardLayer.nonTrainableWeights.concat(this.backwardLayer.nonTrainableWeights)}setFastWeightInitDuringBuild(e){super.setFastWeightInitDuringBuild(e),null!=this.forwardLayer&&this.forwardLayer.setFastWeightInitDuringBuild(e),null!=this.backwardLayer&&this.backwardLayer.setFastWeightInitDuringBuild(e)}getConfig(){const e={mergeMode:this.mergeMode},t=super.getConfig();return Object.assign(e,t),e}static fromConfig(e,t){const n=sw(t.layer);if(delete t.layer,null!=t.numConstants)throw new fy("Deserialization of a Bidirectional layer with numConstants present is not supported yet.");const s=t;return s.layer=n,new e(s)}}bI.className="Bidirectional",Go(bI);class xI extends ix{constructor(e){super(e),this.scale=e.scale,e.offset?this.offset=e.offset:this.offset=0}getConfig(){const e={scale:this.scale,offset:this.offset},t=super.getConfig();return Object.assign(e,t),e}call(e,t){return fo((()=>("float32"!==(e=Kb(e)).dtype&&(e=lb(e,"float32")),Co(Ao(e,this.scale),this.offset))))}}xI.className="Rescaling",Go(xI);const{resizeBilinear:wI,cropAndResize:vI}=Mf;class kI extends ix{constructor(e){super(e),this.height=e.height,this.width=e.width}centerCrop(e,t,n,s,r,a,i,o){return fo((()=>{let l,u=!1;const c=[t/a,n/i,(s+t)/a,(r+n)/i],h=[];3===e.rank?(u=!0,l=Qp([e])):l=e;for(let e=0;e<l.shape[0];e++)h.push(c);const p=ei(h,[h.length,4]),d=Np(0,h.length,1,"int32"),f=vI(l,p,d,[s,r],"nearest");return lb(u?Kb(dd(f)):f,o)}))}upsize(e,t,n,s){return fo((()=>lb(wI(e,[t,n]),s)))}call(e,t){return fo((()=>{const t=Kb(e),n=t.dtype,s=t.shape,r=s[s.length-3],a=s[s.length-2];let i=0;r!==this.height&&(i=Math.floor((r-this.height)/2));let o=0;return a!==this.width&&(o=Math.floor((a-this.width)/2),0===o&&(o=1)),i>=0&&o>=0?this.centerCrop(t,i,o,this.height,this.width,r,a,n):this.upsize(e,this.height,this.width,n)}))}getConfig(){const e={height:this.height,width:this.width},t=super.getConfig();return Object.assign(e,t),e}computeOutputShape(e){const t=(e=Xb(e)).length-3,n=e.length-2;return e[t]=this.height,e[n]=this.width,e}}kI.className="CenterCrop",Go(kI);class II extends ix{constructor(e){super(e),this.numTokens=e.numTokens,e.outputMode?this.outputMode=e.outputMode:this.outputMode="multiHot"}getConfig(){const e={numTokens:this.numTokens,outputMode:this.outputMode},t=super.getConfig();return Object.assign(e,t),e}computeOutputShape(e){return null==(e=Xb(e))?[this.numTokens]:"oneHot"===this.outputMode&&1!==e[e.length-1]?(e.push(this.numTokens),e):(e[e.length-1]=this.numTokens,e)}call(e,t){return fo((()=>{let n;if("int32"!==(e=Kb(e)).dtype&&(e=lb(e,"int32")),void 0!==t.countWeights){if("count"!==this.outputMode)throw new dy(`countWeights is not used when outputMode !== count.\n              Received countWeights=${t.countWeights}`);n=Kb(t.countWeights)}const s=rh(e),r=ah(e),a=yh(this.numTokens,s).bufferSync().get(0),i=bh(r,0).bufferSync().get(0);if(!a||!i)throw new dy(`Input values must be between 0 < values <= numTokens with numTokens=${this.numTokens}`);return function(e,t,n,s){let r=Kb(e);if("int32"!==r.dtype&&(r=lb(r,"int32")),"int"===t)return r;const a=r.shape;if(0===r.rank&&(r=hh(r,-1)),"oneHot"===t&&1!==r.shape[r.shape.length-1]&&(r=hh(r,-1)),r.rank>2)throw new dy(`When outputMode is not int, maximum output rank is 2 Received outputMode ${t} and input shape ${a} which would result in output rank ${r.rank}.`);const i=["multiHot","oneHot"].includes(t),o=r;let l;if(l=Lc(o,void 0!==s&&"count"===t?s:[],n,i),"tfIdf"!==t)return l;if(s)return Ao(l,s);throw new dy("When outputMode is 'tfIdf', weights must be provided.")}(e,this.outputMode,this.numTokens,n)}))}}II.className="CategoryEncoding",Go(II);const NI=new Set(["bilinear","nearest"]);class SI extends ix{constructor(e){if(super(e),this.height=e.height,this.width=e.width,e.interpolation){if(!NI.has(e.interpolation))throw new dy(`Invalid interpolation parameter: ${e.interpolation} is not implemented`);this.interpolation=e.interpolation}else this.interpolation="bilinear";this.cropToAspectRatio=Boolean(e.cropToAspectRatio)}computeOutputShape(e){const t=(e=Xb(e))[2];return[this.height,this.width,t]}getConfig(){const e={height:this.height,width:this.width,interpolation:this.interpolation,cropToAspectRatio:this.cropToAspectRatio},t=super.getConfig();return Object.assign(e,t),e}call(e,t){return fo((()=>{const t=[this.height,this.width];if("bilinear"===this.interpolation)return Mf.resizeBilinear(e,t,!this.cropToAspectRatio);if("nearest"===this.interpolation)return Mf.resizeNearestNeighbor(e,t,!this.cropToAspectRatio);throw new Error(`Interpolation is ${this.interpolation} but only ${[...NI]} are supported`)}))}}SI.className="Resizing",Go(SI);class TI{constructor(e){this.seed=e}next(){if(void 0!==this.seed)return this.seed++}}TI.className="RandomSeed";class CI extends ix{constructor(e){super(e),this.randomGenerator=new TI(e.seed)}getConfig(){const e={seed:this.randomGenerator.seed},t=super.getConfig();return Object.assign(e,t),e}}CI.className="BaseRandomLayer";const $I=new Set(["bilinear","nearest"]);class EI extends CI{constructor(e){super(e);const{factor:t,interpolation:n="bilinear"}=e;if(this.factor=t,Array.isArray(this.factor)&&2===this.factor.length)this.widthLower=this.factor[0],this.widthUpper=this.factor[1];else{if(Array.isArray(this.factor)||!(this.factor>0))throw new dy(`Invalid factor: ${this.factor}. Must be positive number or tuple of 2 numbers`);this.widthLower=-this.factor,this.widthUpper=this.factor}if(this.widthLower<-1||this.widthUpper<-1)throw new dy(`factor must have values larger than -1. Got: ${this.factor}`);if(this.widthUpper<this.widthLower)throw new dy(`factor cannot have upper bound less than lower bound.\n        Got upper bound: ${this.widthUpper}.\n        Got lower bound: ${this.widthLower}\n      `);if(n){if(!$I.has(n))throw new dy(`Invalid interpolation parameter: ${n} is not implemented`);this.interpolation=n}}getConfig(){const e={factor:this.factor,interpolation:this.interpolation},t=super.getConfig();return Object.assign(e,t),e}computeOutputShape(e){const t=(e=Xb(e))[2];return[this.imgHeight,-1,t]}call(e,t){return fo((()=>{const t=Kb(e);this.imgHeight=t.shape[t.shape.length-3];const n=t.shape[t.shape.length-2];this.widthFactor=kp([1],1+this.widthLower,1+this.widthUpper,"float32",this.randomGenerator.next());let s=this.widthFactor.dataSync()[0]*n;s=Math.round(s);const r=[this.imgHeight,s];switch(this.interpolation){case"bilinear":return Mf.resizeBilinear(e,r);case"nearest":return Mf.resizeNearestNeighbor(e,r);default:throw new Error(`Interpolation is ${this.interpolation}\n          but only ${[...$I]} are supported`)}}))}}function AI(e){return new lx(e)}function RI(e){return new Wv(e)}function FI(e){return new zv(e)}function _I(e){return new Pv(e)}function DI(e){return new Bv(e)}function OI(e){return new Uv(e)}function MI(e){return new Vv(e)}function LI(e){return new ik(e)}function zI(e){return new ek(e)}function PI(e){return new nk(e)}function BI(e){return new tk(e)}function WI(e){return new sk(e)}function VI(e){return new ak(e)}function UI(e){return new ok(e)}function GI(e){return new lk(e)}function HI(e){return new uk(e)}function jI(e){return new Ak(e)}function qI(e){return new $k(e)}function KI(e){return new Tk(e)}function XI(e){return new Ck(e)}function YI(e){return new Ek(e)}function ZI(e){return new Rk(e)}function JI(e){return new Fk(e)}function QI(e){return new _k(e)}function eN(e){return new Ok(e)}function tN(e){return new Lk(e)}function nN(e){return new Pk(e)}function sN(e){return new Vk(e)}function rN(e){return new Bk(e)}function aN(e){return new Wk(e)}function iN(e){return new zk(e)}function oN(e){return new Gk(e)}function lN(e){return new Yk(e)}function uN(e){return new Zk(e)}function cN(e){return new Jk(e)}function hN(e){return new sI(e)}function pN(e){return hN(e)}function dN(e){return hN(e)}function fN(e){return new iI(e)}function mN(e){return fN(e)}function gN(e){return fN(e)}function yN(e){return new uI(e)}function bN(e){return yN(e)}function xN(e){return yN(e)}function wN(e){return new hI(e)}function vN(e){return new fI(e)}function kN(e){return new pI(e)}function IN(e){return new mI(e)}function NN(e){return new nI(e)}function SN(e){return new aI(e)}function TN(e){return new lI(e)}function CN(e){return new yk(e)}function $N(e){return new gk(e)}function EN(e){return new xk(e)}function AN(e){return new bk(e)}function RN(e){return new mk(e)}function FN(e){return new fk(e)}function _N(e){return new Sk(e)}function DN(e){return new Nk(e)}function ON(e){return new pk(e)}function MN(e){return new wk(e)}function LN(e){return new bI(e)}function zN(e){return new yI(e)}EI.className="RandomWidth",Go(EI);const PN=kN,BN=IN,WN=NN,VN=SN;function UN(e){return new Hk(e)}function GN(e){return new jk(e)}function HN(e){return new qk(e)}function jN(e){return new Dk(e)}function qN(e){return new xI(e)}function KN(e){return new kI(e)}function XN(e){return new SI(e)}function YN(e){return new II(e)}function ZN(e){return new EI(e)}function JN(e,t){return gw(e,t)}function QN(e,t){return vw(e,t)}function eS(e,t){return kw(e,t)}function tS(e,t){return yw(e,t)}function nS(e,t){return Iw(e,t)}function sS(e,t){return xw(e,t)}function rS(e,t){return ww(e,t)}function aS(e,t){return dw(e,t)}function iS(e,t){return iw(e,t)}function oS(e,t){return ow(e,t)}function lS(e,t){return ow(e,t)}function uS(e,t){return ow(e,t)}function cS(e,t){return aw(e,t)}function hS(e,t){return aw(e,t)}function pS(e,t){return aw(e,t)}function dS(e){return new _v(e)}function fS(e){return Rv(t=e),new _v({l1:null!=t?t.l1:null,l2:0});var t}function mS(e){return Rv(t=e),new _v({l2:null!=t?t.l2:null,l1:0});var t}class gS extends Xx{constructor(){super(...arguments),this.model=null}setModel(e){if(!(e instanceof rv))throw new Error("model must be a LayersModel, not some other Container");this.model=e}}function yS(e,t){return e<t}function bS(e,t){return e>t}class xS extends gS{constructor(e){if(super(),null==e&&(e={}),e.restoreBestWeights)throw new fy("restoreBestWeights = True is not implemented in EarlyStopping yet.");this.monitor=e.monitor||"val_loss",this.minDelta=Math.abs(e.minDelta||0),this.patience=e.patience||0,this.verbose=e.verbose||0,this.mode=e.mode||"auto",this.baseline=e.baseline,-1===["auto","min","max"].indexOf(this.mode)&&(console.warn(`EarlyStopping mode '${this.mode}' is invalid. Falling back to mode 'auto'.`),this.mode="auto"),"min"===this.mode?this.monitorFunc=yS:"max"===this.mode||-1!==this.monitor.indexOf("acc")?this.monitorFunc=bS:this.monitorFunc=yS,this.monitorFunc===yS&&(this.minDelta*=-1)}async onTrainBegin(e){this.wait=0,this.stoppedEpoch=0,null!=this.baseline?this.best=this.baseline:this.best=this.monitorFunc===yS?1/0:-1/0}async onEpochEnd(e,t){await jx(t);const n=this.getMonitorValue(t);null!=n&&(this.monitorFunc(n-this.minDelta,this.best)?(this.best=n,this.wait=0):(this.wait++,this.wait>=this.patience&&(this.stoppedEpoch=e,this.model.stopTraining=!0)))}async onTrainEnd(e){this.stoppedEpoch>0&&this.verbose&&console.log(`Epoch ${this.stoppedEpoch}: early stopping.`)}getMonitorValue(e){null==e&&(e={});const t=e[this.monitor];return null==t&&console.warn(`Metric for EarlyStopping ${this.monitor} is not available. Available metrics are: ${Object.keys(e)}`),t}}const wS={earlyStopping:function(e){return new xS(e)}};var vS,kS;Xe().registerFlag("KEEP_INTERMEDIATE_TENSORS",(()=>!1),(e=>{e&&console.warn("Keep intermediate tensors is ON. This will print the values of all intermediate tensors during model inference. Not all models support this mode. For details, check e2e/benchmarks/ model_config.js. This significantly impacts performance.")})),function(e){e[e.DT_INVALID=0]="DT_INVALID",e[e.DT_FLOAT=1]="DT_FLOAT",e[e.DT_DOUBLE=2]="DT_DOUBLE",e[e.DT_INT32=3]="DT_INT32",e[e.DT_UINT8=4]="DT_UINT8",e[e.DT_INT16=5]="DT_INT16",e[e.DT_INT8=6]="DT_INT8",e[e.DT_STRING=7]="DT_STRING",e[e.DT_COMPLEX64=8]="DT_COMPLEX64",e[e.DT_INT64=9]="DT_INT64",e[e.DT_BOOL=10]="DT_BOOL",e[e.DT_QINT8=11]="DT_QINT8",e[e.DT_QUINT8=12]="DT_QUINT8",e[e.DT_QINT32=13]="DT_QINT32",e[e.DT_BFLOAT16=14]="DT_BFLOAT16",e[e.DT_QINT16=15]="DT_QINT16",e[e.DT_QUINT16=16]="DT_QUINT16",e[e.DT_UINT16=17]="DT_UINT16",e[e.DT_COMPLEX128=18]="DT_COMPLEX128",e[e.DT_HALF=19]="DT_HALF",e[e.DT_RESOURCE=20]="DT_RESOURCE",e[e.DT_VARIANT=21]="DT_VARIANT",e[e.DT_UINT32=22]="DT_UINT32",e[e.DT_UINT64=23]="DT_UINT64",e[e.DT_FLOAT_REF=101]="DT_FLOAT_REF",e[e.DT_DOUBLE_REF=102]="DT_DOUBLE_REF",e[e.DT_INT32_REF=103]="DT_INT32_REF",e[e.DT_UINT8_REF=104]="DT_UINT8_REF",e[e.DT_INT16_REF=105]="DT_INT16_REF",e[e.DT_INT8_REF=106]="DT_INT8_REF",e[e.DT_STRING_REF=107]="DT_STRING_REF",e[e.DT_COMPLEX64_REF=108]="DT_COMPLEX64_REF",e[e.DT_INT64_REF=109]="DT_INT64_REF",e[e.DT_BOOL_REF=110]="DT_BOOL_REF",e[e.DT_QINT8_REF=111]="DT_QINT8_REF",e[e.DT_QUINT8_REF=112]="DT_QUINT8_REF",e[e.DT_QINT32_REF=113]="DT_QINT32_REF",e[e.DT_BFLOAT16_REF=114]="DT_BFLOAT16_REF",e[e.DT_QINT16_REF=115]="DT_QINT16_REF",e[e.DT_QUINT16_REF=116]="DT_QUINT16_REF",e[e.DT_UINT16_REF=117]="DT_UINT16_REF",e[e.DT_COMPLEX128_REF=118]="DT_COMPLEX128_REF",e[e.DT_HALF_REF=119]="DT_HALF_REF",e[e.DT_RESOURCE_REF=120]="DT_RESOURCE_REF",e[e.DT_VARIANT_REF=121]="DT_VARIANT_REF",e[e.DT_UINT32_REF=122]="DT_UINT32_REF",e[e.DT_UINT64_REF=123]="DT_UINT64_REF"}(vS||(vS={})),function(e){let t;!function(e){e[e.LEGACY=0]="LEGACY",e[e.V1=1]="V1",e[e.V2=2]="V2"}(t=e.CheckpointFormatVersion||(e.CheckpointFormatVersion={}))}(kS||(kS={}));const IS={};function NS(e,t){const n={tfOpName:e,category:"custom",inputs:[],attrs:[],customExecutor:t};IS[e]=n}function SS(e){return IS[e]}function TS(e){delete IS[e]}function CS(e,t,n,s,r){const a=t.inputParams[e];if(a&&void 0!==a.inputIndexStart){const e=a.inputIndexStart,i=0===a.inputIndexEnd?void 0:void 0===a.inputIndexEnd?e+1:a.inputIndexEnd,o=e<0?t.inputNames.length+e:e;if("tensor"===a.type)return $S(t.inputNames[o],n,s,r);if("tensors"===a.type){const a=t.inputs.slice(e,i);return t.inputNames.slice(e,i).filter(((e,t)=>{var n;return"NoOp"!==(null===(n=a[t])||void 0===n?void 0:n.op)})).map((e=>$S(e,n,s,r)))}const l=$S(t.inputNames[o],n,s,r),u=l.dataSync();return"number"===a.type?u[0]:Le(l.shape,u)}const i=t.attrParams[e];return i&&i.value}function $S(e,t,n,s){const[r,a]=FS(e,n);if(null!=s){const e=s.getHashTableHandleByName(r);if(null!=e)return e}const i=n.currentContextIds.find((e=>!!t[RS(r,e)]));return void 0!==i?t[RS(r,i)][a]:void 0}function ES(e,t,n){return t[RS(e,n.currentContextId)]}function AS(e,t){const[n,s,r]=FS(e,t);return[RS(n,t&&t.currentContextId),s,r]}function RS(e,t){return t?`${e}-${t}`:e}function FS(e,t){if(""===e)return["",0,void 0];const n=null!=t&&null!=t.parseNodeNameCache;if(n){const n=t.parseNodeNameCache.get(e);if(null!=n)return n}const s=e.split(":");let r;if(1===s.length)r=[e,0,void 0];else{const e=s[0],t=3===s.length?s[1]:void 0;r=[e,Number(s[s.length-1]),t]}return n&&t.parseNodeNameCache.set(e,r),r}function _S(e,t,n){let s=CS("pad",e,t,n);if("explicit"===s){s=CS("explicitPaddings",e,t,n);const r=[[0,0],[0,0],[0,0],[0,0]];for(let e=0;e<4;e++)r[e][0]=s[2*e],r[e][1]=s[2*e+1];return r}return s}function DS(e){return e.kept?e:so(e)}const OS=[{tfOpName:"Add",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"AddV2",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"AddN",category:"arithmetic",inputs:[{start:0,end:0,name:"tensors",type:"tensors"}]},{tfOpName:"BiasAdd",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0}]},{tfOpName:"Sub",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"RealDiv",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Div",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"DivNoNan",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"FloorDiv",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Mul",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Maximum",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Minimum",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Pow",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"SquaredDifference",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Mod",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"FloorMod",category:"arithmetic",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]}],MS=[{tfOpName:"Abs",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Acos",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Asin",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Atan",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Atan2",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"y",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Ceil",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"ClipByValue",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"clipValueMin",type:"number"},{start:2,name:"clipValueMax",type:"number"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Complex",category:"basic_math",inputs:[{start:0,name:"real",type:"tensor"},{start:1,name:"imag",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"ComplexAbs",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Cos",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Cosh",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Elu",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Exp",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Floor",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Log",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Imag",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"Tout",name:"outputType",type:"dtype",notSupported:!0}]},{tfOpName:"Neg",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Real",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"Tout",name:"outputType",type:"dtype",notSupported:!0}]},{tfOpName:"Prelu",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"alpha",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Relu",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Relu6",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Selu",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Sigmoid",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Sin",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Sinh",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Sqrt",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Rsqrt",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Square",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Tan",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Tanh",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Sign",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Round",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Expm1",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Log1p",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Reciprocal",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Softplus",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Asinh",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Acosh",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Atanh",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Erf",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"LeakyRelu",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"alpha",name:"alpha",type:"number",defaultValue:.2},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"IsNan",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"IsFinite",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"IsInf",category:"basic_math",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]}],LS=[{tfOpName:"EmptyTensorList",category:"control",inputs:[{start:0,name:"elementShape",type:"shape"},{start:1,name:"maxNumElements",type:"number"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"LoopCond",category:"control",inputs:[{start:0,name:"pred",type:"tensor"}]},{tfOpName:"Switch",category:"control",inputs:[{start:0,name:"data",type:"tensor"},{start:1,name:"pred",type:"tensor"}]},{tfOpName:"Merge",category:"control",inputs:[{start:0,end:0,name:"tensors",type:"tensors"}]},{tfOpName:"Enter",category:"control",inputs:[{start:0,name:"tensor",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"frame_name",name:"frameName",type:"string"},{tfName:"is_constant",name:"isConstant",type:"bool"}]},{tfOpName:"Exit",category:"control",inputs:[{start:0,name:"tensor",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"NextIteration",category:"control",inputs:[{start:0,name:"tensor",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"TensorArrayV3",category:"control",inputs:[{start:0,name:"size",type:"number"}],attrs:[{tfName:"dtype",name:"dtype",type:"dtype"},{tfName:"element_shape",name:"elementShape",type:"shape"},{tfName:"dynamic_size",name:"dynamicSize",type:"bool"},{tfName:"clear_after_read",name:"clearAfterRead",type:"bool"},{tfName:"identical_element_shapes",name:"identicalElementShapes",type:"bool"},{tfName:"tensor_array_name",name:"name",type:"string"}]},{tfOpName:"TensorArrayWriteV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"},{start:1,name:"index",type:"number"},{start:2,name:"tensor",type:"tensor"},{start:3,name:"flowIn",type:"number"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"TensorArrayReadV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"},{start:1,name:"index",type:"number"},{start:2,name:"flowIn",type:"number"}],attrs:[{tfName:"dtype",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"TensorArrayGatherV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"},{start:1,name:"indices",type:"number[]"},{start:2,name:"flowIn",type:"number"}],attrs:[{tfName:"dtype",name:"dtype",type:"dtype"},{tfName:"element_shape",name:"elementShape",type:"shape"}]},{tfOpName:"TensorArrayScatterV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"},{start:1,name:"indices",type:"number[]"},{start:2,name:"tensor",type:"tensor"},{start:3,name:"flowIn",type:"number"}],attrs:[{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"TensorArrayConcatV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"},{start:1,name:"flowIn",type:"number"}],attrs:[{tfName:"dtype",name:"dtype",type:"dtype"},{tfName:"element_shape_except0",name:"elementShapeExcept0",type:"shape",notSupported:!0}]},{tfOpName:"TensorArraySplitV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"},{start:1,name:"tensor",type:"tensor"},{start:2,name:"lengths",type:"number[]"},{start:3,name:"flowIn",type:"number"}],attrs:[{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"TensorArraySizeV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"},{start:1,name:"flowIn",type:"number"}]},{tfOpName:"TensorArrayCloseV3",category:"control",inputs:[{start:0,name:"tensorArrayId",type:"tensor"}]},{tfOpName:"StatelessIf",category:"control",inputs:[{start:0,name:"cond",type:"tensor"},{start:1,end:0,name:"args",type:"tensors"}],attrs:[{tfName:"then_branch",name:"thenBranch",type:"func"},{tfName:"else_branch",name:"elseBranch",type:"func"}]},{tfOpName:"If",category:"control",inputs:[{start:0,name:"cond",type:"tensor"},{start:1,end:0,name:"args",type:"tensors"}],attrs:[{tfName:"then_branch",name:"thenBranch",type:"func"},{tfName:"else_branch",name:"elseBranch",type:"func"}]},{tfOpName:"StatelessWhile",category:"control",inputs:[{start:0,end:0,name:"args",type:"tensors"}],attrs:[{tfName:"cond",name:"cond",type:"func"},{tfName:"body",name:"body",type:"func"}]},{tfOpName:"While",category:"control",inputs:[{start:0,end:0,name:"args",type:"tensors"}],attrs:[{tfName:"cond",name:"cond",type:"func"},{tfName:"body",name:"body",type:"func"}]},{tfOpName:"TensorListScatter",category:"control",inputs:[{start:0,name:"tensor",type:"tensor"},{start:1,name:"indices",type:"number[]"},{start:2,name:"elementShape",type:"shape"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListScatterV2",category:"control",inputs:[{start:0,name:"tensor",type:"tensor"},{start:1,name:"indices",type:"number[]"},{start:2,name:"elementShape",type:"shape"},{start:3,name:"numElements",type:"number"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListGather",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"},{start:1,name:"indices",type:"number[]"},{start:2,name:"elementShape",type:"shape"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListGetItem",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"},{start:1,name:"index",type:"number"},{start:2,name:"elementShape",type:"shape"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListSetItem",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"},{start:1,name:"index",type:"number"},{start:2,name:"tensor",type:"tensor"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListReserve",category:"control",inputs:[{start:0,name:"elementShape",type:"shape"},{start:1,name:"numElements",type:"number"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListFromTensor",category:"control",inputs:[{start:0,name:"tensor",type:"tensor"},{start:1,name:"elementShape",type:"shape"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListStack",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"},{start:1,name:"elementShape",type:"shape"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"},{tfName:"num_elements",name:"numElements",type:"dtype"}]},{tfOpName:"TensorListSplit",category:"control",inputs:[{start:0,name:"tensor",type:"tensor"},{start:1,name:"elementShape",type:"shape"},{start:2,name:"lengths",type:"number[]"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListConcat",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"}],attrs:[{tfName:"element_shape",name:"elementShape",type:"shape"},{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListConcatV2",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"}],attrs:[{tfName:"element_shape",name:"elementShape",type:"shape"},{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListPopBack",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"},{start:1,name:"elementShape",type:"shape"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListPushBack",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"},{start:1,name:"tensor",type:"tensor"}],attrs:[{tfName:"element_dtype",name:"elementDType",type:"dtype"}]},{tfOpName:"TensorListLength",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"}]},{tfOpName:"TensorListResize",category:"control",inputs:[{start:0,name:"tensorListId",type:"tensor"},{start:1,name:"size",type:"number"}]}],zS=[{tfOpName:"AvgPool",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0},{tfName:"ksize",name:"kernelSize",type:"number[]"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"MaxPool",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0},{tfName:"ksize",name:"kernelSize",type:"number[]"},{tfName:"explicit_paddings",name:"explicitPaddings",type:"number[]",defaultValue:[],notSupported:!0},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"MaxPoolWithArgmax",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"ksize",name:"kernelSize",type:"number[]"},{tfName:"include_batch_in_index",name:"includeBatchInIndex",type:"bool"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"AvgPool3D",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0},{tfName:"ksize",name:"kernelSize",type:"number[]"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"MaxPool3D",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0},{tfName:"ksize",name:"kernelSize",type:"number[]"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Conv1D",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"filter",type:"tensor"}],attrs:[{tfName:"stride",name:"stride",type:"number"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",defaultValue:"NWC"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"dilation",name:"dilation",type:"number",defaultValue:1}]},{tfOpName:"Conv2D",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"filter",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"useCudnnOnGpu",name:"useCudnnOnGpu",type:"bool"},{tfName:"data_format",name:"dataFormat",type:"string",defaultValue:"NHWC"},{tfName:"explicit_paddings",name:"explicitPaddings",type:"number[]",defaultValue:[]},{tfName:"dilations",name:"dilations",type:"number[]"}]},{tfOpName:"_FusedConv2D",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"filter",type:"tensor"},{start:2,end:0,name:"args",type:"tensors"}],attrs:[{tfName:"num_args",name:"numArgs",type:"number"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"explicit_paddings",name:"explicitPaddings",type:"number[]",defaultValue:[]},{tfName:"use_cudnn_on_gpu",name:"useCudnnOnGpu",type:"bool",defaultValue:!0},{tfName:"data_format",name:"dataFormat",type:"string",defaultValue:"NHWC"},{tfName:"dilations",name:"dilations",type:"number[]",defaultValue:[1,1,1,1]},{tfName:"fused_ops",name:"fusedOps",type:"string[]",defaultValue:[]},{tfName:"epsilon",name:"epsilon",type:"number",defaultValue:1e-4},{tfName:"leakyrelu_alpha",name:"leakyreluAlpha",type:"number",defaultValue:.2}]},{tfOpName:"Conv2DBackpropInput",category:"convolution",inputs:[{start:2,name:"x",type:"tensor"},{start:1,name:"filter",type:"tensor"},{start:0,name:"outputShape",type:"number[]"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0},{tfName:"explicit_paddings",name:"explicitPaddings",type:"number[]",defaultValue:[]},{tfName:"dilations",name:"dilations",type:"number[]",notSupported:!0}]},{tfOpName:"DepthwiseConv2d",category:"convolution",inputs:[{start:0,name:"input",type:"tensor"},{start:1,name:"filter",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",defaultValue:"NHWC"},{tfName:"explicit_paddings",name:"explicitPaddings",type:"number[]",defaultValue:[]},{tfName:"dilations",name:"dilations",type:"number[]"}]},{tfOpName:"DepthwiseConv2dNative",category:"convolution",inputs:[{start:0,name:"input",type:"tensor"},{start:1,name:"filter",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",defaultValue:"NHWC"},{tfName:"explicit_paddings",name:"explicitPaddings",type:"number[]",defaultValue:[]},{tfName:"dilations",name:"dilations",type:"number[]"}]},{tfOpName:"FusedDepthwiseConv2dNative",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"filter",type:"tensor"},{start:2,end:0,name:"args",type:"tensors"}],attrs:[{tfName:"num_args",name:"numArgs",type:"number"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",defaultValue:"NHWC"},{tfName:"dilations",name:"dilations",type:"number[]",defaultValue:[1,1,1,1]},{tfName:"fused_ops",name:"fusedOps",type:"string[]",defaultValue:[]},{tfName:"explicit_paddings",name:"explicitPaddings",type:"number[]",defaultValue:[]}]},{tfOpName:"Conv3D",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"filter",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"padding",name:"pad",type:"string"},{tfName:"data_format",name:"dataFormat",type:"string",defaultValue:"NHWC"},{tfName:"dilations",name:"dilations",type:"number[]"}]},{tfOpName:"Dilation2D",category:"convolution",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"filter",type:"tensor"}],attrs:[{tfName:"strides",name:"strides",type:"number[]"},{tfName:"rates",name:"dilations",type:"number[]"},{tfName:"padding",name:"pad",type:"string"}]}],PS=[{tfOpName:"Fill",category:"creation",inputs:[{start:0,name:"shape",type:"number[]"},{start:1,name:"value",type:"number"}],attrs:[{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"LinSpace",category:"creation",inputs:[{start:0,name:"start",type:"number"},{start:1,name:"stop",type:"number"},{start:2,name:"num",type:"number"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"OneHot",category:"creation",inputs:[{start:0,name:"indices",type:"tensor"},{start:1,name:"depth",type:"number"},{start:2,name:"onValue",type:"number",defaultValue:1},{start:3,name:"offValue",type:"number",defaultValue:0}],attrs:[{tfName:"axis",name:"axis",type:"number",notSupported:!0},{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"Ones",category:"creation",inputs:[{start:0,name:"shape",type:"number[]"}],attrs:[{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"OnesLike",category:"creation",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"dtype",name:"dtype",type:"dtype"}]},{tfOpName:"RandomStandardNormal",category:"creation",inputs:[{start:0,name:"shape",type:"number[]"}],attrs:[{tfName:"seed",name:"seed",type:"number",defaultValue:0},{tfName:"seed2",name:"seed2",type:"number",defaultValue:0,notSupported:!0},{tfName:"dtype",name:"dtype",type:"dtype"},{tfName:"T",name:"T",type:"number",notSupported:!0}]},{tfOpName:"RandomUniform",category:"creation",inputs:[{start:0,name:"shape",type:"number[]"}],attrs:[{tfName:"minval",name:"minval",type:"number",defaultValue:0},{tfName:"maxval",name:"maxval",type:"number",defaultValue:1},{tfName:"dtype",name:"dtype",type:"dtype"},{tfName:"seed",name:"seed",type:"number",defaultValue:0},{tfName:"seed2",name:"seed2",type:"number",defaultValue:0,notSupported:!0},{tfName:"T",name:"T",type:"number",notSupported:!0}]},{tfOpName:"RandomUniformInt",category:"creation",inputs:[{start:0,name:"shape",type:"number[]"}],attrs:[{tfName:"minval",name:"minval",type:"number"},{tfName:"maxval",name:"maxval",type:"number"},{tfName:"seed",name:"seed",type:"number",defaultValue:0},{tfName:"seed2",name:"seed2",type:"number",defaultValue:0,notSupported:!0}]},{tfOpName:"Range",category:"creation",inputs:[{start:0,name:"start",type:"number"},{start:1,name:"stop",type:"number"},{start:2,name:"step",type:"number",defaultValue:0}],attrs:[{tfName:"Tidx",name:"dtype",type:"dtype"}]},{tfOpName:"TruncatedNormal",category:"creation",inputs:[{start:0,name:"shape",type:"number[]"}],attrs:[{tfName:"means",name:"mean",type:"number",defaultValue:0},{tfName:"stddev",name:"stdDev",type:"number",defaultValue:1},{tfName:"seed",name:"seed",type:"number"},{tfName:"seed2",name:"seed2",type:"number",defaultValue:0,notSupported:!0},{tfName:"dtype",name:"dtype",type:"dtype"},{tfName:"T",name:"T",type:"number",notSupported:!0}]},{tfOpName:"Zeros",category:"creation",inputs:[{start:0,name:"shape",type:"number[]"}],attrs:[{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"ZerosLike",category:"creation",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"Multinomial",category:"creation",inputs:[{start:0,name:"logits",type:"tensor"},{start:1,name:"numSamples",type:"number"}],attrs:[{tfName:"seed",name:"seed",type:"number"},{tfName:"seed2",name:"seed2",type:"number"},{tfName:"T",name:"dtype",type:"dtype"},{tfName:"output_dtype",name:"output_dtype",type:"dtype"}]}],BS=[{tfOpName:"NonMaxSuppressionV2",category:"dynamic",inputs:[{start:0,name:"boxes",type:"tensor"},{start:1,name:"scores",type:"tensor"},{start:2,name:"maxOutputSize",type:"number"},{start:3,name:"iouThreshold",type:"number"}]},{tfOpName:"NonMaxSuppressionV3",category:"dynamic",inputs:[{start:0,name:"boxes",type:"tensor"},{start:1,name:"scores",type:"tensor"},{start:2,name:"maxOutputSize",type:"number"},{start:3,name:"iouThreshold",type:"number"},{start:4,name:"scoreThreshold",type:"number"}]},{tfOpName:"NonMaxSuppressionV4",category:"dynamic",inputs:[{start:0,name:"boxes",type:"tensor"},{start:1,name:"scores",type:"tensor"},{start:2,name:"maxOutputSize",type:"number"},{start:3,name:"iouThreshold",type:"number"},{start:4,name:"scoreThreshold",type:"number"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0},{tfName:"T_threshold",name:"threshold",type:"dtype",notSupported:!0},{tfName:"pad_to_max_output_size",name:"padToMaxOutputSize",type:"bool"}]},{tfOpName:"NonMaxSuppressionV5",category:"dynamic",inputs:[{start:0,name:"boxes",type:"tensor"},{start:1,name:"scores",type:"tensor"},{start:2,name:"maxOutputSize",type:"number"},{start:3,name:"iouThreshold",type:"number"},{start:4,name:"scoreThreshold",type:"number"},{start:5,name:"softNmsSigma",type:"number"}]},{tfOpName:"Where",category:"dynamic",inputs:[{start:0,name:"condition",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"ListDiff",category:"dynamic",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"y",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]}],WS=[{tfOpName:"LowerBound",category:"evaluation",inputs:[{start:0,name:"sortedSequence",type:"tensor"},{start:1,name:"values",type:"tensor"}]},{tfOpName:"TopKV2",category:"evaluation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"k",type:"number"}],attrs:[{tfName:"sorted",name:"sorted",type:"bool"}]},{tfOpName:"UpperBound",category:"evaluation",inputs:[{start:0,name:"sortedSequence",type:"tensor"},{start:1,name:"values",type:"tensor"}]},{tfOpName:"Unique",category:"evaluation",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"UniqueV2",category:"evaluation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number"}]}],VS=[{tfOpName:"PlaceholderWithDefault",category:"graph",inputs:[{start:0,name:"default",type:"tensor"}],attrs:[{tfName:"shape",name:"shape",type:"shape"},{tfName:"dtype",name:"dtype",type:"dtype"}]},{tfOpName:"Placeholder",category:"graph",attrs:[{tfName:"shape",name:"shape",type:"shape"},{tfName:"dtype",name:"dtype",type:"dtype"}]},{tfOpName:"Const",category:"graph"},{tfOpName:"Identity",category:"graph",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"IdentityN",category:"graph",inputs:[{start:0,end:0,name:"x",type:"tensors"}]},{tfOpName:"Snapshot",category:"graph",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"Rank",category:"graph",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"Size",category:"graph",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"Shape",category:"graph",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"ShapeN",category:"graph",inputs:[{start:0,end:0,name:"x",type:"tensors"}]},{tfOpName:"Print",category:"graph",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"data",type:"tensors"}],attrs:[{tfName:"message",name:"message",type:"string"},{tfName:"first_n",name:"firstN",type:"number",notSupported:!0},{tfName:"summarize",name:"summarize",type:"number",defaultValue:3}]},{tfOpName:"NoOp",category:"graph",inputs:[]},{tfOpName:"StopGradient",category:"graph",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"FakeQuantWithMinMaxVars",category:"graph",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"min",name:"min",type:"number"},{tfName:"max",name:"max",type:"number"}]}],US=[{tfOpName:"HashTable",category:"hash_table",inputs:[],attrs:[{tfName:"shared_name",name:"sharedName",type:"string"},{tfName:"use_node_name_sharing",name:"useNodeNameSharing",type:"bool"},{tfName:"key_dtype",name:"keyDType",type:"dtype"},{tfName:"value_dtype",name:"valueDType",type:"dtype"}]},{tfOpName:"HashTableV2",category:"hash_table",inputs:[],attrs:[{tfName:"shared_name",name:"sharedName",type:"string"},{tfName:"use_node_name_sharing",name:"useNodeNameSharing",type:"bool"},{tfName:"key_dtype",name:"keyDType",type:"dtype"},{tfName:"value_dtype",name:"valueDType",type:"dtype"}]},{tfOpName:"LookupTableImport",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"},{start:1,name:"keys",type:"tensor"},{start:2,name:"values",type:"tensor"}],attrs:[{tfName:"Tin",name:"tIn",type:"dtype",notSupported:!0},{tfName:"Tout",name:"tOut",type:"dtype",notSupported:!0}]},{tfOpName:"LookupTableImportV2",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"},{start:1,name:"keys",type:"tensor"},{start:2,name:"values",type:"tensor"}],attrs:[{tfName:"Tin",name:"tIn",type:"dtype",notSupported:!0},{tfName:"Tout",name:"tOut",type:"dtype",notSupported:!0}]},{tfOpName:"LookupTableFind",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"},{start:1,name:"keys",type:"tensor"},{start:2,name:"defaultValue",type:"tensor"}],attrs:[{tfName:"Tin",name:"tIn",type:"dtype",notSupported:!0},{tfName:"Tout",name:"tOut",type:"dtype",notSupported:!0}]},{tfOpName:"LookupTableFindV2",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"},{start:1,name:"keys",type:"tensor"},{start:2,name:"defaultValue",type:"tensor"}],attrs:[{tfName:"Tin",name:"tIn",type:"dtype",notSupported:!0},{tfName:"Tout",name:"tOut",type:"dtype",notSupported:!0}]},{tfOpName:"LookupTableSize",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"}]},{tfOpName:"LookupTableSizeV2",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"}]},{tfOpName:"InitializeTable",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"},{start:1,name:"keys",type:"tensor"},{start:2,name:"values",type:"tensor"}]},{tfOpName:"InitializeTableV2",category:"hash_table",inputs:[{start:0,name:"tableHandle",type:"tensor"},{start:1,name:"keys",type:"tensor"},{start:2,name:"values",type:"tensor"}]}],GS=[{tfOpName:"ResizeBilinear",category:"image",inputs:[{start:0,name:"images",type:"tensor"},{start:1,name:"size",type:"number[]"}],attrs:[{tfName:"align_corners",name:"alignCorners",type:"bool"},{tfName:"half_pixel_centers",name:"halfPixelCenters",type:"bool"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"ResizeNearestNeighbor",category:"image",inputs:[{start:0,name:"images",type:"tensor"},{start:1,name:"size",type:"number[]"}],attrs:[{tfName:"align_corners",name:"alignCorners",type:"bool"},{tfName:"half_pixel_centers",name:"halfPixelCenters",type:"bool"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"CropAndResize",category:"image",inputs:[{start:0,name:"image",type:"tensor"},{start:1,name:"boxes",type:"tensor"},{start:2,name:"boxInd",type:"tensor"},{start:3,name:"cropSize",type:"number[]"}],attrs:[{tfName:"method",name:"method",type:"string"},{tfName:"extrapolation_value",name:"extrapolationValue",type:"number"}]},{tfOpName:"ImageProjectiveTransformV3",category:"image",inputs:[{start:0,name:"images",type:"tensor"},{start:1,name:"transforms",type:"tensor"},{start:2,name:"outputShape",type:"number[]"},{start:3,name:"fillValue",type:"number"}],attrs:[{tfName:"interpolation",name:"interpolation",type:"string"},{tfName:"fill_mode",name:"fillMode",type:"string"}]}],HS=[{tfOpName:"Equal",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"NotEqual",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Greater",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"GreaterEqual",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Less",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"LessEqual",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"LogicalAnd",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"LogicalNot",category:"logical",inputs:[{start:0,name:"a",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"LogicalOr",category:"logical",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Select",category:"logical",inputs:[{start:0,name:"condition",type:"tensor"},{start:1,name:"a",type:"tensor"},{start:2,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"SelectV2",category:"logical",inputs:[{start:0,name:"condition",type:"tensor"},{start:1,name:"a",type:"tensor"},{start:2,name:"b",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"BitwiseAnd",category:"logical",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"y",type:"tensor"}]}],jS=[{tfOpName:"_FusedMatMul",category:"matrices",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"},{start:2,end:0,name:"args",type:"tensors"}],attrs:[{tfName:"num_args",name:"numArgs",type:"number"},{tfName:"fused_ops",name:"fusedOps",type:"string[]",defaultValue:[]},{tfName:"epsilon",name:"epsilon",type:"number",defaultValue:1e-4},{tfName:"transpose_a",name:"transposeA",type:"bool",defaultValue:!1},{tfName:"transpose_b",name:"transposeB",type:"bool",defaultValue:!1},{tfName:"leakyrelu_alpha",name:"leakyreluAlpha",type:"number",defaultValue:.2},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"MatMul",category:"matrices",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"transpose_a",name:"transposeA",type:"bool",defaultValue:!1},{tfName:"transpose_b",name:"transposeB",type:"bool",defaultValue:!1},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"BatchMatMul",category:"matrices",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"adj_x",name:"transposeA",type:"bool",defaultValue:!1},{tfName:"adj_y",name:"transposeB",type:"bool",defaultValue:!1},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"BatchMatMulV2",category:"matrices",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"b",type:"tensor"}],attrs:[{tfName:"adj_x",name:"transposeA",type:"bool",defaultValue:!1},{tfName:"adj_y",name:"transposeB",type:"bool",defaultValue:!1},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Transpose",category:"matrices",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"perm",type:"number[]"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Einsum",category:"matrices",inputs:[{start:0,end:0,name:"tensors",type:"tensors"}],attrs:[{tfName:"equation",name:"equation",type:"string"},{tfName:"N",name:"n",type:"number",defaultValue:2},{tfName:"T",name:"dtype",type:"dtype"}]},{tfOpName:"MatrixBandPart",category:"matrices",inputs:[{start:0,name:"a",type:"tensor"},{start:1,name:"numLower",type:"tensor"},{start:1,name:"numUpper",type:"tensor"}]}],qS=[{tfOpName:"EuclideanNorm",category:"normalization",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool",defaultValue:!1}]},{tfOpName:"FusedBatchNorm",category:"normalization",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"scale",type:"tensor"},{start:2,name:"offset",type:"tensor"},{start:3,name:"mean",type:"tensor"},{start:4,name:"variance",type:"tensor"}],attrs:[{tfName:"epsilon",name:"epsilon",type:"number",defaultValue:.001},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0}]},{tfOpName:"FusedBatchNormV2",category:"normalization",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"scale",type:"tensor"},{start:2,name:"offset",type:"tensor"},{start:3,name:"mean",type:"tensor"},{start:4,name:"variance",type:"tensor"}],attrs:[{tfName:"epsilon",name:"epsilon",type:"number",defaultValue:.001},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0}]},{tfOpName:"FusedBatchNormV3",category:"normalization",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"scale",type:"tensor"},{start:2,name:"offset",type:"tensor"},{start:3,name:"mean",type:"tensor"},{start:4,name:"variance",type:"tensor"}],attrs:[{tfName:"epsilon",name:"epsilon",type:"number",defaultValue:.001},{tfName:"data_format",name:"dataFormat",type:"string",notSupported:!0}]},{tfOpName:"LRN",category:"normalization",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"depth_radius",name:"radius",type:"number",defaultValue:5},{tfName:"bias",name:"bias",type:"number",defaultValue:1},{tfName:"alpha",name:"alpha",type:"number",defaultValue:1},{tfName:"beta",name:"beta",type:"number",defaultValue:.5}]},{tfOpName:"Softmax",category:"normalization",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"LogSoftmax",category:"normalization",inputs:[{start:0,name:"x",type:"tensor"}]}],KS=[{tfOpName:"Bincount",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"size",type:"number"},{start:2,name:"weights",type:"tensor"}]},{tfOpName:"DenseBincount",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"size",type:"number"},{start:2,name:"weights",type:"tensor"}],attrs:[{tfName:"binary_output",name:"binaryOutput",type:"bool"}]},{tfOpName:"Max",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool"}]},{tfOpName:"Mean",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool"}]},{tfOpName:"Min",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool"}]},{tfOpName:"Sum",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool"}]},{tfOpName:"All",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool"}]},{tfOpName:"Any",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool"}]},{tfOpName:"ArgMax",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number"}]},{tfOpName:"ArgMin",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number"}]},{tfOpName:"Prod",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}],attrs:[{tfName:"keep_dims",name:"keepDims",type:"bool"},{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"Cumprod",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number"}],attrs:[{tfName:"exclusive",name:"exclusive",type:"bool"},{tfName:"reverse",name:"reverse",type:"bool"}]},{tfOpName:"Cumsum",category:"reduction",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number"}],attrs:[{tfName:"exclusive",name:"exclusive",type:"bool"},{tfName:"reverse",name:"reverse",type:"bool"}]}],XS=[{tfOpName:"ConcatV2",category:"slice_join",inputs:[{start:0,end:-1,name:"tensors",type:"tensors"},{start:-1,name:"axis",type:"number"}],attrs:[{tfName:"N",name:"n",type:"number",defaultValue:2}]},{tfOpName:"Concat",category:"slice_join",inputs:[{start:1,end:0,name:"tensors",type:"tensors"},{start:0,name:"axis",type:"number"}],attrs:[{tfName:"N",name:"n",type:"number",defaultValue:2}]},{tfOpName:"GatherV2",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"indices",type:"tensor"},{start:2,name:"axis",type:"number",defaultValue:0}],attrs:[{tfName:"batch_dims",name:"batchDims",type:"number",defaultValue:0}]},{tfOpName:"Gather",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"indices",type:"tensor"}],attrs:[{tfName:"validate_indices",name:"validateIndices",type:"bool",notSupported:!0}]},{tfOpName:"Reverse",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"dims",type:"bool[]"}]},{tfOpName:"ReverseV2",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number[]"}]},{tfOpName:"Slice",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"begin",type:"number[]"},{start:2,name:"size",type:"number[]"}]},{tfOpName:"StridedSlice",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"begin",type:"number[]"},{start:2,name:"end",type:"number[]"},{start:3,name:"strides",type:"number[]"}],attrs:[{tfName:"begin_mask",name:"beginMask",type:"number",defaultValue:0},{tfName:"end_mask",name:"endMask",type:"number",defaultValue:0},{tfName:"new_axis_mask",name:"newAxisMask",type:"number",defaultValue:0},{tfName:"ellipsis_mask",name:"ellipsisMask",type:"number",defaultValue:0},{tfName:"shrink_axis_mask",name:"shrinkAxisMask",type:"number",defaultValue:0}]},{tfOpName:"Pack",category:"slice_join",inputs:[{start:0,end:0,name:"tensors",type:"tensors"}],attrs:[{tfName:"axis",name:"axis",type:"number",defaultValue:0}]},{tfOpName:"Unpack",category:"slice_join",inputs:[{start:0,name:"tensor",type:"tensor"}],attrs:[{tfName:"axis",name:"axis",type:"number",defaultValue:0},{tfName:"num",name:"num",type:"number",defaultValue:0,notSupported:!0}]},{tfOpName:"Tile",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"reps",type:"number[]"}]},{tfOpName:"Split",category:"slice_join",inputs:[{start:0,name:"axis",type:"number",defaultValue:0},{start:1,name:"x",type:"tensor"}],attrs:[{tfName:"num_split",name:"numOrSizeSplits",type:"number",defaultValue:1}]},{tfOpName:"SplitV",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"numOrSizeSplits",type:"number[]"},{start:2,name:"axis",type:"number",defaultValue:0}]},{tfOpName:"ScatterNd",category:"slice_join",inputs:[{start:0,name:"indices",type:"tensor"},{start:1,name:"values",type:"tensor"},{start:2,name:"shape",type:"number[]"}]},{tfOpName:"GatherNd",category:"slice_join",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"indices",type:"tensor"}]},{tfOpName:"SparseToDense",category:"slice_join",inputs:[{start:0,name:"sparseIndices",type:"tensor"},{start:1,name:"outputShape",type:"number[]"},{start:2,name:"sparseValues",type:"tensor"},{start:3,name:"defaultValue",type:"tensor"}],attrs:[{tfName:"validate_indices",name:"validateIndices",type:"bool",defaultValue:!1,notSupported:!0}]},{tfOpName:"TensorScatterUpdate",category:"slice_join",inputs:[{start:0,name:"tensor",type:"tensor"},{start:1,name:"indices",type:"tensor"},{start:2,name:"values",type:"tensor"}]}],YS=[{tfOpName:"SparseFillEmptyRows",category:"sparse",inputs:[{start:0,name:"indices",type:"tensor"},{start:1,name:"values",type:"tensor"},{start:2,name:"denseShape",type:"tensor"},{start:3,name:"defaultValue",type:"tensor"}]},{tfOpName:"SparseReshape",category:"sparse",inputs:[{start:0,name:"inputIndices",type:"tensor"},{start:1,name:"inputShape",type:"tensor"},{start:2,name:"newShape",type:"tensor"}],attrs:[{tfName:"T",name:"dtype",type:"dtype",notSupported:!0}]},{tfOpName:"SparseSegmentMean",category:"sparse",inputs:[{start:0,name:"data",type:"tensor"},{start:1,name:"indices",type:"tensor"},{start:2,name:"segmentIds",type:"tensor"}]},{tfOpName:"SparseSegmentSum",category:"sparse",inputs:[{start:0,name:"data",type:"tensor"},{start:1,name:"indices",type:"tensor"},{start:2,name:"segmentIds",type:"tensor"}]}],ZS=[{tfOpName:"FFT",category:"spectral",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"IFFT",category:"spectral",inputs:[{start:0,name:"x",type:"tensor"}]},{tfOpName:"RFFT",category:"spectral",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"fft_length",type:"number",notSupported:!0}]},{tfOpName:"IRFFT",category:"spectral",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"fft_length",type:"number",notSupported:!0}]}],JS=[{tfOpName:"StaticRegexReplace",category:"string",inputs:[{start:0,name:"input",type:"tensor"}],attrs:[{tfName:"pattern",name:"pattern",type:"string"},{tfName:"rewrite",name:"rewrite",type:"string"},{tfName:"replace_global",name:"replaceGlobal",type:"bool"}]},{tfOpName:"StringNGrams",category:"string",inputs:[{start:0,name:"data",type:"tensor"},{start:1,name:"dataSplits",type:"tensor"}],attrs:[{tfName:"separator",name:"separator",type:"string"},{tfName:"ngram_widths",name:"nGramWidths",type:"number[]"},{tfName:"left_pad",name:"leftPad",type:"string"},{tfName:"right_pad",name:"rightPad",type:"string"},{tfName:"pad_width",name:"padWidth",type:"number"},{tfName:"preserve_short_sequences",name:"preserveShortSequences",type:"bool"}],outputs:["ngrams","ngrams_splits"]},{tfOpName:"StringSplit",category:"string",inputs:[{start:0,name:"input",type:"tensor"},{start:1,name:"delimiter",type:"tensor"}],attrs:[{tfName:"skip_empty",name:"skipEmpty",type:"bool"}],outputs:["indices","values","shape"]},{tfOpName:"StringToHashBucketFast",category:"string",inputs:[{start:0,name:"input",type:"tensor"}],attrs:[{tfName:"num_buckets",name:"numBuckets",type:"number"}]}],QS=[{tfOpName:"Cast",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"SrcT",name:"sdtype",type:"dtype",notSupported:!0},{tfName:"DstT",name:"dtype",type:"dtype"}]},{tfOpName:"ExpandDims",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"axis",type:"number"}]},{tfOpName:"MirrorPad",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"padding",type:"number[]"}],attrs:[{tfName:"mode",name:"mode",type:"string"}]},{tfOpName:"Pad",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"padding",type:"number[]"}],attrs:[{tfName:"constant_value",name:"constantValue",type:"number",defaultValue:0}]},{tfOpName:"PadV2",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"padding",type:"number[]"},{start:2,name:"constantValue",type:"number",defaultValue:0}]},{tfOpName:"Reshape",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"shape",type:"number[]"}]},{tfOpName:"EnsureShape",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"shape",type:"number[]"}]},{tfOpName:"Squeeze",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"axis",tfDeprecatedName:"squeeze_dims",name:"axis",type:"number[]"}]},{tfOpName:"SpaceToBatchND",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"blockShape",type:"number[]"},{start:2,name:"paddings",type:"number[]"}]},{tfOpName:"BatchToSpaceND",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"blockShape",type:"number[]"},{start:2,name:"crops",type:"number[]"}]},{tfOpName:"DepthToSpace",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"}],attrs:[{tfName:"block_size",name:"blockSize",type:"number"},{tfName:"data_format",name:"dataFormat",type:"string"}]},{tfOpName:"BroadcastTo",category:"transformation",inputs:[{start:0,name:"x",type:"tensor"},{start:1,name:"shape",type:"number[]"}],attrs:[]},{tfOpName:"BroadcastArgs",category:"transformation",inputs:[{start:0,name:"s0",type:"tensor"},{start:1,name:"s1",type:"tensor"}],attrs:[]}];class eT{static get Instance(){return this._instance||(this._instance=new this)}constructor(){const e=[].concat(...[S,T,C,$,E,A,R,F,_,D,O,M,L,z,P,B,W,V,U].map((e=>e.json)));this.opMappers=e.reduce(((e,t)=>(e[t.tfOpName]=t,e)),{})}transformGraph(e,t={}){const n=e.node,s=[],r=[],a=[],i=n.reduce(((e,t)=>(e[t.name]=this.mapNode(t),t.op.startsWith("Placeholder")?s.push(e[t.name]):"Const"===t.op?r.push(e[t.name]):null!=t.input&&0!==t.input.length||a.push(e[t.name]),e)),{});let o=[];const l=[];let u={},c={};null!=t&&(u=this.mapSignatureEntries(t.inputs),c=this.mapSignatureEntries(t.outputs));const h=Object.keys(i);h.forEach((e=>{const t=i[e];t.inputNames.forEach(((e,n)=>{const[s,,r]=AS(e),a=i[s];if(null!=a.outputs){const e=a.outputs.indexOf(r);if(-1!==e){const r=`${s}:${e}`;t.inputNames[n]=r}}t.inputs.push(a),a.children.push(t)}))})),0===Object.keys(c).length?h.forEach((e=>{const t=i[e];0===t.children.length&&l.push(t)})):Object.keys(c).forEach((e=>{const[t]=AS(e),n=i[t];null!=n&&(n.signatureKey=c[e],l.push(n))})),Object.keys(u).length>0?Object.keys(u).forEach((e=>{const[t]=AS(e),n=i[t];n&&(n.signatureKey=u[e],o.push(n))})):o=s;let p={};null!=e.library&&null!=e.library.function&&(p=e.library.function.reduce(((e,t)=>(e[t.signature.name]=this.mapFunction(t),e)),{}));const d={nodes:i,inputs:o,outputs:l,weights:r,placeholders:s,signature:t,functions:p};return a.length>0&&(d.initNodes=a),d}mapSignatureEntries(e){return Object.keys(e||{}).reduce(((t,n)=>(t[e[n].name]=n,t)),{})}mapNode(e){const t=SS(e.op)||this.opMappers[e.op]||{};null==e.attr&&(e.attr={});const n={name:e.name,op:e.op,category:t.category,inputNames:(e.input||[]).map((e=>e.startsWith("^")?e.slice(1):e)),inputs:[],children:[],inputParams:{},attrParams:{},rawAttrs:e.attr,outputs:t.outputs};return null!=t.inputs&&(n.inputParams=t.inputs.reduce(((e,t)=>(e[t.name]={type:t.type,inputIndexStart:t.start,inputIndexEnd:t.end},e)),{})),null!=t.attrs&&(n.attrParams=t.attrs.reduce(((t,n)=>{const s=n.type;let r;switch(n.type){case"string":r=nT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=nT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"string[]":r=pT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=pT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"number":r=rT(e.attr,n.tfName,n.defaultValue||0),void 0===r&&n.tfDeprecatedName&&(r=rT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"number[]":r=hT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=hT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"bool":r=sT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=sT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"bool[]":r=fT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=fT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"shape":r=cT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=cT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"shape[]":r=dT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=dT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"dtype":r=oT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=oT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"dtype[]":r=lT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=lT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"func":r=iT(e.attr,n.tfName,n.defaultValue),void 0===r&&n.tfDeprecatedName&&(r=iT(e.attr,n.tfDeprecatedName,n.defaultValue));break;case"tensor":case"tensors":break;default:throw new Error(`Unsupported param type: ${n.type} for op: ${e.op}`)}return t[n.name]={value:r,type:s},t}),{})),n}mapFunction(e){const t=e.nodeDef,n=[];let s={};null!=t&&(s=t.reduce(((e,t)=>(e[t.name]=this.mapNode(t),"Const"===t.op&&n.push(e[t.name]),e)),{}));const r=[],a=[];e.signature.inputArg.forEach((e=>{const[t]=AS(e.name),n={name:t,op:"Placeholder",inputs:[],inputNames:[],category:"graph",inputParams:{},attrParams:{dtype:{value:aT(e.type),type:"dtype"}},children:[]};n.signatureKey=e.name,r.push(n),s[t]=n}));Object.keys(s).forEach((e=>{const t=s[e];t.inputNames.forEach(((e,n)=>{const[r,,a]=AS(e),i=s[r];if(null!=i.outputs){const e=i.outputs.indexOf(a);if(-1!==e){const s=`${r}:${e}`;t.inputNames[n]=s}}t.inputs.push(i),i.children.push(t)}))}));const i=e.ret;e.signature.outputArg.forEach((e=>{const[t,n]=AS(i[e.name]),r=s[t];null!=r&&(r.defaultOutput=n,a.push(r))}));const o=this.mapArgsToSignature(e);return{nodes:s,inputs:r,outputs:a,weights:n,placeholders:[],signature:o}}mapArgsToSignature(e){return{methodName:e.signature.name,inputs:e.signature.inputArg.reduce(((e,t)=>(e[t.name]=this.mapArgToTensorInfo(t),e)),{}),outputs:e.signature.outputArg.reduce(((t,n)=>(t[n.name]=this.mapArgToTensorInfo(n,e.ret),t)),{})}}mapArgToTensorInfo(e,t){let n=e.name;return null!=t&&(n=t[n]),{name:n,dtype:e.type}}}function tT(e,t){const n=Array.isArray(e)?String.fromCharCode.apply(null,e):function(e){const t=Xe().global;if(void 0!==t.atob)return t.atob(e);if("undefined"!=typeof Buffer)return new Buffer(e,"base64").toString();throw new Error("Unable to decode base64 in this environment. Missing built-in atob() or Buffer()")}(e);return t?n:n.toLowerCase()}function nT(e,t,n,s=!1){const r=e[t];return null!=r?tT(r.s,s):n}function sT(e,t,n){const s=e[t];return s?s.b:n}function rT(e,t,n){const s=e[t]||{},r=null!=s.i?s.i:null!=s.f?s.f:n;return"number"==typeof r?r:parseInt(r,10)}function aT(e){switch("string"==typeof e&&(e=vS[e]),e){case vS.DT_FLOAT:case vS.DT_HALF:return"float32";case vS.DT_INT32:case vS.DT_INT64:case vS.DT_INT8:case vS.DT_UINT8:return"int32";case vS.DT_BOOL:return"bool";case vS.DT_DOUBLE:return"float32";case vS.DT_STRING:return"string";default:return null}}function iT(e,t,n){const s=e[t];return s&&s.func?s.func.name:n}function oT(e,t,n){const s=e[t];return s&&s.type?aT(s.type):n}function lT(e,t,n){const s=e[t];return s&&s.list&&s.list.type?s.list.type.map((e=>aT(e))):n}function uT(e){if(!e.unknownRank)return null!=e.dim?e.dim.map((e=>"number"==typeof e.size?e.size:parseInt(e.size,10))):[]}function cT(e,t,n){const s=e[t];return s&&s.shape?uT(s.shape):n}function hT(e,t,n){const s=e[t];return s?((s.list.f&&s.list.f.length?s.list.f:s.list.i)||[]).map((e=>"number"==typeof e?e:parseInt(e,10))):n}function pT(e,t,n,s=!1){const r=e[t];return r&&r.list&&r.list.s?r.list.s.map((e=>tT(e,s))):n}function dT(e,t,n){const s=e[t];return s&&s.list&&s.list.shape?s.list.shape.map((e=>uT(e))):n}function fT(e,t,n){const s=e[t];return s&&s.list&&s.list.b?s.list.b:n}class mT{constructor(e,t,n){this.node=e,this.tensorMap=t,this.context=n,this.inputs=[],this.attrs={},this.inputs=e.inputNames.map((e=>this.getInput(e))),null!=e.rawAttrs&&(this.attrs=Object.keys(e.rawAttrs).reduce(((e,t)=>(e[t]=this.getAttr(t),e)),{}))}getInput(e){return $S(e,this.tensorMap,this.context)}getAttr(e,t){const n=this.node.rawAttrs[e];if(null!=n.tensor)return $S(e,this.tensorMap,this.context);if(null!=n.i||null!=n.f)return rT(this.node.rawAttrs,e,t);if(null!=n.s)return nT(this.node.rawAttrs,e,t);if(null!=n.b)return sT(this.node.rawAttrs,e,t);if(null!=n.shape)return cT(this.node.rawAttrs,e,t);if(null!=n.type)return oT(this.node.rawAttrs,e,t);if(null!=n.list){if(null!=n.list.i||null!=n.list.f)return hT(this.node.rawAttrs,e,t);if(null!=n.list.s)return pT(this.node.rawAttrs,e,t);if(null!=n.list.shape)return dT(this.node.rawAttrs,e,t);if(null!=n.list.b)return fT(this.node.rawAttrs,e,t);if(null!=n.list.type)return lT(this.node.rawAttrs,e,t)}return t}}function gT(e,t,n=""){if("number"!=typeof e&&"number"!=typeof t){ie(e.length===t.length,(()=>n+` Shapes ${e} and ${t} must match`));for(let s=0;s<e.length;s++){const r=e[s],a=t[s];ie(r<0||a<0||r===a,(()=>n+` Shapes ${e} and ${t} must match`))}}}function yT(e){return"number"!=typeof e&&!e.some((e=>e<0))}function bT(e,t,n){let s=xT(e,n);const r=!yT(s);if(r&&0===t.length)throw new Error(`Tried to calculate elements of an empty list with non-fully-defined elementShape: ${s}`);if(r&&t.forEach((e=>{s=xT(e.shape,s)})),!yT(s))throw new Error(`Non-fully-defined elementShape: ${s}`);return s}function xT(e,t){if("number"==typeof e)return t;if("number"==typeof t)return e;if(e.length!==t.length)throw new Error(`Incompatible ranks during merge: ${e} vs. ${t}`);const n=[];for(let s=0;s<e.length;++s){const r=e[s],a=t[s];if(r>=0&&a>=0&&r!==a)throw new Error(`Incompatible shape during merge: ${e} vs. ${t}`);n[s]=r>=0?r:a}return n}class wT{constructor(e,t,n,s,r,a,i){this.name=e,this.dtype=t,this.maxSize=n,this.elementShape=s,this.identicalElementShapes=r,this.dynamicSize=a,this.clearAfterRead=i,this.tensors=[],this.closed_=!1,this.idTensor=Wo(0),go(this.idTensor)}get id(){return this.idTensor.id}get closed(){return this.closed_}clearAndClose(e){this.tensors.forEach((t=>{null!=e&&e.has(t.tensor.id)||t.tensor.dispose()})),this.tensors=[],this.closed_=!0,this.idTensor.dispose()}size(){return this.tensors.length}read(e){if(this.closed_)throw new Error(`TensorArray ${this.name} has already been closed.`);if(e<0||e>=this.size())throw new Error(`Tried to read from index ${e}, but array size is: ${this.size()}`);const t=this.tensors[e];if(t.cleared)throw new Error(`TensorArray ${this.name}: Could not read index ${e} twice because it was cleared after a previous read (perhaps try setting clear_after_read = false?).`);return this.clearAfterRead&&(t.cleared=!0),t.read=!0,t.tensor}readMany(e){return e.map((e=>this.read(e)))}write(e,t){if(this.closed_)throw new Error(`TensorArray ${this.name} has already been closed.`);if(e<0||!this.dynamicSize&&e>=this.maxSize)throw new Error(`Tried to write to index ${e}, but array is not resizeable and size is: ${this.maxSize}`);const n=this.tensors[e]||{};if(t.dtype!==this.dtype)throw new Error(`TensorArray ${this.name}: Could not write to TensorArray index ${e},\n          because the value dtype is ${t.dtype}, but TensorArray dtype is ${this.dtype}.`);if(0!==this.size()||null!=this.elementShape&&0!==this.elementShape.length||(this.elementShape=t.shape),gT(this.elementShape,t.shape,`TensorArray ${this.name}: Could not write to TensorArray index ${e}.`),n.read)throw new Error(`TensorArray ${this.name}: Could not write to TensorArray index ${e}, because it has already been read.`);if(n.written)throw new Error(`TensorArray ${this.name}: Could not write to TensorArray index ${e}, because it has already been written.`);n.tensor=t,go(t),n.written=!0,this.tensors[e]=n}writeMany(e,t){if(e.length!==t.length)throw new Error(`TensorArray ${this.name}: could not write multiple tensors,because the index size: ${e.length} is not the same as tensors size: ${t.length}.`);e.forEach(((e,n)=>this.write(e,t[n])))}gather(e,t){if(t&&t!==this.dtype)throw new Error(`TensorArray dtype is ${this.dtype} but gather requested dtype ${t}`);if(e)e=e.slice(0,this.size());else{e=[];for(let t=0;t<this.size();t++)e.push(t)}if(0===e.length)return ei([],[0].concat(this.elementShape));const n=this.readMany(e);return gT(this.elementShape,n[0].shape,"TensorArray shape mismatch: "),Qp(n,0)}concat(e){if(e&&e!==this.dtype)throw new Error(`TensorArray dtype is ${this.dtype} but concat requested dtype ${e}`);if(0===this.size())return ei([],[0].concat(this.elementShape));const t=[];for(let e=0;e<this.size();e++)t.push(e);const n=this.readMany(t);return gT(this.elementShape,n[0].shape,`TensorArray shape mismatch: tensor array shape (${this.elementShape}) vs first tensor shape (${n[0].shape})`),ic(n,0)}scatter(e,t){if(t.dtype!==this.dtype)throw new Error(`TensorArray dtype is ${this.dtype} but tensor has dtype ${t.dtype}`);if(e.length!==t.shape[0])throw new Error(`Expected len(indices) == tensor.shape[0], but saw: ${e.length} vs. ${t.shape[0]}`);const n=Math.max(...e);if(!this.dynamicSize&&n>=this.maxSize)throw new Error(`Max index must be < array size (${n}  vs. ${this.maxSize})`);this.writeMany(e,dd(t,0))}split(e,t){if(t.dtype!==this.dtype)throw new Error(`TensorArray dtype is ${this.dtype} but tensor has dtype ${t.dtype}`);let n=0;const s=e.map((e=>(n+=e,n)));if(n!==t.shape[0])throw new Error(`Expected sum of lengths to be equal to\n          tensor.shape[0], but sum of lengths is\n        ${n}, and tensor's shape is: ${t.shape}`);if(!this.dynamicSize&&e.length!==this.maxSize)throw new Error(`TensorArray's size is not equal to the size of lengths (${this.maxSize} vs. ${e.length}), and the TensorArray is not marked as dynamically resizeable`);const r=0===n?0:t.size/n,a=[];fo((()=>{t=sc(t,[1,n,r]);for(let n=0;n<e.length;++n){const i=[0,0===n?0:s[n-1],0],o=[1,e[n],r];a[n]=sc(lc(t,i,o),this.elementShape)}return a}));const i=[];for(let t=0;t<e.length;t++)i[t]=t;this.writeMany(i,a)}}class vT{get id(){return this.idTensor.id}constructor(e,t,n,s=-1){this.tensors=e,this.elementShape=t,this.elementDtype=n,null!=e&&e.forEach((e=>{if(n!==e.dtype)throw new Error(`Invalid data types; op elements ${n}, but list elements ${e.dtype}`);gT(t,e.shape,"TensorList shape mismatch: "),go(e)})),this.idTensor=Wo(0),this.maxNumElements=s,go(this.idTensor)}copy(){return new vT([...this.tensors],this.elementShape,this.elementDtype)}clearAndClose(e){this.tensors.forEach((t=>{null!=e&&e.has(t.id)||t.dispose()})),this.tensors.length=0,this.idTensor.dispose()}size(){return this.tensors.length}stack(e,t,n=-1){if(t!==this.elementDtype)throw new Error(`Invalid data types; op elements ${t}, but list elements ${this.elementDtype}`);if(-1!==n&&this.tensors.length!==n)throw new Error(`Operation expected a list with ${n} elements but got a list with ${this.tensors.length} elements.`);gT(e,this.elementShape,"TensorList shape mismatch: ");const s=bT(this.elementShape,this.tensors,e);return fo((()=>{const e=this.tensors.map((e=>sc(e,s)));return Qp(e,0)}))}popBack(e,t){if(t!==this.elementDtype)throw new Error(`Invalid data types; op elements ${t}, but list elements ${this.elementDtype}`);if(0===this.size())throw new Error("Trying to pop from an empty list.");const n=bT(this.elementShape,this.tensors,e),s=this.tensors.pop();return s.kept=!1,gT(s.shape,e,"TensorList shape mismatch: "),sc(s,n)}pushBack(e){if(e.dtype!==this.elementDtype)throw new Error(`Invalid data types; op elements ${e.dtype}, but list elements ${this.elementDtype}`);if(gT(e.shape,this.elementShape,"TensorList shape mismatch: "),this.maxNumElements===this.size())throw new Error("Trying to push element into a full list.");go(e),this.tensors.push(e)}resize(e){if(e<0)throw new Error(`TensorListResize expects size to be non-negative. Got: ${e}`);if(-1!==this.maxNumElements&&e>this.maxNumElements)throw new Error(`TensorListResize input size ${e} is greater maxNumElement ${this.maxNumElements}.`);const t=new vT([],this.elementShape,this.elementDtype,this.maxNumElements);t.tensors.length=e;for(let n=0;n<Math.min(this.tensors.length,e);++n)t.tensors[n]=this.tensors[n];return t}getItem(e,t,n){if(n!==this.elementDtype)throw new Error(`Invalid data types; op elements ${n}, but list elements ${this.elementDtype}`);if(e<0||e>this.tensors.length)throw new Error(`Trying to access element ${e} in a list with ${this.tensors.length} elements.`);if(null==this.tensors[e])throw new Error(`element at index ${e} is null.`);gT(this.tensors[e].shape,t,"TensorList shape mismatch: ");const s=bT(this.elementShape,this.tensors,t);return sc(this.tensors[e],s)}setItem(e,t){if(t.dtype!==this.elementDtype)throw new Error(`Invalid data types; op elements ${t.dtype}, but list elements ${this.elementDtype}`);if(e<0||-1!==this.maxNumElements&&e>=this.maxNumElements)throw new Error(`Trying to set element ${e} in a list with max ${this.maxNumElements} elements.`);gT(this.elementShape,t.shape,"TensorList shape mismatch: "),go(t),null!=this.tensors[e]&&(this.tensors[e].kept=!1),this.tensors[e]=t}gather(e,t,n){if(t!==this.elementDtype)throw new Error(`Invalid data types; op elements ${t}, but list elements ${this.elementDtype}`);gT(this.elementShape,n,"TensorList shape mismatch: "),e=e.slice(0,this.size());const s=bT(this.elementShape,this.tensors,n);return 0===e.length?ei([],[0].concat(s)):fo((()=>{const t=e.map((e=>sc(this.tensors[e],s)));return Qp(t,0)}))}concat(e,t){if(e&&e!==this.elementDtype)throw new Error(`TensorList dtype is ${this.elementDtype} but concat requested dtype ${e}`);gT(this.elementShape,t,"TensorList shape mismatch: ");const n=bT(this.elementShape,this.tensors,t);return 0===this.size()?ei([],[0].concat(n)):fo((()=>{const e=this.tensors.map((e=>sc(e,n)));return ic(e,0)}))}}const kT=async(e,t,n)=>{switch(e.op){case"If":case"StatelessIf":{const s=CS("thenBranch",e,t,n),r=CS("elseBranch",e,t,n),a=CS("cond",e,t,n),i=CS("args",e,t,n);return(await a.data())[0]?n.functionMap[s].executeFunctionAsync(i,n.tensorArrayMap,n.tensorListMap):n.functionMap[r].executeFunctionAsync(i,n.tensorArrayMap,n.tensorListMap)}case"While":case"StatelessWhile":{const s=CS("body",e,t,n),r=CS("cond",e,t,n),a=CS("args",e,t,n),i=await n.functionMap[r].executeFunctionAsync(a,n.tensorArrayMap,n.tensorListMap),o=a.map((e=>e.id));let l=await i[0].data();i.forEach((e=>{e.kept||-1!==o.indexOf(e.id)||e.dispose()}));let u=a;for(;l[0];){const e=u;u=await n.functionMap[s].executeFunctionAsync(u,n.tensorArrayMap,n.tensorListMap);const t=u.map((e=>e.id));e.forEach((e=>{e.kept||-1!==o.indexOf(e.id)||-1!==t.indexOf(e.id)||e.dispose()}));const a=await n.functionMap[r].executeFunctionAsync(u,n.tensorArrayMap,n.tensorListMap);l=await a[0].data(),a.forEach((e=>{e.kept||-1!==o.indexOf(e.id)||-1!==t.indexOf(e.id)||e.dispose()}))}return u}case"LoopCond":return[DS(CS("pred",e,t,n))];case"Switch":{const s=CS("pred",e,t,n);let r=CS("data",e,t,n);return r.kept||(r=DS(r)),(await s.data())[0]?[void 0,r]:[r,void 0]}case"Merge":{const s=e.inputNames.find((e=>void 0!==$S(e,t,n)));if(s){return[DS($S(s,t,n))]}return}case"Enter":{const s=CS("frameName",e,t,n),r=CS("tensor",e,t,n);return n.enterFrame(s),[DS(r)]}case"Exit":{const s=CS("tensor",e,t,n);return n.exitFrame(),[DS(s)]}case"NextIteration":{const s=CS("tensor",e,t,n);return n.nextIteration(),[DS(s)]}case"TensorArrayV3":{const s=CS("size",e,t,n),r=CS("dtype",e,t,n),a=CS("elementShape",e,t,n),i=CS("dynamicSize",e,t,n),o=CS("clearAfterRead",e,t,n),l=CS("identicalElementShapes",e,t,n),u=CS("name",e,t,n),c=new wT(u,r,s,a,l,i,o);return n.addTensorArray(c),[c.idTensor,Wo(1)]}case"TensorArrayWriteV3":{const s=CS("tensorArrayId",e,t,n),r=CS("index",e,t,n),a=CS("tensor",e,t,n),i=n.getTensorArray(s.id);return i.write(r,a),[i.idTensor]}case"TensorArrayReadV3":{const s=CS("tensorArrayId",e,t,n),r=CS("index",e,t,n);return[n.getTensorArray(s.id).read(r)]}case"TensorArrayGatherV3":{const s=CS("tensorArrayId",e,t,n),r=CS("indices",e,t,n),a=CS("dtype",e,t,n);return[n.getTensorArray(s.id).gather(r,a)]}case"TensorArrayScatterV3":{const s=CS("tensorArrayId",e,t,n),r=CS("indices",e,t,n),a=CS("tensor",e,t,n),i=n.getTensorArray(s.id);return i.scatter(r,a),[i.idTensor]}case"TensorArrayConcatV3":{const s=CS("tensorArrayId",e,t,n),r=n.getTensorArray(s.id),a=CS("dtype",e,t,n);return[r.concat(a)]}case"TensorArraySplitV3":{const s=CS("tensorArrayId",e,t,n),r=CS("tensor",e,t,n),a=CS("lengths",e,t,n),i=n.getTensorArray(s.id);return i.split(a,r),[i.idTensor]}case"TensorArraySizeV3":{const s=CS("tensorArrayId",e,t,n);return[Wo(n.getTensorArray(s.id).size(),"int32")]}case"TensorArrayCloseV3":{const s=CS("tensorArrayId",e,t,n),r=n.getTensorArray(s.id);return r.clearAndClose(),[r.idTensor]}case"TensorListSetItem":{const s=CS("tensorListId",e,t,n),r=CS("index",e,t,n),a=CS("tensor",e,t,n),i=n.getTensorList(s.id);return i.setItem(r,a),[i.idTensor]}case"TensorListGetItem":{const s=CS("tensorListId",e,t,n),r=CS("index",e,t,n),a=CS("elementShape",e,t,n),i=CS("elementDType",e,t,n);return[n.getTensorList(s.id).getItem(r,a,i)]}case"TensorListScatterV2":case"TensorListScatter":{const s=CS("indices",e,t,n),r=function(e,t,n,s){if(t.length!==e.shape[0])throw new Error(`Expected len(indices) == tensor.shape[0], but saw: ${t.length} vs. ${e.shape[0]}`);const r=Math.max(...t);if(null!=s&&-1!==s&&r>=s)throw new Error(`Max index must be < array size (${r}  vs. ${s})`);const a=new vT([],n,e.dtype,s),i=dd(e,0);return t.forEach(((e,t)=>{a.setItem(e,i[t])})),a}(CS("tensor",e,t,n),s,CS("elementShape",e,t,n),CS("numElements",e,t,n));return n.addTensorList(r),[r.idTensor]}case"TensorListReserve":case"EmptyTensorList":{const s=CS("elementShape",e,t,n),r=CS("elementDType",e,t,n);let a;a="TensorListReserve"===e.op?"numElements":"maxNumElements";const i=CS(a,e,t,n),o=function(e,t,n,s){return new vT([],e,t,s)}(s,r,0,"TensorListReserve"===e.op?-1:i);return n.addTensorList(o),[o.idTensor]}case"TensorListGather":{const s=CS("tensorListId",e,t,n),r=CS("indices",e,t,n),a=CS("elementShape",e,t,n),i=CS("elementDType",e,t,n);return[n.getTensorList(s.id).gather(r,i,a)]}case"TensorListStack":{const s=CS("tensorListId",e,t,n),r=CS("elementShape",e,t,n),a=CS("elementDType",e,t,n),i=CS("numElements",e,t,n);return[n.getTensorList(s.id).stack(r,a,i)]}case"TensorListFromTensor":{const s=function(e,t,n){const s=e.dtype;if(e.shape.length<1)throw new Error(`Tensor must be at least a vector, but saw shape: ${e.shape}`);if(e.dtype!==n)throw new Error(`Invalid data types; op elements ${e.dtype}, but list elements ${n}`);gT(e.shape.slice(1),t,"TensorList shape mismatch: ");const r=dd(e);return new vT(r,t,s)}(CS("tensor",e,t,n),CS("elementShape",e,t,n),CS("elementDType",e,t,n));return n.addTensorList(s),[s.idTensor]}case"TensorListConcat":case"TensorListConcatV2":{const s=CS("tensorListId",e,t,n),r=n.getTensorList(s.id),a=CS("dtype",e,t,n),i=CS("elementShape",e,t,n);return[r.concat(a,i)]}case"TensorListPushBack":{const s=CS("tensorListId",e,t,n),r=CS("tensor",e,t,n),a=n.getTensorList(s.id);return a.pushBack(r),[a.idTensor]}case"TensorListPopBack":{const s=CS("tensorListId",e,t,n),r=CS("elementShape",e,t,n),a=CS("elementDType",e,t,n);return[n.getTensorList(s.id).popBack(r,a)]}case"TensorListSplit":{const s=CS("tensor",e,t,n),r=CS("elementShape",e,t,n),a=function(e,t,n){let s=0;const r=t.map((e=>(s+=e,s)));if(s!==e.shape[0])throw new Error(`Expected sum of lengths to be equal to\n          tensor.shape[0], but sum of lengths is\n        ${s}, and tensor's shape is: ${e.shape}`);const a=xT(e.shape.slice(1),n),i=0===s?0:e.size/s,o=fo((()=>{const n=[];e=sc(e,[1,s,i]);for(let s=0;s<t.length;++s){const o=[0,0===s?0:r[s-1],0],l=[1,t[s],i];n[s]=sc(lc(e,o,l),a)}return e.dispose(),n})),l=new vT([],n,e.dtype,t.length);for(let e=0;e<o.length;e++)l.setItem(e,o[e]);return l}(s,CS("lengths",e,t,n),r);return n.addTensorList(a),[a.idTensor]}case"TensorListLength":{const s=CS("tensorListId",e,t,n);return[Wo(n.getTensorList(s.id).size(),"int32")]}case"TensorListResize":{const s=CS("tensorListId",e,t,n),r=CS("size",e,t,n),a=n.getTensorList(s.id).resize(r);return n.addTensorList(a),[a.idTensor]}default:throw TypeError(`Node type ${e.op} is not implemented`)}};function IT(e,t,n){const[s,r]=CS("fusedOps",e,t,n),a="biasadd"===s,i=!a,o="prelu"===r,l="fusedbatchnorm"===s,u=CS("numArgs",e,t,n);if(a){if(o&&2!==u)throw new Error("FusedConv2d and DepthwiseConv2d with BiasAdd and Prelu must have two extra arguments: bias and alpha.");if(!o&&a&&1!==u)throw new Error("FusedConv2d and DepthwiseConv2d with BiasAdd must have one extra argument: bias.")}if(l)throw new Error("FusedConv2d and DepthwiseConv2d with FusedBatchNorm is not supported");const c=CS("strides",e,t,n),h=_S(e,t,n),p=CS("dataFormat",e,t,n).toUpperCase(),d=CS("dilations",e,t,n);let[f,m]=CS("args",e,t,n);i&&(m=f,f=void 0);return{stride:c,pad:h,dataFormat:p,dilations:d,biasArg:f,preluArg:m,activationFunc:r,leakyreluAlpha:CS("leakyreluAlpha",e,t,n)}}function NT(e,t,n){return{boxes:CS("boxes",e,t,n),scores:CS("scores",e,t,n),maxOutputSize:CS("maxOutputSize",e,t,n),iouThreshold:CS("iouThreshold",e,t,n),scoreThreshold:CS("scoreThreshold",e,t,n),softNmsSigma:CS("softNmsSigma",e,t,n)}}class ST{get id(){return this.handle.id}constructor(e,t){this.keyDType=e,this.valueDType=t,this.handle=Wo(0),this.tensorMap=new Map,go(this.handle)}clearAndClose(){this.tensorMap.forEach((e=>e.dispose())),this.tensorMap.clear(),this.handle.dispose()}size(){return this.tensorMap.size}tensorSize(){return Wo(this.size(),"int32")}async import(e,t){this.checkKeyAndValueTensor(e,t);const n=await e.data();return this.tensorMap.forEach((e=>e.dispose())),this.tensorMap.clear(),fo((()=>{const e=dd(t),s=n.length,r=e.length;ie(s===r,(()=>`The number of elements doesn't match, keys has ${s} elements, the values has ${r} elements.`));for(let t=0;t<s;t++){const s=n[t],r=e[t];go(r),this.tensorMap.set(s,r)}return this.handle}))}async find(e,t){this.checkKeyAndValueTensor(e,t);const n=await e.data();return fo((()=>{const e=[];for(let s=0;s<n.length;s++){const r=n[s],a=this.findWithDefault(r,t);e.push(a)}return Qp(e)}))}findWithDefault(e,t){const n=this.tensorMap.get(e);return null!=n?n:t}checkKeyAndValueTensor(e,t){if(e.dtype!==this.keyDType)throw new Error(`Expect key dtype ${this.keyDType}, but got ${e.dtype}`);if(t.dtype!==this.valueDType)throw new Error(`Expect value dtype ${this.valueDType}, but got ${t.dtype}`)}}function TT(e,t,n,s,r=fo){const a=((e,t,n)=>{switch(e.category){case"arithmetic":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"BiasAdd":case"AddV2":case"Add":return[s.add(CS("a",e,t,n),CS("b",e,t,n))];case"AddN":return[s.addN(CS("tensors",e,t,n))];case"FloorMod":case"Mod":return[s.mod(CS("a",e,t,n),CS("b",e,t,n))];case"Mul":return[s.mul(CS("a",e,t,n),CS("b",e,t,n))];case"RealDiv":case"Div":return[s.div(CS("a",e,t,n),CS("b",e,t,n))];case"DivNoNan":return[s.divNoNan(CS("a",e,t,n),CS("b",e,t,n))];case"FloorDiv":return[s.floorDiv(CS("a",e,t,n),CS("b",e,t,n))];case"Sub":return[s.sub(CS("a",e,t,n),CS("b",e,t,n))];case"Minimum":return[s.minimum(CS("a",e,t,n),CS("b",e,t,n))];case"Maximum":return[s.maximum(CS("a",e,t,n),CS("b",e,t,n))];case"Pow":return[s.pow(CS("a",e,t,n),CS("b",e,t,n))];case"SquaredDifference":return[s.squaredDifference(CS("a",e,t,n),CS("b",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"basic_math":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"Abs":case"ComplexAbs":return[s.abs(CS("x",e,t,n))];case"Acos":return[s.acos(CS("x",e,t,n))];case"Acosh":return[s.acosh(CS("x",e,t,n))];case"Asin":return[s.asin(CS("x",e,t,n))];case"Asinh":return[s.asinh(CS("x",e,t,n))];case"Atan":return[s.atan(CS("x",e,t,n))];case"Atan2":return[s.atan2(CS("x",e,t,n),CS("y",e,t,n))];case"Atanh":return[s.atanh(CS("x",e,t,n))];case"Ceil":return[s.ceil(CS("x",e,t,n))];case"Complex":return[s.complex(CS("real",e,t,n),CS("imag",e,t,n))];case"Cos":return[s.cos(CS("x",e,t,n))];case"Cosh":return[s.cosh(CS("x",e,t,n))];case"Elu":return[s.elu(CS("x",e,t,n))];case"Erf":return[s.erf(CS("x",e,t,n))];case"Exp":return[s.exp(CS("x",e,t,n))];case"Expm1":return[s.expm1(CS("x",e,t,n))];case"Floor":return[s.floor(CS("x",e,t,n))];case"Log":return[s.log(CS("x",e,t,n))];case"Log1p":return[s.log1p(CS("x",e,t,n))];case"Imag":return[s.imag(CS("x",e,t,n))];case"Neg":return[s.neg(CS("x",e,t,n))];case"Reciprocal":return[s.reciprocal(CS("x",e,t,n))];case"Real":return[s.real(CS("x",e,t,n))];case"Relu":return[s.relu(CS("x",e,t,n))];case"Round":return[s.round(CS("x",e,t,n))];case"Selu":return[s.selu(CS("x",e,t,n))];case"Sigmoid":return[s.sigmoid(CS("x",e,t,n))];case"Sin":return[s.sin(CS("x",e,t,n))];case"Sign":return[s.sign(CS("x",e,t,n))];case"Sinh":return[s.sinh(CS("x",e,t,n))];case"Softplus":return[s.softplus(CS("x",e,t,n))];case"Sqrt":return[s.sqrt(CS("x",e,t,n))];case"Square":return[s.square(CS("x",e,t,n))];case"Tanh":return[s.tanh(CS("x",e,t,n))];case"Tan":return[s.tan(CS("x",e,t,n))];case"ClipByValue":return[s.clipByValue(CS("x",e,t,n),CS("clipValueMin",e,t,n),CS("clipValueMax",e,t,n))];case"Relu6":return[s.relu6(CS("x",e,t,n))];case"Rsqrt":return[s.rsqrt($S(e.inputNames[0],t,n))];case"LeakyRelu":return[s.leakyRelu(CS("x",e,t,n),CS("alpha",e,t,n))];case"Prelu":return[s.prelu(CS("x",e,t,n),CS("alpha",e,t,n))];case"IsNan":return[s.isNaN($S(e.inputNames[0],t,n))];case"IsInf":return[s.isInf($S(e.inputNames[0],t,n))];case"IsFinite":return[s.isFinite($S(e.inputNames[0],t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"control":return kT(e,t,n);case"convolution":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"Conv1D":{const r=CS("stride",e,t,n),a=CS("pad",e,t,n),i=CS("dataFormat",e,t,n).toUpperCase(),o=CS("dilation",e,t,n);return[s.conv1d(CS("x",e,t,n),CS("filter",e,t,n),r,a,i,o)]}case"Conv2D":{const r=CS("strides",e,t,n),a=_S(e,t,n),i=CS("dataFormat",e,t,n).toUpperCase(),o=CS("dilations",e,t,n);return[s.conv2d(CS("x",e,t,n),CS("filter",e,t,n),[r[1],r[2]],a,i,[o[1],o[2]])]}case"_FusedConv2D":{const{stride:r,pad:a,dataFormat:i,dilations:o,biasArg:l,preluArg:u,activationFunc:c,leakyreluAlpha:h}=IT(e,t,n);return[s.fused.conv2d({x:CS("x",e,t,n),filter:CS("filter",e,t,n),strides:[r[1],r[2]],pad:a,dataFormat:i,dilations:[o[1],o[2]],bias:l,activation:c,preluActivationWeights:u,leakyreluAlpha:h})]}case"FusedDepthwiseConv2dNative":{const{stride:r,pad:a,dataFormat:i,dilations:o,biasArg:l,preluArg:u,activationFunc:c,leakyreluAlpha:h}=IT(e,t,n);return[s.fused.depthwiseConv2d({x:CS("x",e,t,n),filter:CS("filter",e,t,n),strides:[r[1],r[2]],pad:a,dataFormat:i,dilations:[o[1],o[2]],bias:l,activation:c,preluActivationWeights:u,leakyreluAlpha:h})]}case"Conv2DBackpropInput":case"Conv2dTranspose":{const r=CS("outputShape",e,t,n),a=CS("strides",e,t,n),i=_S(e,t,n);return[s.conv2dTranspose(CS("x",e,t,n),CS("filter",e,t,n),r,[a[1],a[2]],i)]}case"DepthwiseConv2dNative":case"DepthwiseConv2d":{const r=CS("strides",e,t,n),a=_S(e,t,n),i=CS("dilations",e,t,n),o=CS("dataFormat",e,t,n).toUpperCase();return[s.depthwiseConv2d(CS("input",e,t,n),CS("filter",e,t,n),[r[1],r[2]],a,o,[i[1],i[2]])]}case"Conv3D":{const r=CS("strides",e,t,n),a=CS("pad",e,t,n),i=CS("dataFormat",e,t,n).toUpperCase(),o=CS("dilations",e,t,n);return[s.conv3d(CS("x",e,t,n),CS("filter",e,t,n),[r[1],r[2],r[3]],a,i,[o[1],o[2],o[3]])]}case"AvgPool":{const r=CS("strides",e,t,n),a=CS("pad",e,t,n),i=CS("kernelSize",e,t,n);return[s.avgPool(CS("x",e,t,n),[i[1],i[2]],[r[1],r[2]],a)]}case"MaxPool":{const r=CS("strides",e,t,n),a=CS("pad",e,t,n),i=CS("kernelSize",e,t,n);return[s.maxPool(CS("x",e,t,n),[i[1],i[2]],[r[1],r[2]],a)]}case"MaxPoolWithArgmax":{const r=CS("strides",e,t,n),a=CS("pad",e,t,n),i=CS("kernelSize",e,t,n),o=CS("includeBatchInIndex",e,t,n),{result:l,indexes:u}=s.maxPoolWithArgmax(CS("x",e,t,n),[i[1],i[2]],[r[1],r[2]],a,o);return[l,u]}case"AvgPool3D":{const r=CS("strides",e,t,n),a=CS("pad",e,t,n),i=CS("kernelSize",e,t,n);return[s.avgPool3d(CS("x",e,t,n),[i[1],i[2],i[3]],[r[1],r[2],r[3]],a)]}case"MaxPool3D":{const r=CS("strides",e,t,n),a=CS("pad",e,t,n),i=CS("kernelSize",e,t,n);return[s.maxPool3d(CS("x",e,t,n),[i[1],i[2],i[3]],[r[1],r[2],r[3]],a)]}case"Dilation2D":{const r=CS("strides",e,t,n),a=CS("pad",e,t,n),i=CS("dilations",e,t,n),o=r[1],l=r[2],u=i[1],c=i[2];return[s.dilation2d(CS("x",e,t,n),CS("filter",e,t,n),[o,l],a,[u,c],"NHWC")]}default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"creation":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"Fill":{const r=CS("shape",e,t,n),a=CS("dtype",e,t,n),i=CS("value",e,t,n);return[s.fill(r,i,a)]}case"LinSpace":{const r=CS("start",e,t,n),a=CS("stop",e,t,n),i=CS("num",e,t,n);return[s.linspace(r,a,i)]}case"Multinomial":{const r=CS("logits",e,t,n),a=CS("numSamples",e,t,n),i=CS("seed",e,t,n);return[s.multinomial(r,a,i)]}case"OneHot":{const r=CS("indices",e,t,n),a=CS("depth",e,t,n),i=CS("onValue",e,t,n),o=CS("offValue",e,t,n),l=CS("dtype",e,t,n);return[s.oneHot(r,a,i,o,l)]}case"Ones":return[s.ones(CS("shape",e,t,n),CS("dtype",e,t,n))];case"OnesLike":return[s.onesLike(CS("x",e,t,n))];case"RandomStandardNormal":return[s.randomStandardNormal(CS("shape",e,t,n),CS("dtype",e,t,n),CS("seed",e,t,n))];case"RandomUniform":return[s.randomUniform(CS("shape",e,t,n),CS("minval",e,t,n),CS("maxval",e,t,n),CS("dtype",e,t,n))];case"RandomUniformInt":return[s.randomUniformInt(CS("shape",e,t,n),CS("minval",e,t,n),CS("maxval",e,t,n),CS("seed",e,t,n))];case"Range":{const r=CS("start",e,t,n),a=CS("stop",e,t,n),i=CS("step",e,t,n);return[s.range(r,a,i,CS("dtype",e,t,n))]}case"TruncatedNormal":{const r=CS("shape",e,t,n),a=CS("mean",e,t,n),i=CS("stdDev",e,t,n),o=CS("seed",e,t,n);return[s.truncatedNormal(r,a,i,CS("dtype",e,t,n),o)]}case"Zeros":return[s.zeros(CS("shape",e,t,n),CS("dtype",e,t,n))];case"ZerosLike":return[s.zerosLike(CS("x",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"dynamic":return(async(e,t,n,s,r=G)=>{switch(e.op){case"NonMaxSuppressionV5":{const{boxes:s,scores:a,maxOutputSize:i,iouThreshold:o,scoreThreshold:l,softNmsSigma:u}=NT(e,t,n),c=await r.image.nonMaxSuppressionWithScoreAsync(s,a,i,o,l,u);return[c.selectedIndices,c.selectedScores]}case"NonMaxSuppressionV4":{const{boxes:s,scores:a,maxOutputSize:i,iouThreshold:o,scoreThreshold:l}=NT(e,t,n),u=CS("padToMaxOutputSize",e,t,n),c=await r.image.nonMaxSuppressionPaddedAsync(s,a,i,o,l,u);return[c.selectedIndices,c.validOutputs]}case"NonMaxSuppressionV3":case"NonMaxSuppressionV2":{const{boxes:s,scores:a,maxOutputSize:i,iouThreshold:o,scoreThreshold:l}=NT(e,t,n);return[await r.image.nonMaxSuppressionAsync(s,a,i,o,l)]}case"Where":{const s=r.cast(CS("condition",e,t,n),"bool"),a=[await r.whereAsync(s)];return s.dispose(),a}case"ListDiff":return r.setdiff1dAsync(CS("x",e,t,n),CS("y",e,t,n));default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n);case"evaluation":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"LowerBound":{const r=CS("sortedSequence",e,t,n),a=CS("values",e,t,n);return[s.lowerBound(r,a)]}case"TopKV2":{const r=CS("x",e,t,n),a=CS("k",e,t,n),i=CS("sorted",e,t,n),o=s.topk(r,a,i);return[o.values,o.indices]}case"UpperBound":{const r=CS("sortedSequence",e,t,n),a=CS("values",e,t,n);return[s.upperBound(r,a)]}case"Unique":{const r=CS("x",e,t,n),a=s.unique(r);return[a.values,a.indices]}case"UniqueV2":{const r=CS("x",e,t,n),a=CS("axis",e,t,n),i=s.unique(r,a);return[i.values,i.indices]}default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"image":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"ResizeBilinear":{const r=CS("images",e,t,n),a=CS("size",e,t,n),i=CS("alignCorners",e,t,n),o=CS("halfPixelCenters",e,t,n);return[s.image.resizeBilinear(r,[a[0],a[1]],i,o)]}case"ResizeNearestNeighbor":{const r=CS("images",e,t,n),a=CS("size",e,t,n),i=CS("alignCorners",e,t,n),o=CS("halfPixelCenters",e,t,n);return[s.image.resizeNearestNeighbor(r,[a[0],a[1]],i,o)]}case"CropAndResize":{const r=CS("image",e,t,n),a=CS("boxes",e,t,n),i=CS("boxInd",e,t,n),o=CS("cropSize",e,t,n),l=CS("method",e,t,n),u=CS("extrapolationValue",e,t,n);return[s.image.cropAndResize(r,a,i,o,l,u)]}case"ImageProjectiveTransformV3":{const r=CS("images",e,t,n),a=CS("transforms",e,t,n),i=CS("outputShape",e,t,n),o=CS("fillValue",e,t,n),l=CS("interpolation",e,t,n),u=CS("fillMode",e,t,n);return[s.image.transform(r,a,l.toLowerCase(),u.toLowerCase(),o,i)]}default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"graph":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"Const":return t[e.name];case"PlaceholderWithDefault":const r=CS("default",e,t,n);return[$S(e.name,t,n)||r];case"Placeholder":return[$S(e.name,t,n)];case"Identity":case"StopGradient":case"FakeQuantWithMinMaxVars":case"Snapshot":return[DS(CS("x",e,t,n))];case"IdentityN":return CS("x",e,t,n).map((e=>DS(e)));case"Shape":return[s.tensor1d(CS("x",e,t,n).shape,"int32")];case"ShapeN":return CS("x",e,t,n).map((e=>s.tensor1d(e.shape)));case"Size":return[s.scalar(CS("x",e,t,n).size,"int32")];case"Rank":return[s.scalar(CS("x",e,t,n).rank,"int32")];case"NoOp":return[s.scalar(1)];case"Print":const a=CS("x",e,t,n),i=CS("data",e,t,n),o=CS("message",e,t,n),l=CS("summarize",e,t,n);console.warn("The graph has a tf.print() operation,usually used for debugging, which slows down performance."),console.log(o);for(let e=0;e<i.length;e++)console.log(Array.prototype.slice.call(i[e].dataSync()).slice(0,l));return[a];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"logical":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"Equal":return[s.equal(CS("a",e,t,n),CS("b",e,t,n))];case"NotEqual":return[s.notEqual(CS("a",e,t,n),CS("b",e,t,n))];case"Greater":return[s.greater(CS("a",e,t,n),CS("b",e,t,n))];case"GreaterEqual":return[s.greaterEqual(CS("a",e,t,n),CS("b",e,t,n))];case"Less":return[s.less(CS("a",e,t,n),CS("b",e,t,n))];case"LessEqual":return[s.lessEqual(CS("a",e,t,n),CS("b",e,t,n))];case"LogicalAnd":return[s.logicalAnd(CS("a",e,t,n),CS("b",e,t,n))];case"LogicalNot":return[s.logicalNot(CS("a",e,t,n))];case"LogicalOr":return[s.logicalOr(CS("a",e,t,n),CS("b",e,t,n))];case"Select":case"SelectV2":return[s.where(CS("condition",e,t,n),CS("a",e,t,n),CS("b",e,t,n))];case"BitwiseAnd":return[s.bitwiseAnd(CS("a",e,t,n),CS("b",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"matrices":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"BatchMatMul":case"BatchMatMulV2":case"MatMul":return[s.matMul(CS("a",e,t,n),CS("b",e,t,n),CS("transposeA",e,t,n),CS("transposeB",e,t,n))];case"Einsum":return[s.einsum(CS("equation",e,t,n),...CS("tensors",e,t,n))];case"Transpose":return[s.transpose(CS("x",e,t,n),CS("perm",e,t,n))];case"_FusedMatMul":const[r,a]=CS("fusedOps",e,t,n),i="biasadd"===r,o="prelu"===a,l=CS("numArgs",e,t,n),u=CS("leakyreluAlpha",e,t,n);if(i){if(o&&2!==l)throw new Error("Fused MatMul with BiasAdd and Prelu must have two extra arguments: bias and alpha.");if(!o&&1!==l)throw new Error("Fused MatMul with BiasAdd must have one extra argument: bias.")}const[c,h]=CS("args",e,t,n);return[s.fused.matMul({a:CS("a",e,t,n),b:CS("b",e,t,n),transposeA:CS("transposeA",e,t,n),transposeB:CS("transposeB",e,t,n),bias:c,activation:a,preluActivationWeights:h,leakyreluAlpha:u})];case"MatrixBandPart":return[s.linalg.bandPart(CS("a",e,t,n),CS("numLower",e,t,n),CS("numUpper",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"normalization":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"EuclideanNorm":return[s.euclideanNorm(CS("x",e,t,n),CS("axis",e,t,n),CS("keepDims",e,t,n))];case"FusedBatchNorm":case"FusedBatchNormV2":case"FusedBatchNormV3":return[s.batchNorm(CS("x",e,t,n),CS("mean",e,t,n),CS("variance",e,t,n),CS("offset",e,t,n),CS("scale",e,t,n),CS("epsilon",e,t,n))];case"LRN":return[s.localResponseNormalization(CS("x",e,t,n),CS("radius",e,t,n),CS("bias",e,t,n),CS("alpha",e,t,n),CS("beta",e,t,n))];case"Softmax":return[s.softmax(CS("x",e,t,n))];case"LogSoftmax":return[s.logSoftmax(CS("x",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"ragged":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"RaggedGather":{const{outputNestedSplits:r,outputDenseValues:a}=s.raggedGather(CS("paramsNestedSplits",e,t,n),CS("paramsDenseValues",e,t,n),CS("indices",e,t,n),CS("outputRaggedRank",e,t,n));return r.concat(a)}case"RaggedRange":{const{rtNestedSplits:r,rtDenseValues:a}=s.raggedRange(CS("starts",e,t,n),CS("limits",e,t,n),CS("splits",e,t,n));return[r,a]}case"RaggedTensorToTensor":return[s.raggedTensorToTensor(CS("shape",e,t,n),CS("values",e,t,n),CS("defaultValue",e,t,n),CS("rowPartitionTensors",e,t,n),CS("rowPartitionTypes",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"reduction":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"Max":{const r=CS("axis",e,t,n),a=CS("keepDims",e,t,n);return[s.max(CS("x",e,t,n),r,a)]}case"Mean":{const r=CS("axis",e,t,n),a=CS("keepDims",e,t,n);return[s.mean(CS("x",e,t,n),r,a)]}case"Min":{const r=CS("axis",e,t,n),a=CS("keepDims",e,t,n);return[s.min(CS("x",e,t,n),r,a)]}case"Sum":{const r=CS("axis",e,t,n),a=CS("keepDims",e,t,n);return[s.sum(CS("x",e,t,n),r,a)]}case"All":{const r=CS("axis",e,t,n),a=CS("keepDims",e,t,n);return[s.all(CS("x",e,t,n),r,a)]}case"Any":{const r=CS("axis",e,t,n),a=CS("keepDims",e,t,n);return[s.any(CS("x",e,t,n),r,a)]}case"ArgMax":{const r=CS("axis",e,t,n);return[s.argMax(CS("x",e,t,n),r)]}case"ArgMin":{const r=CS("axis",e,t,n);return[s.argMin(CS("x",e,t,n),r)]}case"Prod":{const r=CS("axis",e,t,n),a=CS("keepDims",e,t,n);return[s.prod(CS("x",e,t,n),r,a)]}case"Cumprod":{const r=CS("axis",e,t,n),a=CS("exclusive",e,t,n),i=CS("reverse",e,t,n);return[s.cumprod(CS("x",e,t,n),r,a,i)]}case"Cumsum":{const r=CS("axis",e,t,n),a=CS("exclusive",e,t,n),i=CS("reverse",e,t,n);return[s.cumsum(CS("x",e,t,n),r,a,i)]}case"Bincount":const r=CS("x",e,t,n),a=CS("weights",e,t,n),i=CS("size",e,t,n);return[s.bincount(r,a,i)];case"DenseBincount":{const r=CS("x",e,t,n),a=CS("weights",e,t,n),i=CS("size",e,t,n),o=CS("binaryOutput",e,t,n);return[s.denseBincount(r,a,i,o)]}default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"slice_join":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"ConcatV2":case"Concat":{const r=CS("n",e,t,n),a=CS("axis",e,t,n);let i=CS("tensors",e,t,n);return i=i.slice(0,r),[s.concat(i,a)]}case"Gather":{const r=CS("x",e,t,n),a=CS("indices",e,t,n);return[s.gather(r,s.cast(a,"int32"),0)]}case"GatherV2":{const r=CS("axis",e,t,n),a=CS("batchDims",e,t,n),i=CS("x",e,t,n),o=CS("indices",e,t,n);return[s.gather(i,s.cast(o,"int32"),r,a)]}case"Reverse":{const r=CS("dims",e,t,n),a=[];for(let e=0;e<r.length;e++)r[e]&&a.push(e);const i=CS("x",e,t,n);return[s.reverse(i,a)]}case"ReverseV2":{const r=CS("axis",e,t,n),a=CS("x",e,t,n);return[s.reverse(a,r)]}case"Slice":{const r=CS("begin",e,t,n),a=CS("size",e,t,n);return[s.slice(CS("x",e,t,n),r,a)]}case"StridedSlice":{const r=CS("begin",e,t,n),a=CS("end",e,t,n),i=CS("strides",e,t,n),o=CS("beginMask",e,t,n),l=CS("endMask",e,t,n),u=CS("ellipsisMask",e,t,n),c=CS("newAxisMask",e,t,n),h=CS("shrinkAxisMask",e,t,n),p=CS("x",e,t,n);return[s.stridedSlice(p,r,a,i,o,l,u,c,h)]}case"Pack":return fo((()=>{const r=CS("axis",e,t,n),a=CS("tensors",e,t,n),i=a[0].shape,o=s.squeeze(a[0]).shape,l=a.map((e=>{const t=pe(e.shape,i);if(!t&&!pe(s.squeeze(e).shape,o))throw new Error("the input tensors shape does not match");return t?e:s.reshape(e,i)}));return[s.stack(l,r)]}));case"Unpack":{const r=CS("axis",e,t,n),a=CS("tensor",e,t,n);return s.unstack(a,r)}case"Tile":{const r=CS("reps",e,t,n);return[s.tile(CS("x",e,t,n),r)]}case"Split":case"SplitV":{const r=CS("axis",e,t,n),a=CS("numOrSizeSplits",e,t,n),i=CS("x",e,t,n);return s.split(i,a,r)}case"ScatterNd":{const r=CS("indices",e,t,n),a=CS("values",e,t,n),i=CS("shape",e,t,n);return[s.scatterND(r,a,i)]}case"GatherNd":{const r=CS("x",e,t,n),a=CS("indices",e,t,n);return[s.gatherND(r,a)]}case"SparseToDense":{const r=CS("sparseIndices",e,t,n),a=CS("outputShape",e,t,n),i=CS("sparseValues",e,t,n),o=CS("defaultValue",e,t,n);return[s.sparseToDense(r,i,a,i.dtype===o.dtype?o:s.cast(o,i.dtype))]}case"TensorScatterUpdate":{const r=CS("indices",e,t,n),a=CS("values",e,t,n),i=CS("tensor",e,t,n);return[s.tensorScatterUpdate(i,r,a)]}default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"sparse":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"SparseFillEmptyRows":{const{outputIndices:r,outputValues:a,emptyRowIndicator:i,reverseIndexMap:o}=s.sparse.sparseFillEmptyRows(CS("indices",e,t,n),CS("values",e,t,n),CS("denseShape",e,t,n),CS("defaultValue",e,t,n));return[r,a,i,o]}case"SparseReshape":{const{outputIndices:r,outputShape:a}=s.sparse.sparseReshape(CS("inputIndices",e,t,n),CS("inputShape",e,t,n),CS("newShape",e,t,n));return[r,a]}case"SparseSegmentMean":return[s.sparse.sparseSegmentMean(CS("data",e,t,n),CS("indices",e,t,n),CS("segmentIds",e,t,n))];case"SparseSegmentSum":return[s.sparse.sparseSegmentSum(CS("data",e,t,n),CS("indices",e,t,n),CS("segmentIds",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"spectral":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"FFT":return[s.fft(CS("x",e,t,n))];case"IFFT":return[s.ifft(CS("x",e,t,n))];case"RFFT":return[s.rfft(CS("x",e,t,n))];case"IRFFT":return[s.irfft(CS("x",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"string":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"StaticRegexReplace":return[s.string.staticRegexReplace(CS("input",e,t,n),CS("pattern",e,t,n),CS("rewrite",e,t,n),CS("replaceGlobal",e,t,n))];case"StringNGrams":{const{nGrams:r,nGramsSplits:a}=s.string.stringNGrams(CS("data",e,t,n),CS("dataSplits",e,t,n),CS("separator",e,t,n),CS("nGramWidths",e,t,n),CS("leftPad",e,t,n),CS("rightPad",e,t,n),CS("padWidth",e,t,n),CS("preserveShortSequences",e,t,n));return[r,a]}case"StringSplit":{const{indices:r,values:a,shape:i}=s.string.stringSplit(CS("input",e,t,n),CS("delimiter",e,t,n),CS("skipEmpty",e,t,n));return[r,a,i]}case"StringToHashBucketFast":return[s.string.stringToHashBucketFast(CS("input",e,t,n),CS("numBuckets",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"transformation":return r((()=>((e,t,n,s=G)=>{switch(e.op){case"Cast":return[s.cast(CS("x",e,t,n),CS("dtype",e,t,n))];case"ExpandDims":{const r=CS("axis",e,t,n);return[s.expandDims(CS("x",e,t,n),r)]}case"Squeeze":{const r=CS("axis",e,t,n);return[s.squeeze(CS("x",e,t,n),r)]}case"Reshape":return[s.reshape(CS("x",e,t,n),CS("shape",e,t,n))];case"EnsureShape":return[s.ensureShape(CS("x",e,t,n),CS("shape",e,t,n))];case"MirrorPad":return[s.mirrorPad(CS("x",e,t,n),CS("padding",e,t,n),CS("mode",e,t,n))];case"PadV2":case"Pad":return[s.pad(CS("x",e,t,n),CS("padding",e,t,n),CS("constantValue",e,t,n))];case"SpaceToBatchND":{const r=CS("blockShape",e,t,n),a=CS("paddings",e,t,n);return[s.spaceToBatchND(CS("x",e,t,n),r,a)]}case"BatchToSpaceND":{const r=CS("blockShape",e,t,n),a=CS("crops",e,t,n);return[s.batchToSpaceND(CS("x",e,t,n),r,a)]}case"DepthToSpace":{const r=CS("blockSize",e,t,n),a=CS("dataFormat",e,t,n).toUpperCase();return[s.depthToSpace(CS("x",e,t,n),r,a)]}case"BroadcastTo":return[s.broadcastTo(CS("x",e,t,n),CS("shape",e,t,n))];case"BroadcastArgs":return[s.broadcastArgs(CS("s0",e,t,n),CS("s1",e,t,n))];default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n)));case"hash_table":return(async(e,t,n,s)=>{switch(e.op){case"HashTable":case"HashTableV2":{const r=s.getHashTableHandleByName(e.name);if(null!=r)return[r];{const r=CS("keyDType",e,t,n),a=CS("valueDType",e,t,n),i=new ST(r,a);return s.addHashTable(e.name,i),[i.handle]}}case"InitializeTable":case"InitializeTableV2":case"LookupTableImport":case"LookupTableImportV2":{const r=CS("tableHandle",e,t,n,s),a=CS("keys",e,t,n),i=CS("values",e,t,n),o=s.getHashTableById(r.id);return[await o.import(a,i)]}case"LookupTableFind":case"LookupTableFindV2":{const r=CS("tableHandle",e,t,n,s),a=CS("keys",e,t,n),i=CS("defaultValue",e,t,n),o=s.getHashTableById(r.id);return[await o.find(a,i)]}case"LookupTableSize":case"LookupTableSizeV2":{const r=CS("tableHandle",e,t,n,s);return[s.getHashTableById(r.id).tensorSize()]}default:throw TypeError(`Node type ${e.op} is not implemented`)}})(e,t,n,s);case"custom":const a=SS(e.op);if(a&&a.customExecutor)return a.customExecutor(new mT(e,t,n));throw TypeError(`Custom op ${e.op} is not registered.`);default:throw TypeError(`Unknown op '${e.op}'. File an issue at https://github.com/tensorflow/tfjs/issues so we can add it, or register a custom execution with tf.registerOp()`)}})(e,t,n);return He(a)?a.then((e=>[].concat(e))):[].concat(a)}class CT{constructor(e={},t={},n={},s={},r){this.weightMap=e,this.tensorArrayMap=t,this.tensorListMap=n,this.functionMap=s,this.parseNodeNameCache=r,this.rootContext={id:0,frameName:"",iterationId:0},this.contexts=[this.rootContext],this.lastId=0,this.generateCurrentContextIds()}newFrame(e,t){return{id:e,frameName:t,iterationId:0}}set currentContext(e){this.contexts!==e&&(this.contexts=e,this.generateCurrentContextIds())}get currentContext(){return this.contexts}get currentContextId(){return this._currentContextIds[0]}get currentContextIds(){return this._currentContextIds}generateCurrentContextIds(){const e=[];for(let t=0;t<this.contexts.length-1;t++){const n=this.contexts.slice(0,this.contexts.length-t);e.push(this.contextIdforContexts(n))}e.push(""),this._currentContextIds=e}contextIdforContexts(e){return e?e.map((e=>0===e.id&&0===e.iterationId?"":`${e.frameName}-${e.iterationId}`)).join("/"):""}enterFrame(e){this.contexts&&(this.lastId++,this.contexts=this.contexts.slice(),this.contexts.push(this.newFrame(this.lastId,e)),this._currentContextIds.unshift(this.contextIdforContexts(this.contexts)))}exitFrame(){if(!(this.contexts&&this.contexts.length>1))throw new Error("Cannot exit frame, the context is empty");this.contexts=this.contexts.slice(),this.contexts.splice(-1),this.currentContextIds.shift()}nextIteration(){if(!(this.contexts&&this.contexts.length>0))throw new Error("Cannot increase frame iteration, the context is empty");{this.contexts=this.contexts.slice(),this.lastId++;const e=Object.assign({},this.contexts[this.contexts.length-1]);e.iterationId+=1,e.id=this.lastId,this.contexts.splice(-1,1,e),this._currentContextIds.splice(0,1,this.contextIdforContexts(this.contexts))}}getWeight(e){return this.weightMap[e]}addTensorArray(e){this.tensorArrayMap[e.id]=e}getTensorArray(e){return this.tensorArrayMap[e]}addTensorList(e){this.tensorListMap[e.id]=e}getTensorList(e){return this.tensorListMap[e]}dispose(e){for(const t in this.tensorArrayMap)this.tensorArrayMap[t].clearAndClose(e);for(const t in this.tensorListMap)this.tensorListMap[t].clearAndClose(e)}}function $T(e,t,n,s){const r=new Set,a=[];let i=null,o=null;const l=new Set,u=new Set(Object.keys(e).map((e=>FS(e)[0])));s=s||[];const c=new Set(s.map((e=>FS(e.name)[0]))),h=[...t];for(;h.length>0;){const e=h.pop();(DT(e)||OT(e)||MT(e))&&null==i&&(i=e,o=i.children.map((e=>e.name)).filter((e=>r.has(e)))),r.add(e.name),null==n[e.name]&&(u.has(e.name)||c.has(e.name)||(0!==e.inputs.length?e.inputs.forEach((e=>{l.has(e.name)||(l.add(e.name),h.push(e))})):a.push(e.name)))}return{inputs:e,outputs:t,usedNodes:r,missingInputs:a,dynamicNode:i,syncInputs:o}}function ET(e,t){const{usedNodes:n,inputs:s}=t,r=Object.keys(s).map((e=>FS(e)[0])).map((t=>e.nodes[t])),a=e.initNodes||[],i=e=>n.has("string"==typeof e?e:e.name);function o(e){return[...new Map(e.map((e=>[e.name,e]))).values()]}const l=o([...r,...e.weights,...a]).filter(i),u=o([...l,...Object.values(e.nodes)]).filter(i),c=new Map(u.map((e=>[e.name,e]))),h={};for(const e of u){h[e.name]=h[e.name]||0;for(const t of e.children)i(t)||(h[t.name]=Number.POSITIVE_INFINITY),h[t.name]=(h[t.name]||0)+1}const p=Object.entries(h).filter((([,e])=>0===e)).map((([e])=>e)),d=[...p];for(;p.length>0;){const e=p.pop(),t=c.get(e);for(const e of t.children.filter(i))0==--h[e.name]&&(d.push(e.name),p.push(e.name))}const f=function(e,t){const n=new Map(e.map((e=>[e.name,e]))),s=t.map((e=>e.name)),r=new Set(s);for(;s.length>0;){const e=s.pop(),t=n.get(e);for(const e of t.children)n.has(e.name)&&!r.has(e.name)&&(r.add(e.name),s.push(e.name))}const a=e.filter((e=>r.has(e.name)));return a}(d.map((e=>c.get(e))),l);return function(e,t){const n=new Map(e.map(((e,t)=>[e.name,t]))),s=new Set(t.map((e=>e.name))),r=e=>s.has("string"==typeof e?e:e.name),a=new Set(e.map((e=>e.name))),i=e=>a.has("string"==typeof e?e:e.name);for(const t of e){for(const e of t.children.filter(i)){if(!n.has(e.name))throw new AT(`Child ${e.name} of node ${t.name} is unreachable.`);if(n.get(t.name)>n.get(e.name))throw new AT(`Node ${t.name} is scheduled to run after its child ${e.name}.`)}if(!r(t))for(const e of t.inputs){if(!n.has(e.name))throw new AT(`Input ${e.name} of node ${t.name} is unreachable.`);if(n.get(e.name)>n.get(t.name))throw new AT(`Node ${t.name} is scheduled to run before its input ${e.name}.`)}}}(f,l),f}class AT extends Error{constructor(e){super(`NodesExecutionOrderError: ${e}`)}}const RT=new Set(["Switch","Merge","Enter","Exit","NextIteration","StatelessIf","StatelessWhile","if","While"]),FT=new Set(["NonMaxSuppressionV2","NonMaxSuppressionV3","NonMaxSuppressionV5","Where"]),_T=new Set(["HashTable","HashTableV2","LookupTableImport","LookupTableImportV2","LookupTableFind","LookupTableFindV2","LookupTableSize","LookupTableSizeV2"]);function DT(e){return RT.has(e.op)}function OT(e){return FT.has(e.op)}function MT(e){return _T.has(e.op)}class LT{get weightIds(){return this.parent?this.parent.weightIds:this._weightIds}get functionExecutorMap(){return this.parent?this.parent.functionExecutorMap:this._functionExecutorMap}get weightMap(){return this.parent?this.parent.weightMap:this._weightMap}set weightMap(e){const t=Object.keys(e).map((t=>e[t].map((e=>e.id))));this._weightIds=[].concat(...t),this._weightMap=e}set resourceManager(e){this._resourceManager=e}get inputs(){return this._inputs.map((e=>({name:e.name,shape:e.attrParams.shape?e.attrParams.shape.value:void 0,dtype:e.attrParams.dtype?e.attrParams.dtype.value:void 0})))}get outputs(){return this._outputs.map((e=>({name:e.name,shape:e.attrParams.shape?e.attrParams.shape.value:void 0,dtype:e.attrParams.dtype?e.attrParams.dtype.value:void 0})))}get inputNodes(){return this._inputs.map((e=>e.signatureKey||e.name))}get outputNodes(){return this._outputs.map((e=>{const t=e.signatureKey||e.name;return e.defaultOutput?`${t}:${e.defaultOutput}`:t}))}get functions(){return Object.keys(this._functions).reduce(((e,t)=>(e[t]=this._functions[t].signature,e)),{})}constructor(e,t){this.graph=e,this.parent=t,this.compiledMap=new Map,this.parseNodeNameCache=new Map,this._weightMap={},this.SEPARATOR=",",this._functions={},this._functionExecutorMap={},this.keepIntermediateTensors=!1,this._outputs=e.outputs,this._inputs=e.inputs,this._initNodes=e.initNodes,this._signature=e.signature,this._functions=e.functions,null!=e.functions&&Object.keys(e.functions).forEach((t=>{this._functionExecutorMap[t]=new LT(e.functions[t],this)}))}getCompilationKey(e,t){const n=e.map((e=>e.name)).sort(),s=t.map((e=>e.name)).sort();return n.join(this.SEPARATOR)+"--"+s.join(this.SEPARATOR)}compile(e,t){const n=$T(e,t,this.weightMap,this._initNodes),{missingInputs:s,dynamicNode:r,syncInputs:a}=n;if(null!=r)throw new Error(`This execution contains the node '${r.name}', which has the dynamic op '${r.op}'. Please use model.executeAsync() instead. Alternatively, to avoid the dynamic ops, specify the inputs [${a}]`);if(s.length>0){const n=t.map((e=>e.name)),r=Object.keys(e);throw new Error(`Cannot compute the outputs [${n}] from the provided inputs [${r}]. Missing the following inputs: [${s}]`)}const i=ET(this.graph,n),o=function(e){const t=new Map(e.map(((e,t)=>[e.name,t]))),n=Number.MAX_SAFE_INTEGER,s=e.map(((e,t)=>DT(e)?n:t)),r=e=>{const n=s[t.get(e.name)];return null==n?-1:n},a=e.map(((e,t)=>e.children.map(r).reduce(((e,t)=>Math.max(e,t)),s[t]))),i=new Map;for(let t=0;t<e.length;++t){const s=a[t];if(s===n)continue;const r=e[t],o=e[s];i.has(o.name)||i.set(o.name,[]),i.get(o.name).push(r)}return i}(i);return{orderedNodes:i,nodeLiveUntilMap:o}}cloneAndKeepTensor(e){if(null==e)return null;const t=e.clone();return go(t),t}cloneTensorList(e){if(!e)return null;const t=e.map((e=>this.cloneAndKeepTensor(e)));return t}cloneTensorMap(e){return Object.fromEntries(Object.entries(e).map((([e,t])=>[e,this.cloneTensorList(t)])))}execute(e,t){this.disposeIntermediateTensors(),e=this.mapInputs(e);const n=Object.keys(e).sort();this.checkInputs(e),this.checkInputShapeAndType(e),t=this.mapOutputs(t),this.checkOutputs(t);const s=n.map((e=>this.graph.nodes[FS(e)[0]])),r=t.map((e=>FS(e)[0])),a=new Set(r);let i=r.map((e=>this.graph.nodes[e]));0===i.length&&(i=this._outputs);const o=this.getCompilationKey(s,i);let l=this.compiledMap.get(o);null==l&&(l=this.compile(e,i),this.compiledMap.set(o,l));try{this.keepIntermediateTensors=Xe().getBool("KEEP_INTERMEDIATE_TENSORS")}catch(e){this.keepIntermediateTensors=!1,console.warn(e.message)}const u={},c={};return fo((()=>{const n=new CT(this.weightMap,u,c,this.functionExecutorMap,this.parseNodeNameCache),s=Object.assign({},this.weightMap);this.keepIntermediateTensors&&(this.clonedTensorsMap=this.cloneTensorMap(this.weightMap)),Object.keys(e).forEach((t=>{const[r,a]=FS(t,n),i=[];i[a]=e[t],s[r]=i,this.keepIntermediateTensors&&(this.clonedTensorsMap[r]=this.cloneTensorList(i))}));const r=this.getFrozenTensorIds(s),{orderedNodes:i,nodeLiveUntilMap:o}=l;for(const e of i){if(s[e.name])continue;const t=TT(e,s,n,this._resourceManager);if(He(t))throw new Error(`The execution of the op '${e.op}' returned a promise. Please use model.executeAsync() instead.`);s[e.name]=t,this.keepIntermediateTensors&&(this.clonedTensorsMap[e.name]=this.cloneTensorList(t)),this.checkTensorForDisposalWithNodeLiveUntilInfo(e,s,n,r,a,o.get(e.name))}return null==this.parent&&n.dispose(r),t.map((e=>$S(e,s,n)))}))}getFrozenTensorIds(e){const t=[].concat.apply([],Object.keys(e).map((t=>e[t])).map((e=>e.map((e=>e.id)))));return new Set(t)}checkTensorForDisposal(e,t,n,s,r,a,i){if(!DT(t)&&!a.has(e)){for(const s of n[e])null!=s&&(i[s.id]=(i[s.id]||0)+t.children.length);for(const e of t.inputs){if(DT(e))continue;const t=ES(e.name,n,s);if(null!=t)for(const e of t){if(!e||e.kept||r.has(e.id))continue;const t=i[e.id];1===t?(e.dispose(),delete i[e.id]):null!=t&&i[e.id]--}}}}checkTensorForDisposalWithNodeLiveUntilInfo(e,t,n,s,r,a){function i(e){return DT(e)||r.has(e.name)}if(!DT(e)&&null!=a)for(const e of a){if(i(e))continue;const r=ES(e.name,t,n);for(const e of r)!e||e.kept||s.has(e.id)||e.dispose()}}async executeAsync(e,t){return this._executeAsync(e,t)}disposeIntermediateTensors(){this.clonedTensorsMap&&(Object.values(this.clonedTensorsMap).forEach((e=>{for(const t of e)t&&!t.isDisposed&&t.dispose()})),this.clonedTensorsMap=null)}getIntermediateTensors(){return this.clonedTensorsMap}async _executeAsync(e,t,n=!1,s={},r={}){this.disposeIntermediateTensors(),n||(e=this.mapInputs(e),this.checkInputs(e),this.checkInputShapeAndType(e),t=this.mapOutputs(t),this.checkOutputs(t));try{this.keepIntermediateTensors=Xe().getBool("KEEP_INTERMEDIATE_TENSORS")}catch(e){this.keepIntermediateTensors=!1,console.warn(e.message)}const a=new CT(this.weightMap,s,r,this.functionExecutorMap,this.parseNodeNameCache);this.keepIntermediateTensors&&(this.clonedTensorsMap=this.cloneTensorMap(this.weightMap));const i=await this.executeWithControlFlow(e,a,t,n),o=t.map((e=>$S(e,i,a))),l=o.map((e=>e.id)),u=Object.keys(e).map((t=>e[t].id)),c=new Set([...l,...u,...this.weightIds]);return Object.values(i).forEach((e=>{e.forEach((e=>{!e||e.isDisposed||c.has(e.id)||e.dispose()}))})),null==this.parent&&a.dispose(c),o}async executeFunctionAsync(e,t,n){const s=e.reduce(((e,t,n)=>(e[this.inputs[n].name]=t,e)),{});return this._executeAsync(s,this.outputNodes,!0,t,n)}async executeWithControlFlow(e,t,n,s){const r=Object.keys(e),a=r.map((e=>this.graph.nodes[FS(e)[0]])),i=n.map((e=>FS(e)[0])),o=new Set(i);let l=i.map((e=>this.graph.nodes[e]));0===l.length&&(l=this._outputs);const{usedNodes:u,missingInputs:c,dynamicNode:h,syncInputs:p}=$T(e,l,this.weightMap,this._initNodes),d=[...a,...this.graph.weights,...this._initNodes||[]].map((e=>({node:e,contexts:t.currentContext}))),f=Object.assign({},this.weightMap);Object.keys(e).forEach((t=>{const[n,s]=FS(t),r=[];r[s]=e[t],f[n]=r}));const m={},g=this.getFrozenTensorIds(f),y={};for(;d.length>0;){const e=this.processStack(a,d,t,f,y,g,o,m,u);await Promise.all(e)}null!=h||s||console.warn("This model execution did not contain any nodes with control flow or dynamic output shapes. You can use model.execute() instead.");const b=l.filter((e=>!DT(e)&&!$S(e.name,f,t))).map((e=>e.name));if(b.length>0){let e="";throw null!=h&&(e=`Alternatively, to avoid the dynamic ops, use model.execute() and specify the inputs [${p}]`),new Error(`Cannot compute the outputs [${b}] from the provided inputs [${r}]. Consider providing the following inputs: [${c}]. ${e}`)}return f}processStack(e,t,n,s,r,a,i,o,l){const u=[];for(;t.length>0;){const e=t.pop();n.currentContext=e.contexts;let c="";if("Enter"===e.node.op&&CS("isConstant",e.node,s,n)&&([c]=AS(e.node.name,n)),null==s[e.node.name]){const h=TT(e.node,s,n,this._resourceManager);c||([c]=AS(e.node.name,n));const p=n.currentContext;He(h)?u.push(h.then((u=>(s[c]=u,this.keepIntermediateTensors&&(this.clonedTensorsMap[c]=this.cloneTensorList(u)),n.currentContext=p,this.checkTensorForDisposal(c,e.node,s,n,a,i,o),this.processChildNodes(e.node,t,n,s,r,l),u)))):(s[c]=h,this.keepIntermediateTensors&&(this.clonedTensorsMap[c]=this.cloneTensorList(h)),this.checkTensorForDisposal(c,e.node,s,n,a,i,o),this.processChildNodes(e.node,t,n,s,r,l))}else this.processChildNodes(e.node,t,n,s,r,l)}return u}processChildNodes(e,t,n,s,r,a){e.children.forEach((e=>{const[i]=AS(e.name,n);!r[i]&&a.has(e.name)&&("Merge"===e.op?e.inputNames.some((e=>!!$S(e,s,n)))&&(r[i]=!0,t.push({contexts:n.currentContext,node:e})):e.inputNames.every((e=>!!$S(e,s,n)))&&(r[i]=!0,t.push({contexts:n.currentContext,node:e})))}))}dispose(){Object.keys(this.weightMap).forEach((e=>this.weightMap[e].forEach((e=>e.dispose()))))}checkInputShapeAndType(e){Object.keys(e).forEach((t=>{const n=e[t],[s]=FS(t),r=this.graph.nodes[s];if(r.attrParams.shape&&r.attrParams.shape.value){const e=r.attrParams.shape.value;ie(e.length===n.shape.length&&n.shape.every(((t,n)=>-1===e[n]||e[n]===t)),(()=>`The shape of dict['${r.name}'] provided in model.execute(dict) must be [${e}], but was [${n.shape}]`))}r.attrParams.dtype&&r.attrParams.dtype.value&&ie(n.dtype===r.attrParams.dtype.value,(()=>`The dtype of dict['${r.name}'] provided in model.execute(dict) must be ${r.attrParams.dtype.value}, but was ${n.dtype}`))}))}mapInputs(e){var t,n;const s={};for(const r in e){const a=null===(n=null===(t=this._signature)||void 0===t?void 0:t.inputs)||void 0===n?void 0:n[r];null!=a?s[a.name]=e[r]:s[r]=e[r]}return s}checkInputs(e){const t=Object.keys(e).filter((e=>{const[t]=FS(e);return null==this.graph.nodes[t]}));if(t.length>0)throw new Error(`The dict provided in model.execute(dict) has keys: [${t}] that are not part of graph`)}mapOutputs(e){return e.map((e=>{var t,n;const s=null===(n=null===(t=this._signature)||void 0===t?void 0:t.outputs)||void 0===n?void 0:n[e];return null!=s?s.name:e}),{})}checkOutputs(e){e.forEach((e=>{const[t]=FS(e);if(!this.graph.nodes[t])throw new Error(`The output '${e}' is not found in the graph`)}))}}class zT{constructor(e={},t={}){this.hashTableNameToHandle=e,this.hashTableMap=t}addHashTable(e,t){this.hashTableNameToHandle[e]=t.handle,this.hashTableMap[t.id]=t}getHashTableHandleByName(e){return this.hashTableNameToHandle[e]}getHashTableById(e){return this.hashTableMap[e]}dispose(){for(const e in this.hashTableMap)this.hashTableMap[e].clearAndClose(),delete this.hashTableMap[e];for(const e in this.hashTableNameToHandle)this.hashTableNameToHandle[e].dispose(),delete this.hashTableNameToHandle[e]}}const PT="?tfjs-format=file",BT="model.json";class WT{get modelVersion(){return this.version}get inputNodes(){return this.executor.inputNodes}get outputNodes(){return this.executor.outputNodes}get inputs(){return this.executor.inputs}get outputs(){return this.executor.outputs}get weights(){return this.executor.weightMap}get metadata(){return this.artifacts.userDefinedMetadata}get modelSignature(){return this.signature}get modelStructuredOutputKeys(){return this.structuredOutputKeys}constructor(e,t={},n=l){this.modelUrl=e,this.loadOptions=t,this.version="n/a",this.io=n,null==t&&(this.loadOptions={}),this.resourceManager=new zT}findIOHandler(){const e=this.modelUrl;if(null!=e.load)this.handler=e;else if(null!=this.loadOptions.requestInit)this.handler=this.io.browserHTTPRequest(e,this.loadOptions);else{const t=this.io.getLoadHandlers(e,this.loadOptions);if(0===t.length)t.push(this.io.browserHTTPRequest(e,this.loadOptions));else if(t.length>1)throw new Error(`Found more than one (${t.length}) load handlers for URL '${[e]}'`);this.handler=t[0]}}load(){if(this.findIOHandler(),null==this.handler.load)throw new Error("Cannot proceed with model loading because the IOHandler provided does not have the `load` method implemented.");const e=this.handler.load();return He(e)?e.then((e=>this.loadSync(e))):this.loadSync(e)}loadSync(e){this.artifacts=e;const t=this.artifacts.modelTopology;let n=this.artifacts.signature;if(null!=this.artifacts.userDefinedMetadata){const e=this.artifacts.userDefinedMetadata;null!=e.signature&&(n=e.signature),null!=e.structuredOutputKeys&&(this.structuredOutputKeys=e.structuredOutputKeys)}this.signature=n,this.version=`${t.versions.producer}.${t.versions.minConsumer}`;const s=this.io.decodeWeights(this.artifacts.weightData,this.artifacts.weightSpecs);if(this.executor=new LT(eT.Instance.transformGraph(t,this.signature)),this.executor.weightMap=this.convertTensorMapToTensorsMap(s),this.executor.resourceManager=this.resourceManager,null!=e.modelInitializer&&null!=e.modelInitializer.node){const t=eT.Instance.transformGraph(e.modelInitializer);this.initializer=new LT(t),this.initializer.weightMap=this.executor.weightMap,this.initializer.resourceManager=this.resourceManager,this.initializerSignature=e.initializerSignature}return!0}async save(e,t){if("string"==typeof e){const t=this.io.getSaveHandlers(e);if(0===t.length)throw new Error(`Cannot find any save handlers for URL '${e}'`);if(t.length>1)throw new Error(`Found more than one (${t.length}) save handlers for URL '${e}'`);e=t[0]}if(null==e.save)throw new Error("GraphModel.save() cannot proceed because the IOHandler provided does not have the `save` attribute defined.");return e.save(this.artifacts)}addStructuredOutputNames(e){if(this.structuredOutputKeys){const t={};return(e instanceof ga?[e]:e).forEach(((e,n)=>t[this.structuredOutputKeys[n]]=e)),t}return e}predict(e,t){const n=this.execute(e,this.outputNodes);return this.addStructuredOutputNames(n)}async predictAsync(e,t){const n=await this.executeAsync(e,this.outputNodes);return this.addStructuredOutputNames(n)}normalizeInputs(e){var t;if(!(e instanceof ga||Array.isArray(e))){const n=null===(t=this.signature)||void 0===t?void 0:t.inputs;if(null!=n)for(const t in n){const s=n[t];null!=s.resourceId&&(e[t]=this.resourceIdToCapturedInput[s.resourceId])}return e}e=Array.isArray(e)?e:[e];const n=Object.keys(this.resourceIdToCapturedInput).length;if(e.length+n!==this.inputNodes.length)throw new Error(`Input tensor count mismatch, the graph model has ${this.inputNodes.length-n} non-resource placeholders, while there are ${e.length} input tensors provided.`);let s=0;return this.inputNodes.reduce(((t,n)=>{var r,a,i;const o=null===(i=null===(a=null===(r=this.signature)||void 0===r?void 0:r.inputs)||void 0===a?void 0:a[n])||void 0===i?void 0:i.resourceId;return t[n]=null!=o?this.resourceIdToCapturedInput[o]:e[s++],t}),{})}normalizeOutputs(e){return e=e||this.outputNodes,Array.isArray(e)?e:[e]}executeInitializerGraph(){return null==this.initializer?[]:null==this.initializerSignature?this.initializer.execute({},[]):this.initializer.execute({},Object.keys(this.initializerSignature.outputs))}async executeInitializerGraphAsync(){return null==this.initializer?[]:null==this.initializerSignature?this.initializer.executeAsync({},[]):this.initializer.executeAsync({},Object.keys(this.initializerSignature.outputs))}setResourceIdToCapturedInput(e){if(this.resourceIdToCapturedInput={},this.initializerSignature){const t=this.initializerSignature.outputs,n=Object.keys(t);for(let s=0;s<n.length;s++){const r=t[n[s]];this.resourceIdToCapturedInput[r.resourceId]=e[s]}}}execute(e,t){null==this.resourceIdToCapturedInput&&this.setResourceIdToCapturedInput(this.executeInitializerGraph()),e=this.normalizeInputs(e),t=this.normalizeOutputs(t);const n=this.executor.execute(e,t);return n.length>1?n:n[0]}async executeAsync(e,t){null==this.resourceIdToCapturedInput&&this.setResourceIdToCapturedInput(await this.executeInitializerGraphAsync()),e=this.normalizeInputs(e),t=this.normalizeOutputs(t);const n=await this.executor.executeAsync(e,t);return n.length>1?n:n[0]}getIntermediateTensors(){return this.executor.getIntermediateTensors()}disposeIntermediateTensors(){this.executor.disposeIntermediateTensors()}convertTensorMapToTensorsMap(e){return Object.keys(e).reduce(((t,n)=>(t[n]=[e[n]],t)),{})}dispose(){this.executor.dispose(),this.initializer&&(this.initializer.dispose(),this.resourceIdToCapturedInput&&mo(this.resourceIdToCapturedInput)),this.resourceManager.dispose()}}async function VT(e,t={},n=l){if(null==e)throw new Error("modelUrl in loadGraphModel() cannot be null. Please provide a url or an IOHandler that loads the model");null==t&&(t={}),t.fromTFHub&&"string"==typeof e&&(e=function(e){e.endsWith("/")||(e+="/");return`${e}${BT}${PT}`}(e));const s=new WT(e,t,n);return await s.load(),s}function UT(e){if(null==e)throw new Error("modelUrl in loadGraphModelSync() cannot be null. Please provide model artifacts or an IOHandler that loads the model");let t;if(e instanceof Array){const[n,s]=e;if(!n)throw new Error("modelJSON must be the first element of the array");if(!(s&&s instanceof ArrayBuffer))throw new Error("An ArrayBuffer of weights must be the second element of the array");if(!("modelTopology"in n))throw new Error("Model JSON is missing 'modelTopology'");if(!("weightsManifest"in n))throw new Error("Model JSON is missing 'weightsManifest'");t=Sl(pi(n,mi(n.weightsManifest),s))}else if("load"in e)t=e;else{if(!("modelTopology"in e&&"weightSpecs"in e&&"weightData"in e))throw new Error("Unknown model format");t=Sl(e)}const n=new WT(t);return n.load(),n}const GT="4.6.0";function HT(e,t,n=new Map,s=new Set){if(null==e)return null;if("function"==typeof Blob&&e instanceof Blob)return e.slice();if(s.has(e))throw new Error("Circular references are not supported.");if(n.has(e))return n.get(e);const r=t(e);if(r.recurse&&null!==r.value)throw new Error("A deep map function may not return both a value and recurse=true.");if(r.recurse){if(YT(e)){const r=Array.isArray(e)?[]:{};s.add(e);for(const a in e){const i=HT(e[a],t,n,s);r[a]=i}return s.delete(e),e.__proto__&&(r.__proto__=e.__proto__),r}throw new Error(`Can't recurse into non-iterable type: ${e}`)}return n.set(e,r.value),r.value}function jT(e,t=KT){return qT(e,t)}function qT(e,t,n=new Set){const s=e[0];if(n.has(s))throw new Error("Circular references are not supported.");const r=t(e);if(r.recurse&&null!==r.value)throw new Error("A deep zip function may not return both a value and recurse=true.");if(r.recurse){if(YT(s)){const r=Array.isArray(s)?[]:{};n.add(s);for(const a in s){const s=qT(e.map((e=>e[a])),t,n);r[a]=s}return n.delete(s),r}throw new Error(`Can't recurse into non-iterable type: ${s}`)}return r.value}function KT(e){return null===e?null:YT(e[0])?{value:null,recurse:!0}:{value:e,recurse:!1}}async function XT(e,t){const n=new Map;HT(e,t,n);for(const e of Array.from(n.keys())){const t=n.get(e);if(He(t)){const s=await t;n.set(e,s)}}return HT(e,t,n)}function YT(e){let t=!1;if(Xe().get("IS_BROWSER"))t=e instanceof TextDecoder;else{const{StringDecoder:s}=n(977);t=e instanceof s}return null!=e&&!ArrayBuffer.isView(e)&&(Array.isArray(e)||"object"==typeof e&&!(e instanceof ga)&&!(e instanceof Promise)&&!t)}function ZT(e){return function(e,t){return HT(e,t)}(e,JT)}function JT(e){return e instanceof ga?{value:e.clone(),recurse:!1}:YT(e)?{value:null,recurse:!0}:{value:e,recurse:!1}}class QT{constructor(e){if(this.capacity=e,this.begin=0,this.end=0,null==e)throw new RangeError("Can't create a ring buffer of unknown capacity.");if(e<1)throw new RangeError("Can't create ring buffer of capacity < 1.");this.data=new Array(e),this.doubledCapacity=2*e}wrap(e){for(;e<0;)e+=this.doubledCapacity;return e%this.doubledCapacity}get(e){if(e<0)throw new RangeError("Can't get item at a negative index.");return this.data[e%this.capacity]}set(e,t){if(e<0)throw new RangeError("Can't set item at a negative index.");this.data[e%this.capacity]=t}length(){let e=this.end-this.begin;return e<0&&(e=this.doubledCapacity+e),e}isFull(){return this.length()===this.capacity}isEmpty(){return 0===this.length()}push(e){if(this.isFull())throw new RangeError("Ring buffer is full.");this.set(this.end,e),this.end=this.wrap(this.end+1)}pushAll(e){for(const t of e)this.push(t)}pop(){if(this.isEmpty())throw new RangeError("Ring buffer is empty.");this.end=this.wrap(this.end-1);const e=this.get(this.end);return this.set(this.end,void 0),e}unshift(e){if(this.isFull())throw new RangeError("Ring buffer is full.");this.begin=this.wrap(this.begin-1),this.set(this.begin,e)}shift(){if(this.isEmpty())throw new RangeError("Ring buffer is empty.");const e=this.get(this.begin);return this.set(this.begin,void 0),this.begin=this.wrap(this.begin+1),e}shuffleExcise(e){if(this.isEmpty())throw new RangeError("Ring buffer is empty.");const t=this.wrap(this.begin+e),n=this.get(t);return this.set(t,this.pop()),n}}class eC extends QT{constructor(){super(eC.INITIAL_CAPACITY)}isFull(){return!1}push(e){super.isFull()&&this.expand(),super.push(e)}unshift(e){super.isFull()&&this.expand(),super.unshift(e)}expand(){const e=2*this.capacity,t=new Array(e),n=this.length();for(let e=0;e<n;e++)t[e]=this.get(this.wrap(this.begin+e));this.data=t,this.capacity=e,this.doubledCapacity=2*this.capacity,this.begin=0,this.end=n}}function tC(e){return new aC(e)}function nC(e){return new iC(e)}function sC(e,t){return new yC(e,t)}eC.INITIAL_CAPACITY=32;class rC{async toArray(){const e=[];let t=await this.next();for(;!t.done;)e.push(t.value),t=await this.next();return e}async toArrayForTest(){const e=this.prefetch(100),t=[];let n=await e.next();for(;!n.done;)t.push(n.value),n=await e.next();return t}async resolveFully(){let e=await this.next();for(;!e.done;)e=await this.next()}async resolveWhile(e){let t=await this.next(),n=e(t.value);for(;!t.done&&n;)t=await this.next(),n=e(t.value)}handleErrors(e){return new dC(this,e)}filter(e){return new hC(this,e)}map(e){return new pC(this,e)}mapAsync(e){return new fC(this,e)}serialMapAsync(e){return new fC(this,e).serial()}flatmap(e){return new gC(this,e)}async forEachAsync(e){return this.map(e).resolveFully()}async serialForEach(e){return this.serialMapAsync(e).resolveWhile((e=>!0===e))}rowMajorBatch(e,t=!0){return new cC(this,e,t)}columnMajorBatch(e,t=!0,n=KT){return this.rowMajorBatch(e,t).map((e=>jT(e,n)))}concatenate(e,t){return new yC(tC([this,e]),t)}take(e){return e<0||null==e?this:new uC(this,e)}skip(e){return e<0||null==e?this:new lC(this,e)}prefetch(e){return new wC(this,e)}shuffle(e,t){return new vC(this,e,t)}serial(){return new oC(this)}}class aC extends rC{constructor(e){super(),this.items=e,this.trav=0}summary(){return`Array of ${this.items.length} items`}async next(){if(this.trav>=this.items.length)return{value:null,done:!0};const e=this.items[this.trav];return this.trav++,{value:ZT(e),done:!1}}}class iC extends rC{constructor(e){super(),this.nextFn=e}summary(){return"Function call"}async next(){try{return this.nextFn()}catch(e){throw e.message=`Error thrown while iterating through a dataset: ${e.message}`,e}}}class oC extends rC{constructor(e){super(),this.upstream=e,this.lastRead=Promise.resolve({value:null,done:!1})}summary(){return`${this.upstream.summary()} -> Serial`}async next(){return this.lastRead=this.lastRead.then((()=>this.serialNext())),this.lastRead}async serialNext(){return this.upstream.next()}}class lC extends rC{constructor(e,t){super(),this.upstream=e,this.maxCount=t,this.count=0,this.lastRead=Promise.resolve({value:null,done:!1})}summary(){return`${this.upstream.summary()} -> Skip`}async next(){return this.lastRead=this.lastRead.then((()=>this.serialNext())),this.lastRead}async serialNext(){for(;this.count++<this.maxCount;){const e=await this.upstream.next();if(e.done)return e;mo(e.value)}return this.upstream.next()}}class uC extends rC{constructor(e,t){super(),this.upstream=e,this.maxCount=t,this.count=0}summary(){return`${this.upstream.summary()} -> Take`}async next(){return this.count++>=this.maxCount?{value:null,done:!0}:this.upstream.next()}}class cC extends rC{constructor(e,t,n=!0){super(),this.upstream=e,this.batchSize=t,this.enableSmallLastBatch=n,this.lastRead=Promise.resolve({value:null,done:!1})}summary(){return`${this.upstream.summary()} -> RowMajorBatch`}async next(){return this.lastRead=this.lastRead.then((()=>this.serialNext())),this.lastRead}async serialNext(){const e=[];for(;e.length<this.batchSize;){const t=await this.upstream.next();if(t.done)return this.enableSmallLastBatch&&e.length>0?{value:e,done:!1}:{value:null,done:!0};e.push(t.value)}return{value:e,done:!1}}}class hC extends rC{constructor(e,t){super(),this.upstream=e,this.predicate=t,this.lastRead=Promise.resolve({value:null,done:!1})}summary(){return`${this.upstream.summary()} -> Filter`}async next(){return this.lastRead=this.lastRead.then((()=>this.serialNext())),this.lastRead}async serialNext(){for(;;){const e=await this.upstream.next();if(e.done||this.predicate(e.value))return e;mo(e.value)}}}class pC extends rC{constructor(e,t){super(),this.upstream=e,this.transform=t}summary(){return`${this.upstream.summary()} -> Map`}async next(){const e=await this.upstream.next();if(e.done)return{value:null,done:!0};const t=Fa(e.value),n=this.transform(e.value),s=Fa(n);for(const e of t)Ra(e,s)||e.dispose();return{value:n,done:!1}}}class dC extends rC{constructor(e,t){super(),this.upstream=e,this.handler=t,this.count=0,this.lastRead=Promise.resolve({value:null,done:!1})}summary(){return`${this.upstream.summary()} -> handleErrors`}async next(){return this.lastRead=this.lastRead.then((()=>this.serialNext())),this.lastRead}async serialNext(){for(;;)try{return await this.upstream.next()}catch(e){if(!this.handler(e))return{value:null,done:!0}}}}class fC extends rC{constructor(e,t){super(),this.upstream=e,this.transform=t}summary(){return`${this.upstream.summary()} -> AsyncMap`}async next(){const e=await this.upstream.next();if(e.done)return{value:null,done:!0};const t=Fa(e.value),n=await this.transform(e.value),s=Fa(n);for(const e of t)Ra(e,s)||e.dispose();return{value:n,done:!1}}}class mC extends rC{constructor(){super(),this.outputQueue=new eC,this.lastRead=Promise.resolve({value:null,done:!1})}async next(){return this.lastRead=this.lastRead.then((()=>this.serialNext())),this.lastRead}async serialNext(){for(;0===this.outputQueue.length();)if(!await this.pump())return{value:null,done:!0};return{value:this.outputQueue.shift(),done:!1}}}class gC extends mC{constructor(e,t){super(),this.upstream=e,this.transform=t}summary(){return`${this.upstream.summary()} -> Flatmap`}async pump(){const e=await this.upstream.next();if(e.done)return!1;const t=Fa(e.value),n=this.transform(e.value),s=Fa(n);this.outputQueue.pushAll(n);for(const e of t)Ra(e,s)||e.dispose();return!0}}class yC extends rC{constructor(e,t){super(),this.baseErrorHandler=t,this.lastRead=null,this.iterator=null,this.moreIterators=e}summary(){return"TODO: fill in upstream of chained summaries -> Chained"}async next(){return this.lastRead=this.readFromChain(this.lastRead),this.lastRead}async readFromChain(e){if(await e,null==this.iterator){const e=await this.moreIterators.next();if(e.done)return{value:null,done:!0};this.iterator=e.value,null!=this.baseErrorHandler&&(this.iterator=this.iterator.handleErrors(this.baseErrorHandler))}const t=await this.iterator.next();return t.done?(this.iterator=null,this.readFromChain(e)):t}}var bC;!function(e){e[e.FAIL=0]="FAIL",e[e.SHORTEST=1]="SHORTEST",e[e.LONGEST=2]="LONGEST"}(bC||(bC={}));class xC extends rC{constructor(e,t=bC.FAIL){super(),this.iterators=e,this.mismatchMode=t,this.count=0,this.currentPromise=null}summary(){return"{TODO: fill in upstream of zip summaries} -> Zip"}async nextState(e){await e;let t=0,n=0;const s=await XT(this.iterators,(function(e){if(e instanceof rC){return{value:e.next().then((e=>(t++,e.done&&n++,e.value))),recurse:!1}}return{value:null,recurse:!0}}));if(t===n)return{value:null,done:!0};if(n>0)switch(this.mismatchMode){case bC.FAIL:throw new Error(`Zipped streams should have the same length. Mismatched at element ${this.count}.`);case bC.SHORTEST:return{value:null,done:!0};case bC.LONGEST:}return this.count++,{value:s,done:!1}}async next(){return this.currentPromise=this.nextState(this.currentPromise),this.currentPromise}}class wC extends rC{constructor(e,t){super(),this.upstream=e,this.bufferSize=t,this.buffer=new QT(t)}summary(){return`${this.upstream.summary()} -> Prefetch`}refill(){for(;!this.buffer.isFull();){const e=this.upstream.next();this.buffer.push(e)}}next(){return this.refill(),this.buffer.shift()}}class vC extends wC{constructor(e,t,n){super(e,t),this.upstream=e,this.windowSize=t,this.upstreamExhausted=!1,this.random=mp.alea(n||Xr().toString()),this.lastRead=Promise.resolve({value:null,done:!1})}async next(){return this.lastRead=this.lastRead.then((()=>this.serialNext())),this.lastRead}randomInt(e){return Math.floor(this.random()*e)}chooseIndex(){return this.randomInt(this.buffer.length())}async serialNext(){for(this.upstreamExhausted||this.refill();!this.buffer.isEmpty();){const e=this.chooseIndex(),t=await this.buffer.shuffleExcise(e);if(!t.done)return this.refill(),t;this.upstreamExhausted=!0}return{value:null,done:!0}}}class kC{constructor(){this.size=null}batch(e,t=!0){const n=this;let s;return ie(e>0,(()=>`batchSize needs to be positive, but it is\n      ${e}`)),s=this.size===1/0||null==this.size?this.size:t?Math.ceil(this.size/e):Math.floor(this.size/e),IC((async()=>(await n.iterator()).columnMajorBatch(e,t,TC)),s)}concatenate(e){const t=this;let n;return n=this.size===1/0||e.size===1/0?1/0:null!=this.size&&null!=e.size?this.size+e.size:null,IC((async()=>(await t.iterator()).concatenate(await e.iterator())),n)}filter(e){const t=this;let n;return n=this.size===1/0?1/0:null,IC((async()=>(await t.iterator()).filter((t=>fo((()=>e(t)))))),n)}async forEachAsync(e){return(await this.iterator()).forEachAsync(e)}map(e){const t=this;return IC((async()=>(await t.iterator()).map((t=>fo((()=>e(t)))))),this.size)}mapAsync(e){const t=this;return IC((async()=>(await t.iterator()).mapAsync(e)),this.size)}prefetch(e){if(null==e)throw new RangeError("`Dataset.prefetch()` requires bufferSize to be specified.");const t=this;return IC((async()=>(await t.iterator()).prefetch(e)),this.size)}repeat(e){const t=this;let n;return n=null!=this.size&&e>0?this.size*e:0===e?0:null!=this.size&&(void 0===e||e<0)?1/0:null,IC((async()=>sC(nC((async()=>({value:await t.iterator(),done:!1}))).take(e))),n)}skip(e){const t=this;let n;return n=null!=this.size&&e>=0&&this.size>=e?this.size-e:null!=this.size&&(this.size<e||void 0===e||e<0)?0:null,IC((async()=>(await t.iterator()).skip(e)),n)}shuffle(e,t,n=!0){if(null==e||e<0)throw null==this.size?new RangeError("`Dataset.shuffle()` requires bufferSize to be specified."):new RangeError(`\`Dataset.shuffle()\` requires bufferSize to be specified.  If your data fits in main memory (for regular JS objects), and/or GPU memory (for \`tf.Tensor\`s), consider setting bufferSize to the dataset size (${this.size} elements)`);const s=this,r=mp.alea(t||Xr().toString());return IC((async()=>{let t=r.int32();return n&&(t+=r.int32()),(await s.iterator()).shuffle(e,t.toString())}),this.size)}take(e){const t=this;let n;return n=null!=this.size&&this.size>e?e:null!=this.size&&this.size<=e?this.size:null,IC((async()=>(await t.iterator()).take(e)),n)}async toArray(){if(this.size===1/0)throw new Error("Can not convert infinite data stream to array.");return(await this.iterator()).toArray()}async toArrayForTest(){if(this.size===1/0)throw new Error("Can not convert infinite data stream to array.");return(await this.iterator()).toArrayForTest()}}function IC(e,t=null){return new class extends kC{constructor(){super(...arguments),this.size=t}async iterator(){return e()}}}function NC(e){return IC((async()=>tC(e)),e.length)}function SC(e){if(!YT(e))throw new Error("The argument to zip() must be an object or array.");let t;if(Array.isArray(e))for(let n=0;n<e.length;n++)t=null==t?e[n].size:Math.min(t,e[n].size);else if(e instanceof Object)for(const n in e)t=null==t?e[n].size:Math.min(t,e[n].size);return IC((async()=>function(e,t=bC.FAIL){return new xC(e,t)}(await XT(e,(e=>{if(e instanceof kC)return{value:e.iterator(),recurse:!1};if(YT(e))return{value:null,recurse:!0};throw new Error("Leaves of the structure passed to zip() must be Datasets, not primitives.")})),bC.SHORTEST)),t)}function TC(e){if(null===e)return null;const t=e[0];if(null==(n=t)||null===(s=n)||"object"!=typeof s&&"function"!=typeof s||Array.isArray(n)||"object"==typeof n&&n instanceof ga||Qr(n)){return{value:function(e){if(0===e.length)throw new Error("Can't make a batch of zero elements.");return e[0]instanceof ga?Qp(e):ei(e)}(e),recurse:!1}}var n,s;return{value:null,recurse:!0}}kC.MAX_BUFFER_SIZE=1e4;class CC extends kC{constructor(e){super(),this.input=e}async iterator(){return(await this.input.iterator()).decodeUTF8().split("\n").map((e=>(e.endsWith("\r")&&(e=e.slice(0,-1)),e)))}}const $C='"',EC=Symbol("out"),AC=Symbol("field"),RC=Symbol("quote"),FC=Symbol("quoteafterquote"),_C=Symbol("quoteinquote");class DC extends kC{async columnNames(){return this.columnNamesValidated||await this.setColumnNames(),this.configuredColumnsOnly?Object.keys(this.columnConfigs):this.fullColumnNames}async setColumnNames(){const e=await this.maybeReadHeaderLine();if(!this.fullColumnNames&&!e)throw new Error("Column names must be provided if there is no header line.");this.fullColumnNames&&e&&ie(e.length===this.fullColumnNames.length,(()=>"The length of provided columnNames ("+this.fullColumnNames.length.toString()+") does not match the length of the header line read from file ("+e.length.toString()+").")),this.fullColumnNames||(this.fullColumnNames=e);const t=this.fullColumnNames.reduce(((e,t)=>(e[t]=e[t]+1||1,e)),{}),n=Object.keys(t).filter((e=>t[e]>1));if(ie(0===n.length,(()=>"Duplicate column names found: "+n.toString())),this.columnConfigs)for(const e of Object.keys(this.columnConfigs)){if(-1===this.fullColumnNames.indexOf(e))throw new Error('The key "'+e+'" provided in columnConfigs does not match any of the column names ('+this.fullColumnNames.toString()+").")}this.columnNamesValidated=!0}async maybeReadHeaderLine(){if(this.hasHeader){const e=await this.base.iterator(),t=await e.next();if(t.done)throw new Error("No data was found for CSV parsing.");const n=t.value;return this.parseRow(n,!1)}return null}constructor(e,t){super(),this.input=e,this.hasHeader=!0,this.fullColumnNames=null,this.columnNamesValidated=!1,this.columnConfigs=null,this.configuredColumnsOnly=!1,this.delimiter=",",this.delimWhitespace=!1,this.base=new CC(e),t||(t={}),this.hasHeader=!1!==t.hasHeader,this.fullColumnNames=t.columnNames,this.columnConfigs=t.columnConfigs,this.configuredColumnsOnly=t.configuredColumnsOnly,t.delimWhitespace?(ie(null==t.delimiter,(()=>"Delimiter should not be provided when delimWhitespace is true.")),this.delimWhitespace=!0,this.delimiter=" "):this.delimiter=t.delimiter?t.delimiter:","}async iterator(){this.columnNamesValidated||await this.setColumnNames();let e=await this.base.iterator();return this.hasHeader&&(e=e.skip(1)),e.map((e=>this.makeDataElement(e)))}makeDataElement(e){const t=this.parseRow(e),n={},s={};for(let r=0;r<this.fullColumnNames.length;r++){const a=this.fullColumnNames[r],i=this.columnConfigs?this.columnConfigs[a]:null;if(!this.configuredColumnsOnly||i){const o=t[r];let l=null;if(""===o)if(i&&void 0!==i.default)l=i.default;else{if(i&&(i.required||i.isLabel))throw new Error(`Required column ${a} is empty in this line: ${e}`);l=void 0}else{const e=Number(o);if(isNaN(e))l=i&&"bool"===i.dtype?this.getBoolean(o):o;else if(i&&i.dtype)switch(i.dtype){case"float32":default:l=e;break;case"int32":l=Math.floor(e);break;case"bool":l=this.getBoolean(o)}else l=e}i&&i.isLabel?s[a]=l:n[a]=l}}return 0===Object.keys(s).length?n:{xs:n,ys:s}}getBoolean(e){return"1"===e||"true"===e.toLowerCase()?1:0}parseRow(e,t=!0){const n=[];let s=0;const r=e.length;let a=EC;for(let t=0;t<r;t++)switch(a){case EC:switch(e.charAt(t)){case $C:s=t+1,a=RC;break;case this.delimiter:if(s=t+1," "===this.delimiter&&this.delimWhitespace)break;n.push(""),a=EC;break;default:a=AC,s=t}break;case AC:if(e.charAt(t)===this.delimiter)n.push(e.substring(s,t)),a=EC,s=t+1;break;case RC:if(e.charAt(t)===$C)a=FC;break;case FC:switch(e.charAt(t)){case this.delimiter:n.push(e.substring(s,t-1)),a=EC,s=t+1;break;case $C:a=RC;break;default:a=_C}break;case _C:if(e.charAt(t)===$C)a=RC}if(a===FC?n.push(e.substring(s,r-1)):n.push(e.substring(s)),t&&n.length!==this.fullColumnNames.length)throw new Error(`Invalid row in csv file. Should have ${this.fullColumnNames.length} elements in a row, but got ${n}`);return n}}class OC extends rC{constructor(e){super(),this.microphoneConfig=e,this.isClosed=!1,this.fftSize=e.fftSize||1024;const t=Math.log2(this.fftSize);if(this.fftSize<0||t<4||t>14||!Number.isInteger(t))throw new Error(`Invalid fftSize: it must be a power of 2 between 2 to 4 and 2 to 14, but got ${this.fftSize}`);if(this.numFrames=e.numFramesPerSpectrogram||43,this.sampleRateHz=e.sampleRateHz,this.columnTruncateLength=e.columnTruncateLength||this.fftSize,this.audioTrackConstraints=e.audioTrackConstraints,this.smoothingTimeConstant=e.smoothingTimeConstant||0,this.includeSpectrogram=!1!==e.includeSpectrogram,this.includeWaveform=!0===e.includeWaveform,!this.includeSpectrogram&&!this.includeWaveform)throw new Error("Both includeSpectrogram and includeWaveform are false. At least one type of data should be returned.")}summary(){return"microphone"}static async create(e={}){if(!Xe().get("IS_BROWSER"))throw new Error("microphone API is only supported in browser environment.");const t=new OC(e);return await t.start(),t}async start(){try{this.stream=await navigator.mediaDevices.getUserMedia({audio:null==this.audioTrackConstraints||this.audioTrackConstraints,video:!1})}catch(e){throw new Error(`Error thrown while initializing video stream: ${e.message}`)}if(!this.stream)throw new Error("Could not obtain audio from microphone.");const e=window.AudioContext||window.webkitAudioContext;if(this.audioContext=new e,this.sampleRateHz){if(this.audioContext.sampleRate!==this.sampleRateHz)throw new Error(`Mismatch in sampling rate: Expected: ${this.sampleRateHz}; Actual: ${this.audioContext.sampleRate}`)}else this.sampleRateHz=this.audioContext.sampleRate;const t=this.audioContext.createMediaStreamSource(this.stream);this.analyser=this.audioContext.createAnalyser(),this.analyser.fftSize=2*this.fftSize,this.analyser.smoothingTimeConstant=this.smoothingTimeConstant,t.connect(this.analyser),this.freqData=new Float32Array(this.fftSize),this.timeData=new Float32Array(this.fftSize)}async next(){if(this.isClosed)return{value:null,done:!0};let e,t;const n=await this.getAudioData();if(this.includeSpectrogram){const t=this.flattenQueue(n.freqDataQueue);e=this.getTensorFromAudioDataArray(t,[this.numFrames,this.columnTruncateLength,1])}if(this.includeWaveform){const e=this.flattenQueue(n.timeDataQueue);t=this.getTensorFromAudioDataArray(e,[this.numFrames*this.fftSize,1])}return{value:{spectrogram:e,waveform:t},done:!1}}async capture(){return(await this.next()).value}async getAudioData(){const e=[],t=[];let n=0;return new Promise((s=>{const r=setInterval((()=>{this.includeSpectrogram&&(this.analyser.getFloatFrequencyData(this.freqData),this.freqData[0]===-1/0&&s({freqDataQueue:e,timeDataQueue:t}),e.push(this.freqData.slice(0,this.columnTruncateLength))),this.includeWaveform&&(this.analyser.getFloatTimeDomainData(this.timeData),t.push(this.timeData.slice())),++n===this.numFrames&&(clearInterval(r),s({freqDataQueue:e,timeDataQueue:t}))}),this.fftSize/this.sampleRateHz*1e3)}))}stop(){this.isClosed||(this.isClosed=!0,this.analyser.disconnect(),this.audioContext.close(),null!=this.stream&&this.stream.getTracks().length>0&&this.stream.getTracks()[0].stop())}toArray(){throw new Error("Can not convert infinite audio stream to array.")}getSampleRate(){return this.sampleRateHz}flattenQueue(e){const t=e[0].length,n=new Float32Array(e.length*t);return e.forEach(((e,s)=>n.set(e,s*t))),n}getTensorFromAudioDataArray(e,t){const n=new Float32Array(ue(t));return n.set(e,n.length-e.length),ei(n,t)}}class MC extends rC{constructor(e,t){if(super(),this.webcamVideoElement=e,this.webcamConfig=t,this.isClosed=!0,this.resize=!1,this.needToResize())if(this.resize=!0,this.cropSize=[this.webcamConfig.resizeHeight,this.webcamConfig.resizeWidth],this.cropBoxInd=sd([0],"int32"),this.webcamConfig.centerCrop){const e=1*this.webcamConfig.resizeWidth/this.webcamVideoElement.width,t=1*this.webcamConfig.resizeHeight/this.webcamVideoElement.height,n=(1-e)/2,s=(1-t)/2,r=n+e,a=t+s;this.cropBox=rd([s,n,a,r],[1,4])}else this.cropBox=rd([0,0,1,1],[1,4])}summary(){return"webcam"}static async create(e,t={}){if(!Xe().get("IS_BROWSER"))throw new Error("tf.data.webcam is only supported in browser environment.");if(!e){if(e=document.createElement("video"),!t.resizeWidth||!t.resizeHeight)throw new Error("Please provide webcam video element, or resizeWidth and resizeHeight to create a hidden video element.");e.width=t.resizeWidth,e.height=t.resizeHeight}const n=new MC(e,t);return await n.start(),n}async start(){this.webcamConfig.facingMode&&ie("user"===this.webcamConfig.facingMode||"environment"===this.webcamConfig.facingMode,(()=>`Invalid webcam facing mode: ${this.webcamConfig.facingMode}. Please provide 'user' or 'environment'`));try{this.stream=await navigator.mediaDevices.getUserMedia({video:{deviceId:this.webcamConfig.deviceId,facingMode:this.webcamConfig.facingMode?this.webcamConfig.facingMode:"user",width:this.webcamVideoElement.width,height:this.webcamVideoElement.height}})}catch(e){throw e.message=`Error thrown while initializing video stream: ${e.message}`,e}if(!this.stream)throw new Error("Could not obtain video from webcam.");try{this.webcamVideoElement.srcObject=this.stream}catch(e){console.log(e),this.webcamVideoElement.src=window.URL.createObjectURL(this.stream)}return this.webcamVideoElement.play(),this.isClosed=!1,new Promise((e=>{this.webcamVideoElement.onloadedmetadata=()=>{e()}}))}async next(){if(this.isClosed)return{value:null,done:!0};let e;try{e=Gl(this.webcamVideoElement)}catch(e){throw new Error(`Error thrown converting video to pixels: ${JSON.stringify(e)}`)}if(!this.resize)return{value:e,done:!1};try{return{value:this.cropAndResizeFrame(e),done:!1}}catch(e){throw new Error(`Error thrown cropping the video: ${e.message}`)}finally{e.dispose()}}needToResize(){return!(!this.webcamConfig.resizeWidth||!this.webcamConfig.resizeHeight||this.webcamVideoElement.width===this.webcamConfig.resizeWidth&&this.webcamVideoElement.height===this.webcamConfig.resizeHeight)}cropAndResizeFrame(e){return fo((()=>{const t=hh(no(e,"float32"),0);let n;n=Mf.cropAndResize(t,this.cropBox,this.cropBoxInd,this.cropSize,"bilinear");const s=n.shape;return sc(n,s.slice(1))}))}async capture(){return(await this.next()).value}stop(){this.stream.getTracks().forEach((e=>e.stop()));try{this.webcamVideoElement.srcObject=null}catch(e){console.log(e),this.webcamVideoElement.src=null}this.isClosed=!0}toArray(){throw new Error("Can not convert infinite video stream to array.")}}class LC{}class zC extends rC{split(e){return new PC(this,e)}}class PC extends zC{constructor(e,t){super(),this.upstream=e,this.impl=new BC(e,t)}summary(){return this.impl.summary()}async next(){return this.impl.next()}}class BC extends mC{constructor(e,t){super(),this.upstream=e,this.separator=t,this.carryover=""}summary(){return`${this.upstream.summary()} -> Split('${this.separator}')`}async pump(){const e=await this.upstream.next();if(e.done)return""!==this.carryover&&(this.outputQueue.push(this.carryover),this.carryover="",!0);const t=e.value.split(this.separator);t[0]=this.carryover+t[0];for(const e of t.slice(0,-1))this.outputQueue.push(e);return this.carryover=t[t.length-1],!0}}class WC extends rC{decodeUTF8(){return new VC(this)}}class VC extends zC{constructor(e){super(),this.upstream=e,this.impl=new UC(e)}summary(){return this.impl.summary()}async next(){return this.impl.next()}}class UC extends mC{constructor(e){if(super(),this.upstream=e,Xe().get("IS_BROWSER"))this.decoder=new TextDecoder("utf-8");else{const{StringDecoder:e}=n(601);this.decoder=new e("utf8")}}summary(){return`${this.upstream.summary()} -> Utf8`}async pump(){const e=await this.upstream.next();let t,n;return!e.done&&(t=e.value,n=Xe().get("IS_BROWSER")?this.decoder.decode(t,{stream:!0}):this.decoder.write(Buffer.from(t.buffer)),this.outputQueue.push(n),!0)}}class GC extends WC{constructor(e,t={}){super(),this.file=e,this.options=t,ie(e instanceof Uint8Array||!!Xe().get("IS_BROWSER")&&(e instanceof File||e instanceof Blob),(()=>"FileChunkIterator only supports File, Blob and Uint8Array right now.")),this.offset=t.offset||0,this.chunkSize=t.chunkSize||1048576}summary(){return`FileChunks ${this.file}`}async next(){if(this.offset>=(this.file instanceof Uint8Array?this.file.byteLength:this.file.size))return{value:null,done:!0};const e=new Promise(((e,t)=>{const n=this.offset+this.chunkSize;if(this.file instanceof Uint8Array)e(new Uint8Array(this.file.slice(this.offset,n)));else{const s=new FileReader;s.onload=n=>{let r=s.result;if(r instanceof ArrayBuffer&&(r=new Uint8Array(r)),!(r instanceof Uint8Array))return t(new TypeError("FileReader returned unknown type."));e(r)},s.onabort=e=>t(new Error("Aborted")),s.onerror=e=>t(new Error(e.type));const r=this.file.slice(this.offset,n);s.readAsArrayBuffer(r)}this.offset=n}));return{value:await e,done:!1}}}const HC=e=>({method:e.method,headers:e.headers,body:e.body,mode:e.mode,credentials:e.credentials,cache:e.cache,redirect:e.redirect,referrer:e.referrer,integrity:e.integrity});function jC(e){return"string"==typeof e&&"file://"===e.slice(0,7)}class qC extends LC{constructor(e,t={}){super(),this.input=e,this.options=t}async iterator(){if(jC(this.input)&&Xe().get("IS_NODE")){const e=n(792);this.input=e.readFileSync(this.input.slice(7))}return new GC(this.input,this.options)}}class KC extends LC{constructor(e,t={}){super(),this.url=e,this.fileOptions=t}async iterator(){return jC(this.url)?new qC(this.url,this.fileOptions).iterator():async function(e,t={},n){let s,r;"string"==typeof e?s=e:(s=e.url,r=HC(e));const a=await(n||Yr)(s,r);if(a.ok){const e=new Uint8Array(await a.arrayBuffer());return new GC(e,t)}throw new Error(a.statusText)}(this.url,this.fileOptions)}}function XC(e,t={}){return new DC(new KC(e),t)}function YC(e){const t=nC(e);return IC((async()=>t))}function ZC(e){return IC((async()=>{const t=await e();return nC((()=>t.next()))}))}async function JC(e,t){return MC.create(e,t)}async function QC(e){return OC.create(e)}const e$="4.6.0";function t$(e,t){Array.isArray(e)||(e=[e]),e.forEach((e=>{null!=e&&ie("complex64"!==e.dtype,(()=>`${t} does not support complex64 tensors in the CPU backend.`))}))}const n$=gd;class s$ extends Y{nextDataId(){return s$.nextDataId++}constructor(){super(),this.blockSize=48,this.firstUse=!0,this.data=new X(this,co())}write(e,t,n){this.firstUse&&(this.firstUse=!1,Xe().get("IS_NODE")&&xr("\n============================\nHi, looks like you are running TensorFlow.js in Node.js. To speed things up dramatically, install our node backend, visit https://github.com/tensorflow/tfjs-node for more details. \n============================"));const s={id:this.nextDataId()};return this.data.set(s,{values:e,dtype:n,refCount:1}),s}makeTensorInfo(e,t,n){let s;if("string"===t&&null!=n&&n.length>0&&Ee(n[0])){const r=n.map((e=>Zr(e)));s=this.write(r,e,t)}else s=this.write(n,e,t);return{dataId:s,shape:e,dtype:t}}refCount(e){if(this.data.has(e)){return this.data.get(e).refCount}return 0}incRef(e){this.data.get(e).refCount++}decRef(e){if(this.data.has(e)){this.data.get(e).refCount--}}move(e,t,n,s,r){this.data.set(e,{values:t,dtype:s,refCount:r})}numDataIds(){return this.data.numDataIds()}async read(e){return this.readSync(e)}readSync(e){const{dtype:t,complexTensorInfos:n}=this.data.get(e);if("complex64"===t){return dm(this.readSync(n.real.dataId),this.readSync(n.imag.dataId))}return ze(this.data.get(e).values,t)}bufferSync(e){const t=this.readSync(e.dataId);if("string"===e.dtype)try{const n=t.map((e=>Jr(e)));return to(e.shape,e.dtype,n)}catch(e){throw new Error("Failed to decode encoded string bytes into utf-8")}return to(e.shape,e.dtype,t)}makeOutput(e,t,n){return co().makeTensorFromTensorInfo(this.makeTensorInfo(t,n,e),this)}disposeData(e,t=!1){if(this.data.has(e)){if(this.data.get(e).refCount--,!t&&this.data.get(e).refCount>0)return!1;const{complexTensorInfos:n}=this.data.get(e);null!=n&&(this.disposeData(n.real.dataId,!0),this.disposeData(n.imag.dataId,!0)),this.data.delete(e)}return!0}disposeIntermediateTensorInfo(e){this.disposeData(e.dataId)}async time(e){const t=Xr();e();return{kernelMs:Xr()-t}}memory(){return{unreliable:!0,reasons:["The reported memory is an upper bound. Due to automatic garbage collection, the true allocated memory may be less."]}}where(e){t$([e],"where");const t=this.readSync(e.dataId);return n$(e.shape,t)}dispose(){}floatPrecision(){return 32}epsilon(){return super.epsilon()}}function r$(e){const t=new Float32Array(e.length);for(let n=0;n<e.length;++n)t[n]=Math.abs(e[n]);return t}s$.nextDataId=0;const a$={kernelName:et,backendName:"cpu",kernelFunc:e=>{const{x:t}=e.inputs,n=e.backend;t$(t,"abs");let s=new Float32Array(ue(t.shape));return s=r$(n.data.get(t.dataId).values),n.makeOutput(s,t.shape,t.dtype)}};function i$(e){return(t,n,s,r,a)=>{const i=tl(t,n),o=i.length,l=Oe(i),u=ke(a,ue(i)),c=t.length,h=n.length,p=Oe(t),d=Oe(n),f=Qo(t,i),m=Qo(n,i);if(f.length+m.length===0)for(let t=0;t<u.length;++t)u[t]=e(s[t%s.length],r[t%r.length]);else for(let t=0;t<u.length;++t){const n=Ge(t,o,l),a=n.slice(-c);f.forEach((e=>a[e]=0));const i=Ue(a,c,p),g=n.slice(-h);m.forEach((e=>g[e]=0));const y=Ue(g,h,d);u[t]=e(s[i],r[y])}return[u,i]}}function o$(e){const{inputs:t,backend:n}=e,{real:s,imag:r}=t,a=n.data.get(s.dataId).values,i=n.data.get(r.dataId).values,o=n.makeTensorInfo(s.shape,"complex64");return n.data.get(o.dataId).complexTensorInfos={real:n.makeTensorInfo(s.shape,"float32",a),imag:n.makeTensorInfo(r.shape,"float32",i)},o}const l$={kernelName:Ct,backendName:"cpu",kernelFunc:o$};function u$(e,t,n="float32"){if("complex64"===n){return o$({inputs:{real:u$(e,t,"float32"),imag:u$(e,t,"float32")},backend:e})}const s=Be(ue(t),n);return e.makeTensorInfo(t,n,s)}function c$(e){const{inputs:t,backend:n}=e,{x:s}=t;return n.incRef(s.dataId),{dataId:s.dataId,shape:s.shape,dtype:s.dtype}}const h$={kernelName:yn,backendName:"cpu",kernelFunc:c$};function p$(e){const{inputs:t,backend:n}=e,{input:s}=t,r=n.data.get(s.dataId).complexTensorInfos.real,a=n.data.get(r.dataId).values;return n.makeTensorInfo(r.shape,r.dtype,a)}const d$={kernelName:ms,backendName:"cpu",kernelFunc:p$};function f$(e,t,n,s){if("int32"===s){return[t,"int32",Int32Array.from(e)]}if("bool"===s){const s=Kr([0],n),[r,a]=i$(((e,t)=>e!==t?1:0))(t,[],e,s,"bool");return[a,"bool",r]}throw new Error(`Error in Cast: failed to cast ${n} to ${s}`)}function m$(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{dtype:a}=s;if("complex64"===a){if("complex64"===r.dtype)return c$({inputs:{x:r},backend:n});const e=u$(n,r.shape,r.dtype),t=m$({inputs:{x:r},backend:n,attrs:{dtype:"float32"}}),s=o$({inputs:{real:t,imag:e},backend:n});return n.disposeIntermediateTensorInfo(e),n.disposeIntermediateTensorInfo(t),s}if("complex64"===r.dtype){const e=p$({inputs:{input:r},backend:n}),t=m$({inputs:{x:e},backend:n,attrs:{dtype:a}});return n.disposeIntermediateTensorInfo(e),t}if(!Te(r.dtype,a)){const e=c$({inputs:{x:r},backend:n});return{dataId:e.dataId,shape:e.shape,dtype:a}}const i=n.data.get(r.dataId).values,[o,l,u]=f$(i,r.shape,r.dtype,a);return n.makeTensorInfo(o,l,u)}const g$={kernelName:Nt,backendName:"cpu",kernelFunc:m$};function y$(e,t,n,s){return null==n?({inputs:n,backend:r})=>{const{a,b:i}=n,o=r;t$([a,i],e);const l=o.data.get(a.dataId).values,u=o.data.get(i.dataId).values,c="string"===a.dtype?qm(l):l,h="string"===a.dtype?qm(u):u,p=s||a.dtype,[d,f]=t(a.shape,i.shape,c,h,p);return o.makeTensorInfo(f,p,d)}:({inputs:e,backend:r})=>{const{a,b:i}=e,o=r;if("complex64"===a.dtype||"complex64"===i.dtype){const e=m$({inputs:{x:a},backend:o,attrs:{dtype:"complex64"}}),t=o.data.get(e.dataId),s=t.complexTensorInfos.real,r=t.complexTensorInfos.imag,l=o.data.get(s.dataId).values,u=o.data.get(r.dataId).values,c=m$({inputs:{x:i},backend:o,attrs:{dtype:"complex64"}}),h=o.data.get(c.dataId),p=h.complexTensorInfos.real,d=h.complexTensorInfos.imag,f=o.data.get(p.dataId).values,m=o.data.get(d.dataId).values,[g,y,b]=n(a.shape,i.shape,l,u,f,m),x=o.makeTensorInfo(b,"float32",g),w=o.makeTensorInfo(b,"float32",y),v=o$({inputs:{real:x,imag:w},backend:o});return o.disposeIntermediateTensorInfo(e),o.disposeIntermediateTensorInfo(c),o.disposeIntermediateTensorInfo(x),o.disposeIntermediateTensorInfo(w),v}{const e=o.data.get(a.dataId).values,n=o.data.get(i.dataId).values,r=s||a.dtype,[l,u]=t(a.shape,i.shape,e,n,r);return o.makeTensorInfo(u,r,l)}}}function b$(e){return(t,n,s,r,a,i)=>{const o=tl(t,n),l=ue(o),u=o.length,c=Oe(o),h=ke("float32",l),p=ke("float32",l),d=Qo(t,o),f=Qo(n,o),m=dm(s,r),g=dm(a,i),y=t.length,b=Oe(t),x=n.length,w=Oe(n);if(d.length+f.length===0)for(let t=0;t<h.length;t++){const n=t%m.length,s=t%g.length,r=e(m[2*n],m[2*n+1],g[2*s],g[2*s+1]);h[t]=r.real,p[t]=r.imag}else for(let t=0;t<h.length;t++){const n=Ge(t,u,c),s=n.slice(-y);d.forEach((e=>s[e]=0));const r=Ue(s,y,b),a=n.slice(-x);f.forEach((e=>a[e]=0));const i=Ue(a,x,w),o=e(m[2*r],m[2*r+1],g[2*i],g[2*i+1]);h[t]=o.real,p[t]=o.imag}return[h,p,o]}}const x$=i$(((e,t)=>e+t)),w$=b$(((e,t,n,s)=>({real:e+n,imag:t+s}))),v$=y$(st,x$,w$),k$={kernelName:st,backendName:"cpu",kernelFunc:v$};function I$(e,t,n,s,r){const a=ue(s),i=Be(r,n);for(let n=0;n<e.length;n++){const s=e[n];if(s<0)throw new Error("Input x must be non-negative!");s>=r||(i[s]+=a>0?t[n]:1)}return i}function N$(e,t,n,s=!1){const r=e.shape[0],a=e.shape[1],i=to([r,n],t.dtype);for(let o=0;o<r;o++)for(let r=0;r<a;r++){const a=e.get(o,r);if(a<0)throw new Error("Input x must be non-negative!");a>=n||(s?i.set(1,o,a):t.size>0?i.set(i.get(o,a)+t.get(o,r),o,a):i.set(i.get(o,a)+1,o,a))}return i}const S$=i$(((e,t)=>e&t)),T$=y$(vt,S$),C$={kernelName:vt,backendName:"cpu",kernelFunc:T$};function $$(e){return(t,n,s)=>{const r=Ie(n,t.length);for(let n=0;n<t.length;++n)r[n]=e(t[n],s);return r}}function E$(e,t,n){return A$(e,$$(t),n)}function A$(e,t,n){return({inputs:s,attrs:r,backend:a})=>{const{x:i}=s;t$(i,e);const o=a,l=o.data.get(i.dataId).values;let u;if("string"===i.dtype){if(!Array.isArray(l))throw new Error("String tensor's value was not an instance of Array");u=qm(l)}else u=l;const c=n||i.dtype,h=t(u,c,r);return o.makeTensorInfo(i.shape,c,h)}}const R$=$$((e=>Math.ceil(e))),F$=A$(St,R$),_$={kernelName:St,backendName:"cpu",kernelFunc:F$};function D$(e,t,n,s){const r=Ie(n,ue(t));if(s&&"string"!==n){let t=0;e.forEach((e=>{const n=ue(e.shape);r.set(e.vals,t),t+=n}))}else{let s=0;e.forEach((e=>{const a="string"===n?qm(e.vals):e.vals;let i=0;for(let n=0;n<e.shape[0];++n){const o=n*t[1]+s;for(let t=0;t<e.shape[1];++t)r[o+t]=a[i++]}s+=e.shape[1]}))}return r}const O$=i$(((e,t)=>e===t?1:0)),M$=y$(nn,O$,null,"bool"),L$={kernelName:nn,backendName:"cpu",kernelFunc:M$},z$=$$((e=>Math.exp(e))),P$=A$(sn,z$,"float32"),B$={kernelName:sn,backendName:"cpu",kernelFunc:P$},W$=$$((e=>Math.expm1(e))),V$=A$(an,W$),U$={kernelName:an,backendName:"cpu",kernelFunc:V$},G$=$$((e=>Math.floor(e))),H$=A$(cn,G$),j$={kernelName:cn,backendName:"cpu",kernelFunc:H$},q$=i$(((e,t)=>Math.floor(e/t))),K$=y$(hn,q$,null,"int32"),X$={kernelName:hn,backendName:"cpu",kernelFunc:K$};function Y$(e,t,n,s,r,a,i,o,l){const u=to([s,a],n);for(let n=0;n<s;n++){const s=[];let c=0;for(let t=0;t<r;t++){const a=e[n*r+t];c+=a*i[t],s.push(a)}if(c<0||c>=l/a)throw new Error(`Invalid indices: ${s} does not index into ${o}`);for(let e=0;e<a;e++)u.values[n*a+e]=t.get(...t.indexToLoc(c*a+e))}return u}function Z$(e,t,n){const s=to(n,e.dtype);for(let n=0;n<s.size;++n){const r=s.indexToLoc(n).slice(),a=r[0],i=r[2],o=t.locToIndex([a,i]);r[2]=t.values[o];const l=e.locToIndex(r);0<=l&&l<e.values.length&&(s.values[n]=e.values[l])}return s}const J$=i$(((e,t)=>e>t?1:0)),Q$=y$(mn,J$,null,"bool"),eE={kernelName:mn,backendName:"cpu",kernelFunc:Q$},tE=i$(((e,t)=>e>=t?1:0)),nE=y$(gn,tE,null,"bool"),sE={kernelName:gn,backendName:"cpu",kernelFunc:nE},rE=i$(((e,t)=>e<t?1:0)),aE=y$(Nn,rE,null,"bool"),iE={kernelName:Nn,backendName:"cpu",kernelFunc:aE},oE=i$(((e,t)=>e<=t?1:0)),lE=y$(Sn,oE,null,"bool"),uE={kernelName:Sn,backendName:"cpu",kernelFunc:lE};function cE(e,t,n){const s=(t-e)/(n-1),r=Be(n,"float32");r[0]=e;for(let e=1;e<r.length;e++)r[e]=r[e-1]+s;return r}const hE=$$((e=>Math.log(e))),pE=A$(Cn,hE),dE={kernelName:Cn,backendName:"cpu",kernelFunc:pE};function fE(e,t,n,s){const r=ke(s,ue(n));for(let n=0;n<r.length;++n){const s=n*t;let a=e[s];for(let n=0;n<t;++n){const t=e[s+n];(Number.isNaN(t)||t>a)&&(a=t)}r[n]=a}return r}const mE=i$(((e,t)=>Math.max(e,t))),gE=y$(Pn,mE),yE={kernelName:Pn,backendName:"cpu",kernelFunc:gE},bE=i$(((e,t)=>Math.min(e,t))),xE=y$(qn,bE),wE={kernelName:qn,backendName:"cpu",kernelFunc:xE},vE=i$(((e,t)=>e*t)),kE=b$(((e,t,n,s)=>({real:e*n-t*s,imag:e*s+t*n}))),IE=y$(Zn,vE,kE),NE={kernelName:Zn,backendName:"cpu",kernelFunc:IE};function SE(e,t,n){const s=qr(-1,n);return vE([],t,s,e,n)}const TE={kernelName:Jn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{x:s}=t;t$(s,"neg");const r=n.data.get(s.dataId).values,[a,i]=SE(r,s.shape,s.dtype);return n.makeTensorInfo(i,s.dtype,a)}},CE=i$(((e,t)=>e!==t?1:0)),$E=y$(Qn,CE,null,"bool"),EE={kernelName:Qn,backendName:"cpu",kernelFunc:$E};function AE(e,t,n,s,r){const a=t.length,i=ue(t),o=Oe(t),l=Oe(r),u=ke(n,ue(r));for(let t=0;t<i;++t){const n=Ge(t,a,o),r=new Array(n.length);for(let e=0;e<r.length;e++)r[e]=n[s[e]];u[Ue(r,a,l)]=e[t]}return u}function RE(e){const{inputs:t,attrs:n,backend:s}=e,{x:r}=t,{perm:a}=n;t$(r,"transpose");const i=r.shape.length,o=new Array(i);for(let e=0;e<o.length;e++)o[e]=r.shape[a[e]];const l=AE(s.data.get(r.dataId).values,r.shape,r.dtype,a,o);return{dataId:s.write(l,o,r.dtype),shape:o,dtype:r.dtype}}const FE={kernelName:or,backendName:"cpu",kernelFunc:RE};function _E(e,t,n,s){const[r,a]=Jc(e,s),i=Sa(t,"int32"),o=Be(ue(r),i),l=ue(a);for(let e=0;e<o.length;++e){const t=e*l;let s=1;for(let e=0;e<l;++e)s*=n[t+e];o[e]=s}return{outVals:o,outShape:r,outDtype:i}}const DE={kernelName:cs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s;t$(r,"prod");const o=r.shape.length,l=we(a,r.shape),u=th(l,o);let c=l,h=r;const p=[];null!=u&&(h=RE({inputs:{x:r},backend:n,attrs:{perm:u}}),p.push(h),c=sh(c.length,o));const d=n.data.get(h.dataId).values,{outVals:f,outShape:m,outDtype:g}=_E(h.shape,h.dtype,d,c);let y=m;return i&&(y=Qc(m,l)),p.forEach((e=>n.disposeIntermediateTensorInfo(e))),n.makeTensorInfo(y,g,f)}};function OE(e,t,n,s){const r=[];let a=0;const i=t.length-1+n.length,o=new Array(i).fill(null).map((()=>[0]));!function(e,t){for(let n=0;n<e.length;++n){const s=e[n],r=n===e.length-1?t:e[n+1].length;if(0===s.length)throw new Error("Ragged splits may not be empty");if(s[0]<0)throw new Error("Ragged splits must be non-negative");if(s[s.length-1]>r)throw new Error("Ragged splits must not point past values");for(let e=1;e<s.length;++e)if(s[e-1]>s[e])throw new Error("Ragged splits must be sorted in ascending order")}}(n,s);let l=1;for(let e=0;e<t.length-1;++e){l*=t[e];const n=t[e+1];for(let t=1;t<l+1;++t)o[e].push(t*n)}for(let s=0;s<e.length;++s){let i=e[s],l=e[s]+1;for(let e=0;e<n.length;++e){const s=n[e],r=e+t.length-1;if(r>=0){const e=o[r],t=e[e.length-1]-s[i];for(let e=i;e<l;++e)o[r].push(s[e+1]+t)}i=s[i],l=s[l]}l!==i&&(r.push([i,l]),a+=l-i)}return{outSplits:o,valueSlices:r,numValues:a}}function ME(e,t){const n=e.slice(0,t);for(;n.length<t;)n.push(1);for(let s=t;s<e.length;s++)n[t-1]*=e[s];return n}function LE(e,t,n,s,r){const a=t.slice();a[0]=r;const i=Ie(n,ue(a)),o=e.length;return function(e,t,n,s,r,a){const i=ME(t,2)[1],o=ME(a,2)[1];let l=0;for(const t of n)for(let n=t[0];n<t[1];++n){for(let t=0;t<s;++t)r[l*o+t]=e[n*i+t];++l}}(e,t,s,0===o?0:o/t[0],i,a),[i,a]}function zE(e,t,n,s,r,a,i,o){if(0===e.length)throw new Error("paramsNestedSplits must be non empty");if(0===t[0].length)throw new Error("Split tensors must not be scalars");if(function(e,t,n){e.forEach(((e,s)=>{if(e<0||e>=n){const r=Ge(s,t.length,Oe(t)).join(",");throw new Error(`indices[${r}] = ${e} is not in [0, ${n})`)}}))}(a,i,t[0][0]-1),0===s.length)throw new Error("params.rank must be nonzero");const l=s[0],{outSplits:u,valueSlices:c,numValues:h}=OE(a,i,e,l),p=function(e){const t=[];for(let n=0;n<e.length;++n){const s=Ie("int32",e[n].length);t.push(s),e[n].forEach(((e,t)=>s[t]=e))}return t}(u),d=LE(n,s,r,c,h);return[p,d[0],d[1]]}const PE=2147483647;function BE(e,t,n,s,r,a,i){if(t.length>1)throw new Error("starts must be a scalar or vector");if(r.length>1)throw new Error("limits must be a scalar or vector");if(i.length>1)throw new Error("deltas must be a scalar or vector");const o=0===t.length,l=0===r.length,u=0===i.length,c=[];o||c.push(t[0]),l||c.push(r[0]),u||c.push(i[0]);for(let e=1;e<c.length;++e)if(c[e]!==c[e-1])throw new Error("starts, limits, and deltas must have the same shape");const h=0===c.length?1:c[0],p=Ie("int32",h+1);p[0]=0;for(let t=0;t<h;++t){const n=o?e[0]:e[t],r=l?s[0]:s[t],i=u?a[0]:a[t];if(0===i)throw new Error("Requires delta != 0");let c;if(i>0&&r<n||i<0&&r>n)c=0;else if(c=Math.ceil(Math.abs((r-n)/i)),c>PE)throw new Error(`Requires ((limit - start) / delta) <= ${PE}`);p[t+1]=p[t]+c}const d=Ie(n,p[h]);let f=0;for(let t=0;t<h;++t){const n=p[t+1]-p[t];let s=o?e[0]:e[t];const r=u?a[0]:a[t];for(let e=0;e<n;++e)d[f++]=s,s+=r}return[p,d]}var WE=jf;class VE{constructor(e,t,n,s,r,a,i,o,l,u){this.shape=e,this.shapeShape=t,this.values=n,this.valuesShape=s,this.valuesDType=r,this.defaultValue=a,this.defaultValueShape=i,this.rowPartitionValues=o,this.rowPartitionValuesShapes=l,this.rowPartitionTypes=Kf(u),this.raggedRank=Xf(this.rowPartitionTypes)}getRowPartitionTypeByDimension(e){return this.rowPartitionTypes[0]===WE.FIRST_DIM_SIZE?this.rowPartitionTypes[e+1]:this.rowPartitionTypes[e]}getRowPartitionTensor(e){return this.rowPartitionTypes[0]===WE.FIRST_DIM_SIZE?this.rowPartitionValues[e+1]:this.rowPartitionValues[e]}getMaxWidth(e){const t=this.getRowPartitionTensor(e-1);switch(this.getRowPartitionTypeByDimension(e-1)){case WE.VALUE_ROWIDS:return VE.getMaxWidthValueRowID(t);case WE.ROW_SPLITS:return VE.getMaxWidthRowSplit(t);default:throw new Error(`Cannot handle partition type ${WE[this.getRowPartitionTypeByDimension(e-1)]}`)}}static getMaxWidthRowSplit(e){const t=e.length;if(0===t||1===t)return 0;let n=0;for(let s=0;s<t-1;++s){const t=e[s+1]-e[s];t>n&&(n=t)}return n}static getMaxWidthValueRowID(e){const t=e.length;if(0===t)return 0;let n=0,s=e[0],r=0;for(let a=1;a<t;++a){const t=e[a];t!==s&&(s=t,r=Math.max(a-n,r),n=a)}return Math.max(t-n,r)}tensorShapeFromTensor(e,t,n=!0){if(0===t.length){if(-1===e[0])return[];throw new Error("The only valid scalar shape tensor is the fully unknown shape specified as -1.")}return GE(e,n)}calculateOutputSize(e){const t=this.valuesShape;Yf(this.defaultValueShape,t);const n=this.tensorShapeFromTensor(this.shape,this.shapeShape),s=qf(this.raggedRank,n,t);s[0]<0&&(s[0]=e);for(let e=1;e<=this.raggedRank;++e)s[e]<0&&(s[e]=this.getMaxWidth(e));return s}calculateFirstParentOutputIndex(e,t,n){const s=Math.min(e,n),r=[];let a=0;for(let e=0;e<s;++e,a+=t)r.push(a);for(let t=s;t<e;++t)r.push(-1);return ie(r.length===e,(()=>"Final length of result must be equal to firstDimension.")),r}calculateOutputIndexRowSplit(e,t,n,s){const r=e.length,a=[];for(let i=0;i<r-1;++i){const r=e[i+1]-e[i];let o=Math.min(s,r),l=t[i];-1===l&&(o=0);for(let e=0;e<o;++e)a.push(l),l+=n;for(let e=0;e<r-o;++e)a.push(-1)}if(r>0&&a.length!==e[r-1])throw new Error("Invalid row split size.");return a}calculateOutputIndexValueRowID(e,t,n,s){const r=e.length,a=[];if(0===r)return[];let i=0,o=e[0];if(o>=t.length)throw new Error(`Got currentValueRowId=${o}, which is not less than ${t.length}`);let l=t[o];a.push(l);for(let u=1;u<r;++u){const r=e[u];if(r===o)l>=0&&(++i,i<s?l+=n:l=-1);else{if(i=0,o=r,r>=t.length)throw new Error(`Got nextValueRowId=${r} which is not less than ${t.length}`);l=t[r]}a.push(l)}if(a.length!==e.length)throw new Error("Invalid row ids.");return a}calculateOutputIndex(e,t,n,s){const r=this.getRowPartitionTensor(e),a=this.getRowPartitionTypeByDimension(e);switch(a){case WE.VALUE_ROWIDS:return this.calculateOutputIndexValueRowID(r,t,n,s);case WE.ROW_SPLITS:if(r.length-1>t.length)throw new Error(`Row partition size is greater than output size: ${r.length-1} > ${t.length}`);return this.calculateOutputIndexRowSplit(r,t,n,s);default:throw new Error(`Unsupported partition type: ${WE[a]}`)}}getFirstDimensionSize(){const e=this.rowPartitionValues[0];if(0===this.rowPartitionTypes.length)throw new Error("No row_partition_types given.");const t=this.rowPartitionTypes[0];switch(t){case WE.FIRST_DIM_SIZE:return e[0];case WE.VALUE_ROWIDS:throw new Error("Cannot handle VALUE_ROWIDS in first dimension.");case WE.ROW_SPLITS:return this.rowPartitionValuesShapes[0][0]-1;default:throw new Error(`Cannot handle type ${WE[t]}`)}}compute(){if(this.rowPartitionValues[0].length<=0)throw new Error("Invalid first partition input. Tensor requires at least one element.");const e=this.getFirstDimensionSize(),t=this.calculateOutputSize(e),n=new Array(this.raggedRank+1);n[n.length-1]=1;for(let e=n.length-2;e>=0;--e)n[e]=n[e+1]*t[e+1];const s=GE(t,!1),r=Ie(this.valuesDType,ue(s));if(n[0]*t[0]>0){let a=this.calculateFirstParentOutputIndex(e,n[0],t[0]);for(let e=1;e<=this.raggedRank;++e){a=this.calculateOutputIndex(e-1,a,n[e],t[e])}this.setOutput(this.raggedRank,a,r,s)}return[s,r]}setOutput(e,t,n,s){if(0===n.length)return;const r=this.values,a=n;let i=s.slice();i=i.slice(e+1);const o=ue(i),l=t.length;let u=this.defaultValue;if(u.length!==o&&1!==u.length){const e=this.defaultValueShape;fo((()=>{const t=sc(u,e),n=xc(t,i);u=n.dataSync()}))}let c=0,h=0,p=0;for(let e=0;e<=l;++e){let s=e<l?t[e]:-1;if(s!==p){if(h<p){const e=r.subarray(c*o);UE(a.subarray(h*o),e,(p-h)*o)}if(e>=l){const e=n.length;s=Math.floor(e/o)}if(s>p)if(1===this.defaultValue.length)a.subarray(p*o,s*o).fill(this.defaultValue[0]),p=s;else for(;s>p;){UE(a.slice(p*o),u,o),++p}s<0?(c=e+1,h=p):(c=e,h=p,p=h+1)}else++p}}}function UE(e,t,n){for(let s=0;s<n;s++)e[s]=t[s]}function GE(e,t){const n=[];for(let s of e){if(s<0){if(!t)throw new Error(`Dimension ${s} must be >= 0`);if(s<-1)throw new Error(`Dimension ${s} must be >= -1`);s=-1}n.push(s)}return n}function HE(e,t,n,s,r,a,i,o,l,u){return new VE(e,t,n,s,r,a,i,o,l,u).compute()}function jE(e,t,n,s){if(e===t||e<t&&n<0||t<e&&n>1)return Be(0,s);const r=Be(Math.abs(Math.ceil((t-e)/n)),s);t<e&&1===n&&(n=-1),r[0]=e;for(let e=1;e<r.length;e++)r[e]=r[e-1]+n;return r}const qE=$$((e=>1/Math.sqrt(e))),KE=A$(Ts,qE),XE={kernelName:Ts,backendName:"cpu",kernelFunc:KE};function YE(e,t,n,s,r,a,i,o,l,u){const c=[s/r,r],h=e.values,p=t.values;if(0===s)return to(n,t.dtype);const d=l instanceof pa?l:to(c,t.dtype);"string"==typeof l||"number"==typeof l?d.values.fill(l):"boolean"==typeof l&&d.values.fill(+l);for(let e=0;e<a;e++){const a=[];let l=0;for(let t=0;t<i;t++){const n=h[e*i+t];a.push(n),l+=n*o[t]}if(l<0||l>=s/r)throw new Error(`Invalid indices: ${a} does not index into ${n}`);for(let n=0;n<r;n++)u?d.values[l*r+n]+=p[e*r+n]:d.values[l*r+n]=0===t.rank?p[0]:p[e*r+n]}return d}const ZE=$$((e=>1/(1+Math.exp(-e)))),JE=E$(Ms,(e=>1/(1+Math.exp(-e)))),QE={kernelName:Ms,backendName:"cpu",kernelFunc:JE};function eA(e,t,n,s,r){const a=uu(s,t,n),i=ue(n),o=Oe(s);if(a){const n=cu(t,o);return"string"===r?e.slice(n,n+i):e.subarray(n,n+i)}const l=to(s,r,"string"===r?qm(e):e),u=to(n,r);for(let e=0;e<u.size;++e){const n=u.indexToLoc(e),s=n.map(((e,n)=>e+t[n]));u.set(l.get(...s),...n)}return"string"===r?Km(u.values):u.values}function tA(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{begin:a,size:i}=s;t$(r,"slice");const[o,l]=hu(r,a,i);Zl(r,o,l);const u=eA(n.data.get(r.dataId).values,o,l,r.shape,r.dtype);return n.makeTensorInfo(l,r.dtype,u)}const nA={kernelName:Fs,backendName:"cpu",kernelFunc:tA};function sA(e,t,n,s,r,a,i){const o=t[0],l=a[0],u=new Array(l),c=new Array(o),h=t[1];if(0===l){if(0!==o)throw new Error(Fm(o));return[Ie(n,0),[0,h],Ie(r,0),u,c]}let p=!0,d=0;const f=new Array(l).fill(0);for(let t=0;t<o;++t){const n=e[t*h];if(n<0)throw new Error(_m(t,n));if(n>=l)throw new Error(Dm(t,n,l));++f[n],p=p&&n>=d,d=n}let m=!0;for(let e=0;e<l;++e){const t=0===f[e];u[e]=t,m=m&&!t,f[e]=Math.max(f[e],1),e>0&&(f[e]+=f[e-1])}if(m&&p){const t=e,n=s;for(let e=0;e<o;++e)c[e]=e;return[t,[o,h],n,u,c]}{const t=f[l-1],a=Ie(n,t*h),p=Ie(r,t),d=new Array(l).fill(0);for(let t=0;t<o;++t){const n=e[t*h],r=d[n],i=(0===n?0:f[n-1])+r;d[n]++;for(let n=0;n<h;++n)a[i*h+n]=e[t*h+n];p[i]=s[t],c[t]=i}for(let e=0;e<l;++e){if(0===d[e]){const t=0===e?0:f[e-1];a[t*h+0]=e;for(let e=1;e<h;++e)a[t*h+e]=0;p[t]=i}}return[a,[t,h],p,u,c]}}function rA(e,t,n,s,r){const a=ue(s),i=t[0],o=r.length,l=[];let u=1,c=-1;for(let e=0;e<o;++e){const t=r[e];if(-1===t){if(-1!==c)throw new Error(Om(c,e));c=e,l.push(1)}else{if(t<0)throw new Error(Mm(e,t));u*=t,l.push(t)}}if(-1!==c){if(u<=0)throw new Error("reshape cannot infer the missing input size for an empty tensor unless all specified input sizes are non-zero");const e=Math.trunc(a/u);if(u*e!==a)throw new Error(zm(s,l));l[c]=e}if(ue(l)!==a)throw new Error(Pm(s,l));const h=s.length,p=[];if(h>0){p[h-1]=1;for(let e=h-2;e>=0;--e)p[e]=p[e+1]*s[e+1]}const d=[];if(o>0){d[o-1]=1;for(let e=o-2;e>=0;--e)d[e]=d[e+1]*l[e+1]}const f=Ie(n,i*o);for(let t=0;t<i;++t){let n=0;for(let s=0;s<h;++s)n+=e[t*h+s]*p[s];for(let e=0;e<o;++e)f[t*o+e]=Math.trunc(n/d[e]),n%=d[e]}return[f,[i,o],l]}function aA(e,t,n,s,r,a=!1,i=0){const o=s.length,l=[t[0],e.length/t[0]],u=l[1],c=o>0?r[o-1]+1:0;if(c<0)throw new Error("segment ids must be >= 0");const h=t.slice();h[0]=c;const p=Ie(n,h.reduce(((e,t)=>e*t),1));if(0===o)return c>0&&p.fill(i),[p,h];if(c<=0)throw new Error("segment ids must be >= 0");let d=0,f=1,m=0,g=r[d];for(;;){let t=0;if(f<o){if(t=r[f],g===t){++f;continue}if(g>=t)throw new Error("segment ids are not increasing")}if(g<0||g>=c)throw new Error(Vm(g,c));g>m&&p.fill(i,m*u,g*u);for(let t=d;t<f;++t){const n=s[t];if(n<0||n>=l[0])throw new Error(Um(t,s[t],l[0]));for(let t=0;t<u;t++)p[g*u+t]+=e[n*u+t]}if(a)for(let e=0;e<u;e++)p[g*u+e]/=f-d;if(d=f,++f,m=g+1,g=t,f>o)break}return m<c&&p.fill(i,m*u,c*u),[p,h]}const iA=$$((e=>Math.sqrt(e))),oA=E$(zs,(e=>Math.sqrt(e))),lA={kernelName:zs,backendName:"cpu",kernelFunc:oA},uA=i$(((e,t)=>{const n=e-t;return n*n})),cA=y$(Ks,uA),hA={kernelName:Ks,backendName:"cpu",kernelFunc:cA},pA=$$(((e,t)=>{const{pattern:n,replaceGlobal:s,rewrite:r}=t;return e.replace(new RegExp(n,s?"g":""),r)})),dA=A$(Ys,pA),fA={kernelName:Ys,backendName:"cpu",kernelFunc:dA};function mA(e,t,n,s){const r=to(e,t.dtype);for(let e=0;e<r.size;e++){const a=r.indexToLoc(e),i=new Array(a.length);for(let e=0;e<i.length;e++)i[e]=a[e]*n[e]+s[e];r.set(t.get(...i),...a)}return r}class gA{constructor(e,t,n,s,r,a){this.separator=Zr(e),this.nGramWidths=t,this.leftPad=Zr(n),this.rightPad=Zr(s),this.padWidth=r,this.preserveShort=a}getPadWidth(e){return Math.min(this.padWidth<0?e-1:this.padWidth,e-1)}getNumNGrams(e,t){const n=this.getPadWidth(t);return Math.max(0,e+2*n-t+1)}createNGrams(e,t,n,s,r,a){for(let i=0;i<r;++i){const o=this.getPadWidth(a),l=Math.max(0,o-i),u=Math.max(0,o-(r-(i+1))),c=a-(l+u),h=t+(l>0?0:i-o);let p=0;p+=l*this.leftPad.length;for(let t=0;t<c;++t)p+=e[h+t].length;p+=u*this.rightPad.length;p+=(l+u+c-1)*this.separator.length,n[s+i]=new Uint8Array(p);const d=n[s+i];let f=0;const m=e=>e.forEach((e=>d[f++]=e));for(let e=0;e<l;++e)m(this.leftPad),m(this.separator);for(let t=0;t<c-1;++t)m(e[h+t]),m(this.separator);if(c>0){m(e[h+c-1]);for(let e=0;e<u;++e)m(this.separator),m(this.rightPad)}else{for(let e=0;e<u-1;++e)m(this.rightPad),m(this.separator);m(this.rightPad)}}}compute(e,t){const n=e.length,s=t.length;if(s>0){let e=t[0];if(0!==e)throw new Error(`First split value must be 0, got ${e}`);for(let r=1;r<s;++r){let s=t[r]>=e;if(s=s&&t[r]<=n,!s)throw new Error(`Invalid split value ${t[r]}, must be in [${e}, ${n}]`);e=t[r]}if(e!==n)throw new Error(`Last split value must be data size. Expected ${n}, got ${e}`)}const r=s-1,a=Ie("int32",s);if(0===n||0===s){const e=new Array(n);for(let e=0;e<=r;++e)a[e]=0;return[e,a]}a[0]=0;for(let e=1;e<=r;++e){const n=t[e]-t[e-1];let s=0;this.nGramWidths.forEach((e=>{s+=this.getNumNGrams(n,e)})),this.preserveShort&&n>0&&0===s&&(s=1),a[e]=a[e-1]+s}const i=new Array(a[r]);for(let n=0;n<r;++n){const s=t[n];let r=a[n];if(this.nGramWidths.forEach((a=>{const o=t[n+1]-t[n],l=this.getNumNGrams(o,a);this.createNGrams(e,s,i,r,l,a),r+=l})),this.preserveShort&&r===a[n]){const a=t[n+1]-t[n];if(0===a)continue;const o=a+2*this.padWidth,l=1;this.createNGrams(e,s,i,r,l,o)}}return[i,a]}}function yA(e,t,n,s,r,a,i,o){return new gA(n,s,r,a,i,o).compute(e,t)}function bA(e,t,n,s){if(!e.length)return;if(0===t.length){for(let t=0;t<e.length;++t)s.push(e.subarray(t,t+1));return}if(1===t.length){const r=t[0];let a=e.indexOf(r);for(;-1!==a;){const t=e.subarray(0,a);n&&0===t.length||s.push(t),a=(e=e.subarray(a+1)).indexOf(r)}return void(n&&0===e.length||s.push(e))}let r=0;for(let a=0;a<e.length+1;a++)if(a===e.length||-1!==t.indexOf(e[a])){const t=e.subarray(r,a);n&&0===t.length||s.push(t),r=a+1}}function xA(e,t,n){const s=e.length,r=[];let a=0,i=0;const o=new Array(s);for(let l=0;l<s;++l){const s=r.length;bA(e[l],t,n,r);const u=r.length-s;o[l]=u,a+=u,i=Math.max(i,u)}const l=Ie("int32",2*a),u=new Array(a),c=[s,i];let h=0;for(let e=0;e<s;++e)for(let t=0;t<o[e];++t)l[2*h]=e,l[2*h+1]=t,u[h]=r[h],++h;return[l,u,c]}function wA(e,t){const n=Ie("int32",e.length);for(let s=0;s<e.length;++s)n[s]=jr(e[s]).modulo(t).getLowBitsUnsigned();return n}const vA=i$(((e,t)=>e-t)),kA=b$(((e,t,n,s)=>({real:e-n,imag:t-s}))),IA=y$(tr,vA,kA),NA={kernelName:tr,backendName:"cpu",kernelFunc:IA};function SA(e,t){const n=new Array(e.rank);for(let s=0;s<n.length;s++)n[s]=e.shape[s]*t[s];const s=to(n,e.dtype);for(let t=0;t<s.values.length;++t){const n=s.indexToLoc(t),r=new Array(e.rank);for(let t=0;t<r.length;t++)r[t]=n[t]%e.shape[t];const a=e.locToIndex(r);s.values[t]=e.values[a]}return s}const TA=(e,t)=>{const n=t.value-e.value;return 0===n?e.index-t.index:n};function CA(e,t,n=0,s=e.length-1){for(;s>n;){if(s-n>600){const r=s-n+1,a=t-n+1,i=Math.log(r),o=.5*Math.exp(2*i/3),l=.5*Math.sqrt(i*o*(r-o)/r)*Math.sign(a-r/2);CA(e,t,Math.max(n,Math.floor(t-a*o/r+l)),Math.min(s,Math.floor(t+(r-a)*o/r+l)))}const r=e[t];let a=n,i=s;for(ne(e,n,t),TA(e[s],r)>0&&ne(e,n,s);a<i;){for(ne(e,a,i),a++,i--;TA(e[a],r)<0;)a+=1;for(;TA(e[i],r)>0;)i-=1}0===TA(e[n],r)?ne(e,n,i):(i+=1,ne(e,i,s)),i<=t&&(n=i+1),t<=i&&(s=i-1)}}function $A(e,t,n,s,r){const a=t[t.length-1],[i,o]=[e.length/a,a],l=ke(n,i*s),u=ke("int32",i*s);for(let t=0;t<i;t++){const n=t*o,a=e.subarray(n,n+o);let i=new Array(a.length);a.forEach(((e,t)=>i[t]={value:e,index:t})),s<i.length&&(CA(i,s),i=i.slice(0,s)),r&&i.sort(TA);const c=t*s,h=l.subarray(c,c+s),p=u.subarray(c,c+s);for(let e=0;e<s;e++)h[e]=i[e].value,p[e]=i[e].index}const c=t.slice();return c[c.length-1]=s,[to(c,n,l),to(c,"int32",u)]}function EA(e,t,n,s){const r=we(t,n)[0],a=[1,n[0],1];for(let e=0;e<r;e++)a[0]*=n[e];a[1]=n[r];for(let e=r+1;e<n.length;e++)a[2]*=n[e];const i=new Map,o=new Int32Array(n[r]),l=new pa(a,s,e),u=[],c=1===a[0]&&1===a[2];for(let t=0;t<n[r];t++){let n;if(c)n=e[t].toString();else{const e=[];for(let n=0;n<a[0];n++)for(let s=0;s<a[2];s++)e.push(l.get(n,t,s));n=e.join(",")}const s=i.get(n);if(null!=s)o[t]=s;else{const e=i.size;i.set(n,e),o[t]=e,u.push(t)}}const h=a.slice();h[1]=i.size;const p=new pa(h,s);u.forEach(((e,t)=>{for(let n=0;n<a[0];n++)for(let s=0;s<a[2];s++)p.set(l.get(n,e,s),n,t,s)}));const d=n.slice();return d[r]=h[1],{outputValues:p.values,outputShape:d,indices:o}}const AA="4.6.0";No("cpu",(()=>new s$),1);const RA=E$(Qt,(e=>e>=0?e:Math.exp(e)-1)),FA={kernelName:Qt,backendName:"cpu",kernelFunc:RA};function _A(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{alpha:a}=s;t$([r],"leakyRelu");const i=ue(r.shape),o=n.data.get(r.dataId).values,l=ke("float32",i);for(let e=0;e<o.length;e++)l[e]=o[e]<0?a*o[e]:o[e];return n.makeTensorInfo(r.shape,"float32",l)}const DA={kernelName:In,backendName:"cpu",kernelFunc:_A},OA=i$(((e,t)=>e<0?t*e:e));function MA(e){const{inputs:t,backend:n}=e,{x:s,alpha:r}=t;t$([s,r],"prelu");const a=n.data.get(s.dataId).values,i=n.data.get(r.dataId).values,[o,l]=OA(s.shape,r.shape,a,i,"float32");return n.makeTensorInfo(l,"float32",o)}const LA={kernelName:us,backendName:"cpu",kernelFunc:MA},zA=E$(ys,(e=>Math.max(0,e))),PA={kernelName:ys,backendName:"cpu",kernelFunc:zA},BA=E$(Is,(e=>Math.min(Math.max(0,e),6))),WA={kernelName:Is,backendName:"cpu",kernelFunc:BA};function VA(e,t,n,s,r){if("linear"===n)return c$({inputs:{x:t},backend:e});if("relu"===n)return zA({inputs:{x:t},backend:e});if("elu"===n)return RA({inputs:{x:t},backend:e});if("relu6"===n)return BA({inputs:{x:t},backend:e});if("prelu"===n)return MA({inputs:{x:t,alpha:s},backend:e});if("leakyrelu"===n)return _A({inputs:{x:t},backend:e,attrs:{alpha:r}});if("sigmoid"===n)return JE({inputs:{x:t},backend:e});throw new Error(`Activation ${n} has not been implemented for the CPU backend.`)}function UA(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{shape:a}=s,i=ue(r.shape),o=xe(a,i),l=ue(o);ie(i===l,(()=>`The new shape (${o}) has ${l} elements and the old shape (${r.shape}) has ${i} elements. The new shape and old shape must have the same number of elements.`)),n.incRef(r.dataId);const u=n.data.get(r.dataId);if(null!=u.complexTensorInfos){const e=u.complexTensorInfos.real,t=u.complexTensorInfos.imag;e.shape=o,t.shape=o}return{dataId:r.dataId,shape:o,dtype:r.dtype}}const GA={kernelName:bs,backendName:"cpu",kernelFunc:UA};function HA(e){const{inputs:t,backend:n,attrs:s}=e,{a:r,b:a}=t,{transposeA:i,transposeB:o}=s;t$([r,a],"matMul");const l=r.shape.length,u=a.shape.length,c=i?r.shape[l-2]:r.shape[l-1],h=o?a.shape[u-1]:a.shape[u-2],p=i?r.shape[l-1]:r.shape[l-2],d=o?a.shape[u-2]:a.shape[u-1],f=r.shape.slice(0,-2),m=a.shape.slice(0,-2),g=ue(f),y=ue(m),b=tl(r.shape.slice(0,-2),a.shape.slice(0,-2)).concat([p,d]);ie(c===h,(()=>`Error in matMul: inner shapes (${c}) and (${h}) of Tensors with shapes ${r.shape} and ${a.shape} and transposeA=${i} and transposeB=${o} must match.`));const x=o?[y,d,h]:[y,h,d],w=UA({inputs:{x:r},backend:n,attrs:{shape:i?[g,c,p]:[g,p,c]}}),v=UA({inputs:{x:a},backend:n,attrs:{shape:x}}),k=i?w.shape[1]:w.shape[2],I=i?w.shape[2]:w.shape[1],N=o?v.shape[1]:v.shape[2],S=Math.max(g,y),T=n.data.get(w.dataId).values,C=n.data.get(v.dataId).values,$=Oe(w.shape),E=Oe(v.shape),[A,R,F]=i?[$[0],1,$[1]]:[$[0],$[1],1],[_,D,O]=o?[1,E[1],E[0]]:[E[1],1,E[0]],M=I*N,L=to([S,I,N],w.dtype),z=L.values,P=n.blockSize;for(let e=0;e<S;e++){const t=e%g,n=e%y;for(let s=0;s<I;s+=P){const r=Math.min(s+P,I);for(let a=0;a<N;a+=P){const i=Math.min(a+P,N);for(let o=0;o<k;o+=P){const l=Math.min(o+P,k);for(let u=s;u<r;u++)for(let s=a;s<i;s++){let r=0;for(let e=o;e<l;e++){r+=T[t*A+u*R+e*F]*C[e*_+s*D+n*O]}z[e*M+(u*N+s)]+=r}}}}}return n.disposeIntermediateTensorInfo(w),n.disposeIntermediateTensorInfo(v),n.makeTensorInfo(b,L.dtype,L.values)}const jA={kernelName:bt,backendName:"cpu",kernelFunc:HA};const qA={kernelName:gr,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{a:r,b:a,bias:i,preluActivationWeights:o}=t,{transposeA:l,transposeB:u,activation:c,leakyreluAlpha:h}=s;let p,d,f;const m=[];p=HA({inputs:{a:r,b:a},attrs:{transposeA:l,transposeB:u},backend:n}),i&&(d=v$({inputs:{a:p,b:i},backend:n}),m.push(p),p=d),c&&(f=VA(n,p,c,o,h),m.push(p),p=f);for(const e of m)n.disposeIntermediateTensorInfo(e);return p}},KA=E$(tt,(e=>Math.acos(e))),XA={kernelName:tt,backendName:"cpu",kernelFunc:KA},YA=E$(nt,(e=>Math.acosh(e))),ZA={kernelName:nt,backendName:"cpu",kernelFunc:YA};const JA={kernelName:rt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,s=t;t$(t,"addN");const r=s.map((e=>n.data.get(e.dataId).values)),a=to(s[0].shape,s[0].dtype),i=a.values;for(let e=0;e<s.length;e++){const t=r[e];for(let e=0;e<i.length;e++)i[e]+=t[e]}return n.makeTensorInfo(a.shape,a.dtype,a.values)}};const QA={kernelName:at,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s;t$(r,"all");const o=we(a,r.shape);let l=o;const u=th(l,r.shape.length);let c=r;null!=u&&(c=RE({inputs:{x:r},backend:n,attrs:{perm:u}}),l=sh(l.length,r.shape.length)),eh("all",l,c.shape.length);const[h,p]=Jc(c.shape,l),d=ue(p),f=Be(ue(h),c.dtype),m=n.data.get(c.dataId).values;for(let e=0;e<f.length;++e){const t=e*d;let n=m[t];for(let e=0;e<d;++e){const s=m[t+e];n=n&&s}f[e]=n}null!=u&&n.disposeIntermediateTensorInfo(c);const g=n.makeTensorInfo(h,c.dtype,f);if(i){const e=UA({inputs:{x:g},backend:n,attrs:{shape:Qc(h,o)}});return n.disposeIntermediateTensorInfo(g),e}return g}};const eR={kernelName:it,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s;t$(r,"any");const o=we(a,r.shape);let l=o;const u=th(l,r.shape.length);let c=r;null!=u&&(c=RE({inputs:{x:r},backend:n,attrs:{perm:u}}),l=sh(l.length,r.shape.length)),eh("any",l,c.shape.length);const[h,p]=Jc(c.shape,l),d=ue(p),f=Be(ue(h),c.dtype),m=n.data.get(c.dataId).values;for(let e=0;e<f.length;++e){const t=e*d;let n=m[t];for(let e=0;e<d;++e){const s=m[t+e];n=n||s}f[e]=n}null!=u&&n.disposeIntermediateTensorInfo(c);const g=n.makeTensorInfo(h,c.dtype,f);if(i){const e=UA({inputs:{x:g},backend:n,attrs:{shape:Qc(h,o)}});return n.disposeIntermediateTensorInfo(g),e}return g}};const tR={kernelName:ot,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a}=s;t$(r,"argMax");let i=we(a,r.shape);const o=th(i,r.shape.length);let l=r;const u=[];null!=o&&(l=RE({inputs:{x:r},backend:n,attrs:{perm:o}}),u.push(l),i=sh(i.length,l.shape.length)),i=[i[0]],eh("argMax",i,l.shape.length);const[c,h]=Jc(l.shape,i),p=Be(ue(c),"int32"),d=ue(h),f=n.data.get(l.dataId).values;for(let e=0;e<p.length;++e){const t=e*d;let n=f[t],s=0;for(let e=0;e<d;++e){const r=f[t+e];r>n&&(n=r,s=e)}p[e]=s}return u.forEach((e=>n.disposeIntermediateTensorInfo(e))),n.makeTensorInfo(c,"int32",p)}};const nR={kernelName:lt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a}=s;t$(r,"argMin");let i=we(a,r.shape);const o=th(i,r.shape.length);let l=r;const u=[];null!=o&&(l=RE({inputs:{x:r},backend:n,attrs:{perm:o}}),u.push(l),i=sh(i.length,l.shape.length)),i=[i[0]],eh("argMin",i,l.shape.length);const[c,h]=Jc(l.shape,i),p=Be(ue(c),"int32"),d=ue(h),f=n.data.get(l.dataId).values;for(let e=0;e<p.length;++e){const t=e*d;let n=f[t],s=0;for(let e=0;e<d;++e){const r=f[t+e];r<n&&(n=r,s=e)}p[e]=s}return u.forEach((e=>n.disposeIntermediateTensorInfo(e))),n.makeTensorInfo(c,"int32",p)}},sR=E$(ut,(e=>Math.asin(e))),rR={kernelName:ut,backendName:"cpu",kernelFunc:sR},aR=E$(ct,(e=>Math.asinh(e))),iR={kernelName:ct,backendName:"cpu",kernelFunc:aR},oR=E$(ht,(e=>Math.atan(e))),lR={kernelName:ht,backendName:"cpu",kernelFunc:oR},uR=i$(((e,t)=>Math.atan2(e,t))),cR=y$(dt,uR),hR={kernelName:dt,backendName:"cpu",kernelFunc:cR},pR=E$(pt,(e=>Math.atanh(e))),dR={kernelName:pt,backendName:"cpu",kernelFunc:pR};function fR(e,t,n,s,r,a){const i=r.strideHeight,o=r.strideWidth,l=r.dilationHeight,u=r.dilationWidth,c=r.effectiveFilterHeight,h=r.effectiveFilterWidth,p=r.padInfo.top,d=r.padInfo.left,f="max"===a?Number.NEGATIVE_INFINITY:Number.POSITIVE_INFINITY,m=to(r.outShape,n),g=m.values,y=r.outShape[1]*r.outShape[2]*r.outShape[3],b=r.outShape[2]*r.outShape[3],x=r.outShape[3];for(let t=0;t<r.batchSize;++t){const n=t*y,m=t*s[0];for(let t=0;t<r.inChannels;++t)for(let y=0;y<r.outHeight;++y){const w=y*i-p,v=Math.max(0,w),k=Math.min(r.inHeight,c+w),I=n+y*b;for(let n=0;n<r.outWidth;++n){const i=n*o-d,c=Math.max(0,i),p=Math.min(r.inWidth,h+i);let y=f,b=0,w=0;for(let n=v;n<k;n+=l){const r=m+n*s[1];for(let n=c;n<p;n+=u){const i=e[r+n*s[2]+t];"max"===a&&i>y?y=i:"avg"===a&&(b+=i,w++)}if(isNaN(y))break}g[I+n*x+t]="avg"===a?b/w:y}}}return m}function mR(e,t,n,s,r=!1,a=!1){const i=to(s.outShape,"int32"),o=s.strideHeight,l=s.strideWidth,u=s.dilationHeight,c=s.dilationWidth,h=s.effectiveFilterHeight,p=s.effectiveFilterWidth,d=s.padInfo.top,f=s.padInfo.left,m=to(t,n,e);for(let e=0;e<s.batchSize;++e)for(let t=0;t<s.inChannels;++t)for(let n=0;n<s.outHeight;++n){const g=n*o-d;let y=g;for(;y<0;)y+=u;const b=Math.min(s.inHeight,h+g);for(let o=0;o<s.outWidth;++o){const h=o*l-f;let d=h;for(;d<0;)d+=c;const x=Math.min(s.inWidth,p+h);let w=Number.NEGATIVE_INFINITY,v=-1;for(let n=y;n<b;n+=u){const i=n-g;for(let o=d;o<x;o+=c){const l=o-h,u=m.get(e,n,o,t);u>w&&(w=u,v=r?a?((e*s.inHeight+n)*s.inWidth+o)*s.inChannels+t:(n*s.inWidth+o)*s.inChannels+t:i*p+l)}}i.set(v,e,n,o,t)}}return i}function gR(e,t,n,s,r,a){const i=r.strideDepth,o=r.strideHeight,l=r.strideWidth,u=r.dilationDepth,c=r.dilationHeight,h=r.dilationWidth,p=r.effectiveFilterDepth,d=r.effectiveFilterHeight,f=r.effectiveFilterWidth,m=r.padInfo.front,g=r.padInfo.top,y=r.padInfo.left,b="max"===a?Number.NEGATIVE_INFINITY:Number.POSITIVE_INFINITY,x=to(r.outShape,n),w=x.values,v=r.outShape[1]*r.outShape[2]*r.outShape[3]*r.outShape[4],k=r.outShape[2]*r.outShape[3]*r.outShape[4],I=r.outShape[3]*r.outShape[4],N=r.outShape[4];for(let t=0;t<r.batchSize;++t){const n=t*v,x=t*s[0];for(let t=0;t<r.inChannels;++t)for(let v=0;v<r.outDepth;++v){const S=v*i-m;let T=S;for(;T<0;)T+=u;const C=Math.min(r.inDepth,p+S),$=n+v*k;for(let n=0;n<r.outHeight;++n){const i=n*o-g;let p=i;for(;p<0;)p+=c;const m=Math.min(r.inHeight,d+i),v=$+n*I;for(let n=0;n<r.outWidth;++n){const i=n*l-y;let o=i;for(;o<0;)o+=h;const d=Math.min(r.inWidth,f+i),g=v+n*N;let k=b,I=0,S=0;for(let n=T;n<C;n+=u){const r=x+n*s[1];for(let n=p;n<m;n+=c){const i=r+n*s[2];for(let n=o;n<d;n+=h){const r=e[i+n*s[3]+t];if("max"===a&&r>k?k=r:"avg"===a&&(I+=r,S++),isNaN(k))break}if(isNaN(k))break}if(isNaN(k))break}w[g+t]="avg"===a?I/Math.max(S,1):k}}}}return x}const yR={kernelName:ft,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t;t$(r,"avgPool");const{filterSize:a,strides:i,pad:o,dimRoundingMode:l}=s;ie(Qu(i,1),(()=>`Error in avgPool: Either strides or dilations must be 1. Got strides ${i} and dilations '1'`));const u=Uu(r.shape,a,i,1,o,l);let c;if(1===u.filterWidth&&1===u.filterHeight&&pe(u.inShape,u.outShape))c=c$({inputs:{x:r},backend:n});else{const e=n.data.get(r.dataId).values,t=Oe(r.shape),s=fR(e,r.shape,r.dtype,t,u,"avg");c=n.makeTensorInfo(u.outShape,r.dtype,s.values)}return c}};const bR={kernelName:gt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{filterSize:a,strides:i,pad:o,dimRoundingMode:l,dataFormat:u}=s;t$(r,"avgPool3d");const c=Gu(r.shape,a,i,1,o,l,u),h=gR(n.data.get(r.dataId).values,r.shape,r.dtype,Oe(r.shape),c,"avg");return n.makeTensorInfo(h.shape,"float32",h.values)}};const xR={kernelName:yt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a}=t,{filterSize:i,strides:o,pad:l,dimRoundingMode:u}=s;t$([r,a],"avgPool3DGrad");const c=Gu(a.shape,i,o,1,l,u),h=c.strideDepth,p=c.strideHeight,d=c.strideWidth,f=c.filterDepth,m=c.filterHeight,g=c.filterWidth,y=c.dilationDepth,b=c.dilationHeight,x=c.dilationWidth,w=c.effectiveFilterDepth,v=c.effectiveFilterHeight,k=c.effectiveFilterWidth,I=w-1-c.padInfo.front,N=k-1-c.padInfo.left,S=v-1-c.padInfo.top,T=to(a.shape,"float32"),C=1/(f*m*g),$=n.bufferSync(r);for(let e=0;e<c.batchSize;++e)for(let t=0;t<c.inChannels;++t)for(let n=0;n<c.inDepth;++n)for(let s=0;s<c.inHeight;++s)for(let r=0;r<c.inWidth;++r){const a=n-I,i=s-S,o=r-N;let l=0;for(let n=0;n<w;n+=y){const s=(a+n)/h;if(!(s<0||s>=c.outDepth||Math.floor(s)!==s))for(let n=0;n<v;n+=b){const r=(i+n)/p;if(!(r<0||r>=c.outHeight||Math.floor(r)!==r))for(let n=0;n<k;n+=x){const a=(o+n)/d;if(a<0||a>=c.outWidth||Math.floor(a)!==a)continue;l+=$.get(e,s,r,a,t)}}}T.set(l*C,e,n,s,r,t)}return n.makeTensorInfo(T.shape,T.dtype,T.values)}};const wR={kernelName:mt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a}=t,i=a;t$([r,a],"avgPoolGrad");const{filterSize:o,strides:l,pad:u}=s,c=Uu(i.shape,o,l,1,u),h=c.strideHeight,p=c.strideWidth,d=c.filterHeight,f=c.filterWidth,m=c.dilationHeight,g=c.dilationWidth,y=c.effectiveFilterHeight,b=c.effectiveFilterWidth,x=b-1-c.padInfo.left,w=y-1-c.padInfo.top,v=to(i.shape,"float32"),k=1/(d*f),I=n.data.get(r.dataId).values,N=to(r.shape,"float32",I);for(let e=0;e<c.batchSize;++e)for(let t=0;t<c.inChannels;++t)for(let n=0;n<c.inHeight;++n)for(let s=0;s<c.inWidth;++s){const r=n-w,a=s-x;let i=0;for(let n=0;n<y;n+=m){const s=(r+n)/h;if(!(s<0||s>=c.outHeight||Math.floor(s)!==s))for(let n=0;n<b;n+=g){const r=(a+n)/p;if(r<0||r>=c.outWidth||Math.floor(r)!==r)continue;i+=N.get(e,s,r,t)}}v.set(i*k,e,n,s,t)}return n.makeTensorInfo(v.shape,v.dtype,v.values)}};const vR={kernelName:pn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,scale:a,offset:i,mean:o,variance:l}=t;ie(o.shape.length===l.shape.length,(()=>"Batch normalization gradient requires mean and variance to have equal ranks.")),ie(null==i||o.shape.length===i.shape.length,(()=>"Batch normalization gradient requires mean and offset to have equal ranks.")),ie(null==a||o.shape.length===a.shape.length,(()=>"Batch normalization gradient requires mean and scale to have equal ranks.")),t$([r,o,l,a,i],"batchNorm");let{varianceEpsilon:u}=s;null==u&&(u=.001);const c=n.data.get(r.dataId).values,h=n.data.get(o.dataId).values,p=n.data.get(l.dataId).values,d=a?n.data.get(a.dataId).values:new Float32Array([1]),f=i?n.data.get(i.dataId).values:new Float32Array([0]),m=new Float32Array(c.length),g=f.length,y=d.length,b=p.length,x=h.length;let w=0,v=0,k=0,I=0;for(let e=0;e<c.length;++e)m[e]=f[w++]+(c[e]-h[v++])*d[k++]/Math.sqrt(p[I++]+u),w>=g&&(w=0),v>=x&&(v=0),k>=y&&(k=0),I>=b&&(I=0);return n.makeTensorInfo(r.shape,r.dtype,m)}};const kR={kernelName:xt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{blockShape:a,crops:i}=s;t$([r],"batchToSpaceND");const o=a.reduce(((e,t)=>e*t)),l=em(r.shape,a,o),u=tm(l.length,a.length),c=nm(r.shape,a,o),h=sm(i,a.length),p=rm(c,i,a.length),d=UA({inputs:{x:r},backend:n,attrs:{shape:l}}),f=RE({inputs:{x:d},backend:n,attrs:{perm:u}}),m=UA({inputs:{x:f},backend:n,attrs:{shape:c}}),g=tA({inputs:{x:m},backend:n,attrs:{begin:h,size:p}});return n.disposeIntermediateTensorInfo(d),n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(m),g}};const IR={kernelName:wt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,weights:a}=t,{size:i}=s,o=I$(n.data.get(r.dataId).values,n.data.get(a.dataId).values,a.dtype,a.shape,i);return n.makeTensorInfo([i],a.dtype,o)}};const NR={kernelName:It,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{s0:s,s1:r}=t,a=n.data.get(s.dataId).values,i=n.data.get(r.dataId).values,o=tl(Array.from(a),Array.from(i));return n.makeTensorInfo([o.length],"int32",Int32Array.from(o))}},SR=E$(Tt,((e,t)=>{const n=t;return e>n.clipValueMax?n.clipValueMax:e<n.clipValueMin?n.clipValueMin:e})),TR={kernelName:Tt,backendName:"cpu",kernelFunc:SR},CR={kernelName:$t,backendName:"cpu",kernelFunc:e=>{const{x:t}=e.inputs,n=e.backend,s=new Float32Array(ue(t.shape)),r=n.data.get(t.dataId),a=r.complexTensorInfos.real,i=r.complexTensorInfos.imag,o=n.data.get(a.dataId).values,l=n.data.get(i.dataId).values;for(let e=0;e<o.length;e++){const t=o[e],n=l[e];s[e]=Math.hypot(t,n)}return n.makeOutput(s,t.shape,"float32")}};function $R(e){const{inputs:t,backend:n}=e,{input:s}=t,r=n.data.get(s.dataId).complexTensorInfos.imag,a=n.data.get(r.dataId).values;return n.makeTensorInfo(r.shape,r.dtype,a)}const ER={kernelName:xn,backendName:"cpu",kernelFunc:$R};function AR(e){const{inputs:t,backend:n,attrs:s}=e,{axis:r}=s,a=we(r,t[0].shape)[0];Gf(t.map((e=>e.shape)),a);let i=Hf(t.map((e=>e.shape)),a);if(0===ue(i))return n.makeTensorInfo(i,t[0].dtype,[]);const o=t.filter((e=>ue(e.shape)>0));if(1===o.length)return c$({inputs:{x:o[0]},backend:n});if("complex64"===o[0].dtype){const e=o.map((e=>p$({inputs:{input:e},backend:n}))),t=o.map((e=>$R({inputs:{input:e},backend:n}))),s=AR({inputs:e,backend:n,attrs:{axis:a}}),r=AR({inputs:t,backend:n,attrs:{axis:a}}),i=o$({inputs:{real:s,imag:r},backend:n});return e.forEach((e=>n.disposeIntermediateTensorInfo(e))),t.forEach((e=>n.disposeIntermediateTensorInfo(e))),n.disposeIntermediateTensorInfo(s),n.disposeIntermediateTensorInfo(r),i}const l=o.map((e=>{const t=ue(e.shape.slice(a));return UA({inputs:{x:e},backend:n,attrs:{shape:[-1,t]}})})),u=l.map((e=>({vals:n.data.get(e.dataId).values,shape:e.shape})));i=Hf(l.map((e=>e.shape)),1);const c=1===l[0].shape[0],h=D$(u,i,t[0].dtype,c),p=Hf(o.map((e=>e.shape)),a),d=n.makeTensorInfo(p,t[0].dtype,h);return l.forEach((e=>n.disposeIntermediateTensorInfo(e))),d}const RR={kernelName:Et,backendName:"cpu",kernelFunc:AR};function FR(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a}=t,{strides:i,pad:o,dataFormat:l,dilations:u,dimRoundingMode:c}=s;t$([r,a],"conv2d");const h=tc(l),p=Hu(r.shape,a.shape,i,u,o,c,!1,h),d=p.filterHeight,f=p.filterWidth,m=p.dilationHeight,g=p.dilationWidth,y=p.padInfo.left,b=p.padInfo.top,x="channelsLast"===p.dataFormat,w=new pa(p.outShape,r.dtype),v=Oe(r.shape),k=Oe(a.shape),I=v[0],N=x?v[1]:v[2],S=x?v[2]:1,T=x?1:v[1],C=w.strides[0],$=x?w.strides[1]:w.strides[2],E=x?w.strides[2]:1,A=x?1:w.strides[1],R=n.data.get(r.dataId).values,F=n.data.get(a.dataId).values,_=w.values;for(let e=0;e<p.batchSize;++e){const t=e*I,n=e*C;for(let e=0;e<p.outHeight;++e){const s=n+e*$,r=e*p.strideHeight-b;for(let e=0;e<d;++e){const n=r+e*m;if(n<0||n>=p.inHeight)continue;const a=e*k[0],i=t+n*N;for(let e=0;e<p.outWidth;++e){const t=s+e*E,n=e*p.strideWidth-y;for(let e=0;e<f;++e){const s=n+e*g;if(s<0||s>=p.inWidth)continue;const r=i+s*S;let o=a+e*k[1];for(let e=0;e<p.inChannels;++e){const n=R[r+e*T];for(let e=0;e<p.outChannels;++e)_[t+e*A]+=n*F[o+e];o+=p.outChannels}}}}}}return n.makeTensorInfo(w.shape,w.dtype,_)}const _R={kernelName:At,backendName:"cpu",kernelFunc:FR};const DR={kernelName:Rt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,dy:a}=t,{strides:i,pad:o,dataFormat:l,dimRoundingMode:u,filterShape:c}=s;t$([r,a],"conv2dBackpropFilter");const h=tc(l),p=Hu(r.shape,c,i,1,o,u,!1,h),{strideHeight:d,strideWidth:f,filterHeight:m,filterWidth:g}=p,y="channelsLast"===p.dataFormat,b=new pa(p.filterShape,"float32"),x=p.padInfo.left,w=p.padInfo.top,v=n.data.get(r.dataId).values,k=n.data.get(a.dataId).values,I=new pa(r.shape,r.dtype,v),N=new pa(a.shape,a.dtype,k);for(let e=0;e<m;++e){const t=Math.max(0,Math.ceil((w-e)/d)),n=Math.min(p.outHeight,(p.inHeight+w-e)/d);for(let s=0;s<g;++s){const r=Math.max(0,Math.ceil((x-s)/f)),a=Math.min(p.outWidth,(p.inWidth+x-s)/f);for(let i=0;i<p.inChannels;++i)for(let o=0;o<p.outChannels;++o){let l=0;for(let u=0;u<p.batchSize;++u)for(let c=t;c<n;++c){const t=e+c*d-w;for(let e=r;e<a;++e){const n=s+e*f-x;l+=y?I.get(u,t,n,i)*N.get(u,c,e,o):I.get(u,i,t,n)*N.get(u,o,c,e)}}b.set(l,e,s,i,o)}}}return n.makeTensorInfo(b.shape,b.dtype,b.values)}};const OR={kernelName:Ft,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,filter:a}=t,{inputShape:i,strides:o,pad:l,dataFormat:u,dimRoundingMode:c}=s;t$([r,a],"conv2dBackpropInput");const h=Oe(a.shape),p=Oe(r.shape);let d=tc(u);const f=Hu(i,a.shape,o,1,l,c,!1,d),m=new pa(f.inShape,"float32"),g=m.values,y=n.data.get(r.dataId).values,b=n.data.get(a.dataId).values,[x,w,v]=h,{batchSize:k,filterHeight:I,filterWidth:N,inChannels:S,inHeight:T,inWidth:C,outChannels:$,outHeight:E,outWidth:A,strideHeight:R,strideWidth:F}=f;d=f.dataFormat;const _=I-1-f.padInfo.top,D=N-1-f.padInfo.left,O="channelsLast"===d,M=m.strides[0],L=O?m.strides[1]:m.strides[2],z=O?m.strides[2]:1,P=O?1:m.strides[1],B=p[0],W=O?p[1]:p[2],V=O?p[2]:1,U=O?1:p[1];for(let e=0;e<k;++e)for(let t=0;t<S;++t)for(let n=0;n<T;++n){const s=n-_,r=Math.max(0,Math.ceil(s/R)),a=Math.min(E,(I+s)/R);for(let i=0;i<C;++i){const o=i-D,l=Math.max(0,Math.ceil(o/F)),u=Math.min(A,(N+o)/F);let c=0;for(let n=r;n<a;++n){const r=n*R-s;for(let s=l;s<u;++s){const a=B*e+W*n+V*s,i=x*(I-1-r)+w*(N-1-(s*F-o))+v*t;for(let e=0;e<$;++e){c+=y[a+U*e]*b[i+e]}}}g[M*e+L*n+z*i+P*t]=c}}return n.makeTensorInfo(m.shape,m.dtype,m.values)}};const MR={kernelName:_t,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a}=t,{strides:i,pad:o,dilations:l}=s;t$([r,a],"conv3d");const u=ju(r.shape,a.shape,i,l,o),{filterDepth:c,filterHeight:h,filterWidth:p,dilationDepth:d,dilationHeight:f,dilationWidth:m,padInfo:g}=u,y=g.front,b=g.left,x=g.top,w=new pa(u.outShape,r.dtype),v=n.data.get(r.dataId).values,k=n.data.get(a.dataId).values,I=w.values,N=Oe(r.shape),S=Oe(a.shape);for(let e=0;e<u.batchSize;++e){const t=e*N[0],n=e*w.strides[0];for(let e=0;e<u.outDepth;++e){const s=n+e*w.strides[1],r=e*u.strideDepth-y;for(let e=0;e<c;++e){const n=r+e*d;if(n<0||n>=u.inDepth)continue;const a=e*S[0],i=t+n*N[1];for(let e=0;e<u.outHeight;++e){const t=s+e*w.strides[2],n=e*u.strideHeight-x;for(let e=0;e<h;++e){const s=n+e*f;if(s<0||s>=u.inHeight)continue;const r=a+e*S[1],o=i+s*N[2];for(let e=0;e<u.outWidth;++e){const n=t+e*u.outChannels,s=e*u.strideWidth-b;for(let e=0;e<p;++e){const t=s+e*m;if(t<0||t>=u.inWidth)continue;const a=r+e*S[2],i=o+t*u.inChannels;let l=a;for(let e=0;e<u.inChannels;++e){const t=v[i+e];for(let e=0;e<u.outChannels;++e)I[n+e]+=t*k[l+e];l+=u.outChannels}}}}}}}}return n.makeTensorInfo(w.shape,w.dtype,w.values)}};const LR={kernelName:Dt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,dy:a}=t,{strides:i,pad:o,filterShape:l}=s;t$([r,a],"conv3dBackpropFilterV2");const u=Oe(r.shape),c=Oe(a.shape),h=ju(r.shape,l,i,1,o),p=h.strideDepth,d=h.strideHeight,f=h.strideWidth,m=h.filterDepth,g=h.filterHeight,y=h.filterWidth,b=new pa(h.filterShape,"float32"),x=b.values,[w,v,k,I]=b.strides,N=n.data.get(a.dataId).values,[S,T,C,$]=c,E=n.data.get(r.dataId).values,[A,R,F,_]=u,D=h.padInfo.front,O=h.padInfo.left,M=h.padInfo.top;for(let e=0;e<m;++e){const t=Math.max(0,Math.ceil((D-e)/p)),n=Math.min(h.outDepth,(h.inDepth+D-e)/p),s=e*w;for(let r=0;r<g;++r){const a=Math.max(0,Math.ceil((M-r)/d)),i=Math.min(h.outHeight,(h.inHeight+M-r)/d),o=r*v+s;for(let s=0;s<y;++s){const l=Math.max(0,Math.ceil((O-s)/f)),u=Math.min(h.outWidth,(h.inWidth+O-s)/f),c=s*k+o;for(let o=0;o<h.inChannels;++o){const m=o*I+c;for(let c=0;c<h.outChannels;++c){let g=0;for(let m=0;m<h.batchSize;++m){const h=m*A,y=m*S;for(let m=t;m<n;++m){const t=(e+m*p-D)*R+h,n=m*T+y;for(let e=a;e<i;++e){const a=(r+e*d-M)*F+t,i=e*C+n;for(let e=l;e<u;++e){const t=e*$+i;g+=E[(s+e*f-O)*_+a+o]*N[t+c]}}}}x[m+c]=g}}}}}return n.makeTensorInfo(b.shape,b.dtype,b.values)}};const zR={kernelName:Ot,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,filter:a}=t,{pad:i,strides:o,inputShape:l}=s;t$([r],"conv3dBackpropInputV2");const u=Oe(r.shape),c=Oe(a.shape),h=ju(l,a.shape,o,1,i),p=new pa(h.inShape,"float32"),d=p.values,[f,m,g,y]=p.strides,b=n.data.get(r.dataId).values,[x,w,v,k]=u,I=n.data.get(a.dataId).values,[N,S,T,C]=c,{batchSize:$,filterDepth:E,filterHeight:A,filterWidth:R,inChannels:F,inDepth:_,inHeight:D,inWidth:O,outChannels:M,outDepth:L,outHeight:z,outWidth:P,strideDepth:B,strideHeight:W,strideWidth:V}=h,U=E-1-h.padInfo.front,G=A-1-h.padInfo.top,H=R-1-h.padInfo.left;for(let e=0;e<$;++e)for(let t=0;t<F;++t)for(let n=0;n<_;++n){const s=n-U,r=Math.max(0,Math.ceil(s/B)),a=Math.min(L,(E+s)/B);for(let i=0;i<D;++i){const o=i-G,l=Math.max(0,Math.ceil(o/W)),u=Math.min(z,(A+o)/W);for(let c=0;c<O;++c){const h=c-H,p=Math.max(0,Math.ceil(h/V)),$=Math.min(P,(R+h)/V);let F=0;for(let n=r;n<a;++n){const r=n*B-s;for(let s=l;s<u;++s){const a=s*W-o;for(let i=p;i<$;++i){const o=x*e+w*n+v*s+k*i,l=N*(E-1-r)+S*(A-1-a)+T*(R-1-(i*V-h))+C*t;for(let e=0;e<M;++e){F+=b[o+e]*I[l+e]}}}}d[f*e+m*n+g*i+y*c+t]=F}}}return n.makeTensorInfo(p.shape,p.dtype,p.values)}},PR=E$(Mt,(e=>Math.cos(e))),BR={kernelName:Mt,backendName:"cpu",kernelFunc:PR},WR=E$(Lt,(e=>Math.cosh(e))),VR={kernelName:Lt,backendName:"cpu",kernelFunc:WR};const UR={kernelName:Bt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{image:r,boxes:a,boxInd:i}=t,{cropSize:o,method:l,extrapolationValue:u}=s,[c,h,p,d]=r.shape,f=a.shape[0],[m,g]=o,y=to([f,m,g,d],"float32"),b=n.data.get(a.dataId).values,x=n.data.get(i.dataId).values,w=n.data.get(r.dataId).values,v=Oe(r.shape),k=Oe(y.shape);for(let e=0;e<f;e++){const t=4*e,n=b[t],s=b[t+1],r=b[t+2],a=b[t+3],i=x[e];if(i>=c)continue;const o=m>1?(r-n)*(h-1)/(m-1):0,f=g>1?(a-s)*(p-1)/(g-1):0;for(let t=0;t<m;t++){const c=m>1?n*(h-1)+t*o:.5*(n+r)*(h-1);if(c<0||c>h-1)for(let n=0;n<g;n++)for(let s=0;s<d;s++){const r=s+n*k[2]+t*k[1]+e*k[0];y.values[r]=u}else if("bilinear"===l){const n=Math.floor(c),r=Math.ceil(c),o=c-n;for(let l=0;l<g;l++){const c=g>1?s*(p-1)+l*f:.5*(s+a)*(p-1);if(c<0||c>p-1){for(let n=0;n<d;n++){const s=n+l*k[2]+t*k[1]+e*k[0];y.values[s]=u}continue}const h=Math.floor(c),m=Math.ceil(c),b=c-h;for(let s=0;s<d;s++){let a=s+h*v[2]+n*v[1]+i*v[0];const u=w[a];a=s+m*v[2]+n*v[1]+i*v[0];const c=w[a];a=s+h*v[2]+r*v[1]+i*v[0];const p=w[a];a=s+m*v[2]+r*v[1]+i*v[0];const d=u+(c-u)*b,f=p+(w[a]-p)*b;a=s+l*k[2]+t*k[1]+e*k[0],y.values[a]=d+(f-d)*o}}}else for(let n=0;n<g;++n){const r=g>1?s*(p-1)+n*f:.5*(s+a)*(p-1);if(r<0||r>p-1){for(let s=0;s<d;s++){const r=s+n*k[2]+t*k[1]+e*k[0];y.values[r]=u}continue}const o=Math.round(r),l=Math.round(c);for(let s=0;s<d;s++){const r=s+o*v[2]+l*v[1]+i*v[0],a=s+n*k[2]+t*k[1]+e*k[0];y.values[a]=w[r]}}}}return n.makeTensorInfo(y.shape,y.dtype,y.values)}};const GR={kernelName:zt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,exclusive:i,reverse:o}=s;t$(r,"cumprod");const l=th([a],r.shape.length);let u=r;null!=l&&(u=RE({inputs:{x:r},backend:n,attrs:{perm:l}}));const c=sh(1,r.shape.length)[0];if(c!==u.shape.length-1)throw new Error(`backend.cumprod in CPU expects an inner-most axis=${u.shape.length-1} but got axis=${c}`);const h=Sa(u.dtype,"int32"),p=Pe(ue(u.shape),h),d=n.data.get(u.dataId).values,f=u.shape[u.shape.length-1],m=o?(e,t)=>e+f-t-1:(e,t)=>e+t;for(let e=0;e<d.length;e+=f)for(let t=0;t<f;t++){const n=m(e,t);if(0===t)p[n]=i?1:d[n];else{const s=m(e,t-1);p[n]=i?d[s]*p[s]:d[n]*p[s]}}const g=n.makeTensorInfo(u.shape,h,p);if(null!=l){const e=RE({inputs:{x:g},backend:n,attrs:{perm:nh(l)}});return n.disposeIntermediateTensorInfo(g),n.disposeIntermediateTensorInfo(u),e}return g}};const HR={kernelName:Pt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,exclusive:i,reverse:o}=s;t$(r,"cumsum");const l=th([a],r.shape.length);let u=r;null!=l&&(u=RE({inputs:{x:r},backend:n,attrs:{perm:l}}));const c=sh(1,r.shape.length)[0];if(c!==u.shape.length-1)throw new Error(`backend.cumsum in CPU expects an inner-most axis=${u.shape.length-1} but got axis=${c}`);const h=Sa(u.dtype,"int32"),p=Be(ue(u.shape),h),d=n.data.get(u.dataId).values,f=u.shape[u.shape.length-1],m=o?(e,t)=>e+f-t-1:(e,t)=>e+t;for(let e=0;e<d.length;e+=f)for(let t=0;t<f;t++){const n=m(e,t);if(0===t)p[n]=i?0:d[n];else{const s=m(e,t-1);p[n]=i?d[s]+p[s]:d[n]+p[s]}}const g=n.makeTensorInfo(u.shape,h,p);if(null!=l){const e=RE({inputs:{x:g},backend:n,attrs:{perm:nh(l)}});return n.disposeIntermediateTensorInfo(g),n.disposeIntermediateTensorInfo(u),e}return g}};const jR={kernelName:Wt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,weights:a}=t,{size:i,binaryOutput:o}=s;if(1===r.shape.length){const e=I$(n.data.get(r.dataId).values,n.data.get(a.dataId).values,a.dtype,a.shape,i);return n.makeTensorInfo([i],a.dtype,e)}if(2===r.shape.length){const e=N$(n.bufferSync(r),n.bufferSync(a),i,o);return n.makeTensorInfo(e.shape,a.dtype,e.values)}throw new Error(`Error in denseBincount: input must be at most rank 2, but got rank${r.shape.length}.`)}};const qR={kernelName:Vt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{blockSize:a,dataFormat:i}=s;ie("NHWC"===i,(()=>`Only NHWC dataFormat supported on CPU for depthToSpace. Got ${i}`));const o=r.shape[0],l=r.shape[1],u=r.shape[2],c=r.shape[3],h=l*a,p=u*a,d=c/(a*a),f=n.data.get(r.dataId).values,m=new Float32Array(o*h*p*d);let g=0;for(let e=0;e<o;++e)for(let t=0;t<h;++t){const n=Math.floor(t/a),s=t%a;for(let t=0;t<p;++t){const r=Math.floor(t/a),i=(s*a+t%a)*d;for(let t=0;t<d;++t){const s=t+i+c*(r+u*(n+l*e));m[g++]=f[s]}}}return n.makeTensorInfo([o,h,p,d],r.dtype,m)}};function KR(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a}=t,{strides:i,pad:o,dilations:l,dimRoundingMode:u}=s;t$([r,a],"depthwiseConv2DNative");const c=Oe(r.shape),h=Oe(a.shape);let p=l;null==p&&(p=[1,1]),ie(Qu(i,p),(()=>`Error in depthwiseConv2d: Either strides or dilations must be 1. Got strides ${i} and dilations '${p}'`));const d=Hu(r.shape,a.shape,i,p,o,u,!0),{filterHeight:f,filterWidth:m,dilationHeight:g,dilationWidth:y,padInfo:b}=d,x=b.left,w=b.top,v=d.outChannels/d.inChannels,k=new pa(d.outShape,r.dtype),I=n.data.get(r.dataId).values,N=n.data.get(a.dataId).values,S=k.values;for(let e=0;e<d.batchSize;++e){const t=e*c[0],n=e*k.strides[0];for(let e=0;e<d.outHeight;++e){const s=n+e*k.strides[1],r=e*d.strideHeight-w;for(let e=0;e<f;++e){const n=r+e*g;if(n<0||n>=d.inHeight)continue;const a=e*h[0],i=t+n*c[1];for(let e=0;e<d.outWidth;++e){const t=s+e*k.strides[2],n=e*d.strideWidth-x;for(let e=0;e<m;++e){const s=n+e*y;if(s<0||s>=d.inWidth)continue;const r=a+e*h[1],o=i+s*d.inChannels;let l=t,u=r;for(let e=0;e<d.inChannels;++e){const t=I[o+e];for(let e=0;e<v;++e)S[l+e]+=t*N[u+e];l+=v,u+=v}}}}}}return n.makeTensorInfo(k.shape,k.dtype,k.values)}const XR={kernelName:Ut,backendName:"cpu",kernelFunc:KR};const YR={kernelName:Gt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,dy:a}=t,{strides:i,dilations:o,pad:l,dimRoundingMode:u,filterShape:c}=s;t$([r,a],"depthwiseConv2dNativeBackpropFilter");const h=Hu(r.shape,c,i,o,l,u,!0),{strideHeight:p,strideWidth:d,filterHeight:f,filterWidth:m}=h,g=new pa(h.filterShape,"float32"),y=h.padInfo.left,b=h.padInfo.top,x=h.outChannels/h.inChannels,w=n.data.get(r.dataId).values,v=new pa(r.shape,r.dtype,w),k=n.data.get(a.dataId).values,I=new pa(a.shape,a.dtype,k);for(let e=0;e<f;++e){const t=Math.max(0,Math.ceil((b-e)/p)),n=Math.min(h.outHeight,(h.inHeight+b-e)/p);for(let s=0;s<m;++s){const r=Math.max(0,Math.ceil((y-s)/d)),a=Math.min(h.outWidth,(h.inWidth+y-s)/d);for(let i=0;i<h.outChannels;++i){const o=Math.trunc(i/x),l=i%x;let u=0;for(let l=0;l<h.batchSize;++l)for(let c=t;c<n;++c){const t=e+c*p-b;for(let e=r;e<a;++e){const n=s+e*d-y;u+=v.get(l,t,n,o)*I.get(l,c,e,i)}}g.set(u,e,s,o,l)}}}return n.makeTensorInfo(g.shape,g.dtype,g.values)}};const ZR={kernelName:Ht,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,filter:a}=t,{strides:i,dilations:o,pad:l,dimRoundingMode:u,inputShape:c}=s;t$([r,a],"depthwiseConv2DNativeBackpropInput");const h=Oe(r.shape),p=Oe(a.shape),d=Hu(c,a.shape,i,o,l,u,!0),f=new pa(d.inShape,"float32"),m=f.values,[g,y,b]=f.strides,x=n.data.get(r.dataId).values,[w,v,k]=h,I=n.data.get(a.dataId).values,[N,S,T]=p,{batchSize:C,filterHeight:$,filterWidth:E,inChannels:A,inHeight:R,inWidth:F,outChannels:_,outHeight:D,outWidth:O,strideHeight:M,strideWidth:L}=d,z=$-1-d.padInfo.top,P=E-1-d.padInfo.left,B=_/A;for(let e=0;e<C;++e)for(let t=0;t<A;++t)for(let n=0;n<R;++n){const s=n-z,r=Math.max(0,Math.ceil(s/M)),a=Math.min(D,($+s)/M);for(let i=0;i<F;++i){const o=i-P,l=Math.max(0,Math.ceil(o/L)),u=Math.min(O,(E+o)/L);let c=0;for(let n=r;n<a;++n){const r=n*M-s;for(let s=l;s<u;++s){const a=w*e+v*n+k*s,i=N*($-1-r)+S*(E-1-(s*L-o))+T*t;for(let e=0;e<B;++e){c+=x[a+(t*B+e)]*I[i+e]}}}m[g*e+y*n+b*i+t]=c}}return n.makeTensorInfo(f.shape,f.dtype,f.values)}};const JR={kernelName:jt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{x:s}=t,r=ue(s.shape),a=n.data.get(s.dataId).values,i=to([r,r],s.dtype),o=i.values;for(let e=0;e<a.length;e++)o[e*r+e]=a[e];const l=[...s.shape,...s.shape];return n.makeTensorInfo(l,i.dtype,i.values)}},QR={kernelName:qt,backendName:"cpu",kernelFunc:({inputs:e,backend:t,attrs:n})=>{const{x:s,filter:r}=e,{strides:a,pad:i,dilations:o}=n,l=t,u=l.data.get(s.dataId).values,c=s.shape.length,h=l.data.get(r.dataId).values,p=r.shape.length,{batchSize:d,inHeight:f,inWidth:m,inChannels:g,outHeight:y,outWidth:b,padInfo:x,strideHeight:w,strideWidth:v,filterHeight:k,filterWidth:I,dilationHeight:N,dilationWidth:S,outShape:T}=Vu(s.shape,r.shape,a,i,"NHWC",o),C=ue(T),$=T.length,E=Ie(s.dtype,C);for(let e=0;e<d;++e)for(let t=0;t<y;++t){const n=t*w-x.top;for(let a=0;a<b;++a){const i=a*v-x.left;for(let o=0;o<g;++o){let l=Number.MIN_SAFE_INTEGER;for(let t=0;t<k;++t){const a=n+t*N;if(a>=0&&a<f)for(let n=0;n<I;++n){const d=i+n*S;if(d>=0&&d<m){const i=Ue([e,a,d,o],c,Oe(s.shape)),f=Ue([t,n,o],p,Oe(r.shape)),m=u[i]+h[f];m>l&&(l=m)}}}E[Ue([e,t,a,o],$,Oe(T))]=l}}}return{dataId:l.write(Kr(E,s.dtype),T,s.dtype),shape:T,dtype:s.dtype}}},eF={kernelName:Xt,backendName:"cpu",kernelFunc:({inputs:e,backend:t,attrs:n})=>{const{x:s,filter:r,dy:a}=e,{strides:i,pad:o,dilations:l}=n,u=t,c=Le(s.shape,u.data.get(s.dataId).values),h=Le(r.shape,u.data.get(r.dataId).values),{batchSize:p,inHeight:d,inWidth:f,inChannels:m,outHeight:g,outWidth:y,padInfo:b,strideHeight:x,strideWidth:w,filterHeight:v,filterWidth:k,dilationHeight:I,dilationWidth:N,outShape:S}=Vu(s.shape,r.shape,i,o,"NHWC",l);ie(a.rank===S.length,(()=>`Error in ${Xt}, dy must have the same rank as output ${S.length}, but got ${a.rank}`));const T=Le(S,u.data.get(a.dataId).values),C=We(r.shape,r.dtype);for(let e=0;e<p;++e)for(let t=0;t<g;++t){const n=t*x-b.top;for(let s=0;s<y;++s){const r=s*w-b.left;for(let a=0;a<m;++a){let i=Number.MIN_SAFE_INTEGER,o=0,l=0;for(let t=0;t<v;++t){const s=n+t*I;if(s>=0&&s<d)for(let n=0;n<k;++n){const u=r+n*N;if(u>=0&&u<f){const r=c[e][s][u][a]+h[t][n][a];r>i&&(i=r,o=t,l=n)}}}C[o][l][a]+=T[e][t][s][a]}}}return{dataId:u.write(Kr(C,s.dtype),r.shape,r.dtype),shape:r.shape,dtype:r.dtype}}},tF={kernelName:Kt,backendName:"cpu",kernelFunc:({inputs:e,backend:t,attrs:n})=>{const{x:s,filter:r,dy:a}=e,{strides:i,pad:o,dilations:l}=n,u=t,c=Le(s.shape,u.data.get(s.dataId).values),h=Le(r.shape,u.data.get(r.dataId).values),{batchSize:p,inHeight:d,inWidth:f,inChannels:m,outHeight:g,outWidth:y,padInfo:b,strideHeight:x,strideWidth:w,filterHeight:v,filterWidth:k,dilationHeight:I,dilationWidth:N,outShape:S}=Vu(s.shape,r.shape,i,o,"NHWC",l);ie(a.rank===S.length,(()=>`Error in ${Kt}, dy must have the same rank as output ${S.length}, but got ${a.rank}`));const T=Le(S,u.data.get(a.dataId).values),C=We(s.shape,s.dtype);for(let e=0;e<p;++e)for(let t=0;t<g;++t){const n=t*x-b.top;for(let s=0;s<y;++s){const r=s*w-b.left;for(let a=0;a<m;++a){let i=Number.MIN_SAFE_INTEGER,o=n<0?0:n,l=r<0?0:r;for(let t=0;t<v;++t){const s=n+t*I;if(s>=0&&s<d)for(let n=0;n<k;++n){const u=r+n*N;if(u>=0&&u<f){const r=c[e][s][u][a]+h[t][n][a];r>i&&(i=r,o=s,l=u)}}}C[e][o][l][a]+=T[e][t][s][a]}}}return{dataId:u.write(Kr(C,s.dtype),s.shape,s.dtype),shape:s.shape,dtype:s.dtype}}};const nF={kernelName:Yt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{image:r}=t,{canvas:a,options:i}=s,{contextOptions:o,imageOptions:l}=i||{},u=(null==l?void 0:l.alpha)||1,c=(null==o?void 0:o.contextType)||"2d";if("2d"!==c)throw new Error(`Context type ${o.contextType} is not supported by the CPU backend.`);const h=a.getContext(c,(null==o?void 0:o.contextAttributes)||{});if(null==h)throw new Error(`Could not get the context with ${c} type.`);const[p,d]=r.shape.slice(0,2),f=2===r.shape.length?1:r.shape[2],m=n.data.get(r.dataId).values,g="float32"===r.dtype?255:1,y=new Uint8ClampedArray(d*p*4);for(let e=0;e<p*d;++e){const t=[0,0,0,255*u];for(let n=0;n<f;n++){const s=m[e*f+n];if("float32"===r.dtype){if(s<0||s>1)throw new Error(`Tensor values for a float32 Tensor must be in the range [0 - 1] but encountered ${s}.`)}else if("int32"===r.dtype&&(s<0||s>255))throw new Error(`Tensor values for a int32 Tensor must be in the range [0 - 255] but encountered ${s}.`);1===f?(t[0]=s*g,t[1]=s*g,t[2]=s*g):t[n]=s*g}const n=4*e;y[n+0]=Math.round(t[0]),y[n+1]=Math.round(t[1]),y[n+2]=Math.round(t[2]),y[n+3]=Math.round(t[3])}a.width=d,a.height=p;const b=new ImageData(y,d,p);return h.putImageData(b,0,0),r}};function sF(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s;let o;t$(r,"sum"),o="bool"===r.dtype?m$({inputs:{x:r},backend:n,attrs:{dtype:"int32"}}):c$({inputs:{x:r},backend:n});const l=o.shape.length,u=we(a,o.shape),c=th(u,l);let h=u,p=o;null!=c&&(p=RE({inputs:{x:o},backend:n,attrs:{perm:c}}),h=sh(h.length,l)),eh("sum",h,p.shape.length);const[d,f]=Jc(p.shape,h);let m=u$(n,d,Sa(p.dtype,"int32"));const g=ue(f),y=n.data.get(m.dataId).values,b=n.data.get(p.dataId).values;for(let e=0;e<y.length;++e){const t=e*g;let n=0;for(let e=0;e<g;++e)n+=b[t+e];y[e]=n}if(i){const e=m;m=UA({inputs:{x:m},backend:n,attrs:{shape:Qc(m.shape,u)}}),n.disposeIntermediateTensorInfo(e)}return n.disposeIntermediateTensorInfo(o),null!=c&&n.disposeIntermediateTensorInfo(p),m}const rF={kernelName:Ps,backendName:"cpu",kernelFunc:sF};const aF={kernelName:Jt,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{equation:r}=s,a=t,{allDims:i,summedDims:o,idDims:l}=Sm(r,a.length);Cm(i.length,l,a);const{path:u,steps:c}=$m(o,l),h=c.length;let p=null,d=i.length;const f=[];for(let e=0;e<h;++e){for(const t of c[e]){const{permutationIndices:e,expandDims:s}=Tm(d,l[t]);let r;Em(e)?r=a[t]:(r=RE({inputs:{x:a[t]},backend:n,attrs:{perm:e}}),f.push(r));const i=r.shape.slice();for(let e=0;e<s.length;++e)i.splice(s[e],0,1);pe(r.shape,i)||(r=UA({inputs:{x:r},backend:n,attrs:{shape:i}}),f.push(r)),null===p?p=r:(p=IE({inputs:{a:r,b:p},backend:n}),f.push(p))}e<h-1&&(u[e]>=0&&(p=sF({inputs:{x:p},backend:n,attrs:{axis:u[e]-(i.length-d),keepDims:!1}}),f.push(p)),d--)}for(const e of f)e!==p&&n.disposeIntermediateTensorInfo(e);return p}};const iF={kernelName:en,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{dy:s,y:r}=t;t$([s,r],"eluGrad");const a=new Float32Array(ue(r.shape)),i=n.data.get(r.dataId).values,o=n.data.get(s.dataId).values;for(let e=0;e<i.length;++e){const t=i[e];a[e]=t>=0?o[e]:o[e]*(t+1)}return n.makeTensorInfo(r.shape,"float32",a)}},oF=om,lF=lm,uF=um,cF=cm,hF=hm,pF=pm,dF=E$(tn,(e=>{const t=Math.sign(e),n=Math.abs(e),s=1/(1+oF*n);return t*(1-((((pF*s+hF)*s+cF)*s+uF)*s+lF)*s*Math.exp(-n*n))})),fF={kernelName:tn,backendName:"cpu",kernelFunc:dF};function mF(e){const{inputs:t,backend:n,attrs:s}=e,{input:r}=t,{dim:a}=s,i=r.shape.length,o=r.shape.slice();let l=a;return a<0&&(ie(-(i+1)<=a,(()=>`Axis must be in the interval [${-(i+1)}, ${i}]`)),l=i+a+1),o.splice(l,0,1),UA({inputs:{x:r},backend:n,attrs:{shape:o}})}const gF={kernelName:rn,backendName:"cpu",kernelFunc:mF},yF=i$(((e,t)=>e/t)),bF=y$(Zt,yF),xF={kernelName:Zt,backendName:"cpu",kernelFunc:bF};function wF(e,t,n){const s=e.shape,r=s[0],a=s[1],i=n.data.get(e.dataId),o=i.complexTensorInfos.real,l=i.complexTensorInfos.imag,u=[r,a],c=ue(u),h=ke("float32",c),p=ke("float32",c);for(let e=0;e<r;e++){const s=tA({inputs:{x:o},backend:n,attrs:{begin:[e,0],size:[1,a]}}),r=tA({inputs:{x:l},backend:n,attrs:{begin:[e,0],size:[1,a]}}),i=o$({inputs:{real:s,imag:r},backend:n}),{real:u,imag:c}=vF(i,t,n),d=dm(u,c);for(let t=0;t<a;t++){const n=ym(d,t);h[e*a+t]=n.real,p[e*a+t]=n.imag}n.disposeIntermediateTensorInfo(s),n.disposeIntermediateTensorInfo(r),n.disposeIntermediateTensorInfo(i)}const d=n.makeTensorInfo(u,"float32",h),f=n.makeTensorInfo(u,"float32",p),m=o$({inputs:{real:d,imag:f},backend:n});return n.disposeIntermediateTensorInfo(d),n.disposeIntermediateTensorInfo(f),m}function vF(e,t,n){const s=ue(e.shape),r=n.data.get(e.dataId),a=n.data.get(r.complexTensorInfos.real.dataId).values,i=n.data.get(r.complexTensorInfos.imag.dataId).values;if(0==((o=s)&o-1)){const r=kF(a,i,s,t,n),o=[e.shape[0],e.shape[1]];if(t){const e=n.makeTensorInfo(o,"float32",r.real),t=n.makeTensorInfo(o,"float32",r.imag),a=n.makeTensorInfo([],"float32",qr(s,"float32")),i=c$({inputs:{x:a},backend:n}),l=xF.kernelFunc({inputs:{a:e,b:a},backend:n}),u=xF.kernelFunc({inputs:{a:t,b:i},backend:n}),c=n.data.get(l.dataId).values,h=n.data.get(u.dataId).values;return n.disposeIntermediateTensorInfo(e),n.disposeIntermediateTensorInfo(t),n.disposeIntermediateTensorInfo(a),n.disposeIntermediateTensorInfo(i),n.disposeIntermediateTensorInfo(l),n.disposeIntermediateTensorInfo(u),{real:c,imag:h}}return r}{const e=function(e,t,n){const s=new Float32Array(2*t);for(let r=0;r<t;r++){let a=0,i=0;for(let s=0;s<t;s++){const o=wm(r*s,t,n),l=ym(e,s);a+=l.real*o.real-l.imag*o.imag,i+=l.real*o.imag+l.imag*o.real}n&&(a/=t,i/=t),bm(s,a,i,r)}return s}(dm(a,i),s,t);return fm(e)}var o}function kF(e,t,n,s,r){if(1===n)return{real:e,imag:t};const a=dm(e,t),i=n/2,o=mm(a),l=o.real,u=o.imag,c=[l.length],h=r.makeTensorInfo(c,"float32",l),p=r.makeTensorInfo(c,"float32",u),d=o$({inputs:{real:h,imag:p},backend:r}),f=gm(a),m=f.real,g=f.imag,y=[m.length],b=r.makeTensorInfo(y,"float32",m),x=r.makeTensorInfo(y,"float32",g),w=o$({inputs:{real:b,imag:x},backend:r}),v=kF(l,u,i,s,r),k=v.real,I=v.imag,N=[k.length],S=r.makeTensorInfo(N,"float32",k),T=r.makeTensorInfo(N,"float32",I),C=o$({inputs:{real:S,imag:T},backend:r}),$=kF(m,g,i,s,r),E=$.real,A=$.imag,R=[E.length],F=r.makeTensorInfo(R,"float32",E),_=r.makeTensorInfo(R,"float32",A),D=o$({inputs:{real:F,imag:_},backend:r}),O=xm(n,s),M=[O.real.length],L=r.makeTensorInfo(M,"float32",O.real),z=r.makeTensorInfo(M,"float32",O.imag),P=o$({inputs:{real:L,imag:z},backend:r}),B=IE({inputs:{a:P,b:D},backend:r}),W=v$({inputs:{a:C,b:B},backend:r}),V=IA({inputs:{a:C,b:B},backend:r}),U=p$({inputs:{input:W},backend:r}),G=p$({inputs:{input:V},backend:r}),H=$R({inputs:{input:W},backend:r}),j=$R({inputs:{input:V},backend:r}),q=AR({inputs:[U,G],backend:r,attrs:{axis:0}}),K=AR({inputs:[H,j],backend:r,attrs:{axis:0}}),X=r.data.get(q.dataId).values,Y=r.data.get(K.dataId).values;return r.disposeIntermediateTensorInfo(h),r.disposeIntermediateTensorInfo(p),r.disposeIntermediateTensorInfo(d),r.disposeIntermediateTensorInfo(b),r.disposeIntermediateTensorInfo(x),r.disposeIntermediateTensorInfo(w),r.disposeIntermediateTensorInfo(S),r.disposeIntermediateTensorInfo(T),r.disposeIntermediateTensorInfo(C),r.disposeIntermediateTensorInfo(F),r.disposeIntermediateTensorInfo(_),r.disposeIntermediateTensorInfo(D),r.disposeIntermediateTensorInfo(L),r.disposeIntermediateTensorInfo(z),r.disposeIntermediateTensorInfo(P),r.disposeIntermediateTensorInfo(B),r.disposeIntermediateTensorInfo(W),r.disposeIntermediateTensorInfo(V),r.disposeIntermediateTensorInfo(U),r.disposeIntermediateTensorInfo(H),r.disposeIntermediateTensorInfo(G),r.disposeIntermediateTensorInfo(j),r.disposeIntermediateTensorInfo(q),r.disposeIntermediateTensorInfo(K),{real:X,imag:Y}}const IF={kernelName:on,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{input:s}=t,r=ue(s.shape),a=s.shape[s.shape.length-1],i=UA({inputs:{x:s},backend:n,attrs:{shape:[r/a,a]}}),o=wF(i,!1,n),l=UA({inputs:{x:o},backend:n,attrs:{shape:s.shape}});return n.disposeIntermediateTensorInfo(i),n.disposeIntermediateTensorInfo(o),l}};function NF(e){const{backend:t,attrs:n}=e,{shape:s,value:r,dtype:a}=n,i=a||Fe(r),o=Ie(i,ue(s));return function(e,t,n){e.fill(t)}(o,r),t.makeTensorInfo(s,i,o)}const SF={kernelName:ln,backendName:"cpu",kernelFunc:NF};const TF={kernelName:un,backendName:"cpu",kernelFunc:({inputs:e,attrs:t,backend:n})=>{const{image:s}=e,r=n,a=ke(s.dtype,ue(s.shape)),[i,o,l,u]=s.shape,c=r.data.get(s.dataId).values;for(let e=0;e<i;e++){const t=e*l*o*u;for(let e=0;e<o;e++){const n=e*(l*u);for(let e=0;e<l;e++){const s=e*u;for(let r=0;r<u;r++){const i=Math.round(l-e-1),o=t+n+s+r;let h=c[o];if(i>=0&&i<l){h=c[t+n+i*u+r]}a[o]=h}}}}return{dataId:r.write(a,s.shape,s.dtype),shape:s.shape,dtype:s.dtype}}};const CF={kernelName:yr,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a,bias:i,preluActivationWeights:o}=t,{strides:l,pad:u,dataFormat:c,dilations:h,dimRoundingMode:p,activation:d,leakyreluAlpha:f}=s;let m=FR({inputs:{x:r,filter:a},backend:n,attrs:{strides:l,pad:u,dataFormat:c,dilations:h,dimRoundingMode:p}});if(i){const e=m;if("NCHW"===c&&1===i.shape.length&&1!==i.shape[0]){const e=UA({inputs:{x:i},backend:n,attrs:{shape:[i.shape[0],1,1]}});m=v$({inputs:{a:m,b:e},backend:n}),n.disposeIntermediateTensorInfo(e)}else m=v$({inputs:{a:m,b:i},backend:n});n.disposeIntermediateTensorInfo(e)}if(d){const e=m;if("NCHW"===c&&"prelu"===d&&1===o.shape.length&&1!==o.shape[0]){const e=UA({inputs:{x:o},backend:n,attrs:{shape:[o.shape[0],1,1]}});m=VA(n,m,d,e,f),n.disposeIntermediateTensorInfo(e)}else m=VA(n,m,d,o,f);n.disposeIntermediateTensorInfo(e)}return m}};const $F={kernelName:br,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a,bias:i,preluActivationWeights:o}=t,{strides:l,pad:u,dataFormat:c,dilations:h,dimRoundingMode:p,activation:d,leakyreluAlpha:f}=s;let m=KR({inputs:{x:r,filter:a},backend:n,attrs:{strides:l,pad:u,dataFormat:c,dilations:h,dimRoundingMode:p}});if(i){const e=m;m=v$({inputs:{a:m,b:i},backend:n}),n.disposeIntermediateTensorInfo(e)}if(d){const e=m;m=VA(n,m,d,o,f),n.disposeIntermediateTensorInfo(e)}return m}};const EF={kernelName:fn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{params:s,indices:r}=t,a=ue(s.shape),i=r.shape,o=i[i.length-1],[l,u,c,h]=Hl(s,r);if(0===u)return n.makeTensorInfo(l,s.dtype,[]);const p=Y$(n.data.get(r.dataId).values,n.bufferSync(s),s.dtype,u,o,c,h,s.shape,a);return n.makeTensorInfo(l,s.dtype,p.values)}};const AF={kernelName:dn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,indices:a}=t,{axis:i,batchDims:o}=s;t$([r,a],"gatherV2");const l=we(i,r.shape)[0],u=n.data.get(a.dataId).values,c=r.shape[l];for(let e=0;e<u.length;++e){const t=u[e];ie(t<=c-1&&t>=0,(()=>`GatherV2: the index value ${t} is not in [0, ${c-1}]`))}let h=o;null==o&&(h=0);const p=ue(a.shape),d=jm(r,a,l,h),f=UA({inputs:{x:r},backend:n,attrs:{shape:[d.batchSize,d.outerSize,d.dimSize,d.sliceSize]}}),m=UA({inputs:{x:a},backend:n,attrs:{shape:[d.batchSize,p/d.batchSize]}}),g=[d.batchSize,d.outerSize,p/d.batchSize,d.sliceSize],y=n.bufferSync(m),b=Z$(n.bufferSync(f),y,g);return n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(m),n.makeTensorInfo(d.outputShape,b.dtype,b.values)}};const RF={kernelName:bn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{input:s}=t,r=ue(s.shape),a=s.shape[s.shape.length-1],i=UA({inputs:{x:s},backend:n,attrs:{shape:[r/a,a]}}),o=wF(i,!0,n),l=UA({inputs:{x:o},backend:n,attrs:{shape:s.shape}});return n.disposeIntermediateTensorInfo(i),n.disposeIntermediateTensorInfo(o),l}},FF=E$(wn,(e=>Number.isFinite(e)?1:0),"bool"),_F={kernelName:wn,backendName:"cpu",kernelFunc:FF},DF=E$(vn,(e=>Math.abs(e)===1/0?1:0),"bool"),OF={kernelName:vn,backendName:"cpu",kernelFunc:DF},MF=E$(kn,(e=>Number.isNaN(e)?1:0),"bool"),LF={kernelName:kn,backendName:"cpu",kernelFunc:MF};const zF={kernelName:Tn,backendName:"cpu",kernelFunc:function(e){const{backend:t,attrs:n}=e,{start:s,stop:r,num:a}=n,i=cE(s,r,a);return t.makeTensorInfo([i.length],"float32",i)}},PF=E$($n,(e=>Math.log1p(e))),BF={kernelName:$n,backendName:"cpu",kernelFunc:PF},WF=i$(((e,t)=>e&&t)),VF=y$(En,WF,null,"bool"),UF={kernelName:En,backendName:"cpu",kernelFunc:VF},GF=E$(An,(e=>e?0:1),"bool"),HF={kernelName:An,backendName:"cpu",kernelFunc:GF},jF=i$(((e,t)=>e||t)),qF=y$(Rn,jF,null,"bool"),KF={kernelName:Rn,backendName:"cpu",kernelFunc:qF};const XF={kernelName:On,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{depthRadius:a,bias:i,alpha:o,beta:l}=s;t$(r,"LRN");const u=r.shape[3],c=u-1,h=n.data.get(r.dataId).values,p=ue(r.shape),d=new Float32Array(p);function f(e){const t=e%u;let n=e-t+Math.max(0,t-a);const s=e-t+Math.min(t+a,c);let r=0;for(;n<=s;n++){const e=h[n];r+=e*e}return r}for(let e=0;e<p;e++){const t=f(e),n=h[e]*Math.pow(i+o*t,-l);d[e]=n}return n.makeTensorInfo(r.shape,r.dtype,d)}};const YF={kernelName:Mn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,y:a,dy:i}=t,{depthRadius:o,bias:l,alpha:u,beta:c}=s;t$(i,"LRNGrad");const h=ue(i.shape),p=i.shape[3],d=n.data.get(i.dataId).values,f=n.data.get(r.dataId).values,m=n.data.get(a.dataId).values,g=new Float32Array(h),y=h;for(let e=0;e<y;e++){const t=e%p,n=e-t+Math.max(0,t-o),s=e-t+Math.min(p,t+o+1);let r=0;for(let e=n;e<s;e++)r+=Math.pow(f[e],2);r=u*r+l;for(let t=n;t<s;t++){let n=-2*u*c*f[t]*m[e]/r;e===t&&(n+=Math.pow(r,-c)),n*=d[e],g[t]+=n}}return n.makeTensorInfo(i.shape,r.dtype,g)}};function ZF(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{reductionIndices:a,keepDims:i}=s,o=n;let l=r.shape;const u=l.length,c=we(a,l);let h=c;const p=th(h,u);let d=o.data.get(r.dataId).values;if(null!=p){const e=new Array(u);for(let t=0;t<e.length;t++)e[t]=l[p[t]];d=AE(d,l,r.dtype,p,e),h=sh(h.length,u),l=e}t$(r,"max"),eh("max",h,u);const[f,m]=Jc(l,h),g=fE(d,ue(m),f,r.dtype),y=o.write(g,f,r.dtype);let b=f;if(i){b=Qc(f,c)}return{dataId:y,shape:b,dtype:r.dtype}}const JF={kernelName:zn,backendName:"cpu",kernelFunc:ZF};const QF={kernelName:Bn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t;t$(r,"maxPool");const{filterSize:a,strides:i,pad:o,dimRoundingMode:l}=s;ie(Qu(i,1),(()=>`Error in maxPool: Either strides or dilations must be 1. Got strides ${i} and dilations '1'`));const u=Uu(r.shape,a,i,1,o,l);let c;if(1===u.filterWidth&&1===u.filterHeight&&pe(u.inShape,u.outShape))c=c$({inputs:{x:r},backend:n});else{const e=n.data.get(r.dataId).values,t=Oe(r.shape),s=fR(e,r.shape,r.dtype,t,u,"max");c=n.makeTensorInfo(u.outShape,r.dtype,s.values)}return c}};const e_={kernelName:Vn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{filterSize:a,strides:i,pad:o,dimRoundingMode:l,dataFormat:u}=s;t$(r,"maxPool3d");const c=Gu(r.shape,a,i,1,o,l,u),h=gR(n.data.get(r.dataId).values,r.shape,r.dtype,Oe(r.shape),c,"max");return n.makeTensorInfo(h.shape,"float32",h.values)}};const t_={kernelName:Un,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a}=t,{filterSize:i,strides:o,pad:l,dimRoundingMode:u}=s;t$([r,a],"maxPool3DGrad");const c=Gu(a.shape,i,o,1,l,u),h=function(e,t){const n=to(t.outShape,"int32"),s=t.strideDepth,r=t.strideHeight,a=t.strideWidth,i=t.dilationDepth,o=t.dilationHeight,l=t.dilationWidth,u=t.effectiveFilterDepth,c=t.effectiveFilterHeight,h=t.effectiveFilterWidth,p=t.padInfo.front,d=t.padInfo.top,f=t.padInfo.left;for(let m=0;m<t.batchSize;++m)for(let g=0;g<t.inChannels;++g)for(let y=0;y<t.outDepth;++y){const b=y*s-p;let x=b;for(;x<0;)x+=i;const w=Math.min(t.inDepth,u+b);for(let s=0;s<t.outHeight;++s){const u=s*r-d;let p=u;for(;p<0;)p+=o;const v=Math.min(t.inHeight,c+u);for(let r=0;r<t.outWidth;++r){const d=r*a-f;let k=d;for(;k<0;)k+=l;const I=Math.min(t.inWidth,h+d);let N=Number.NEGATIVE_INFINITY,S=-1;for(let t=x;t<w;t+=i){const n=t-b;for(let s=p;s<v;s+=o){const r=s-u;for(let a=k;a<I;a+=l){const i=a-d,o=e.get(m,t,s,a,g);o>=N&&(N=o,S=n*c*h+r*c+i)}}}n.set(S,m,y,s,r,g)}}}return n}(n.bufferSync(a),c),p=c.strideDepth,d=c.strideHeight,f=c.strideWidth,m=c.dilationDepth,g=c.dilationHeight,y=c.dilationWidth,b=c.effectiveFilterDepth,x=c.effectiveFilterHeight,w=c.effectiveFilterWidth,v=b-1-c.padInfo.front,k=w-1-c.padInfo.left,I=x-1-c.padInfo.top,N=to(a.shape,"float32"),S=n.bufferSync(r);for(let e=0;e<c.batchSize;++e)for(let t=0;t<c.inChannels;++t)for(let n=0;n<c.inDepth;++n)for(let s=0;s<c.inHeight;++s)for(let r=0;r<c.inWidth;++r){const a=n-v,i=s-I,o=r-k;let l=0;for(let n=0;n<b;n+=m){const s=(a+n)/p;if(!(s<0||s>=c.outDepth||Math.floor(s)!==s))for(let r=0;r<x;r+=g){const a=(i+r)/d;if(!(a<0||a>=c.outHeight||Math.floor(a)!==a))for(let i=0;i<w;i+=y){const u=(o+i)/f;if(u<0||u>=c.outWidth||Math.floor(u)!==u)continue;const p=b*x*w-1-h.get(e,s,a,u,t)===n*x*w+r*w+i?1:0;if(0===p)continue;l+=S.get(e,s,a,u,t)*p}}}N.set(l,e,n,s,r,t)}return n.makeTensorInfo(N.shape,N.dtype,N.values)}};const n_={kernelName:Wn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a,output:i}=t,o=a;t$([a,i],"maxPoolGrad");const{filterSize:l,strides:u,pad:c,dimRoundingMode:h}=s,p=Uu(o.shape,l,u,1,c,h),d=n.data.get(o.dataId).values,f=to(p.outShape,o.dtype,mR(d,o.shape,o.dtype,p).values),m=p.strideHeight,g=p.strideWidth,y=p.dilationHeight,b=p.dilationWidth,x=p.effectiveFilterHeight,w=p.effectiveFilterWidth,v=w-1-p.padInfo.left,k=x-1-p.padInfo.top,I=to(o.shape,"float32"),N=n.data.get(r.dataId).values,S=to(r.shape,"float32",N);for(let e=0;e<p.batchSize;++e)for(let t=0;t<p.inChannels;++t)for(let n=0;n<p.inHeight;++n)for(let s=0;s<p.inWidth;++s){const r=n-k,a=s-v;let i=0;for(let n=0;n<x;n+=y){const s=(r+n)/m;if(!(s<0||s>=p.outHeight||Math.floor(s)!==s))for(let r=0;r<w;r+=b){const o=(a+r)/g;if(o<0||o>=p.outWidth||Math.floor(o)!==o)continue;const l=x*w-1-f.get(e,s,o,t)===n*w+r?1:0;if(0===l)continue;i+=S.get(e,s,o,t)*l}}I.set(i,e,n,s,t)}return n.makeTensorInfo(I.shape,I.dtype,I.values)}};const s_={kernelName:Gn,backendName:"cpu",kernelFunc:({inputs:e,attrs:t,backend:n})=>{const{x:s}=e,{filterSize:r,strides:a,pad:i,includeBatchInIndex:o}=t,l=n;t$(s,"MaxPoolWithArgmax");const u=l.data.get(s.dataId).values,c=Uu(s.shape,r,a,[1,1],i),[h,p]=function(e,t,n,s,r){const a=fR(e,0,n,Oe(t),r,"max"),i=mR(e,t,n,r,!0,s);return[a.values,i.values]}(u,s.shape,s.dtype,o,c),d=l.write(h,c.outShape,s.dtype),f=l.write(p,c.outShape,s.dtype);return[{dataId:d,shape:c.outShape,dtype:s.dtype},{dataId:f,shape:c.outShape,dtype:"int32"}]}};const r_={kernelName:Hn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s,o=we(a,r.shape),l=ue(Jc(r.shape,o)[1]),u=[],c=n.makeTensorInfo([],"float32",new Float32Array([l]));u.push(c);const h=m$({inputs:{x:r},backend:n,attrs:{dtype:"float32"}});u.push(h);const p=bF({inputs:{a:h,b:c},backend:n});u.push(p);const d=sF({inputs:{x:p},backend:n,attrs:{axis:a,keepDims:i}});return u.forEach((e=>n.disposeIntermediateTensorInfo(e))),d}};const a_={kernelName:jn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s;t$(r,"min");const o=we(a,r.shape);let l=o;const u=th(l,r.shape.length);let c=r;null!=u&&(c=RE({inputs:{x:r},backend:n,attrs:{perm:u}}),l=sh(l.length,r.shape.length)),eh("min",l,c.shape.length);const[h,p]=Jc(c.shape,l),d=ue(p),f=Be(ue(h),c.dtype),m=n.data.get(c.dataId).values;for(let e=0;e<f.length;++e){const t=e*d;let n=m[t];for(let e=0;e<d;++e){const s=m[t+e];(Number.isNaN(s)||s<n)&&(n=s)}f[e]=n}null!=u&&n.disposeIntermediateTensorInfo(c);const g=n.makeTensorInfo(h,c.dtype,f);if(i){const e=UA({inputs:{x:g},backend:n,attrs:{shape:Qc(h,o)}});return n.disposeIntermediateTensorInfo(g),e}return g}};const i_={kernelName:Kn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{paddings:a,mode:i}=s;t$(r,"mirrorPad");const o=a.map(((e,t)=>e[0]+r.shape[t]+e[1])),l=a.map((e=>e[0])),u=a.map(((e,t)=>e[0]+r.shape[t])),c="reflect"===i?0:1,h=n.data.get(r.dataId).values,p=r.shape.length,d=Oe(r.shape),f=ue(o),m=o.length,g=Oe(o),y=ke(r.dtype,f);for(let e=0;e<f;e++){let t=Ge(e,m,g);for(let e=0;e<m;e++)t[e]<l[e]?t[e]=2*l[e]-t[e]-c:t[e]>=u[e]&&(t[e]=2*(u[e]-1)-t[e]+c);t=t.map(((e,t)=>e-l[t]));const n=Ue(t,p,d);y[e]=h[n]}return{dataId:n.write(y,o,r.dtype),shape:o,dtype:r.dtype}}},o_=i$(((e,t)=>{const n=e%t;return e<0&&t<0||e>=0&&t>=0?n:(n+t)%t})),l_=y$(Xn,o_),u_={kernelName:Xn,backendName:"cpu",kernelFunc:l_};function c_(e){const{inputs:t,backend:n,attrs:s}=e,{logits:r}=t,{dim:a}=s,i=r.shape.length;let o=a;if(-1===o&&(o=i-1),o!==i-1)throw Error(`Softmax along a non-last dimension is not yet supported. Logits was rank ${i} and dim was ${o}`);const l=we([o],r.shape),u=ZF({inputs:{x:r},backend:n,attrs:{reductionIndices:l,keepDims:!1}}),c=Qc(u.shape,l),h=UA({inputs:{x:u},backend:n,attrs:{shape:c}}),p=IA({inputs:{a:r,b:h},backend:n}),d=P$({inputs:{x:p},backend:n}),f=sF({inputs:{x:d},backend:n,attrs:{axis:l,keepDims:!1}}),m=UA({inputs:{x:f},backend:n,attrs:{shape:c}}),g=bF({inputs:{a:d,b:m},backend:n});return n.disposeIntermediateTensorInfo(u),n.disposeIntermediateTensorInfo(h),n.disposeIntermediateTensorInfo(p),n.disposeIntermediateTensorInfo(d),n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(m),g}const h_={kernelName:Vs,backendName:"cpu",kernelFunc:c_};const p_={kernelName:Yn,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{logits:r}=t,{numSamples:a,seed:i,normalized:o}=s;t$(r,"multinomial");const l=o?r:c_({inputs:{logits:r},backend:n,attrs:{dim:-1}}),u=l.shape[0],c=l.shape[1],h=n.data.get(l.dataId).values,p=[u,a],d=Be(ue(p),"int32");for(let e=0;e<u;++e){const t=e*c,n=new Float32Array(c-1);n[0]=h[t];for(let e=1;e<n.length;++e)n[e]=n[e-1]+h[t+e];const s=mp.alea(i.toString()),r=e*a;for(let e=0;e<a;++e){const t=s();d[r+e]=n.length;for(let s=0;s<n.length;s++)if(t<n[s]){d[r+e]=s;break}}}return o||n.disposeIntermediateTensorInfo(l),n.makeTensorInfo(p,"int32",d)}},d_=Xd;const f_={kernelName:es,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{boxes:r,scores:a}=t,{maxOutputSize:i,iouThreshold:o,scoreThreshold:l}=s;t$(r,"NonMaxSuppression");const u=n.data.get(r.dataId).values,c=n.data.get(a.dataId).values,{selectedIndices:h}=d_(u,c,i,o,l);return n.makeTensorInfo([h.length],"int32",new Int32Array(h))}},m_=Yd;const g_={kernelName:ts,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{boxes:r,scores:a}=t,{maxOutputSize:i,iouThreshold:o,scoreThreshold:l,padToMaxOutputSize:u}=s;t$(r,"NonMaxSuppressionPadded");const c=n.data.get(r.dataId).values,h=n.data.get(a.dataId).values,{selectedIndices:p,validOutputs:d}=m_(c,h,i,o,l,u);return[n.makeTensorInfo([p.length],"int32",new Int32Array(p)),n.makeTensorInfo([],"int32",new Int32Array([d]))]}},y_=Zd;const b_={kernelName:ns,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{boxes:r,scores:a}=t,{maxOutputSize:i,iouThreshold:o,scoreThreshold:l,softNmsSigma:u}=s;t$(r,"NonMaxSuppressionWithScore");const c=n.data.get(r.dataId).values,h=n.data.get(a.dataId).values,p=i,d=o,f=l,m=u,{selectedIndices:g,selectedScores:y}=y_(c,h,p,d,f,m);return[n.makeTensorInfo([g.length],"int32",new Int32Array(g)),n.makeTensorInfo([y.length],"float32",new Float32Array(y))]}};const x_={kernelName:rs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{indices:r}=t,{dtype:a,depth:i,onValue:o,offValue:l}=s;t$(r,"oneHot");const u=ue(r.shape),c=new Float32Array(u*i);c.fill(l);const h=n.data.get(r.dataId).values;for(let e=0;e<u;++e)h[e]>=0&&h[e]<i&&(c[e*i+h[e]]=o);return n.makeTensorInfo([...r.shape,i],a,c)}};function w_(e){const{inputs:t,backend:n}=e,{x:s}=t;if("string"===s.dtype)throw new Error("zerosLike is not supported for string tensors");if("complex64"===s.dtype){const e=p$({inputs:{input:s},backend:n}),t=w_({inputs:{x:e},backend:n}),r=$R({inputs:{input:s},backend:n}),a=w_({inputs:{x:r},backend:n}),i=o$({inputs:{real:t,imag:a},backend:n});return n.disposeIntermediateTensorInfo(e),n.disposeIntermediateTensorInfo(t),n.disposeIntermediateTensorInfo(r),n.disposeIntermediateTensorInfo(a),i}return NF({backend:n,attrs:{shape:s.shape,value:0,dtype:s.dtype}})}const v_={kernelName:pr,backendName:"cpu",kernelFunc:w_};const k_={kernelName:ss,backendName:"cpu",kernelFunc:function e(t){const{inputs:n,backend:s}=t,{x:r}=n;if("string"===r.dtype)throw new Error("onesLike is not supported for string tensors");if("complex64"===r.dtype){const t=p$({inputs:{input:r},backend:s}),n=e({inputs:{x:t},backend:s}),a=$R({inputs:{input:r},backend:s}),i=w_({inputs:{x:a},backend:s}),o=o$({inputs:{real:n,imag:i},backend:s});return s.disposeIntermediateTensorInfo(t),s.disposeIntermediateTensorInfo(n),s.disposeIntermediateTensorInfo(a),s.disposeIntermediateTensorInfo(i),o}return NF({backend:s,attrs:{shape:r.shape,value:1,dtype:r.dtype}})}};function I_(e){const{inputs:t,backend:n,attrs:s}=e,{axis:r}=s;if(1===t.length)return mF({inputs:{input:t[0]},backend:n,attrs:{dim:r}});const a=t[0].shape,i=t[0].dtype;t.forEach((e=>{oe(a,e.shape,"All tensors passed to stack must have matching shapes"),ie(i===e.dtype,(()=>"All tensors passed to stack must have matching dtypes"))}));const o=[],l=AR({inputs:t.map((e=>{const t=mF({inputs:{input:e},backend:n,attrs:{dim:r}});return o.push(t),t})),backend:n,attrs:{axis:r}});return o.forEach((e=>n.disposeIntermediateTensorInfo(e))),l}const N_={kernelName:as,backendName:"cpu",kernelFunc:I_};const S_={kernelName:is,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{paddings:a,constantValue:i}=s;t$(r,"pad");const o=a.map(((e,t)=>e[0]+r.shape[t]+e[1])),l=a.map((e=>e[0])),u=n.data.get(r.dataId).values,c=ue(r.shape),h=r.shape.length,p=Oe(r.shape),d=ue(o),f=o.length,m=Oe(o),g=ke(r.dtype,d);0!==i&&g.fill(i);for(let e=0;e<c;e++){g[Ue(Ge(e,h,p).map(((e,t)=>e+l[t])),f,m)]=u[e]}return{dataId:n.write(g,o,r.dtype),shape:o,dtype:r.dtype}}},T_=i$(((e,t)=>Math.pow(e,t))),C_=y$(ls,T_),$_={kernelName:ls,backendName:"cpu",kernelFunc:C_};const E_={kernelName:hs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{paramsNestedSplits:r,paramsDenseValues:a,indices:i}=t,{outputRaggedRank:o}=s,l=r.map((e=>n.data.get(e.dataId).values)),u=r.map((e=>e.shape)),c=n.data.get(a.dataId).values,h=n.data.get(i.dataId).values,[p,d,f]=zE(l,u,c,a.shape,a.dtype,h,i.shape),m=p.map((e=>n.makeTensorInfo([e.length],"int32",e))),g=n.makeTensorInfo(f,a.dtype,d);return m.concat([g])}};const A_={kernelName:ps,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{starts:s,limits:r,deltas:a}=t,i=n.data.get(s.dataId).values,o=n.data.get(r.dataId).values,l=n.data.get(a.dataId).values,[u,c]=BE(i,s.shape,s.dtype,o,r.shape,l,a.shape);return[n.makeTensorInfo([u.length],"int32",u),n.makeTensorInfo([c.length],s.dtype,c)]}};const R_={kernelName:ds,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{shape:r,values:a,defaultValue:i,rowPartitionTensors:o}=t,{rowPartitionTypes:l}=s,u=n.data.get(r.dataId).values,c=n.data.get(a.dataId).values,h=n.data.get(i.dataId).values,p=o.map((e=>n.data.get(e.dataId).values)),d=o.map((e=>e.shape)),[f,m]=HE(u,r.shape,c,a.shape,a.dtype,h,i.shape,p,d,l);return n.makeTensorInfo(f,a.dtype,m)}};const F_={kernelName:fs,backendName:"cpu",kernelFunc:function(e){const{backend:t,attrs:n}=e,{start:s,stop:r,dtype:a,step:i}=n,o=jE(s,r,i,a);return t.makeTensorInfo([o.length],a,o)}},__=E$(gs,(e=>1/e)),D_={kernelName:gs,backendName:"cpu",kernelFunc:__};const O_={kernelName:vs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r}=t,{alignCorners:a,halfPixelCenters:i,size:o}=s;t$(r,"resizeBilinear");const l=Oe(r.shape),[u,c]=o,[h,p,d,f]=r.shape,m=n.data.get(r.dataId).values,g=new Float32Array(ue([h,u,c,f])),y=[a&&u>1?p-1:p,a&&c>1?d-1:d],b=[a&&u>1?u-1:u,a&&c>1?c-1:c];let x=0;const w=y[0]/b[0],v=y[1]/b[1];for(let e=0;e<h;e++)for(let t=0;t<u;t++){let n;n=i?w*(t+.5)-.5:w*t;const s=Math.max(0,Math.floor(n)),r=n-s,a=Math.min(p-1,Math.ceil(n)),o=e*l[0]+s*l[1],u=e*l[0]+a*l[1];for(let e=0;e<c;e++){let t;t=i?v*(e+.5)-.5:v*e;const n=Math.max(0,Math.floor(t)),s=t-n,a=Math.min(d-1,Math.ceil(t)),c=o+n*l[2],h=u+n*l[2],p=o+a*l[2],y=u+a*l[2];for(let e=0;e<f;e++){const t=m[c+e],n=m[h+e],a=t+(m[p+e]-t)*s,i=a+(n+(m[y+e]-n)*s-a)*r;g[x++]=i}}}return n.makeTensorInfo([h,u,c,f],"float32",g)}};const M_={kernelName:ks,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r,dy:a}=t,{alignCorners:i}=s;t$([a,r],"resizeBilinearGrad");const o=Oe(r.shape),[l,u,c,h]=r.shape,[,p,d]=a.shape,f=new Float32Array(l*u*c*h),m=[i&&p>1?u-1:u,i&&d>1?c-1:c],g=[i&&p>1?p-1:p,i&&d>1?d-1:d],y=m[0]/g[0],b=m[1]/g[1],x=n.data.get(a.dataId).values;let w=0;for(let e=0;e<l;e++){const t=e*o[0];for(let e=0;e<p;e++){const n=e*y,s=Math.floor(n),r=Math.min(Math.ceil(n),u-1),a=t+s*o[1],i=t+r*o[1],l=n-s,p=1-l;for(let e=0;e<d;e++){const t=e*b,n=Math.floor(t),s=Math.min(Math.ceil(t),c-1),r=t-n,u=1-r,d=a+n*o[2],m=a+s*o[2],g=i+n*o[2],y=i+s*o[2],v=p*u,k=p*r,I=l*u,N=l*r;for(let e=0;e<h;e++){const t=x[w++];f[d+e]+=t*v,f[m+e]+=t*k,f[g+e]+=t*I,f[y+e]+=t*N}}}}return n.makeTensorInfo([l,c,u,h],"float32",f)}};const L_={kernelName:xs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r}=t,{alignCorners:a,halfPixelCenters:i,size:o}=s;t$(r,"resizeNearestNeighbor");const l=Oe(r.shape),[u,c]=o,[h,p,d,f]=r.shape,m=n.data.get(r.dataId).values,g=new Float32Array(h*u*c*f),y=[a&&u>1?p-1:p,a&&c>1?d-1:d],b=[a&&u>1?u-1:u,a&&c>1?c-1:c],x=y[0]/b[0],w=y[1]/b[1];let v=0;for(let e=0;e<h;e++){const t=e*l[0];for(let e=0;e<u;e++){const n=i?x*(e+.5):x*e;let s=Math.min(p-1,a?Math.round(n):Math.floor(n));i&&(s=Math.max(0,s));const r=t+s*l[1];for(let e=0;e<c;e++){const t=i?w*(e+.5):w*e;let n=Math.min(d-1,a?Math.round(t):Math.floor(t));i&&(n=Math.max(0,n));const s=r+n*l[2];for(let e=0;e<f;e++){const t=m[s+e];g[v++]=t}}}}return n.makeTensorInfo([h,u,c,f],r.dtype,g)}};const z_={kernelName:ws,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r,dy:a}=t,{alignCorners:i}=s;t$([a,r],"resizeNearestNeighborGrad");const o=Oe(r.shape),l=Oe(a.shape),[u,c,h,p]=r.shape,[,d,f]=a.shape,m=new Float32Array(u*c*h*p),g=n.data.get(a.dataId).values,y=[i&&d>1?c-1:c,i&&f>1?h-1:h],b=[i&&d>1?d-1:d,i&&f>1?f-1:f],x=y[0]/b[0],w=y[1]/b[1],v=1/x,k=1/w,I=2*Math.ceil(v)+2,N=2*Math.ceil(k)+2;for(let e=0;e<u;e++){const t=e*o[0];for(let e=0;e<c;e++){const n=t+e*o[1],s=Math.floor(e*v),r=Math.floor(s-I/2);for(let s=0;s<h;s++){const a=n+s*o[2],u=Math.floor(s*k),y=Math.floor(u-N/2);for(let n=0;n<p;n++){let o=0;for(let a=0;a<I;a++){const u=a+r;if(u<0||u>=d)continue;const p=t+u*l[1],m=u*x;if(e===Math.min(c-1,i?Math.round(m):Math.floor(m)))for(let e=0;e<N;e++){const t=e+y;if(t<0||t>=f)continue;const r=p+t*l[2],a=t*w;s===Math.min(h-1,i?Math.round(a):Math.floor(a))&&(o+=g[r+n])}}m[a+n]=o}}}}return n.makeTensorInfo(r.shape,r.dtype,m)}};const P_={kernelName:Ns,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{dims:a}=s;t$(r,"reverse");const i=r.shape.length,o=we(a,r.shape);if(0===i)return c$({inputs:{x:r},backend:n});const l=new pa(r.shape,r.dtype),u=n.bufferSync(r);for(let e=0;e<l.size;e++){const t=l.indexToLoc(e),n=t.slice();o.forEach((e=>n[e]=r.shape[e]-1-n[e])),l.set(u.get(...n),...t)}return n.makeTensorInfo(l.shape,l.dtype,l.values)}},B_={kernelName:mr,backendName:"cpu",kernelFunc:({inputs:e,attrs:t,backend:n})=>{const{image:s}=e,{radians:r,fillValue:a,center:i}=t,o=n,l=ke(s.dtype,ue(s.shape)),[u,c,h,p]=s.shape,[d,f]=Qf(i,c,h),m=Math.sin(r),g=Math.cos(r),y=o.data.get(s.dataId).values;for(let e=0;e<u;e++){const t=e*h*c*p;for(let e=0;e<c;e++){const n=e*(h*p);for(let s=0;s<h;s++){const r=s*p;for(let i=0;i<p;i++){const o=[u,e,s,i],b=o[2],x=o[1];let w=(b-d)*g-(x-f)*m,v=(b-d)*m+(x-f)*g;w=Math.round(w+d),v=Math.round(v+f);let k=a;if("number"!=typeof a&&(k=3===i?255:a[i]),w>=0&&w<h&&v>=0&&v<c){k=y[t+v*(h*p)+w*p+i]}l[t+n+r+i]=k}}}}return{dataId:o.write(l,s.shape,s.dtype),shape:s.shape,dtype:s.dtype}}},W_=E$(Ss,(e=>{const t=Math.floor(e);return e-t<.5?Math.floor(e):e-t>.5?Math.ceil(e):t%2==0?t:t+1})),V_={kernelName:Ss,backendName:"cpu",kernelFunc:W_};const U_={kernelName:Cs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{indices:r,updates:a}=t,{shape:i}=s,{sliceRank:o,numUpdates:l,sliceSize:u,strides:c,outputSize:h}=Kl(0,r,i),p=YE(n.bufferSync(r),n.bufferSync(a),i,h,u,l,o,c,0,!0);return n.makeTensorInfo(i,p.dtype,p.values)}};function G_(e,t){let n=0,s=e.length,r=0;for(;n<s;)r=Math.floor((n+s)/2),e[r]<t?n=r+1:s=r;return s}function H_(e,t){let n=0,s=e.length,r=0;for(;n<s;)r=Math.floor((n+s)/2),e[r]<=t?n=r+1:s=r;return s}const j_={kernelName:Es,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{sortedSequence:r,values:a}=t,{side:i}=s,o=function(e,t,n,s,r,a){const i=Ie("int32",n*r);for(let o=0;o<n;++o){const n=e.slice(o*s,(o+1)*s),l=o*r;for(let e=0;e<r;++e)i[l+e]="left"===a?G_(n,t[e+l]):H_(n,t[e+l])}return i}(n.data.get(r.dataId).values,n.data.get(a.dataId).values,r.shape[0],r.shape[1],a.shape[1],i);return n.makeTensorInfo(a.shape,"int32",o)}};const q_={kernelName:As,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{condition:s,t:r,e:a}=t;t$([s,r,a],"select");const i=s.shape.length,o=n.data.get(s.dataId).values,l=n.data.get(r.dataId).values,u=n.data.get(a.dataId).values,c=Sa(r.dtype,a.dtype),h=Be(ue(r.shape),c);let p=0;const d=0===i||i>1||1===r.shape.length?1:ue(r.shape.slice(1));for(let e=0;e<o.length;e++)for(let t=0;t<d;t++)1===o[e]?h[p++]=l[e]:h[p++]=u[e];return n.makeTensorInfo(r.shape,c,h)}},K_=am,X_=im,Y_=E$(Rs,(e=>e>=0?X_*e:K_*(Math.exp(e)-1))),Z_={kernelName:Rs,backendName:"cpu",kernelFunc:Y_},J_=E$(Os,(e=>e<0?-1:e>0?1:0)),Q_={kernelName:Os,backendName:"cpu",kernelFunc:J_},eD=E$(_s,(e=>Math.sin(e))),tD={kernelName:_s,backendName:"cpu",kernelFunc:eD},nD=E$(Ds,(e=>Math.sinh(e))),sD={kernelName:Ds,backendName:"cpu",kernelFunc:nD},rD=Math.log(1.1920928955078125e-7)+2,aD=E$(Ls,(e=>{const t=e>-rD,n=e<rD,s=Math.exp(e);let r;return r=n?s:t?e:Math.log(1+s),r})),iD={kernelName:Ls,backendName:"cpu",kernelFunc:aD};const oD={kernelName:Bs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{blockShape:a,paddings:i}=s;t$([r],"spaceToBatchND");const o=ue(a),l=[[0,0]];l.push(...i);for(let e=1+a.length;e<r.shape.length;++e)l.push([0,0]);const u=S_.kernelFunc({inputs:{x:r},backend:n,attrs:{paddings:l,constantValue:0}}),c=em(u.shape,a,o,!1),h=tm(c.length,a.length,!1),p=nm(u.shape,a,o,!1),d=UA({inputs:{x:u},backend:n,attrs:{shape:c}}),f=RE({inputs:{x:d},backend:n,attrs:{perm:h}}),m=UA({inputs:{x:f},backend:n,attrs:{shape:p}});return n.disposeIntermediateTensorInfo(u),n.disposeIntermediateTensorInfo(d),n.disposeIntermediateTensorInfo(f),m}};const lD={kernelName:Us,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{indices:s,values:r,denseShape:a,defaultValue:i}=t;if(1!==a.shape.length)throw new Error(`Dense shape must be a vector, saw:\n        ${a.shape}`);if(2!==s.shape.length)throw new Error(`Indices must be a matrix, saw:\n        ${s.shape}`);if(1!==r.shape.length)throw new Error(`Values must be a vector, saw:\n        ${r.shape}`);if(0!==i.shape.length)throw new Error(`Default value must be a scalar, saw:\n        ${i.shape}`);const o=n.data.get(s.dataId).values,l=n.data.get(r.dataId).values,u=n.data.get(a.dataId).values,c=n.data.get(i.dataId).values[0],[h,p,d,f,m]=sA(o,s.shape,s.dtype,l,r.dtype,u,c);return[n.makeTensorInfo(p,s.dtype,h),n.makeTensorInfo([p[0]],r.dtype,d),n.makeTensorInfo([f.length],"bool",new Uint8Array(f.map((e=>Number(e))))),n.makeTensorInfo([m.length],s.dtype,new Int32Array(m))]}};const uD={kernelName:Gs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{inputIndices:s,inputShape:r,newShape:a}=t;if(2!==s.shape.length)throw new Error(`Input indices should be a matrix but received shape\n        ${s.shape}`);if(1!==r.shape.length)throw new Error(`Input shape should be a vector but received shape\n        ${r.shape}`);if(1!==a.shape.length)throw new Error(`Target shape should be a vector but received shape ${a.shape}`);const i=Array.from(n.data.get(r.dataId).values),o=n.data.get(s.dataId).values,l=Array.from(n.data.get(a.dataId).values),[u,c,h]=rA(o,s.shape,s.dtype,i,l);return[n.makeTensorInfo(c,s.dtype,u),n.makeTensorInfo([h.length],a.dtype,new Int32Array(h))]}};const cD={kernelName:Hs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{data:s,indices:r,segmentIds:a}=t;if(s.shape.length<1)throw new Error("Data should be at least 1 dimensional but received scalar");if(1!==r.shape.length)throw new Error(`Indices should be a vector but received shape\n          ${r.shape}`);if(1!==a.shape.length)throw new Error(`Segment ids should be a vector but received shape\n          ${a.shape}`);if(r.shape[0]!==a.shape[0])throw new Error("segmentIds and indices should have same size.");const i=n.data.get(s.dataId).values,o=n.data.get(r.dataId).values,l=n.data.get(a.dataId).values,[u,c]=aA(i,s.shape,s.dtype,o,l,!0);return n.makeTensorInfo(c,s.dtype,u)}};const hD={kernelName:js,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{data:s,indices:r,segmentIds:a}=t;if(s.shape.length<1)throw new Error("Data should be at least 1 dimensional but received scalar");if(1!==r.shape.length)throw new Error(`Indices should be a vector but received shape\n         ${r.shape}`);if(1!==a.shape.length)throw new Error(`Segment ids should be a vector but received shape\n         ${a.shape}`);if(r.shape[0]!==a.shape[0])throw new Error("segmentIds and indices should have same size.");const i=n.data.get(s.dataId).values,o=n.data.get(r.dataId).values,l=n.data.get(a.dataId).values,[u,c]=aA(i,s.shape,s.dtype,o,l);return n.makeTensorInfo(c,s.dtype,u)}};const pD={kernelName:qs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{sparseIndices:r,sparseValues:a,defaultValue:i}=t,{outputShape:o}=s,{sliceRank:l,numUpdates:u,sliceSize:c,strides:h,outputSize:p}=Kl(0,r,o),d=!1,f=n.bufferSync(r);let m;switch(a.dtype){case"bool":m=YE(f,n.bufferSync(a),o,p,c,u,l,h,Boolean(n.data.get(i.dataId).values[0]),d);break;case"float32":m=YE(f,n.bufferSync(a),o,p,c,u,l,h,n.data.get(i.dataId).values[0],d);break;case"int32":m=YE(f,n.bufferSync(a),o,p,c,u,l,h,n.data.get(i.dataId).values[0],d);break;case"string":m=YE(f,n.bufferSync(a),o,p,c,u,l,h,Jr(n.data.get(i.dataId).values[0]),d);break;default:throw new Error(`Unsupported type ${a.dtype}`)}return n.makeTensorInfo(o,m.dtype,m.values)}};const dD={kernelName:Ws,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{numOrSizeSplits:a,axis:i}=s,o=we(i,r.shape)[0],l=Rm(r,a,o),u=new Array(r.shape.length).fill(0),c=r.shape.slice();return l.map((e=>{const t=[...c];t[o]=e;const s=tA({inputs:{x:r},backend:n,attrs:{begin:u,size:t}});return u[o]+=e,s}))}},fD={kernelName:Xs,backendName:"cpu",kernelFunc:({inputs:e,backend:t})=>{const{x:n}=e,s=t;t$(n,"square");const r=s.data.get(n.dataId).values,a=new Float32Array(r.length);for(let e=0;e<r.length;++e){const t=r[e];a[e]=t*t}return{dataId:s.write(a,n.shape,n.dtype),shape:n.shape,dtype:n.dtype}}},mD=E$(dr,((e,t)=>{const n=t;return isNaN(e)?NaN:e>0?1:n.alpha})),gD={kernelName:dr,backendName:"cpu",kernelFunc:mD};const yD={kernelName:Zs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{begin:a,end:i,strides:o,beginMask:l,endMask:u,ellipsisMask:c,newAxisMask:h,shrinkAxisMask:p}=s;t$(r,"stridedSlice");const{finalShapeSparse:d,finalShape:f,isIdentity:m,sliceDim0:g,isSimpleSlice:y,begin:b,end:x,strides:w}=pu(r.shape,a,i,o,l,u,c,h,p);let v;if(m)v=UA({inputs:{x:r},backend:n,attrs:{shape:f}});else if(g||y){ie(r.shape.length>=1,(()=>`Input must have rank at least 1, got: ${r.shape.length}`));const e=Ql(b,x,w),t=tA({inputs:{x:r},backend:n,attrs:{begin:b,size:e}});v=UA({inputs:{x:t},backend:n,attrs:{shape:f}}),n.disposeIntermediateTensorInfo(t)}else{const e=mA(d,n.bufferSync(r),w,b);v=n.makeTensorInfo(f,e.dtype,e.values)}return v}};const bD={kernelName:Js,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{separator:r,nGramWidths:a,leftPad:i,rightPad:o,padWidth:l,preserveShortSequences:u}=s,{data:c,dataSplits:h}=t,p=n.data.get(c.dataId).values,d=n.data.get(h.dataId).values,[f,m]=yA(p,d,r,a,i,o,l,u);return[n.makeTensorInfo([f.length],"string",f),n.makeTensorInfo(h.shape,"int32",m)]}};const xD={kernelName:Qs,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{skipEmpty:r}=s,{input:a,delimiter:i}=t;if("string"!==a.dtype)throw new Error("Input must be of datatype string");if(1!==a.shape.length)throw new Error(`Input must be a vector, got shape: ${a.shape}`);if(0!==i.shape.length)throw new Error(`Delimiter must be a scalar, got shape: ${i.shape}`);const o=n.data.get(a.dataId).values,l=n.data.get(i.dataId).values[0],[u,c,h]=xA(o,l,r),p=c.length;return[n.makeTensorInfo([p,2],"int32",u),n.makeTensorInfo([p],"string",c),n.makeTensorInfo([2],"int32",new Int32Array(h))]}};const wD={kernelName:er,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{numBuckets:r}=s,{input:a}=t;if("string"!==a.dtype)throw new Error("Input must be of datatype string");if(r<=0)throw new Error("Number of buckets must be at least 1");const i=wA(n.data.get(a.dataId).values,r);return n.makeTensorInfo(a.shape,"int32",i)}},vD=E$(nr,(e=>Math.tan(e))),kD={kernelName:nr,backendName:"cpu",kernelFunc:vD},ID=E$(sr,(e=>Math.tanh(e)));const ND={kernelName:$s,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n}=e,{tensor:s,indices:r,updates:a}=t,{sliceRank:i,numUpdates:o,sliceSize:l,strides:u,outputSize:c}=Kl(0,r,s.shape),h=n.bufferSync(r),p=n.bufferSync(a),d=n.bufferSync(s),f=YE(h,p,s.shape,c,l,o,i,u,d,!1);return n.makeTensorInfo(s.shape,f.dtype,f.values)}};const SD={kernelName:rr,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{reps:a}=s;t$(r,"tile");const i=SA(n.bufferSync(r),a);return n.makeTensorInfo(i.shape,i.dtype,i.values)}};const TD={kernelName:ar,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{k:a,sorted:i}=s;t$(r,"topk");const o=n.data.get(r.dataId).values,[l,u]=$A(o,r.shape,r.dtype,a,i);return[n.makeTensorInfo(l.shape,l.dtype,l.values),n.makeTensorInfo(u.shape,u.dtype,u.values)]}};const CD={kernelName:ir,backendName:"cpu",kernelFunc:function(e){const{inputs:t,attrs:n,backend:s}=e,{image:r,transforms:a}=t,{interpolation:i,fillMode:o,fillValue:l,outputShape:u}=n,[c,h,p,d]=r.shape,[f,m]=null!=u?u:[h,p],g=[c,f,m,d],y=Oe(r.shape),b=y[0],x=y[1],w=y[2],v=Oe(g),k=v[0],I=v[1],N=v[2],S=ke(r.dtype,ue(g));S.fill(l);const T=s.data.get(r.dataId).values,C=s.data.get(a.dataId).values;for(let e=0;e<c;++e){const t=1===a.shape[0]?C:C.subarray(8*e,8*e+8);for(let n=0;n<f;++n)for(let s=0;s<m;++s)for(let r=0;r<d;++r){let a;const u=t[6]*s+t[7]*n+1;if(0===u)continue;const c=(t[0]*s+t[1]*n+t[2])/u,d=(t[3]*s+t[4]*n+t[5])/u,f=$D(c,p,o),m=$D(d,h,o);switch(i){case"nearest":a=AD(T,h,p,b,x,w,e,m,f,r,l);break;case"bilinear":a=RD(T,h,p,b,x,w,e,m,f,r,l);break;default:throw new Error(`Error in Transform: Expect 'nearest' or 'bilinear', but got ${i}`)}S[e*k+n*I+s*N+r]=a}return s.makeTensorInfo(g,r.dtype,S)}return{dataId:s.write(S,g,r.dtype),shape:r.shape,dtype:r.dtype}}};function $D(e,t,n){switch(n){case"reflect":return function(e,t){let n=e;if(n<0)if(t<=1)n=0;else{const e=2*t;n<e&&(n=e*Math.trunc(-n/e)+n),n=n<-t?n+e:-n-1}else if(n>t-1)if(t<=1)n=0;else{const e=2*t;n-=e*Math.trunc(n/e),n>=t&&(n=e-n-1)}return ee(0,n,t-1)}(e,t);case"wrap":return function(e,t){let n=e;if(n<0)if(t<=1)n=0;else{const e=t-1;n+=t*(Math.trunc(-n/e)+1)}else if(n>t-1)if(t<=1)n=0;else{const e=t-1;n-=t*Math.trunc(n/e)}return ee(0,n,t-1)}(e,t);case"nearest":return function(e,t){return ee(0,e,t-1)}(e,t);default:return function(e,t){return e}(e)}}function ED(e,t,n,s,r,a,i,o,l,u,c){return 0<=o&&o<t&&0<=l&&l<n?e[i*s+o*r+l*a+u]:c}function AD(e,t,n,s,r,a,i,o,l,u,c){return ED(e,t,n,s,r,a,i,Math.round(o),Math.round(l),u,c)}function RD(e,t,n,s,r,a,i,o,l,u,c){const h=Math.floor(o),p=Math.floor(l),d=h+1,f=p+1;return(d-o)*((f-l)*ED(e,t,n,s,r,a,i,h,p,u,c)+(l-p)*ED(e,t,n,s,r,a,i,h,f,u,c))+(o-h)*((f-l)*ED(e,t,n,s,r,a,i,d,p,u,c)+(l-p)*ED(e,t,n,s,r,a,i,d,f,u,c))}const FD={kernelName:lr,backendName:"cpu",kernelFunc:function(e){const{inputs:t,attrs:n,backend:s}=e,{axis:r}=n,{x:a}=t;t$(a,"unique");const i=s.data.get(a.dataId).values,{outputValues:o,outputShape:l,indices:u}=EA(i,r,a.shape,a.dtype);return[s.makeTensorInfo(l,a.dtype,o),s.makeTensorInfo([u.length],"int32",u)]}};const _D={kernelName:ur,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{value:r}=t;let{axis:a}=s;a<0&&(a+=r.shape.length);const i=r.shape.length,o=r.shape[a],l=new Array(i-1);let u=0;for(let e=0;e<i;e++)e!==a&&(l[u++]=r.shape[e]);const c=new Array(i).fill(0),h=r.shape.slice();h[a]=1;const p=new Array(o);for(let e=0;e<p.length;e++){c[a]=e;const t=tA({inputs:{x:r},backend:n,attrs:{begin:c,size:h}});p[e]=UA({inputs:{x:t},backend:n,attrs:{shape:l}}),n.disposeIntermediateTensorInfo(t)}return p}};const DD={kernelName:cr,backendName:"cpu",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,segmentIds:a}=t,{numSegments:i}=s;t$(r,"unsortedSegmentSum");const o=[],l=[],u=r.shape.length-a.shape.length;let c=a;for(let e=0;e<u;++e){const t=mF({inputs:{input:c},backend:n,attrs:{dim:e+1}});c=t,l.push(t)}for(let e=0;e<i;++e){const t=qr(e,"int32"),s=n.makeTensorInfo([],"int32",t),a=M$({inputs:{a:s,b:c},backend:n}),i=m$({inputs:{x:a},backend:n,attrs:{dtype:"float32"}}),u=IE({inputs:{a:i,b:r},backend:n}),h=sF({inputs:{x:u},backend:n,attrs:{axis:0,keepDims:!1}});o.push(h),l.push(s),l.push(a),l.push(i),l.push(u),l.push(h)}const h=I_({inputs:o,backend:n,attrs:{axis:0}});return l.forEach((e=>n.disposeIntermediateTensorInfo(e))),h}},OD=[qA,a$,XA,ZA,k$,JA,QA,eR,tR,nR,rR,iR,lR,hR,dR,yR,bR,xR,wR,jA,vR,kR,IR,C$,NR,g$,_$,TR,l$,CR,RR,_R,DR,OR,MR,LR,zR,BR,VR,UR,GR,HR,jR,qR,XR,YR,ZR,JR,QR,eF,tF,nF,aF,FA,iF,L$,fF,B$,gF,U$,IF,SF,TF,j$,X$,CF,$F,EF,AF,eE,sE,h$,RF,ER,_F,OF,LF,DA,iE,uE,zF,dE,BF,UF,HF,KF,XF,YF,JF,yE,QF,e_,t_,n_,s_,r_,a_,wE,i_,u_,p_,NE,TE,f_,g_,b_,EE,x_,k_,N_,S_,$_,LA,DE,E_,A_,R_,F_,d$,xF,D_,PA,WA,GA,O_,M_,L_,z_,P_,B_,V_,XE,U_,j_,q_,Z_,QE,Q_,tD,sD,nA,h_,iD,oD,lD,uD,cD,hD,pD,dD,lA,fD,hA,fA,gD,yD,bD,xD,wD,NA,rF,kD,{kernelName:sr,backendName:"cpu",kernelFunc:ID},ND,SD,TD,CD,FE,FD,_D,DD,v_];for(const e of OD)Tr(e);const MD={},LD={alpha:!1,antialias:!1,premultipliedAlpha:!1,preserveDrawingBuffer:!1,depth:!1,stencil:!1,failIfMajorPerformanceCaveat:!0};function zD(e,t){MD[e]=t}function PD(e,t){if(!(e in MD)||null!=t){const n=function(e,t){if(1!==e&&2!==e)throw new Error("Cannot get WebGL rendering context, WebGL is disabled.");const n=null==t?function(e){if(Xe().getBool("IS_SAFARI")||"undefined"==typeof OffscreenCanvas||2!==e){if("undefined"!=typeof document)return document.createElement("canvas");throw new Error("Cannot create a canvas in this context")}return new OffscreenCanvas(300,150)}(e):t;n.addEventListener("webglcontextlost",(t=>{t.preventDefault(),delete MD[e]}),!1),Xe().getBool("SOFTWARE_WEBGL_ENABLED")&&(LD.failIfMajorPerformanceCaveat=!1);if(1===e)return n.getContext("webgl",LD)||n.getContext("experimental-webgl",LD);return n.getContext("webgl2",LD)}(e,t);if(null===n)return console.log("Could not get context for WebGL version",e),null;MD[e]=n}const n=MD[e];return null==n||n.isContextLost()?(delete MD[e],PD(e)):(n.disable(n.DEPTH_TEST),n.disable(n.STENCIL_TEST),n.disable(n.BLEND),n.disable(n.DITHER),n.disable(n.POLYGON_OFFSET_FILL),n.disable(n.SAMPLE_COVERAGE),n.enable(n.SCISSOR_TEST),n.enable(n.CULL_FACE),n.cullFace(n.BACK),MD[e])}var BD,WD,VD;function UD(e,t){return[t,e]}function GD(e){const t=ue(e);return me(Math.ceil(t/4))}function HD(e,t){return[Math.max(1,Math.ceil(t/2)),Math.max(1,Math.ceil(e/2))]}function jD(e,t){const n=e;let s,r,a,i,o,l,u,c,h,p;return 2===Xe().getNumber("WEBGL_VERSION")?(s=n.R32F,r=n.R16F,a=n.RGBA16F,i=n.RGBA32F,o=n.RED,u=4,c=1,h=n.HALF_FLOAT,p=n.FLOAT,l=n.RGBA8):(s=e.RGBA,r=e.RGBA,a=e.RGBA,i=n.RGBA,o=e.RGBA,u=4,c=4,h=null!=t?t.HALF_FLOAT_OES:null,p=e.FLOAT,l=e.RGBA),{internalFormatFloat:s,internalFormatHalfFloat:r,internalFormatPackedHalfFloat:a,internalFormatPackedFloat:i,textureFormatFloat:o,downloadTextureFormat:l,downloadUnpackNumChannels:u,defaultNumChannels:c,textureTypeHalfFloat:h,textureTypeFloat:p}}function qD(e,t){const n=t();return Xe().getBool("DEBUG")&&function(e){const t=e.getError();if(t!==e.NO_ERROR)throw new Error("WebGL Error: "+ZD(e,t))}(e),n}!function(e){e[e.DENSE=0]="DENSE",e[e.SHARED_BATCH=1]="SHARED_BATCH"}(BD||(BD={})),function(e){e[e.RENDER=0]="RENDER",e[e.UPLOAD=1]="UPLOAD",e[e.PIXELS=2]="PIXELS",e[e.DOWNLOAD=3]="DOWNLOAD"}(WD||(WD={})),function(e){e[e.UNPACKED_FLOAT16=0]="UNPACKED_FLOAT16",e[e.UNPACKED_FLOAT32=1]="UNPACKED_FLOAT32",e[e.PACKED_4X1_UNSIGNED_BYTE=2]="PACKED_4X1_UNSIGNED_BYTE",e[e.PACKED_2X2_FLOAT32=3]="PACKED_2X2_FLOAT32",e[e.PACKED_2X2_FLOAT16=4]="PACKED_2X2_FLOAT16"}(VD||(VD={}));const KD=5.96e-8,XD=65504;function YD(e){return!!(Xe().getBool("WEBGL_RENDER_FLOAT32_ENABLED")||0===e||KD<Math.abs(e)&&Math.abs(e)<XD)}function ZD(e,t){switch(t){case e.NO_ERROR:return"NO_ERROR";case e.INVALID_ENUM:return"INVALID_ENUM";case e.INVALID_VALUE:return"INVALID_VALUE";case e.INVALID_OPERATION:return"INVALID_OPERATION";case e.INVALID_FRAMEBUFFER_OPERATION:return"INVALID_FRAMEBUFFER_OPERATION";case e.OUT_OF_MEMORY:return"OUT_OF_MEMORY";case e.CONTEXT_LOST_WEBGL:return"CONTEXT_LOST_WEBGL";default:return`Unknown error code ${t}`}}function JD(e,t){return IO(e,(()=>e.getExtension(t)),'Extension "'+t+'" not supported on this browser.')}function QD(e,t){const n=IO(e,(()=>e.createShader(e.VERTEX_SHADER)),"Unable to create vertex WebGLShader.");if(qD(e,(()=>e.shaderSource(n,t))),qD(e,(()=>e.compileShader(n))),!1===e.getShaderParameter(n,e.COMPILE_STATUS))throw console.log(e.getShaderInfoLog(n)),new Error("Failed to compile vertex shader.");return n}function eO(e,t){const n=IO(e,(()=>e.createShader(e.FRAGMENT_SHADER)),"Unable to create fragment WebGLShader.");if(qD(e,(()=>e.shaderSource(n,t))),qD(e,(()=>e.compileShader(n))),Xe().get("ENGINE_COMPILE_ONLY"))return n;if(!1===e.getShaderParameter(n,e.COMPILE_STATUS))throw nO(t,e.getShaderInfoLog(n)),new Error("Failed to compile fragment shader.");return n}const tO=/ERROR: [0-9]+:([0-9]+):/g;function nO(e,t){const n=tO.exec(t);if(null==n)return console.log(`Couldn't parse line number in error: ${t}`),void console.log(e);const s=+n[1],r=e.split("\n"),a=r.length.toString().length+2,i=r.map(((e,t)=>ye((t+1).toString(),a)+e));let o=0;for(let e=0;e<i.length;e++)o=Math.max(i[e].length,o);const l=i.slice(0,s-1),u=i.slice(s-1,s),c=i.slice(s);console.log(l.join("\n")),console.log(t.split("\n")[0]),console.log(`%c ${ye(u[0],o)}`,"border:1px solid red; background-color:#e3d2d2; color:#a61717"),console.log(c.join("\n"))}function sO(e){return IO(e,(()=>e.createProgram()),"Unable to create WebGLProgram.")}function rO(e,t){if(qD(e,(()=>e.linkProgram(t))),!Xe().get("ENGINE_COMPILE_ONLY")&&!1===e.getProgramParameter(t,e.LINK_STATUS))throw console.log(e.getProgramInfoLog(t)),new Error("Failed to link vertex and fragment shaders.")}function aO(e,t){if(qD(e,(()=>e.validateProgram(t))),!1===e.getProgramParameter(t,e.VALIDATE_STATUS))throw console.log(e.getProgramInfoLog(t)),new Error("Shader program validation failed.")}function iO(e,t){const n=IO(e,(()=>e.createBuffer()),"Unable to create WebGLBuffer");return qD(e,(()=>e.bindBuffer(e.ARRAY_BUFFER,n))),qD(e,(()=>e.bufferData(e.ARRAY_BUFFER,t,e.STATIC_DRAW))),n}function oO(e,t){const n=IO(e,(()=>e.createBuffer()),"Unable to create WebGLBuffer");return qD(e,(()=>e.bindBuffer(e.ELEMENT_ARRAY_BUFFER,n))),qD(e,(()=>e.bufferData(e.ELEMENT_ARRAY_BUFFER,t,e.STATIC_DRAW))),n}function lO(){return 2===Xe().getNumber("WEBGL_VERSION")?1:4}function uO(e){return IO(e,(()=>e.createTexture()),"Unable to create WebGLTexture.")}function cO(e,t){const n=Xe().getNumber("WEBGL_MAX_TEXTURE_SIZE");if(e<=0||t<=0){throw new Error("Requested texture size "+`[${e}x${t}]`+" is invalid.")}if(e>n||t>n){throw new Error("Requested texture size "+`[${e}x${t}]`+" greater than WebGL maximum on this browser / GPU "+`[${n}x${n}]`+".")}}function hO(e){return IO(e,(()=>e.createFramebuffer()),"Unable to create WebGLFramebuffer.")}function pO(e,t,n,s,r,a,i){const o=e.getAttribLocation(t,n);return-1!==o&&(qD(e,(()=>e.bindBuffer(e.ARRAY_BUFFER,s))),qD(e,(()=>e.vertexAttribPointer(o,r,e.FLOAT,!1,a,i))),qD(e,(()=>e.enableVertexAttribArray(o))),!0)}function dO(e,t,n){NO(e,n),qD(e,(()=>e.activeTexture(e.TEXTURE0+n))),qD(e,(()=>e.bindTexture(e.TEXTURE_2D,t)))}function fO(e,t){NO(e,t),qD(e,(()=>e.activeTexture(e.TEXTURE0+t))),qD(e,(()=>e.bindTexture(e.TEXTURE_2D,null)))}function mO(e,t,n){return IO(e,(()=>e.getUniformLocation(t,n)),'uniform "'+n+'" not present in program.')}function gO(e,t,n){return e.getUniformLocation(t,n)}function yO(e,t,n,s){qD(e,(()=>dO(e,t,s))),qD(e,(()=>e.uniform1i(n,s)))}function bO(e){qD(e,(()=>e.bindFramebuffer(e.FRAMEBUFFER,null))),qD(e,(()=>e.viewport(0,0,e.canvas.width,e.canvas.height))),qD(e,(()=>e.scissor(0,0,e.canvas.width,e.canvas.height)))}function xO(e,t,n){qD(e,(()=>e.bindFramebuffer(e.FRAMEBUFFER,n))),qD(e,(()=>e.framebufferTexture2D(e.FRAMEBUFFER,e.COLOR_ATTACHMENT0,e.TEXTURE_2D,t,0)))}function wO(e,t){qD(e,(()=>e.bindFramebuffer(e.FRAMEBUFFER,t))),qD(e,(()=>e.framebufferTexture2D(e.FRAMEBUFFER,e.COLOR_ATTACHMENT0,e.TEXTURE_2D,null,0)))}function vO(e){const t=e.checkFramebufferStatus(e.FRAMEBUFFER);if(t!==e.FRAMEBUFFER_COMPLETE)throw new Error("Error binding framebuffer: "+kO(e,t))}function kO(e,t){switch(t){case e.FRAMEBUFFER_INCOMPLETE_ATTACHMENT:return"FRAMEBUFFER_INCOMPLETE_ATTACHMENT";case e.FRAMEBUFFER_INCOMPLETE_MISSING_ATTACHMENT:return"FRAMEBUFFER_INCOMPLETE_MISSING_ATTACHMENT";case e.FRAMEBUFFER_INCOMPLETE_DIMENSIONS:return"FRAMEBUFFER_INCOMPLETE_DIMENSIONS";case e.FRAMEBUFFER_UNSUPPORTED:return"FRAMEBUFFER_UNSUPPORTED";default:return`unknown error ${t}`}}function IO(e,t,n){const s=qD(e,(()=>t()));if(null==s)throw new Error(n);return s}function NO(e,t){const n=e.MAX_COMBINED_TEXTURE_IMAGE_UNITS-1,s=t+e.TEXTURE0;if(s<e.TEXTURE0||s>n){throw new Error(`textureUnit must be in ${`[gl.TEXTURE0, gl.TEXTURE${n}]`}.`)}}function SO(e,t=2){return ue(e.slice(0,e.length-t))}function TO(e){if(0===e.length)throw Error("Cannot get rows and columns of an empty shape array.");return[e.length>1?e[e.length-2]:1,e[e.length-1]]}function CO(e){let t=[1,1,1];return 0===e.length||1===e.length&&1===e[0]||(t=[SO(e),...TO(e)]),t}function $O(e,t=!1){let n=Xe().getNumber("WEBGL_MAX_TEXTURE_SIZE"),s=Xe().getNumber("WEBGL_MAX_SIZE_FOR_NARROW_TEXTURE");if(s===1/0&&Xe().getBool("WEBGL_AUTO_SQUARIFY_NARROW_TEXTURE_SHAPE")&&(s=n/2),t&&(n*=2,s*=2,1===(e=e.map(((t,n)=>n>=e.length-2?te(e[n]):e[n]))).length&&(e=[2,e[0]])),2!==e.length){const t=ve(e);e=t.newShape}let r=ue(e),a=null;e.length<=1&&r<=n?a=[1,r]:2===e.length&&e[0]<=n&&e[1]<=n?a=e:3===e.length&&e[0]*e[1]<=n&&e[2]<=n?a=[e[0]*e[1],e[2]]:3===e.length&&e[0]<=n&&e[1]*e[2]<=n?a=[e[0],e[1]*e[2]]:4===e.length&&e[0]*e[1]*e[2]<=n&&e[3]<=n?a=[e[0]*e[1]*e[2],e[3]]:4===e.length&&e[0]<=n&&e[1]*e[2]*e[3]<=n&&(a=[e[0],e[1]*e[2]*e[3]]);const i=null!=a&&Math.max(...a)>s&&Math.min(...a)<=(t?2:1)&&Math.min(...a)>0;if(null==a||i)if(t){const t=SO(e);let n=2,s=2;e.length&&([n,s]=TO(e)),r=t*(n/2)*(s/2),a=me(r).map((e=>2*e))}else a=me(r);return a}function EO(e){return e%2==0}function AO(e,t){if(pe(e=e.slice(-2),t=t.slice(-2)))return!0;if(!e.length||!t.length)return!0;if(0===e[0]||0===e[1]||0===t[0]||0===t[1])return!0;if(e.length!==t.length){const n=e[e.length-1],s=t[t.length-1];if(n===s)return!0;if(EO(n)&&EO(s)&&(1===e[0]||1===t[0]))return!0}return e[1]===t[1]&&EO(e[0])&&EO(t[0])}let RO,FO;function _O(e){if(null==RO){const t=PD(e);RO=t.getParameter(t.MAX_TEXTURE_SIZE)}return RO}function DO(){RO=null}function OO(){FO=null}function MO(e){if(null==FO){const t=PD(e);FO=t.getParameter(t.MAX_TEXTURE_IMAGE_UNITS)}return Math.min(16,FO)}function LO(e){if(0===e)return 0;let t;const n=PD(e);return t=zO(n,"EXT_disjoint_timer_query_webgl2")&&2===e?2:zO(n,"EXT_disjoint_timer_query")?1:0,t}function zO(e,t){return null!=e.getExtension(t)}function PO(e){try{if(null!=PD(e))return!0}catch(e){return console.log("Error when getting WebGL context: ",e),!1}return!1}function BO(e){if(0===e)return!1;const t=PD(e);if(1===e){if(!zO(t,"OES_texture_float"))return!1}else if(!zO(t,"EXT_color_buffer_float"))return!1;return VO(t)}function WO(e){if(0===e)return!1;const t=PD(e);if(1!==e){if(zO(t,"EXT_color_buffer_float"))return VO(t);const e="EXT_color_buffer_half_float";if(zO(t,e)){const n=t.getExtension(e);return function(e,t){const n=jD(e,t),s=e.createTexture();e.bindTexture(e.TEXTURE_2D,s);const r=1,a=1;e.texImage2D(e.TEXTURE_2D,0,n.internalFormatHalfFloat,r,a,0,n.textureFormatFloat,n.textureTypeHalfFloat,null);const i=e.createFramebuffer();e.bindFramebuffer(e.FRAMEBUFFER,i),e.framebufferTexture2D(e.FRAMEBUFFER,e.COLOR_ATTACHMENT0,e.TEXTURE_2D,s,0);const o=e.checkFramebufferStatus(e.FRAMEBUFFER)===e.FRAMEBUFFER_COMPLETE;return e.bindTexture(e.TEXTURE_2D,null),e.bindFramebuffer(e.FRAMEBUFFER,null),e.deleteTexture(s),e.deleteFramebuffer(i),o}(t,n)}return!1}if(!zO(t,"OES_texture_float"))return!1;if(!zO(t,"WEBGL_color_buffer_float"))return!1;return VO(t)}function VO(e){const t=jD(e),n=e.createTexture();e.bindTexture(e.TEXTURE_2D,n);e.texImage2D(e.TEXTURE_2D,0,t.internalFormatFloat,1,1,0,t.textureFormatFloat,t.textureTypeFloat,null);const s=e.createFramebuffer();e.bindFramebuffer(e.FRAMEBUFFER,s),e.framebufferTexture2D(e.FRAMEBUFFER,e.COLOR_ATTACHMENT0,e.TEXTURE_2D,n,0);const r=e.checkFramebufferStatus(e.FRAMEBUFFER)===e.FRAMEBUFFER_COMPLETE;return e.bindTexture(e.TEXTURE_2D,null),e.bindFramebuffer(e.FRAMEBUFFER,null),e.deleteTexture(n),e.deleteFramebuffer(s),r}function UO(e){if(2!==e)return!1;return null!=PD(e).fenceSync}function GO(e,t){Array.isArray(e)||(e=[e]),e.forEach((e=>{null!=e&&ie("complex64"!==e.dtype,(()=>`${t} does not support complex64 tensors in the WebGL backend.`))}))}const HO=Xe();function jO(){let e,t,n,s,r,a,i,o,l,u;return 2===Xe().getNumber("WEBGL_VERSION")?(e="#version 300 es",t="in",n="out",s="in",r="texture",a="outputColor",i="out vec4 outputColor;",o=Xe().getBool("WEBGL2_ISNAN_CUSTOM")?"\n      bool isnan_custom(float val) {\n        uint floatToUint = floatBitsToUint(val);\n        return (floatToUint & 0x7fffffffu) > 0x7f800000u;\n      }\n\n      bvec4 isnan_custom(vec4 val) {\n        return bvec4(isnan_custom(val.x),\n          isnan_custom(val.y), isnan_custom(val.z), isnan_custom(val.w));\n      }\n\n      #define isnan(value) isnan_custom(value)\n    ":"",l="",u="\n      #define round(value) newRound(value)\n      int newRound(float value) {\n        return int(floor(value + 0.5));\n      }\n\n      ivec4 newRound(vec4 value) {\n        return ivec4(floor(value + vec4(0.5)));\n      }\n    "):(e="",t="attribute",n="varying",s="varying",r="texture2D",a="gl_FragColor",i="",o="\n      #define isnan(value) isnan_custom(value)\n      bool isnan_custom(float val) {\n        return (val > 0. || val < 1. || val == 0.) ? false : true;\n      }\n      bvec4 isnan_custom(vec4 val) {\n        return bvec4(isnan(val.x), isnan(val.y), isnan(val.z), isnan(val.w));\n      }\n    ",l="\n      uniform float INFINITY;\n\n      bool isinf(float val) {\n        return abs(val) == INFINITY;\n      }\n      bvec4 isinf(vec4 val) {\n        return equal(abs(val), vec4(INFINITY));\n      }\n    ",u="\n      int round(float value) {\n        return int(floor(value + 0.5));\n      }\n\n      ivec4 round(vec4 value) {\n        return ivec4(floor(value + vec4(0.5)));\n      }\n    "),{version:e,attribute:t,varyingVs:n,varyingFs:s,texture2D:r,output:a,defineOutput:i,defineSpecialNaN:o,defineSpecialInf:l,defineRound:u}}function qO(e,t,n="index"){const s=Oe(t);return s.map(((t,r)=>`${`int ${e[r]} = ${n} / ${t}`}; ${r===s.length-1?`int ${e[r+1]} = ${n} - ${e[r]} * ${t}`:`index -= ${e[r]} * ${t}`};`)).join("")}function KO(e,t,n="index"){const s=Oe(t);return s.map(((t,r)=>`${`int ${e[r]} = ${n} / outShapeStrides[${r}]`}; ${r===s.length-1?`int ${e[r+1]} = ${n} - ${e[r]} * outShapeStrides[${r}]`:`index -= ${e[r]} * outShapeStrides[${r}]`};`)).join("")}function XO(e,t,n="index"){const s=function(e,t){const n=e.length,s=e.map((e=>`${t}[${e}]`)),r=new Array(n-1);r[n-2]=s[n-1];for(let e=n-3;e>=0;--e)r[e]=`(${r[e+1]} * ${s[e+1]})`;return r}(e.map(((e,t)=>t)),t);return s.map(((t,r)=>`${`int ${e[r]} = ${n} / ${s[r]}`}; ${r===s.length-1?`int ${e[r+1]} = ${n} - ${e[r]} * ${s[r]}`:`index -= ${e[r]} * ${s[r]}`};`)).join("")}function YO(e){const t=Oe(e).map((e=>e.toString()));return`\n  int getFlatIndex(ivec3 coords) {\n    return coords.x * ${t[0]} + coords.y * ${t[1]} + coords.z;\n  }\n`}HO.registerFlag("HAS_WEBGL",(()=>HO.getNumber("WEBGL_VERSION")>0)),HO.registerFlag("WEBGL_VERSION",(()=>PO(2)?2:PO(1)?1:0)),HO.registerFlag("WEBGL_CHECK_NUMERICAL_PROBLEMS",(()=>!1)),HO.registerFlag("WEBGL_BUFFER_SUPPORTED",(()=>2===HO.get("WEBGL_VERSION"))),HO.registerFlag("WEBGL_CPU_FORWARD",(()=>!0)),HO.registerFlag("WEBGL_FORCE_F16_TEXTURES",(()=>!1)),HO.registerFlag("WEBGL_PACK",(()=>HO.getBool("HAS_WEBGL"))),HO.registerFlag("WEBGL_PACK_NORMALIZATION",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_PACK_CLIP",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_PACK_DEPTHWISECONV",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_PACK_BINARY_OPERATIONS",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_PACK_UNARY_OPERATIONS",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_PACK_ARRAY_OPERATIONS",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_PACK_IMAGE_OPERATIONS",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_PACK_REDUCE",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_LAZILY_UNPACK",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_CONV_IM2COL",(()=>HO.getBool("WEBGL_PACK"))),HO.registerFlag("WEBGL_MAX_TEXTURE_SIZE",(()=>_O(HO.getNumber("WEBGL_VERSION")))),HO.registerFlag("WEBGL_MAX_TEXTURES_IN_SHADER",(()=>MO(HO.getNumber("WEBGL_VERSION")))),HO.registerFlag("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION",(()=>{const e=HO.getNumber("WEBGL_VERSION");return 0===e?0:LO(e)})),HO.registerFlag("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_RELIABLE",(()=>HO.getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION")>0&&!Va())),HO.registerFlag("WEBGL_RENDER_FLOAT32_CAPABLE",(()=>BO(HO.getNumber("WEBGL_VERSION")))),HO.registerFlag("WEBGL_RENDER_FLOAT32_ENABLED",(()=>!HO.getBool("WEBGL_FORCE_F16_TEXTURES")&&HO.getBool("WEBGL_RENDER_FLOAT32_CAPABLE"))),HO.registerFlag("WEBGL_DOWNLOAD_FLOAT_ENABLED",(()=>WO(HO.getNumber("WEBGL_VERSION")))),HO.registerFlag("WEBGL_FENCE_API_ENABLED",(()=>UO(HO.getNumber("WEBGL_VERSION")))),HO.registerFlag("WEBGL_SIZE_UPLOAD_UNIFORM",(()=>HO.getBool("WEBGL_RENDER_FLOAT32_ENABLED")?4:0)),HO.registerFlag("WEBGL_DELETE_TEXTURE_THRESHOLD",(()=>-1),(e=>{if(e<0&&-1!==e)throw new Error(`WEBGL_DELETE_TEXTURE_THRESHOLD must be -1 (indicating never delete) or at least 0, but got ${e}.`)})),HO.registerFlag("WEBGL_FLUSH_THRESHOLD",(()=>Va()?1:-1),(e=>{if(e<0&&-1!==e)throw new Error(`WEBGL_FLUSH_THRESHOLD must be -1 (indicating never manual flush) or at least 0, but got ${e}.`)})),HO.registerFlag("CPU_HANDOFF_SIZE_THRESHOLD",(()=>128)),HO.registerFlag("WEBGL_USE_SHAPES_UNIFORMS",(()=>!1)),HO.registerFlag("TOPK_LAST_DIM_CPU_HANDOFF_SIZE_THRESHOLD",(()=>1e5)),HO.registerFlag("TOPK_K_CPU_HANDOFF_THRESHOLD",(()=>128)),HO.registerFlag("WEBGL_EXP_CONV",(()=>!1)),HO.registerFlag("SOFTWARE_WEBGL_ENABLED",(()=>HO.getBool("IS_TEST"))),HO.registerFlag("WEBGL_MAX_SIZE_FOR_NARROW_TEXTURE",(()=>1/0)),HO.registerFlag("WEBGL_AUTO_SQUARIFY_NARROW_TEXTURE_SHAPE",(()=>!1)),HO.registerFlag("WEBGL2_ISNAN_CUSTOM",(()=>!1)),HO.registerFlag("ENGINE_COMPILE_ONLY",(()=>!1));const ZO="\n  const float FLOAT_MAX = 1.70141184e38;\n  const float FLOAT_MIN = 1.17549435e-38;\n\n  lowp vec4 encode_float(highp float v) {\n    if (isnan(v)) {\n      return vec4(255, 255, 255, 255);\n    }\n\n    highp float av = abs(v);\n\n    if(av < FLOAT_MIN) {\n      return vec4(0.0, 0.0, 0.0, 0.0);\n    } else if(v > FLOAT_MAX) {\n      return vec4(0.0, 0.0, 128.0, 127.0) / 255.0;\n    } else if(v < -FLOAT_MAX) {\n      return vec4(0.0, 0.0,  128.0, 255.0) / 255.0;\n    }\n\n    highp vec4 c = vec4(0,0,0,0);\n\n    highp float e = floor(log2(av));\n    highp float m = exp2(fract(log2(av))) - 1.0;\n\n    c[2] = floor(128.0 * m);\n    m -= c[2] / 128.0;\n    c[1] = floor(32768.0 * m);\n    m -= c[1] / 32768.0;\n    c[0] = floor(8388608.0 * m);\n\n    highp float ebias = e + 127.0;\n    c[3] = floor(ebias / 2.0);\n    ebias -= c[3] * 2.0;\n    c[2] += floor(ebias) * 128.0;\n\n    c[3] += 128.0 * step(0.0, -v);\n\n    return c / 255.0;\n  }\n",{getBroadcastDims:JO}=y;function QO(e,t,n){const s=[];if(e.forEach((e=>{const t=ue(e.shapeInfo.logicalShape);if(e.shapeInfo.isUniform?s.push(`uniform float ${e.name}${t>1?`[${t}]`:""};`):(s.push(`uniform sampler2D ${e.name};`),s.push(`uniform int offset${e.name};`)),n.enableShapeUniforms){const{uniformShape:t}=cM(n.packedInputs,e.shapeInfo.logicalShape,e.shapeInfo.texShape);switch(t.length){case 1:s.push(`uniform int ${e.name}Shape;`);break;case 2:s.push(`uniform ivec2 ${e.name}Shape;`);break;case 3:s.push(`uniform ivec3 ${e.name}Shape;`);break;case 4:s.push(`uniform ivec4 ${e.name}Shape;`)}s.push(`uniform ivec2 ${e.name}TexShape;`)}})),n.enableShapeUniforms){switch(t.logicalShape.length){case 1:s.push("uniform int outShape;");break;case 2:s.push("uniform ivec2 outShape;"),s.push("uniform int outShapeStrides;");break;case 3:s.push("uniform ivec3 outShape;"),s.push("uniform ivec2 outShapeStrides;");break;case 4:s.push("uniform ivec4 outShape;"),s.push("uniform ivec3 outShapeStrides;")}s.push("uniform ivec2 outTexShape;")}n.customUniforms&&n.customUniforms.forEach((e=>{s.push(`uniform ${e.type} ${e.name}${e.arrayIndex?`[${e.arrayIndex}]`:""};`)}));const r=s.join("\n"),a=e.map((e=>function(e,t,n=!1,s){let r="";r+=n?tM(e,s):eM(e,s);const a=e.shapeInfo.logicalShape,i=t.logicalShape;a.length<=i.length&&(r+=n?function(e,t){const n=e.name,s=n.charAt(0).toUpperCase()+n.slice(1),r="get"+s+"AtOutCoords",a=e.shapeInfo.logicalShape.length,i=t.logicalShape.length,o=JO(e.shapeInfo.logicalShape,t.logicalShape),l=uM(i),u=i-a;let c;const h=["x","y","z","w","u","v"];c=0===a?"":i<2&&o.length>=1?"coords = 0;":o.map((e=>`coords.${h[e+u]} = 0;`)).join("\n");let p="";p=i<2&&a>0?"coords":e.shapeInfo.logicalShape.map(((e,t)=>`coords.${h[t+u]}`)).join(", ");let d="return outputValue;";const f=1===ue(e.shapeInfo.logicalShape),m=ue(t.logicalShape),g=1===m;if(1!==a||f||g){if(f&&!g)d=1===i?"\n        return vec4(outputValue.x, outputValue.x, 0., 0.);\n      ":"\n        return vec4(outputValue.x);\n      ";else if(o.length){const e=a-2,t=a-1;o.indexOf(e)>-1&&o.indexOf(t)>-1?d="return vec4(outputValue.x);":o.indexOf(e)>-1?d="return vec4(outputValue.x, outputValue.y, outputValue.x, outputValue.y);":o.indexOf(t)>-1&&(d="return vec4(outputValue.xx, outputValue.zz);")}}else d="\n      return vec4(outputValue.xy, outputValue.xy);\n    ";return`\n    vec4 ${r}() {\n      ${l} coords = getOutputCoords();\n      ${c}\n      vec4 outputValue = get${s}(${p});\n      ${d}\n    }\n  `}(e,t):function(e,t){const n=e.name,s=n.charAt(0).toUpperCase()+n.slice(1),r="get"+s+"AtOutCoords",a=t.texShape,i=e.shapeInfo.texShape,o=e.shapeInfo.logicalShape.length,l=t.logicalShape.length;if(!e.shapeInfo.isUniform&&o===l&&null==e.shapeInfo.flatOffset&&pe(i,a))return`\n      float ${r}() {\n        return sampleTexture(${n}, resultUV);\n      }\n    `;const u=uM(l),c=JO(e.shapeInfo.logicalShape,t.logicalShape),h=l-o;let p;const d=["x","y","z","w","u","v"];p=0===o?"":l<2&&c.length>=1?"coords = 0;":c.map((e=>`coords.${d[e+h]} = 0;`)).join("\n");let f="";f=l<2&&o>0?"coords":e.shapeInfo.logicalShape.map(((e,t)=>`coords.${d[t+h]}`)).join(", ");return`\n    float ${r}() {\n      ${u} coords = getOutputCoords();\n      ${p}\n      return get${s}(${f});\n    }\n  `}(e,t));return r}(e,t,n.packedInputs,n.enableShapeUniforms))).join("\n"),i=t.texShape,o=jO(),l=function(e){return`\n    float sampleTexture(sampler2D textureSampler, vec2 uv) {\n      return ${e.texture2D}(textureSampler, uv).r;\n    }\n  `}(o);let u,c,h=function(e){const t=`${e.version}\n    precision highp float;\n    precision highp int;\n    precision highp sampler2D;\n    ${e.varyingFs} vec2 resultUV;\n    ${e.defineOutput}\n    const vec2 halfCR = vec2(0.5, 0.5);\n\n    struct ivec5\n    {\n      int x;\n      int y;\n      int z;\n      int w;\n      int u;\n    };\n\n    struct ivec6\n    {\n      int x;\n      int y;\n      int z;\n      int w;\n      int u;\n      int v;\n    };\n\n    uniform float NAN;\n    ${e.defineSpecialNaN}\n    ${e.defineSpecialInf}\n    ${e.defineRound}\n\n    int imod(int x, int y) {\n      return x - y * (x / y);\n    }\n\n    int idiv(int a, int b, float sign) {\n      int res = a / b;\n      int mod = imod(a, b);\n      if (sign < 0. && mod != 0) {\n        res -= 1;\n      }\n      return res;\n    }\n\n    //Based on the work of Dave Hoskins\n    //https://www.shadertoy.com/view/4djSRW\n    #define HASHSCALE1 443.8975\n    float random(float seed){\n      vec2 p = resultUV * seed;\n      vec3 p3  = fract(vec3(p.xyx) * HASHSCALE1);\n      p3 += dot(p3, p3.yzx + 19.19);\n      return fract((p3.x + p3.y) * p3.z);\n    }\n\n    ${nM}\n    ${sM}\n    ${rM}\n  `;return t}(o);t.isPacked?(u=function(e,t,n){switch(e.length){case 0:return iM();case 1:return function(e,t,n){const s=[Math.ceil(t[0]/2),Math.ceil(t[1]/2)];if(1===s[0])return n?"\n      int getOutputCoords() {\n        return 2 * int(resultUV.x * ceil(float(outTexShape[1]) / 2.0));\n      }\n    ":`\n      int getOutputCoords() {\n        return 2 * int(resultUV.x * ${s[1]}.0);\n      }\n    `;if(1===s[1])return n?"\n      int getOutputCoords() {\n        return 2 * int(resultUV.y * ceil(float(outTexShape[0]) / 2.0));\n      }\n    ":`\n      int getOutputCoords() {\n        return 2 * int(resultUV.y * ${s[0]}.0);\n      }\n    `;if(n)return"\n    int getOutputCoords() {\n      ivec2 packedTexShape = ivec2(ceil(float(outTexShape[0]) / 2.0), ceil(float(outTexShape[1]) / 2.0));\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(packedTexShape[0], packedTexShape[1]));\n      return 2 * (resTexRC.x * packedTexShape[1] + resTexRC.y);\n    }\n  ";return`\n    int getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(${s[0]}, ${s[1]}));\n      return 2 * (resTexRC.x * ${s[1]} + resTexRC.y);\n    }\n  `}(0,t,n);case 2:return function(e,t,n){const s=[Math.ceil(t[0]/2),Math.ceil(t[1]/2)];if(pe(e,t))return n?"\n      ivec2 getOutputCoords() {\n        ivec2 packedTexShape = ivec2(ceil(float(outTexShape[0]) / 2.0), ceil(float(outTexShape[1]) / 2.0));\n        return 2 * ivec2(resultUV.yx * vec2(packedTexShape[0], packedTexShape[1]));\n      }\n    ":`\n      ivec2 getOutputCoords() {\n        return 2 * ivec2(resultUV.yx * vec2(${s[0]}, ${s[1]}));\n      }\n    `;const r=Math.ceil(e[1]/2);if(n)return"\n    ivec2 getOutputCoords() {\n      ivec2 packedTexShape = ivec2(ceil(float(outTexShape[0]) / 2.0), ceil(float(outTexShape[1]) / 2.0));\n      int texelsInLogicalRow = int(ceil(float(outShape[1]) / 2.0));\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(packedTexShape[0], packedTexShape[1]));\n\n      int index = resTexRC.x * packedTexShape[1] + resTexRC.y;\n      int r = 2 * (index / texelsInLogicalRow);\n      int c = imod(index, texelsInLogicalRow) * 2;\n\n      return ivec2(r, c);\n    }\n  ";return`\n    ivec2 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(${s[0]}, ${s[1]}));\n\n      int index = resTexRC.x * ${s[1]} + resTexRC.y;\n      int r = 2 * (index / ${r});\n      int c = imod(index, ${r}) * 2;\n\n      return ivec2(r, c);\n    }\n  `}(e,t,n);case 3:return function(e,t,n){if(n)return"\n    ivec3 getOutputCoords() {\n      ivec2 packedTexShape = ivec2(ceil(float(outTexShape[0]) / 2.0), ceil(float(outTexShape[1]) / 2.0));\n      int texelsInLogicalRow = int(ceil(float(outShape[2]) / 2.0));\n      int texelsInBatch = texelsInLogicalRow * int(ceil(float(outShape[1]) / 2.0));\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(packedTexShape[0], packedTexShape[1]));\n      int index = resTexRC.x * packedTexShape[1] + resTexRC.y;\n\n      int b = index / texelsInBatch;\n      index -= b * texelsInBatch;\n\n      int r = 2 * (index / texelsInLogicalRow);\n      int c = imod(index, texelsInLogicalRow) * 2;\n\n      return ivec3(b, r, c);\n    }\n  ";const s=[Math.ceil(t[0]/2),Math.ceil(t[1]/2)],r=Math.ceil(e[2]/2),a=r*Math.ceil(e[1]/2);return`\n    ivec3 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(${s[0]}, ${s[1]}));\n      int index = resTexRC.x * ${s[1]} + resTexRC.y;\n\n      int b = index / ${a};\n      index -= b * ${a};\n\n      int r = 2 * (index / ${r});\n      int c = imod(index, ${r}) * 2;\n\n      return ivec3(b, r, c);\n    }\n  `}(e,t,n);default:return function(e,t,n){if(n)return"\n    ivec4 getOutputCoords() {\n      ivec2 packedTexShape = ivec2(ceil(float(outTexShape[0]) / 2.0), ceil(float(outTexShape[1]) / 2.0));\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(packedTexShape[0], packedTexShape[1]));\n      int index = resTexRC.x * packedTexShape[1] + resTexRC.y;\n\n      int texelsInLogicalRow = int(ceil(float(outShape[3]) / 2.0));\n      int texelsInBatch = texelsInLogicalRow * int(ceil(float(outShape[2]) / 2.0));\n      int texelsInBatchN = texelsInBatch * outShape[1];\n\n      int b2 = index / texelsInBatchN;\n      index -= b2 * texelsInBatchN;\n\n      int b = index / texelsInBatch;\n      index -= b * texelsInBatch;\n\n      int r = 2 * (index / texelsInLogicalRow);\n      int c = imod(index, texelsInLogicalRow) * 2;\n\n      return ivec4(b2, b, r, c);\n    }\n  ";const s=[Math.ceil(t[0]/2),Math.ceil(t[1]/2)],r=Math.ceil(e[e.length-1]/2),a=r*Math.ceil(e[e.length-2]/2);let i=a,o="",l="b, r, c";for(let t=2;t<e.length-1;t++)i*=e[e.length-t-1],o=`\n      int b${t} = index / ${i};\n      index -= b${t} * ${i};\n    `+o,l=`b${t}, `+l;return`\n    ivec${e.length} getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(${s[0]}, ${s[1]}));\n      int index = resTexRC.x * ${s[1]} + resTexRC.y;\n\n      ${o}\n\n      int b = index / ${a};\n      index -= b * ${a};\n\n      int r = 2 * (index / ${r});\n      int c = imod(index, ${r}) * 2;\n\n      return ivec${e.length}(${l});\n    }\n  `}(e,t,n)}}(t.logicalShape,i,n.enableShapeUniforms),c=function(e){return`\n    void setOutput(vec4 val) {\n      ${e.output} = val;\n    }\n  `}(o)):(u=function(e,t,n){switch(e.length){case 0:return iM();case 1:return function(e,t,n){if(1===t[0])return n?"\n      int getOutputCoords() {\n        return int(resultUV.x * float(outTexShape[1]));\n      }\n    ":`\n      int getOutputCoords() {\n        return int(resultUV.x * ${t[1]}.0);\n      }\n    `;if(1===t[1])return n?"\n      int getOutputCoords() {\n        return int(resultUV.y * float(outTexShape[0]));\n      }\n    ":`\n      int getOutputCoords() {\n        return int(resultUV.y * ${t[0]}.0);\n      }\n    `;if(n)return"\n    int getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(outTexShape[0], outTexShape[1]));\n      return resTexRC.x * outTexShape[1] + resTexRC.y;\n    }\n  ";return`\n    int getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(${t[0]}, ${t[1]}));\n      return resTexRC.x * ${t[1]} + resTexRC.y;\n    }\n  `}(0,t,n);case 2:return function(e,t,n){if(pe(e,t))return n?"\n      ivec2 getOutputCoords() {\n        return ivec2(resultUV.yx * vec2(outTexShape[0], outTexShape[1]));\n      }\n    ":`\n      ivec2 getOutputCoords() {\n        return ivec2(resultUV.yx * vec2(${t[0]}, ${t[1]}));\n      }\n    `;if(1===e[1])return n?"\n      ivec2 getOutputCoords() {\n        ivec2 resTexRC = ivec2(resultUV.yx *\n                               vec2(outTexShape[0], outTexShape[1]));\n        int index = resTexRC.x * outTexShape[1] + resTexRC.y;\n        return ivec2(index, 0);\n      }\n    ":`\n      ivec2 getOutputCoords() {\n        ivec2 resTexRC = ivec2(resultUV.yx *\n                               vec2(${t[0]}, ${t[1]}));\n        int index = resTexRC.x * ${t[1]} + resTexRC.y;\n        return ivec2(index, 0);\n      }\n    `;if(1===e[0])return n?"\n      ivec2 getOutputCoords() {\n        ivec2 resTexRC = ivec2(resultUV.yx *\n                               vec2(outTexShape[0], outTexShape[1]));\n        int index = resTexRC.x * outTexShape[1] + resTexRC.y;\n        return ivec2(0, index);\n      }\n    ":`\n      ivec2 getOutputCoords() {\n        ivec2 resTexRC = ivec2(resultUV.yx *\n                               vec2(${t[0]}, ${t[1]}));\n        int index = resTexRC.x * ${t[1]} + resTexRC.y;\n        return ivec2(0, index);\n      }\n    `;if(n)return"\n    ivec2 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(outTexShape[0], outTexShape[1]));\n      int index = resTexRC.x * outTexShape[1] + resTexRC.y;\n      int r = index / outShape[1];\n      int c = index - r * outShape[1];\n      return ivec2(r, c);\n    }\n  ";return`\n    ivec2 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(${t[0]}, ${t[1]}));\n      int index = resTexRC.x * ${t[1]} + resTexRC.y;\n      int r = index / ${e[1]};\n      int c = index - r * ${e[1]};\n      return ivec2(r, c);\n    }\n  `}(e,t,n);case 3:return function(e,t,n){if(n){return`\n  ivec3 getOutputCoords() {\n    ivec2 resTexRC = ivec2(resultUV.yx *\n                           vec2(outTexShape[0], outTexShape[1]));\n    int index = resTexRC.x * outTexShape[1] + resTexRC.y;\n    ${KO(["r","c","d"],e)}\n    return ivec3(r, c, d);\n  }\n`}const s=qO(["r","c","d"],e);return`\n    ivec3 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n                             vec2(${t[0]}, ${t[1]}));\n      int index = resTexRC.x * ${t[1]} + resTexRC.y;\n      ${s}\n      return ivec3(r, c, d);\n    }\n  `}(e,t,n);case 4:return function(e,t,n){if(n){return`\n    ivec4 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n        vec2(outTexShape[0], outTexShape[1]));\n      int index = resTexRC.x * outTexShape[1] + resTexRC.y;\n      ${KO(["r","c","d","d2"],e)}\n      return ivec4(r, c, d, d2);\n    }\n  `}const s=qO(["r","c","d","d2"],e);return`\n    ivec4 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n        vec2(${t[0]}, ${t[1]}));\n      int index = resTexRC.x * ${t[1]} + resTexRC.y;\n      ${s}\n      return ivec4(r, c, d, d2);\n    }\n  `}(e,t,n);case 5:return function(e,t){const n=qO(["r","c","d","d2","d3"],e);return`\n    ivec5 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx * vec2(${t[0]},\n                             ${t[1]}));\n\n      int index = resTexRC.x * ${t[1]} + resTexRC.y;\n\n      ${n}\n\n      ivec5 outShape = ivec5(r, c, d, d2, d3);\n      return outShape;\n    }\n  `}(e,t);case 6:return function(e,t){const n=qO(["r","c","d","d2","d3","d4"],e);return`\n    ivec6 getOutputCoords() {\n      ivec2 resTexRC = ivec2(resultUV.yx *\n        vec2(${t[0]}, ${t[1]}));\n      int index = resTexRC.x * ${t[1]} + resTexRC.y;\n\n      ${n}\n\n      ivec6 result = ivec6(r, c, d, d2, d3, d4);\n      return result;\n    }\n  `}(e,t);default:throw new Error(`${e.length}-D output sampling is not yet supported`)}}(t.logicalShape,i,n.enableShapeUniforms),c=function(e){return`\n    void setOutput(float val) {\n      ${e.output} = vec4(val, 0, 0, 0);\n    }\n  `}(o)),n.packedInputs&&(h+=aM);return[h,l,c,r,u,a,n.userCode].join("\n")}function eM(e,t=!1){const n=e.shapeInfo.logicalShape;switch(n.length){case 0:return function(e,t){const n=e.name,s="get"+n.charAt(0).toUpperCase()+n.slice(1);if(e.shapeInfo.isUniform)return`float ${s}() {return ${n};}`;const[r,a]=e.shapeInfo.texShape;if(1===r&&1===a)return`\n      float ${s}() {\n        return sampleTexture(${n}, halfCR);\n      }\n    `;const i=oM(n);if(t)return`\n    float ${s}() {\n      vec2 uv = uvFromFlat(${n}TexShape[0], ${n}TexShape[1], ${i});\n      return sampleTexture(${n}, uv);\n    }\n  `;const[o,l]=e.shapeInfo.texShape;return`\n    float ${s}() {\n      vec2 uv = uvFromFlat(${o}, ${l}, ${i});\n      return sampleTexture(${n}, uv);\n    }\n  `}(e,t);case 1:return function(e,t){const n=e.name,s="get"+n.charAt(0).toUpperCase()+n.slice(1);if(e.shapeInfo.isUniform)return`\n      float ${s}(int index) {\n        ${lM(e)}\n      }\n    `;const r=e.shapeInfo.texShape,a=r[0],i=r[1];if(1===i&&1===a)return`\n      float ${s}(int index) {\n        return sampleTexture(${n}, halfCR);\n      }\n    `;const o=oM(n);if(1===i)return t?`\n      float ${s}(int index) {\n        vec2 uv = vec2(0.5, (float(index + ${o}) + 0.5) / float(${n}TexShape[0]));\n        return sampleTexture(${n}, uv);\n      }\n    `:`\n      float ${s}(int index) {\n        vec2 uv = vec2(0.5, (float(index + ${o}) + 0.5) / ${a}.0);\n        return sampleTexture(${n}, uv);\n      }\n    `;if(1===a)return t?`\n      float ${s}(int index) {\n        vec2 uv = vec2((float(index + ${o}) + 0.5) / float(${n}TexShape[1]), 0.5);\n        return sampleTexture(${n}, uv);\n      }\n    `:`\n      float ${s}(int index) {\n        vec2 uv = vec2((float(index + ${o}) + 0.5) / ${i}.0, 0.5);\n        return sampleTexture(${n}, uv);\n      }\n    `;if(t)return`\n    float ${s}(int index) {\n      vec2 uv = uvFromFlat(${n}TexShape[0], ${n}TexShape[1], index + ${o});\n      return sampleTexture(${n}, uv);\n    }\n  `;return`\n    float ${s}(int index) {\n      vec2 uv = uvFromFlat(${a}, ${i}, index + ${o});\n      return sampleTexture(${n}, uv);\n    }\n  `}(e,t);case 2:return function(e,t){const n=e.shapeInfo.logicalShape,s=e.name,r="get"+s.charAt(0).toUpperCase()+s.slice(1),a=e.shapeInfo.texShape;if(null!=a&&pe(n,a)){if(t)return`\n      float ${r}(int row, int col) {\n        vec2 uv = (vec2(col, row) + halfCR) / vec2(${s}TexShape[1], ${s}TexShape[0]);\n        return sampleTexture(${s}, uv);\n      }\n    `;const e=a[0];return`\n    float ${r}(int row, int col) {\n      vec2 uv = (vec2(col, row) + halfCR) / vec2(${a[1]}.0, ${e}.0);\n      return sampleTexture(${s}, uv);\n    }\n  `}const{newShape:i,keptDims:o}=ve(n),l=i;if(l.length<n.length){const n=["row","col"];return`\n      ${eM(hM(e,l),t)}\n      float ${r}(int row, int col) {\n        return ${r}(${pM(n,o)});\n      }\n    `}if(e.shapeInfo.isUniform)return`\n      float ${r}(int row, int col) {\n        int index = round(dot(vec2(row, col), vec2(${n[1]}, 1)));\n        ${lM(e)}\n      }\n    `;const u=a[0],c=a[1],h=oM(s);if(1===c)return t?`\n      float ${r}(int row, int col) {\n        float index = dot(vec3(row, col, ${h}), vec3(${s}Shape[1], 1, 1));\n        vec2 uv = vec2(0.5, (index + 0.5) / float(${s}TexShape[0]));\n        return sampleTexture(${s}, uv);\n      }\n    `:`\n    float ${r}(int row, int col) {\n      float index = dot(vec3(row, col, ${h}), vec3(${n[1]}, 1, 1));\n      vec2 uv = vec2(0.5, (index + 0.5) / ${u}.0);\n      return sampleTexture(${s}, uv);\n    }\n  `;if(1===u)return t?`\n      float ${r}(int row, int col) {\n        float index = dot(vec3(row, col, ${h}), vec3(${s}Shape[1], 1, 1));\n        vec2 uv = vec2((index + 0.5) / float(${s}TexShape[1]), 0.5);\n        return sampleTexture(${s}, uv);\n      }\n    `:`\n    float ${r}(int row, int col) {\n      float index = dot(vec3(row, col, ${h}), vec3(${n[1]}, 1, 1));\n      vec2 uv = vec2((index + 0.5) / ${c}.0, 0.5);\n      return sampleTexture(${s}, uv);\n    }\n  `;if(t)return`\n      float ${r}(int row, int col) {\n        // Explicitly use integer operations as dot() only works on floats.\n        int index = row * ${s}Shape[1] + col + ${h};\n        vec2 uv = uvFromFlat(${s}TexShape[0], ${s}TexShape[1], index);\n        return sampleTexture(${s}, uv);\n      }\n    `;return`\n  float ${r}(int row, int col) {\n    // Explicitly use integer operations as dot() only works on floats.\n    int index = row * ${n[1]} + col + ${h};\n    vec2 uv = uvFromFlat(${u}, ${c}, index);\n    return sampleTexture(${s}, uv);\n  }\n`}(e,t);case 3:return function(e,t){const n=e.shapeInfo.logicalShape,s=e.name,r="get"+s.charAt(0).toUpperCase()+s.slice(1),a=n[1]*n[2],i=n[2],{newShape:o,keptDims:l}=ve(n),u=o;if(u.length<n.length){const n=["row","col","depth"];return`\n        ${eM(hM(e,u),t)}\n        float ${r}(int row, int col, int depth) {\n          return ${r}(${pM(n,l)});\n        }\n      `}if(e.shapeInfo.isUniform)return`\n      float ${r}(int row, int col, int depth) {\n        int index = round(dot(vec3(row, col, depth),\n                          vec3(${a}, ${i}, 1)));\n        ${lM(e)}\n      }\n    `;const c=e.shapeInfo.texShape,h=c[0],p=c[1],d=e.shapeInfo.flatOffset;if(p===a&&null==d)return t?`\n      float ${r}(int row, int col, int depth) {\n        int stride1 = ${s}Shape[2];\n        float texR = float(row);\n        float texC = dot(vec2(col, depth), vec2(stride1, 1));\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                   vec2(${s}TexShape[1], ${s}TexShape[0]);\n        return sampleTexture(${s}, uv);\n      }\n    `:`\n        float ${r}(int row, int col, int depth) {\n          float texR = float(row);\n          float texC = dot(vec2(col, depth), vec2(${i}, 1));\n          vec2 uv = (vec2(texC, texR) + halfCR) /\n                     vec2(${p}.0, ${h}.0);\n          return sampleTexture(${s}, uv);\n        }\n      `;if(p===i&&null==d)return t?`\n      float ${r}(int row, int col, int depth) {\n        float texR = dot(vec2(row, col), vec2(${s}Shape[1], 1));\n        float texC = float(depth);\n        vec2 uv = (vec2(texC, texR) + halfCR) / vec2(${s}TexShape[1], ${s}TexShape[0]);\n        return sampleTexture(${s}, uv);\n      }\n    `:`\n    float ${r}(int row, int col, int depth) {\n      float texR = dot(vec2(row, col), vec2(${n[1]}, 1));\n      float texC = float(depth);\n      vec2 uv = (vec2(texC, texR) + halfCR) / vec2(${p}.0, ${h}.0);\n      return sampleTexture(${s}, uv);\n    }\n  `;const f=oM(s);if(t)return`\n    float ${r}(int row, int col, int depth) {\n      // Explicitly use integer operations as dot() only works on floats.\n      int stride0 = ${s}Shape[1] * ${s}Shape[2];\n      int stride1 = ${s}Shape[2];\n      int index = row * stride0 + col * stride1 + depth + ${f};\n      vec2 uv = uvFromFlat(${s}TexShape[0], ${s}TexShape[1], index);\n      return sampleTexture(${s}, uv);\n    }\n    `;return`\n      float ${r}(int row, int col, int depth) {\n        // Explicitly use integer operations as dot() only works on floats.\n        int index = row * ${a} + col * ${i} + depth + ${f};\n        vec2 uv = uvFromFlat(${h}, ${p}, index);\n        return sampleTexture(${s}, uv);\n      }\n  `}(e,t);case 4:return function(e,t){const n=e.shapeInfo.logicalShape,s=e.name,r="get"+s.charAt(0).toUpperCase()+s.slice(1),a=n[3],i=n[2]*a,o=n[1]*i,{newShape:l,keptDims:u}=ve(n);if(l.length<n.length){const n=["row","col","depth","depth2"];return`\n      ${eM(hM(e,l),t)}\n      float ${r}(int row, int col, int depth, int depth2) {\n        return ${r}(${pM(n,u)});\n      }\n    `}if(e.shapeInfo.isUniform)return`\n      float ${r}(int row, int col, int depth, int depth2) {\n        int index = round(dot(vec4(row, col, depth, depth2),\n                          vec4(${o}, ${i}, ${a}, 1)));\n        ${lM(e)}\n      }\n    `;const c=e.shapeInfo.flatOffset,h=e.shapeInfo.texShape,p=h[0],d=h[1],f=`int stride2 = ${s}Shape[3];`,m=`int stride1 = ${s}Shape[2] * stride2;`,g=`int stride0 = ${s}Shape[1] * stride1;`;if(d===o&&null==c)return t?`\n      float ${r}(int row, int col, int depth, int depth2) {\n        ${f}\n        ${m}\n        float texR = float(row);\n        float texC =\n            dot(vec3(col, depth, depth2),\n                vec3(stride1, stride2, 1));\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                   vec2(${s}TexShape[1], ${s}TexShape[0]);\n        return sampleTexture(${s}, uv);\n      }\n    `:`\n      float ${r}(int row, int col, int depth, int depth2) {\n        float texR = float(row);\n        float texC =\n            dot(vec3(col, depth, depth2),\n                vec3(${i}, ${a}, 1));\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                   vec2(${d}.0, ${p}.0);\n        return sampleTexture(${s}, uv);\n      }\n    `;if(d===a&&null==c)return t?`\n      float ${r}(int row, int col, int depth, int depth2) {\n        float texR = dot(vec3(row, col, depth),\n                         vec3(${s}Shape[1] * ${s}Shape[2], ${s}Shape[2], 1));\n        float texC = float(depth2);\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                  vec2(${s}TexShape[1], ${s}TexShape[0]);\n        return sampleTexture(${s}, uv);\n      }\n    `:`\n      float ${r}(int row, int col, int depth, int depth2) {\n        float texR = dot(vec3(row, col, depth),\n                         vec3(${n[1]*n[2]}, ${n[2]}, 1));\n        float texC = float(depth2);\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                  vec2(${d}.0, ${p}.0);\n        return sampleTexture(${s}, uv);\n      }\n    `;const y=oM(s);if(t)return`\n    float ${r}(int row, int col, int depth, int depth2) {\n      // Explicitly use integer operations as dot() only works on floats.\n      ${f}\n      ${m}\n      ${g}\n      int index = row * stride0 + col * stride1 +\n          depth * stride2 + depth2;\n      vec2 uv = uvFromFlat(${s}TexShape[0], ${s}TexShape[1], index + ${y});\n      return sampleTexture(${s}, uv);\n    }\n  `;return`\n    float ${r}(int row, int col, int depth, int depth2) {\n      // Explicitly use integer operations as dot() only works on floats.\n      int index = row * ${o} + col * ${i} +\n          depth * ${a} + depth2;\n      vec2 uv = uvFromFlat(${p}, ${d}, index + ${y});\n      return sampleTexture(${s}, uv);\n    }\n  `}(e,t);case 5:return function(e){const t=e.shapeInfo.logicalShape,n=e.name,s="get"+n.charAt(0).toUpperCase()+n.slice(1),r=t[4],a=t[3]*r,i=t[2]*a,o=t[1]*i,{newShape:l,keptDims:u}=ve(t);if(l.length<t.length){const t=["row","col","depth","depth2","depth3"];return`\n      ${eM(hM(e,l))}\n      float ${s}(int row, int col, int depth, int depth2, int depth3) {\n        return ${s}(${pM(t,u)});\n      }\n    `}if(e.shapeInfo.isUniform)return`\n      float ${s}(int row, int col, int depth, int depth2, int depth3) {\n        float index = dot(\n          vec4(row, col, depth, depth2),\n          vec4(${o}, ${i}, ${a}, ${r})) +\n          depth3;\n        ${lM(e)}\n      }\n    `;const c=e.shapeInfo.flatOffset,h=e.shapeInfo.texShape,p=h[0],d=h[1];if(d===o&&null==c)return`\n      float ${s}(int row, int col, int depth, int depth2, int depth3) {\n        int texR = row;\n        float texC = dot(vec4(col, depth, depth2, depth3),\n                         vec4(${i}, ${a}, ${r}, 1));\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                   vec2(${d}.0, ${p}.0);\n        return sampleTexture(${n}, uv);\n      }\n    `;if(d===r&&null==c)return`\n      float ${s}(int row, int col, int depth, int depth2, int depth3) {\n        float texR = dot(\n          vec4(row, col, depth, depth2),\n          vec4(${t[1]*t[2]*t[3]},\n               ${t[2]*t[3]}, ${t[3]}, 1));\n        int texC = depth3;\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                  vec2(${d}.0, ${p}.0);\n        return sampleTexture(${n}, uv);\n      }\n    `;const f=oM(n);return`\n    float ${s}(int row, int col, int depth, int depth2, int depth3) {\n      // Explicitly use integer operations as dot() only works on floats.\n      int index = row * ${o} + col * ${i} + depth * ${a} +\n          depth2 * ${r} + depth3 + ${f};\n      vec2 uv = uvFromFlat(${p}, ${d}, index);\n      return sampleTexture(${n}, uv);\n    }\n  `}(e);case 6:return function(e){const t=e.shapeInfo.logicalShape,n=e.name,s="get"+n.charAt(0).toUpperCase()+n.slice(1),{newShape:r,keptDims:a}=ve(t);if(r.length<t.length){const t=["row","col","depth","depth2","depth3","depth4"];return`\n      ${eM(hM(e,r))}\n      float ${s}(int row, int col, int depth,\n                    int depth2, int depth3, int depth4) {\n        return ${s}(${pM(t,a)});\n      }\n    `}const i=t[5],o=t[4]*i,l=t[3]*o,u=t[2]*l,c=t[1]*u;if(e.shapeInfo.isUniform)return`\n      float ${s}(int row, int col, int depth,\n                  int depth2, int depth3, int depth4) {\n        int index = round(dot(\n          vec4(row, col, depth, depth2),\n          vec4(${c}, ${u}, ${l}, ${o})) +\n          dot(\n            vec2(depth3, depth4),\n            vec2(${i}, 1)));\n        ${lM(e)}\n      }\n    `;const h=e.shapeInfo.flatOffset,p=e.shapeInfo.texShape,d=p[0],f=p[1];if(f===c&&null==h)return`\n      float ${s}(int row, int col, int depth,\n                    int depth2, int depth3, int depth4) {\n        int texR = row;\n        float texC = dot(vec4(col, depth, depth2, depth3),\n          vec4(${u}, ${l}, ${o}, ${i})) +\n               float(depth4);\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                   vec2(${f}.0, ${d}.0);\n        return sampleTexture(${n}, uv);\n      }\n    `;if(f===i&&null==h)return`\n      float ${s}(int row, int col, int depth,\n                    int depth2, int depth3, int depth4) {\n        float texR = dot(vec4(row, col, depth, depth2),\n          vec4(${t[1]*t[2]*t[3]*t[4]},\n               ${t[2]*t[3]*t[4]},\n               ${t[3]*t[4]},\n               ${t[4]})) + float(depth3);\n        int texC = depth4;\n        vec2 uv = (vec2(texC, texR) + halfCR) /\n                  vec2(${f}.0, ${d}.0);\n        return sampleTexture(${n}, uv);\n      }\n    `;const m=oM(n);return`\n    float ${s}(int row, int col, int depth,\n                  int depth2, int depth3, int depth4) {\n      // Explicitly use integer operations as dot() only works on floats.\n      int index = row * ${c} + col * ${u} + depth * ${l} +\n          depth2 * ${o} + depth3 * ${i} + depth4 + ${m};\n      vec2 uv = uvFromFlat(${d}, ${f}, index);\n      return sampleTexture(${n}, uv);\n    }\n  `}(e);default:throw new Error(`${n.length}-D input sampling is not yet supported`)}}function tM(e,t){switch(e.shapeInfo.logicalShape.length){case 0:return function(e){const t=e.name,n="get"+t.charAt(0).toUpperCase()+t.slice(1),s=jO();return`\n    vec4 ${n}() {\n      return ${s.texture2D}(${t}, halfCR);\n    }\n  `}(e);case 1:return function(e,t){const n=e.name,s="get"+n.charAt(0).toUpperCase()+n.slice(1),r=e.shapeInfo.texShape,a=jO();if(t)return`\n    vec4 ${s}(int index) {\n      ivec2 packedTexShape = ivec2(ceil(float(${n}TexShape[0]) / 2.0), ceil(float(${n}TexShape[1]) / 2.0));\n      vec2 uv = packedUVfrom1D(\n        packedTexShape[0], packedTexShape[1], index);\n      return ${a.texture2D}(${n}, uv);\n    }\n  `;const i=[Math.ceil(r[0]/2),Math.ceil(r[1]/2)];return`\n    vec4 ${s}(int index) {\n      vec2 uv = packedUVfrom1D(\n        ${i[0]}, ${i[1]}, index);\n      return ${a.texture2D}(${n}, uv);\n    }\n  `}(e,t);case 2:return function(e,t){const n=e.shapeInfo.logicalShape,s=e.name,r="get"+s.charAt(0).toUpperCase()+s.slice(1),a=e.shapeInfo.texShape,i=a[0],o=a[1],l=jO();if(null!=a&&pe(n,a))return t?`\n      vec4 ${r}(int row, int col) {\n        vec2 uv = (vec2(col, row) + halfCR) / vec2(${s}TexShape[1], ${s}TexShape[0]);\n\n        return ${l.texture2D}(${s}, uv);\n      }\n    `:`\n      vec4 ${r}(int row, int col) {\n        vec2 uv = (vec2(col, row) + halfCR) / vec2(${o}.0, ${i}.0);\n\n        return ${l.texture2D}(${s}, uv);\n      }\n    `;if(t)return`\n    vec4 ${r}(int row, int col) {\n      ivec2 packedTexShape = ivec2(ceil(float(${s}TexShape[0]) / 2.0), ceil(float(${s}TexShape[1]) / 2.0));\n      int valuesPerRow = int(ceil(float(${s}Shape[1]) / 2.0));\n      vec2 uv = packedUVfrom2D(valuesPerRow, packedTexShape[0], packedTexShape[1], row, col);\n      return ${l.texture2D}(${s}, uv);\n    }\n  `;const u=[Math.ceil(a[0]/2),Math.ceil(a[1]/2)],c=Math.ceil(n[1]/2);return`\n    vec4 ${r}(int row, int col) {\n      vec2 uv = packedUVfrom2D(${c}, ${u[0]}, ${u[1]}, row, col);\n      return ${l.texture2D}(${s}, uv);\n    }\n  `}(e,t);case 3:return function(e,t){const n=e.shapeInfo.logicalShape,s=e.name,r="get"+s.charAt(0).toUpperCase()+s.slice(1),a=e.shapeInfo.texShape,i=[Math.ceil(a[0]/2),Math.ceil(a[1]/2)];if(1===n[0]){const s=[1,2],a=["b","row","col"];return`\n        ${tM(hM(e,n.slice(1)),t)}\n        vec4 ${r}(int b, int row, int col) {\n          return ${r}(${pM(a,s)});\n        }\n      `}const o=jO();if(t)return`\n    vec4 ${r}(int b, int row, int col) {\n      ivec2 packedTexShape = ivec2(ceil(float(${s}TexShape[0]) / 2.0), ceil(float(${s}TexShape[1]) / 2.0));\n      int valuesPerRow = int(ceil(float(${s}Shape[2]) / 2.0));\n      int texelsInBatch = valuesPerRow * int(ceil(float(${s}Shape[1]) / 2.0));\n      vec2 uv = packedUVfrom3D(\n        packedTexShape[0], packedTexShape[1], texelsInBatch, valuesPerRow, b, row, col);\n      return ${o.texture2D}(${s}, uv);\n    }\n  `;const l=i[0],u=i[1],c=Math.ceil(n[2]/2),h=c*Math.ceil(n[1]/2);return`\n    vec4 ${r}(int b, int row, int col) {\n      vec2 uv = packedUVfrom3D(\n        ${l}, ${u}, ${h}, ${c}, b, row, col);\n      return ${o.texture2D}(${s}, uv);\n    }\n  `}(e,t);default:return function(e,t){const n=e.name,s="get"+n.charAt(0).toUpperCase()+n.slice(1),r=jO();if(t)return`\n    vec4 ${s}(int b2, int b, int row, int col) {\n      int valuesPerRow = int(ceil(float(${n}Shape[3]) / 2.0));\n      int texelsInBatch = valuesPerRow * int(ceil(float(${n}Shape[2]) / 2.0));\n      int index = b * texelsInBatch + (row / 2) * valuesPerRow + (col / 2);\n      texelsInBatch *= ${n}Shape[1];\n      index = b2 * texelsInBatch + index;\n      ivec2 packedTexShape = ivec2(ceil(float(${n}TexShape[0]) / 2.0), ceil(float(${n}TexShape[1]) / 2.0));\n      int texR = index / packedTexShape[1];\n      int texC = index - texR * packedTexShape[1];\n      vec2 uv = (vec2(texC, texR) + halfCR) / vec2(packedTexShape[1], packedTexShape[0]); return ${r.texture2D}(${n}, uv);\n    }\n  `;const a=e.shapeInfo.logicalShape,i=a.length,o=e.shapeInfo.texShape,l=[Math.ceil(o[0]/2),Math.ceil(o[1]/2)],u=l[0],c=l[1],h=Math.ceil(a[i-1]/2);let p=h*Math.ceil(a[i-2]/2),d="int b, int row, int col",f=`b * ${p} + (row / 2) * ${h} + (col / 2)`;for(let e=2;e<i-1;e++)d=`int b${e}, `+d,p*=a[i-e-1],f=`b${e} * ${p} + `+f;return`\n    vec4 ${s}(${d}) {\n      int index = ${f};\n      int texR = index / ${c};\n      int texC = index - texR * ${c};\n      vec2 uv = (vec2(texC, texR) + halfCR) / vec2(${c}, ${u});\n      return ${r.texture2D}(${n}, uv);\n    }\n  `}(e,t)}}const nM="\nvec2 uvFromFlat(int texNumR, int texNumC, int index) {\n  int texR = index / texNumC;\n  int texC = index - texR * texNumC;\n  return (vec2(texC, texR) + halfCR) / vec2(texNumC, texNumR);\n}\nvec2 packedUVfrom1D(int texNumR, int texNumC, int index) {\n  int texelIndex = index / 2;\n  int texR = texelIndex / texNumC;\n  int texC = texelIndex - texR * texNumC;\n  return (vec2(texC, texR) + halfCR) / vec2(texNumC, texNumR);\n}\n",sM="\nvec2 packedUVfrom2D(int texelsInLogicalRow, int texNumR,\n  int texNumC, int row, int col) {\n  int texelIndex = (row / 2) * texelsInLogicalRow + (col / 2);\n  int texR = texelIndex / texNumC;\n  int texC = texelIndex - texR * texNumC;\n  return (vec2(texC, texR) + halfCR) / vec2(texNumC, texNumR);\n}\n",rM="\nvec2 packedUVfrom3D(int texNumR, int texNumC,\n    int texelsInBatch, int texelsInLogicalRow, int b,\n    int row, int col) {\n  int index = b * texelsInBatch + (row / 2) * texelsInLogicalRow + (col / 2);\n  int texR = index / texNumC;\n  int texC = index - texR * texNumC;\n  return (vec2(texC, texR) + halfCR) / vec2(texNumC, texNumR);\n}\n",aM="\n  float getChannel(vec4 frag, vec2 innerDims) {\n    vec2 modCoord = mod(innerDims, 2.);\n    return modCoord.x == 0. ?\n      (modCoord.y == 0. ? frag.r : frag.g) :\n      (modCoord.y == 0. ? frag.b : frag.a);\n  }\n  float getChannel(vec4 frag, int dim) {\n    float modCoord = mod(float(dim), 2.);\n    return modCoord == 0. ? frag.r : frag.g;\n  }\n";function iM(){return"\n    int getOutputCoords() {\n      return 0;\n    }\n  "}function oM(e){return`offset${e}`}function lM(e){const t=e.name,n=ue(e.shapeInfo.logicalShape);return n<2?`return ${t};`:`\n    for (int i = 0; i < ${n}; i++) {\n      if (i == index) {\n        return ${t}[i];\n      }\n    }\n  `}function uM(e){if(e<=1)return"int";if(2===e)return"ivec2";if(3===e)return"ivec3";if(4===e)return"ivec4";if(5===e)return"ivec5";if(6===e)return"ivec6";throw Error(`GPU for rank ${e} is not yet supported`)}function cM(e,t,n){const{newShape:s,keptDims:r}=ve(t),a=t.length,i=e&&3===a&&1===t[0],o=i?t.slice(1):s,l=!e&&a>1&&!pe(t,n)&&s.length<a||i;return{useSqueezeShape:l,uniformShape:l?o:t,keptDims:r}}function hM(e,t){const n=JSON.parse(JSON.stringify(e));return n.shapeInfo.logicalShape=t,n}function pM(e,t){return t.map((t=>e[t])).join(", ")}function dM(e,t,n){const s=[],r=[];let a,i,o,l=null,u=null;u=e.getUniformLocation(n,"NAN",!1),1===Xe().getNumber("WEBGL_VERSION")&&(l=e.getUniformLocation(n,"INFINITY",!1));const c=!1;for(const r of t.variableNames){const a={name:r,uniform:e.getUniformLocation(n,r,c),offset:e.getUniformLocation(n,`offset${r}`,c)};t.enableShapeUniforms&&(a.shape=e.getUniformLocation(n,`${r}Shape`,c),a.texShape=e.getUniformLocation(n,`${r}TexShape`,c)),s.push(a)}if(t.enableShapeUniforms&&(a=e.getUniformLocation(n,"outShape",c),o=e.getUniformLocation(n,"outShapeStrides",c),i=e.getUniformLocation(n,"outTexShape",c)),t.customUniforms)for(const s of t.customUniforms)r.push(e.getUniformLocation(n,s.name,c));return{variablesLocations:s,customUniformLocations:r,infLoc:l,nanLoc:u,outShapeLocation:a,outShapeStridesLocation:o,outTexShapeLocation:i}}function fM(e,t){if(e.length!==t.length)throw Error(`Binary was compiled with ${e.length} inputs, but was executed with ${t.length} inputs`);e.forEach(((e,n)=>{const s=e.logicalShape,r=t[n],a=r.shape;if(!pe(s,a))throw Error(`Binary was compiled with different shapes than the current args. Shapes ${s} and ${a} must match`);if(e.isUniform&&r.isUniform)return;const i=e.texShape,o=r.isUniform?null:r.texData.texShape;if(!pe(i,o))throw Error(`Binary was compiled with different texture shapes than the current args. Shape ${i} and ${o} must match`)}))}function mM(e){return Xe().getBool("WEBGL_USE_SHAPES_UNIFORMS")&&e<=4}class gM{constructor(e){this.variableNames=["A"],this.packedInputs=!1,this.packedOutput=!0,this.outPackingScheme=BD.DENSE,this.customUniforms=[{name:"texShape",type:"ivec2"}];const t=jO();this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length),this.userCode=`\n      ivec3 outCoordsFromFlatIndex(int index) {\n        ${this.enableShapeUniforms?KO(["r","c","d"],e):qO(["r","c","d"],e)}\n        return ivec3(r, c, d);\n      }\n\n      void main() {\n        ivec2 resTexRC = ivec2(resultUV.yx * vec2(texShape[0], texShape[1]));\n        int index = 4 * (resTexRC.x * texShape[1] + resTexRC.y);\n\n        vec4 result = vec4(0.);\n\n        for (int i=0; i<4; i++) {\n          int flatIndex = index + i;\n          ivec3 rc = outCoordsFromFlatIndex(flatIndex);\n          result[i] = getA(rc.x, rc.y, rc.z);\n        }\n\n        ${t.output} = result;\n      }\n    `}}class yM{constructor(e){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,this.outPackingScheme=BD.DENSE,this.customUniforms=[{name:"texShape",type:"ivec2"}];const t=jO();this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length),this.userCode=`\n      ivec3 outCoordsFromFlatIndex(int index) {\n        ${this.enableShapeUniforms?KO(["r","c","d"],e):qO(["r","c","d"],e)}\n        return ivec3(r, c, d);\n      }\n\n      void main() {\n        ivec2 resTexRC = ivec2(resultUV.yx * vec2(texShape[0], texShape[1]));\n        int index = 4 * (resTexRC.x * texShape[1] + resTexRC.y);\n\n        vec4 result = vec4(0.);\n\n        for (int i=0; i<4; i++) {\n          int flatIndex = index + i;\n          ivec3 rc = outCoordsFromFlatIndex(flatIndex);\n          result[i] = getChannel(getA(rc.x, rc.y, rc.z), vec2(rc.y, rc.z));\n        }\n\n        ${t.output} = result;\n      }\n    `}}class bM{constructor(e){this.variableNames=["A"],this.outTexUsage=WD.DOWNLOAD;const t=jO();this.outputShape=e,this.userCode=`\n      ${ZO}\n\n      void main() {\n        float x = getAAtOutCoords();\n        ${t.output} = encode_float(x);\n      }\n    `}}class xM{constructor(e){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!1,this.outTexUsage=WD.DOWNLOAD;const t=jO();this.outputShape=e,this.userCode=`\n      ${ZO}\n\n      void main() {\n        ivec3 coords = getOutputCoords();\n        float x = getChannel(getAAtOutCoords(), vec2(coords.y, coords.z));\n        ${t.output} = encode_float(x);\n      }\n    `}}const wM={R:0,G:1,B:2,A:3};class vM{constructor(e,t=!1,n="RGBA"){this.variableNames=["A"],this.customUniforms=[{name:"texShape",type:"ivec2"}];const s=jO();this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length);let r="result";t&&(r="floor(result * 255. + 0.5)");let a="";for(let e=0;e<n.length;e++){const t=n[e];a+=`\n          if(offset == ${e}) {\n            result = values[${wM[t]}];\n          }`}this.userCode=`\n      ${this.enableShapeUniforms?"\n  int getFlatIndex(ivec3 coords) {\n    return coords.x * outShapeStrides[0] + coords.y * outShapeStrides[1] + coords.z;\n  }\n":YO(e)}\n\n      void main() {\n        ivec3 coords = getOutputCoords();\n        int flatIndex = getFlatIndex(coords);\n        float result = 0.;\n        int offset = imod(flatIndex, ${n.length});\n\n        flatIndex = idiv(flatIndex, ${n.length}, 1.);\n\n        int r = flatIndex / texShape[1];\n        if (r < texShape[0]) {\n          int c = imod(flatIndex, texShape[1]);\n          vec2 uv = (vec2(c, r) + halfCR) / vec2(texShape[1], texShape[0]);\n          vec4 values = ${s.texture2D}(A, uv);\n          ${a}\n        }\n        ${s.output} = vec4(${r}, 0., 0., 0.);\n      }\n    `}}class kM{constructor(e,t=!1){this.variableNames=["A"],this.packedInputs=!1,this.packedOutput=!0,this.customUniforms=[{name:"texShape",type:"ivec2"}];const n=jO();this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length);let s="",r="result";t&&(r="floor(result * 255. + 0.5)");for(let t=0;t<=1;t++)for(let r=0;r<=1;r++){const a=2*t+r;s+=`\n          localCoords = coords;\n          if(localCoords[2] + ${r} < ${this.enableShapeUniforms?"outShape[2]":`${e[2]}`}) {\n          localCoords[2] += ${r};\n          if (localCoords[1] + ${t} < ${this.enableShapeUniforms?"outShape[1]":`${e[1]}`}) {\n            localCoords[1] += ${t};\n\n            flatIndex = getFlatIndex(localCoords);\n            offset = imod(flatIndex, 4);\n\n            flatIndex = idiv(flatIndex, 4, 1.);\n\n            int r = flatIndex / texShape[1];\n            int c = imod(flatIndex, texShape[1]);\n            vec2 uv = (vec2(c, r) + halfCR) / vec2(texShape[1], texShape[0]);\n            values = ${n.texture2D}(A, uv);\n\n            if (offset == 0) {\n              result[${a}] = values[0];\n            } else if (offset == 1) {\n              result[${a}] = values[1];\n            } else if (offset == 2) {\n              result[${a}] = values[2];\n            } else {\n              result[${a}] = values[3];\n            }\n          }\n        }\n        `}this.userCode=`\n        ${this.enableShapeUniforms?"\n  int getFlatIndex(ivec3 coords) {\n    return coords.x * outShapeStrides[0] + coords.y * outShapeStrides[1] + coords.z;\n  }\n":YO(e)}\n\n        void main() {\n          ivec3 coords = getOutputCoords();\n\n          vec4 result = vec4(0.);\n          int flatIndex, r, c, offset;\n          ivec3 localCoords;\n          vec2 uv;\n          vec4 values;\n\n          ${s}\n\n          ${n.output} = ${r};\n        }\n    `}}function IM(e){const t=jO();return QD(e,`${t.version}\n    precision highp float;\n    ${t.attribute} vec3 clipSpacePos;\n    ${t.attribute} vec2 uv;\n    ${t.varyingVs} vec2 resultUV;\n\n    void main() {\n      gl_Position = vec4(clipSpacePos, 1);\n      resultUV = uv;\n    }`)}function NM(e){return iO(e,new Float32Array([-1,1,0,0,1,-1,-1,0,0,0,1,1,0,1,1,1,-1,0,1,0]))}function SM(e){return oO(e,new Uint16Array([0,1,2,2,1,3]))}function TM(e,t,n,s,r,a){cO(t,n);const i=uO(e),o=e.TEXTURE_2D;return qD(e,(()=>e.bindTexture(o,i))),qD(e,(()=>e.texParameteri(o,e.TEXTURE_WRAP_S,e.CLAMP_TO_EDGE))),qD(e,(()=>e.texParameteri(o,e.TEXTURE_WRAP_T,e.CLAMP_TO_EDGE))),qD(e,(()=>e.texParameteri(o,e.TEXTURE_MIN_FILTER,e.NEAREST))),qD(e,(()=>e.texParameteri(o,e.TEXTURE_MAG_FILTER,e.NEAREST))),1===Xe().getNumber("WEBGL_VERSION")?qD(e,(()=>e.texImage2D(o,0,s,t,n,0,r,a,null))):qD(e,(()=>e.texStorage2D(o,1,s,t,n))),qD(e,(()=>e.bindTexture(e.TEXTURE_2D,null))),{texture:i,texShape:[n,t]}}function CM(e){return e.internalFormatFloat}function $M(e,t,n,s){const[r,a]=UD(t,n);return TM(e,r,a,CM(s),s.textureFormatFloat,e.FLOAT)}function EM(e){return e.internalFormatHalfFloat}function AM(e,t,n,s){const[r,a]=UD(t,n);return TM(e,r,a,EM(s),s.textureFormatFloat,s.textureTypeHalfFloat)}function RM(e){return e.downloadTextureFormat}function FM(e,t,n,s){const[r,a]=UD(t,n);return TM(e,r,a,RM(s),e.RGBA,e.UNSIGNED_BYTE)}function _M(e){return e.internalFormatPackedFloat}function DM(e,t,n,s){const[r,a]=HD(t,n);return TM(e,r,a,_M(s),e.RGBA,e.FLOAT)}function OM(e){return e.internalFormatPackedHalfFloat}function MM(e,t,n,s){const[r,a]=HD(t,n);return TM(e,r,a,OM(s),e.RGBA,s.textureTypeHalfFloat)}function LM(e,t,n){qD(e,(()=>e.bindBuffer(e.ARRAY_BUFFER,n)));return pO(e,t,"clipSpacePos",n,3,20,0)&&pO(e,t,"uv",n,2,20,12)}function zM(e,t,n,s,r,a){let i,o,l;qD(e,(()=>e.bindTexture(e.TEXTURE_2D,t))),r instanceof Uint8Array?(i=new Uint8Array(n*s*4),o=e.UNSIGNED_BYTE,l=e.RGBA):(i=new Float32Array(n*s*4),o=e.FLOAT,l=a.internalFormatPackedFloat),i.set(r),2===Xe().getNumber("WEBGL_VERSION")?qD(e,(()=>e.texSubImage2D(e.TEXTURE_2D,0,0,0,n,s,e.RGBA,o,i))):qD(e,(()=>e.texImage2D(e.TEXTURE_2D,0,l,n,s,0,e.RGBA,o,i))),qD(e,(()=>e.bindTexture(e.TEXTURE_2D,null)))}function PM(e,t,n){qD(e,(()=>e.bindTexture(e.TEXTURE_2D,t))),n.data instanceof Uint8Array?2===Xe().getNumber("WEBGL_VERSION")?qD(e,(()=>e.texSubImage2D(e.TEXTURE_2D,0,0,0,n.width,n.height,e.RGBA,e.UNSIGNED_BYTE,n.data))):qD(e,(()=>e.texImage2D(e.TEXTURE_2D,0,e.RGBA,n.width,n.height,0,e.RGBA,e.UNSIGNED_BYTE,n.data))):2===Xe().getNumber("WEBGL_VERSION")?qD(e,(()=>e.texSubImage2D(e.TEXTURE_2D,0,0,0,e.RGBA,e.UNSIGNED_BYTE,n))):qD(e,(()=>e.texImage2D(e.TEXTURE_2D,0,e.RGBA,e.RGBA,e.UNSIGNED_BYTE,n))),qD(e,(()=>e.bindTexture(e.TEXTURE_2D,null)))}function BM(e,t,n,s){const r=e.createBuffer();qD(e,(()=>e.bindBuffer(e.PIXEL_PACK_BUFFER,r)));const a=16*t*n;return qD(e,(()=>e.bufferData(e.PIXEL_PACK_BUFFER,a,e.STREAM_READ))),qD(e,(()=>e.readPixels(0,0,n,t,e.RGBA,e.FLOAT,0))),qD(e,(()=>e.bindBuffer(e.PIXEL_PACK_BUFFER,null))),r}function WM(e,t,n){const s=e,r=new Float32Array(n);return s.bindBuffer(s.PIXEL_PACK_BUFFER,t),s.getBufferSubData(s.PIXEL_PACK_BUFFER,0,r),s.bindBuffer(s.PIXEL_PACK_BUFFER,null),r}function VM(e,t,n,s){const[r,a]=UD(t,n),i=new Uint8Array(t*n*4);return qD(e,(()=>e.readPixels(0,0,r,a,s.downloadTextureFormat,e.UNSIGNED_BYTE,i))),new Float32Array(i.buffer)}function UM(e,t,n,s,r,a,i,o){const l=e,u=new Float32Array(function(e,t){const[n,s]=HD(e,t);return n*s*4}(a,i));return l.bindBuffer(l.PIXEL_PACK_BUFFER,t),l.getBufferSubData(l.PIXEL_PACK_BUFFER,0,u),l.bindBuffer(l.PIXEL_PACK_BUFFER,null),u}function GM(e,t,n){const s=new Float32Array(t*n*4);return qD(e,(()=>e.readPixels(0,0,n,t,e.RGBA,e.FLOAT,s))),s}class HM{constructor(e){this.outputTexture=null,this.program=null,this.disposed=!1,this.itemsToPoll=[];const t=Xe().getNumber("WEBGL_VERSION");if(null!=e?(this.gl=e,zD(t,e)):this.gl=PD(t),e=this.gl,2===Xe().getNumber("WEBGL_VERSION")){const t=e;this.createVertexArray=()=>qD(t,(()=>t.createVertexArray())),this.bindVertexArray=e=>qD(t,(()=>t.bindVertexArray(e))),this.deleteVertexArray=e=>qD(t,(()=>t.deleteVertexArray(e))),this.getVertexArray=()=>qD(t,(()=>t.getParameter(t.VERTEX_ARRAY_BINDING)))}else if(null!=e){const t=e.getExtension("OES_vertex_array_object");if(null==t)throw new Error("All WebGL1 implementations are expected to offer OES_vertex_array_object.");this.createVertexArray=()=>qD(e,(()=>t.createVertexArrayOES())),this.bindVertexArray=n=>qD(e,(()=>t.bindVertexArrayOES(n))),this.deleteVertexArray=n=>qD(e,(()=>t.deleteVertexArrayOES(n))),this.getVertexArray=()=>qD(e,(()=>e.getParameter(t.VERTEX_ARRAY_BINDING_OES)))}let n="WEBGL_color_buffer_float";const s="EXT_color_buffer_half_float";if(this.parallelCompilationExtension=this.gl.getExtension("KHR_parallel_shader_compile"),1===Xe().getNumber("WEBGL_VERSION")){const e="OES_texture_float",t="OES_texture_half_float";if(this.textureFloatExtension=JD(this.gl,e),zO(this.gl,t))this.textureHalfFloatExtension=JD(this.gl,t);else if(Xe().get("WEBGL_FORCE_F16_TEXTURES"))throw new Error("GL context does not support half float textures, yet the environment flag WEBGL_FORCE_F16_TEXTURES is set to true.");if(this.colorBufferFloatExtension=this.gl.getExtension(n),zO(this.gl,s))this.colorBufferHalfFloatExtension=JD(this.gl,s);else if(Xe().get("WEBGL_FORCE_F16_TEXTURES"))throw new Error("GL context does not support color renderable half floats, yet the environment flag WEBGL_FORCE_F16_TEXTURES is set to true.")}else if(n="EXT_color_buffer_float",zO(this.gl,n))this.colorBufferFloatExtension=this.gl.getExtension(n);else{if(!zO(this.gl,s))throw new Error("GL context does not support color renderable floats");this.colorBufferHalfFloatExtension=this.gl.getExtension(s)}this.vertexBuffer=NM(this.gl),this.indexBuffer=SM(this.gl),this.framebuffer=hO(this.gl),this.textureConfig=jD(this.gl,this.textureHalfFloatExtension)}get debug(){return Xe().getBool("DEBUG")}dispose(){if(this.disposed)return;null!=this.program&&console.warn("Disposing a GPGPUContext that still has a bound WebGLProgram. This is probably a resource leak, delete the program with GPGPUContext.deleteProgram before disposing."),null!=this.outputTexture&&console.warn("Disposing a GPGPUContext that still has a bound output matrix texture.  This is probably a resource leak, delete the output matrix texture with GPGPUContext.deleteMatrixTexture before disposing.");const e=this.gl;qD(e,(()=>e.finish())),qD(e,(()=>e.bindFramebuffer(e.FRAMEBUFFER,null))),qD(e,(()=>e.deleteFramebuffer(this.framebuffer))),qD(e,(()=>e.bindBuffer(e.ARRAY_BUFFER,null))),qD(e,(()=>e.bindBuffer(e.ELEMENT_ARRAY_BUFFER,null))),qD(e,(()=>e.deleteBuffer(this.indexBuffer))),this.disposed=!0}createFloat32MatrixTexture(e,t){return this.throwIfDisposed(),$M(this.gl,e,t,this.textureConfig)}createFloat16MatrixTexture(e,t){return this.throwIfDisposed(),AM(this.gl,e,t,this.textureConfig)}createUnsignedBytesMatrixTexture(e,t){return this.throwIfDisposed(),FM(this.gl,e,t,this.textureConfig)}uploadPixelDataToTexture(e,t){this.throwIfDisposed(),PM(this.gl,e,t)}uploadDenseMatrixToTexture(e,t,n,s){this.throwIfDisposed(),zM(this.gl,e,t,n,s,this.textureConfig)}createFloat16PackedMatrixTexture(e,t){return this.throwIfDisposed(),MM(this.gl,e,t,this.textureConfig)}createPackedMatrixTexture(e,t){return this.throwIfDisposed(),DM(this.gl,e,t,this.textureConfig)}deleteMatrixTexture(e){this.throwIfDisposed(),this.outputTexture===e&&(wO(this.gl,this.framebuffer),this.outputTexture=null),qD(this.gl,(()=>this.gl.deleteTexture(e)))}downloadByteEncodedFloatMatrixFromOutputTexture(e,t,n){return this.downloadMatrixDriver(e,(()=>VM(this.gl,t,n,this.textureConfig)))}downloadPackedMatrixFromBuffer(e,t,n,s,r,a){return UM(this.gl,e,0,0,0,r,a,this.textureConfig)}downloadFloat32MatrixFromBuffer(e,t){return WM(this.gl,e,t)}createBufferFromTexture(e,t,n){this.bindTextureToFrameBuffer(e);const s=BM(this.gl,t,n,this.textureConfig);return this.unbindTextureToFrameBuffer(),s}createAndWaitForFence(){const e=this.createFence(this.gl);return this.pollFence(e)}createFence(e){let t,n;if(Xe().getBool("WEBGL_FENCE_API_ENABLED")){const s=e,r=s.fenceSync(s.SYNC_GPU_COMMANDS_COMPLETE,0);e.flush(),n=()=>{const e=s.clientWaitSync(r,0,0);return e===s.ALREADY_SIGNALED||e===s.CONDITION_SATISFIED},t=r}else Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION")>0?(t=this.beginQuery(),this.endQuery(),n=()=>this.isQueryAvailable(t,Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION"))):n=()=>!0;return{query:t,isFencePassed:n}}downloadMatrixFromPackedTexture(e,t,n){return this.downloadMatrixDriver(e,(()=>GM(this.gl,t,n)))}createProgram(e){this.throwIfDisposed();const t=this.gl;null==this.vertexShader&&(this.vertexShader=IM(t));const n=sO(t);qD(t,(()=>t.attachShader(n,this.vertexShader))),qD(t,(()=>t.attachShader(n,e))),rO(t,n);const s=Object.assign(n,{vao:this.createVertexArray()});return this.debug&&aO(t,s),s}buildVao(e){this.setProgram(e),this.bindVertexArray(e.vao);const t=this.gl;qD(t,(()=>t.bindBuffer(t.ELEMENT_ARRAY_BUFFER,this.indexBuffer))),LM(t,e,this.vertexBuffer)}deleteProgram(e){this.throwIfDisposed(),e===this.program&&(this.program=null),null!=e&&(qD(this.gl,(()=>this.gl.deleteProgram(e))),this.deleteVertexArray(e.vao))}setProgram(e){this.throwIfDisposed(),this.program=e,null!=this.program&&this.debug&&aO(this.gl,this.program),qD(this.gl,(()=>this.gl.useProgram(e)))}getUniformLocation(e,t,n=!0){return this.throwIfDisposed(),n?mO(this.gl,e,t):gO(this.gl,e,t)}getAttributeLocation(e,t){return this.throwIfDisposed(),qD(this.gl,(()=>this.gl.getAttribLocation(e,t)))}getUniformLocationNoThrow(e,t){return this.throwIfDisposed(),this.gl.getUniformLocation(e,t)}setInputMatrixTexture(e,t,n){this.throwIfDisposed(),this.throwIfNoProgram(),yO(this.gl,e,t,n)}setOutputMatrixTexture(e,t,n){this.setOutputMatrixTextureDriver(e,n,t)}setOutputPackedMatrixTexture(e,t,n){this.throwIfDisposed();const[s,r]=HD(t,n);this.setOutputMatrixTextureDriver(e,s,r)}setOutputMatrixWriteRegion(e,t,n,s){this.setOutputMatrixWriteRegionDriver(n,e,s,t)}setOutputPackedMatrixWriteRegion(e,t,n,s){throw new Error("setOutputPackedMatrixWriteRegion not implemented.")}debugValidate(){null!=this.program&&aO(this.gl,this.program),vO(this.gl)}executeProgram(){this.throwIfDisposed(),this.throwIfNoProgram();const e=this.gl;if(this.debug){const e=this.getVertexArray();console.assert(e===this.program.vao,"VAO changed between setProgram and executeProgram!"),this.debugValidate()}qD(e,(()=>e.drawElements(e.TRIANGLES,6,e.UNSIGNED_SHORT,0)))}blockUntilAllProgramsCompleted(){this.throwIfDisposed(),qD(this.gl,(()=>this.gl.finish()))}getQueryTimerExtension(){return null==this.disjointQueryTimerExtension&&(this.disjointQueryTimerExtension=JD(this.gl,2===Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION")?"EXT_disjoint_timer_query_webgl2":"EXT_disjoint_timer_query")),this.disjointQueryTimerExtension}getQueryTimerExtensionWebGL2(){return this.getQueryTimerExtension()}getQueryTimerExtensionWebGL1(){return this.getQueryTimerExtension()}beginQuery(){if(2===Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION")){const e=this.gl,t=this.getQueryTimerExtensionWebGL2(),n=e.createQuery();return e.beginQuery(t.TIME_ELAPSED_EXT,n),n}const e=this.getQueryTimerExtensionWebGL1(),t=e.createQueryEXT();return e.beginQueryEXT(e.TIME_ELAPSED_EXT,t),t}endQuery(){if(2===Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION")){const e=this.gl,t=this.getQueryTimerExtensionWebGL2();return void e.endQuery(t.TIME_ELAPSED_EXT)}const e=this.getQueryTimerExtensionWebGL1();e.endQueryEXT(e.TIME_ELAPSED_EXT)}async waitForQueryAndGetTime(e){return await be((()=>this.disposed||this.isQueryAvailable(e,Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION")))),this.getQueryTime(e,Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_VERSION"))}getQueryTime(e,t){if(0===t)return null;if(2===t){const t=this.gl;return t.getQueryParameter(e,t.QUERY_RESULT)/1e6}{const t=this.getQueryTimerExtensionWebGL1();return t.getQueryObjectEXT(e,t.QUERY_RESULT_EXT)/1e6}}isQueryAvailable(e,t){if(0===t)return!0;if(2===t){const t=this.gl,n=this.getQueryTimerExtensionWebGL2(),s=t.getQueryParameter(e,t.QUERY_RESULT_AVAILABLE);return null==this.disjoint&&(this.disjoint=this.gl.getParameter(n.GPU_DISJOINT_EXT)),s&&!this.disjoint}{const t=this.getQueryTimerExtensionWebGL1(),n=t.getQueryObjectEXT(e,t.QUERY_RESULT_AVAILABLE_EXT);return null==this.disjoint&&(this.disjoint=this.gl.getParameter(t.GPU_DISJOINT_EXT)),n&&!this.disjoint}}pollFence(e){return new Promise((t=>{this.addItemToPoll((()=>e.isFencePassed()),(()=>t()))}))}pollItems(){const e=function(e){let t=0;for(;t<e.length;++t){if(!e[t]())break}return t-1}(this.itemsToPoll.map((e=>e.isDoneFn)));for(let t=0;t<=e;++t){const{resolveFn:e}=this.itemsToPoll[t];e()}this.itemsToPoll=this.itemsToPoll.slice(e+1)}addItemToPoll(e,t){if(this.itemsToPoll.push({isDoneFn:e,resolveFn:t}),this.itemsToPoll.length>1)return;let n;"setTimeoutCustom"in Xe().platform&&(n=Xe().platform.setTimeoutCustom.bind(Xe().platform)),be((()=>(this.pollItems(),0===this.itemsToPoll.length)),(()=>0),null,n)}bindTextureToFrameBuffer(e){this.throwIfDisposed(),xO(this.gl,e,this.framebuffer),this.debug&&vO(this.gl)}unbindTextureToFrameBuffer(){null!=this.outputTexture?(xO(this.gl,this.outputTexture,this.framebuffer),this.debug&&vO(this.gl)):wO(this.gl,this.framebuffer)}downloadMatrixDriver(e,t){this.bindTextureToFrameBuffer(e);const n=t();return this.unbindTextureToFrameBuffer(),n}setOutputMatrixTextureDriver(e,t,n){this.throwIfDisposed();const s=this.gl;xO(s,e,this.framebuffer),this.debug&&vO(s),this.outputTexture=e,qD(s,(()=>s.viewport(0,0,t,n))),qD(s,(()=>s.scissor(0,0,t,n)))}setOutputMatrixWriteRegionDriver(e,t,n,s){this.throwIfDisposed(),qD(this.gl,(()=>this.gl.scissor(e,t,n,s)))}throwIfDisposed(){if(this.disposed)throw new Error("Attempted to use disposed GPGPUContext.")}throwIfNoProgram(){if(null==this.program)throw new Error("No GPU program is currently set.")}}const{addImpl:jM,bincountImpl:qM,bincountReduceImpl:KM,bitwiseAndImpl:XM,castImpl:YM,ceilImpl:ZM,concatImpl:JM,equalImpl:QM,expImpl:eL,expm1Impl:tL,floorImpl:nL,gatherNdImpl:sL,gatherV2Impl:rL,greaterImpl:aL,greaterEqualImpl:iL,lessImpl:oL,lessEqualImpl:lL,linSpaceImpl:uL,logImpl:cL,maxImpl:hL,maximumImpl:pL,minimumImpl:dL,multiplyImpl:fL,negImpl:mL,notEqualImpl:gL,prodImpl:yL,raggedGatherImpl:bL,raggedRangeImpl:xL,raggedTensorToTensorImpl:wL,rangeImpl:vL,rsqrtImpl:kL,scatterImpl:IL,sigmoidImpl:NL,simpleAbsImpl:SL,sliceImpl:TL,sparseFillEmptyRowsImpl:CL,sparseReshapeImpl:$L,sparseSegmentReductionImpl:EL,sqrtImpl:AL,staticRegexReplaceImpl:RL,stridedSliceImpl:FL,stringNGramsImpl:_L,stringSplitImpl:DL,stringToHashBucketFastImpl:OL,subImpl:ML,tileImpl:LL,topKImpl:zL,transposeImpl:PL,uniqueImpl:BL}=j;function WL(e,t){return["x","y","z","w","u","v"].slice(0,t).map((t=>`${e}.${t}`))}function VL(e,t){return 1===t?[e]:WL(e,t)}class UL{constructor(e){if(this.variableNames=["A"],this.packedInputs=!1,this.packedOutput=!0,this.outputShape=e,this.rank=e.length,this.enableShapeUniforms=mM(this.outputShape.length),0===this.rank)this.userCode="\n        void main() {\n          setOutput(vec4(getA(), 0., 0., 0.));\n        }\n      ";else{const e=VL("rc",this.rank),t=uM(this.rank),n=this.getOutOfBoundsCondition(e),s=this.getSetup(e),r=this.getOutput(e);this.userCode=`\n        void main() {\n          ${t} rc = getOutputCoords();\n\n          if(${n}) {\n            setOutput(vec4(0));\n          } else {\n            ${s}\n\n            setOutput(vec4(${r}));\n          }\n        }\n      `}}getSourceCoordsArr(e){const t=[];for(let n=0;n<=1;n++)for(let s=0;s<=1;s++){let r=`${0===n?"r":"rp1"}, ${0===s?"c":"cp1"}`;for(let t=2;t<this.rank;t++)r=`${e[e.length-1-t]},`+r;t.push(r)}return t}getOutOfBoundsCondition(e){if(1===this.rank)return`rc > ${this.enableShapeUniforms?"outShape":this.outputShape[0]}`;let t="";for(let n=this.rank-2;n<this.rank;n++)t+=`${e[n]} >= ${this.enableShapeUniforms?`outShape[${n}]`:this.outputShape[n]}`,n<this.rank-1&&(t+="||");return t}getSetup(e){if(1===this.rank)return"";const t=e.slice(-2),n=this.enableShapeUniforms?`outShape[${this.rank} - 1]`:this.outputShape[this.rank-1],s=this.enableShapeUniforms?`outShape[${this.rank} - 2]`:this.outputShape[this.rank-2];return`\n      int r = ${t[0]};\n      int c = ${t[1]};\n      int rp1 = r + 1;\n      int cp1 = c + 1;\n\n      bool cEdge = cp1 >= ${n};\n      bool rEdge = rp1 >= ${s};\n    `}getOutput(e){const t=this.getSourceCoordsArr(e);if(1===this.rank){return`getA(rc), (rc + 1 >= ${this.enableShapeUniforms?"outShape":this.outputShape[0]} ? 0. : getA(rc + 1)), 0, 0`}return`getA(${t[0]}),\n            cEdge ? 0. : getA(${t[1]}),\n            rEdge ? 0. : getA(${t[2]}),\n            rEdge || cEdge ? 0. : getA(${t[3]})`}}class GL{constructor(e,t){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,this.customUniforms=[{name:"inputShape",type:"ivec3"}],this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length);let n="";for(let e=0;e<4;e++){let t="thisRC = rc;";e%2==1&&(t+="thisRC.z += 1;"),e>1&&(t+="thisRC.y += 1;"),n+=`\n        ${t}\n        ${e>0?"if(thisRC.y < rows && thisRC.z < cols){":""}\n          int flatIndex = getFlatIndex(thisRC);\n\n          ivec3 inputRC = inputCoordsFromReshapedOutCoords(flatIndex);\n          vec2 inputRCInnerDims = vec2(float(inputRC.y),float(inputRC.z));\n\n          result[${e}] =\n            getChannel(getA(inputRC.x, inputRC.y, inputRC.z), inputRCInnerDims);\n        ${e>0?"}":""}\n      `}var s,r;this.userCode=`\n      ${s=t,r=this.enableShapeUniforms,`\n    ivec3 inputCoordsFromReshapedOutCoords(int index) {\n      ${r?XO(["r","c","d"],"inputShape"):qO(["r","c","d"],s)}\n      return ivec3(r, c, d);\n    }\n  `}\n      ${this.enableShapeUniforms?"\n  int getFlatIndex(ivec3 coords) {\n    return coords.x * outShapeStrides[0] + coords.y * outShapeStrides[1] + coords.z;\n  }\n":YO(e)}\n\n      void main() {\n        ivec3 rc = getOutputCoords();\n\n        vec4 result = vec4(0.);\n\n        ivec3 thisRC;\n        int rows = ${this.enableShapeUniforms?"outShape[1]":e[1]};\n        int cols = ${this.enableShapeUniforms?"outShape[2]":e[2]};\n\n        ${n}\n\n        setOutput(result);\n      }\n    `}}class HL{constructor(e){this.gpgpu=e,this.numUsedTextures=0,this.numFreeTextures=0,this._numBytesAllocated=0,this._numBytesFree=0,this.freeTextures={},this.usedTextures={},this.logEnabled=!1}acquireTexture(e,t,n){const s=qL(t,n),r=KL(e,s,n);r in this.freeTextures||(this.freeTextures[r]=[]),r in this.usedTextures||(this.usedTextures[r]=[]);const a=jL(e,s,this.gpgpu.gl,this.gpgpu.textureConfig,n);if(this.freeTextures[r].length>0){this.numFreeTextures--,this.numUsedTextures++,this._numBytesFree-=a,this.log();const e=this.freeTextures[r].pop();return this.usedTextures[r].push(e),e}let i;return s===VD.PACKED_2X2_FLOAT32?i=this.gpgpu.createPackedMatrixTexture(e[0],e[1]):s===VD.PACKED_2X2_FLOAT16?i=this.gpgpu.createFloat16PackedMatrixTexture(e[0],e[1]):s===VD.UNPACKED_FLOAT32?i=this.gpgpu.createFloat32MatrixTexture(e[0],e[1]):s===VD.UNPACKED_FLOAT16?i=this.gpgpu.createFloat16MatrixTexture(e[0],e[1]):s===VD.PACKED_4X1_UNSIGNED_BYTE&&(i=this.gpgpu.createUnsignedBytesMatrixTexture(e[0],e[1])),this.usedTextures[r].push(i),this.numUsedTextures++,this._numBytesAllocated+=a,this.log(),i}releaseTexture(e,t,n,s){if(null==this.freeTextures)return;const r=qL(n,s),a=KL(t,r,s);a in this.freeTextures||(this.freeTextures[a]=[]);const i=jL(t,r,this.gpgpu.gl,this.gpgpu.textureConfig,s),o=Xe().get("WEBGL_DELETE_TEXTURE_THRESHOLD");-1!==o&&this._numBytesAllocated>o?(this.gpgpu.deleteMatrixTexture(e.texture),this._numBytesAllocated-=i):(this.freeTextures[a].push(e),this.numFreeTextures++,this._numBytesFree+=i),this.numUsedTextures--;const l=this.usedTextures[a],u=l&&l.indexOf(e);if(null==u||u<0)throw new Error("Cannot release a texture that was never provided by this texture manager");l[u]=l[l.length-1],l.pop(),this.log()}log(){if(!this.logEnabled)return;const e=this.numFreeTextures+this.numUsedTextures;console.log("Free/Used",`${this.numFreeTextures} / ${this.numUsedTextures}`,`(${e})`);const t=this._numBytesFree/this._numBytesAllocated;console.log(`Bytes allocated: ${this._numBytesAllocated}`),console.log(`Bytes unused: ${this._numBytesFree} (${Math.round(100*t)}%)`)}get numBytesAllocated(){return this._numBytesAllocated}get numBytesFree(){return this._numBytesFree}getNumUsedTextures(){return this.numUsedTextures}getNumFreeTextures(){return this.numFreeTextures}dispose(){if(null!=this.freeTextures){for(const e in this.freeTextures)this.freeTextures[e].forEach((e=>{this.gpgpu.deleteMatrixTexture(e.texture)}));for(const e in this.usedTextures)this.usedTextures[e].forEach((e=>{this.gpgpu.deleteMatrixTexture(e.texture)}));this.freeTextures=null,this.usedTextures=null,this.numUsedTextures=0,this.numFreeTextures=0,this._numBytesAllocated=0,this._numBytesFree=0}}}function jL(e,t,n,s,r){const a=function(e,t){switch(e){case VD.PACKED_2X2_FLOAT32:return _M(t);case VD.PACKED_2X2_FLOAT16:return OM(t);case VD.UNPACKED_FLOAT32:return CM(t);case VD.UNPACKED_FLOAT16:return EM(t);case VD.PACKED_4X1_UNSIGNED_BYTE:return RM(t);default:throw new Error(`Unknown physical texture type ${e}`)}}(t,s);let i;if(r){const[t,n]=HD(e[0],e[1]);i=t*n}else{const[t,n]=UD(e[0],e[1]);i=t*n}const o=function(e,t){const n=e;if(t===n.R32F)return 4;if(t===n.R16F)return 2;if(t===n.RGBA32F)return 16;if(t===e.RGBA)return 16;if(t===n.RGBA16F)return 8;if(t===n.RGBA8)return 4;throw new Error(`Unknown internal format ${t}`)}(n,a);return i*o}function qL(e,t){if(e===WD.UPLOAD)return VD.PACKED_2X2_FLOAT32;if(e===WD.RENDER||null==e)return function(e){return Xe().getBool("WEBGL_RENDER_FLOAT32_ENABLED")?e?VD.PACKED_2X2_FLOAT32:VD.UNPACKED_FLOAT32:e?VD.PACKED_2X2_FLOAT16:VD.UNPACKED_FLOAT16}(t);if(e===WD.DOWNLOAD||e===WD.PIXELS)return VD.PACKED_4X1_UNSIGNED_BYTE;throw new Error(`Unknown logical texture type ${e}`)}function KL(e,t,n){return`${e[0]}_${e[1]}_${t}_${n}`}class XL{constructor(e,t){this.variableNames=["A"],this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length),this.userCode=`\n      float unaryOperation(float x) {\n        ${t}\n      }\n\n      void main() {\n        float x = getAAtOutCoords();\n        float y = unaryOperation(x);\n\n        setOutput(y);\n      }\n    `}}const YL="if (isnan(x)) return x;",ZL="return x;",JL="return abs(x);";const QL="return (x >= 0.0) ? x : (exp(x) - 1.0);",ez=YL+"\n  return (x < 0.0) ? 0.0 : x;\n",tz=YL+"\n  return (x < 0.0) ? 0.0 : min(6.0, x);\n",nz="return x;",sz="return 1.0 / (1.0 + exp(-1.0 * x));",rz="return x;",az="\n  vec4 result;\n\n  result.r = (x.r >= 0.0) ? x.r : (exp(x.r) - 1.0);\n  result.g = (x.g >= 0.0) ? x.g : (exp(x.g) - 1.0);\n  result.b = (x.b >= 0.0) ? x.b : (exp(x.b) - 1.0);\n  result.a = (x.a >= 0.0) ? x.a : (exp(x.a) - 1.0);\n\n  return result;\n",iz="\n  vec4 result = x * vec4(greaterThanEqual(x, vec4(0.0)));\n  bvec4 isNaN = isnan(x);\n\n  result.r = isNaN.r ? x.r : result.r;\n  result.g = isNaN.g ? x.g : result.g;\n  result.b = isNaN.b ? x.b : result.b;\n  result.a = isNaN.a ? x.a : result.a;\n\n  return result;\n",oz="\n  vec4 result = min(x, vec4(6.)) * vec4(greaterThanEqual(x, vec4(0.0)));\n  bvec4 isNaN = isnan(x);\n\n  result.r = isNaN.r ? x.r : result.r;\n  result.g = isNaN.g ? x.g : result.g;\n  result.b = isNaN.b ? x.b : result.b;\n  result.a = isNaN.a ? x.a : result.a;\n\n  return result;\n",lz="return 1.0 / (1.0 + exp(-1.0 * x));";class uz{constructor(e,t){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length),this.userCode=`\n      vec4 unaryOperation(vec4 x) {\n        ${t}\n      }\n\n      void main() {\n        vec4 x = getAAtOutCoords();\n        vec4 y = unaryOperation(x);\n\n        setOutput(y);\n      }\n    `}}class cz{constructor(e){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!1,this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length);const t=e.length,n=VL("rc",t),s=uM(t),r=function(e,t){if(1===e)return"rc";let n="";for(let s=0;s<e;s++)n+=t[s],s<e-1&&(n+=",");return n}(t,n),a=n.slice(-2),i=t<=1?"rc":`vec2(${a.join(",")})`;this.userCode=`\n      void main() {\n        ${s} rc = getOutputCoords();\n        vec4 packedInput = getA(${r});\n\n        setOutput(getChannel(packedInput, ${i}));\n      }\n    `}}const hz=gd,pz={};const dz=Xe().getNumber("CPU_HANDOFF_SIZE_THRESHOLD");class fz extends Y{nextDataId(){return fz.nextDataId++}constructor(e){if(super(),this.pendingRead=new WeakMap,this.pendingDisposal=new WeakSet,this.dataRefCount=new WeakMap,this.numBytesInGPU=0,this.uploadWaitMs=0,this.downloadWaitMs=0,this.lastGlFlushTime=0,this.warnedAboutMemory=!1,this.pendingDeletes=0,this.disposed=!1,!Xe().getBool("HAS_WEBGL"))throw new Error("WebGL is not supported on this device");let t;if(null!=e){if(e instanceof HM)t=e;else{const n=PD(Xe().getNumber("WEBGL_VERSION"),e);t=new HM(n)}this.binaryCache={},this.gpgpuCreatedLocally=!1}else{const e=PD(Xe().getNumber("WEBGL_VERSION"));t=new HM(e),this.binaryCache=((n=Xe().getNumber("WEBGL_VERSION"))in pz||(pz[n]={}),pz[n]),this.gpgpuCreatedLocally=!0}var n;this.gpgpu=t,this.canvas=this.gpgpu.gl.canvas,this.textureManager=new HL(this.gpgpu),this.numMBBeforeWarning=null==Xe().global.screen?1024:Xe().global.screen.height*Xe().global.screen.width*window.devicePixelRatio*600/1024/1024,this.texData=new X(this,co())}numDataIds(){return this.texData.numDataIds()-this.pendingDeletes}writeTexture(e,t,n,s,r,a){const i=this.makeTensorInfo(t,n),o=this.texData.get(i.dataId);o.isPacked=!1,o.texture={texture:e,texShape:[s,r]},o.texShape=[s,r];const l=CO(t),u=new vM(l,!1,a),c=this.runWebGLProgram(u,[i],n,[[s,r]]);return c.shape=t,o.texture=null,this.disposeIntermediateTensorInfo(i),c.dataId}write(e,t,n){if((Xe().getBool("WEBGL_CHECK_NUMERICAL_PROBLEMS")||Xe().getBool("DEBUG"))&&this.checkNumericalProblems(e),"complex64"===n&&null!=e)throw new Error("Cannot write to a complex64 dtype. Please use tf.complex(real, imag).");const s={id:this.nextDataId()};return this.texData.set(s,{shape:t,dtype:n,values:e,usage:WD.UPLOAD,refCount:1}),s}refCount(e){if(this.texData.has(e)){return this.texData.get(e).refCount}return 0}incRef(e){this.texData.get(e).refCount++}decRef(e){if(this.texData.has(e)){this.texData.get(e).refCount--}}move(e,t,n,s,r){if(Xe().getBool("DEBUG")&&this.checkNumericalProblems(t),"complex64"===s)throw new Error("Cannot write to a complex64 dtype. Please use tf.complex(real, imag).");this.texData.set(e,{shape:n,dtype:s,values:t,usage:WD.UPLOAD,refCount:r})}disposeIntermediateTensorInfo(e){this.disposeData(e.dataId)}readSync(e){const t=this.texData.get(e),{values:n,dtype:s,complexTensorInfos:r,slice:a,shape:i,isPacked:o}=t;if(null!=a){let t;t=o?new uz(i,nz):new XL(i,nz);const n=this.runWebGLProgram(t,[{dataId:e,shape:i,dtype:s}],s),r=this.readSync(n.dataId);return this.disposeIntermediateTensorInfo(n),r}if(null!=n)return this.convertAndCacheOnCPU(e);if("string"===s)return n;const l=null!=this.activeTimers;let u,c;if(l&&(u=Xr()),"complex64"===s){c=dm(this.readSync(r.real.dataId),this.readSync(r.imag.dataId))}else c=this.getValuesFromTexture(e);return l&&(this.downloadWaitMs+=Xr()-u),this.convertAndCacheOnCPU(e,c)}async read(e){if(this.pendingRead.has(e)){const t=this.pendingRead.get(e);return new Promise((e=>t.push(e)))}const t=this.texData.get(e),{values:n,shape:s,slice:r,dtype:a,complexTensorInfos:i,isPacked:o}=t;if(null!=r){let t;t=o?new uz(s,nz):new XL(s,nz);const n=this.runWebGLProgram(t,[{dataId:e,shape:s,dtype:a}],a),r=this.read(n.dataId);return this.disposeIntermediateTensorInfo(n),r}if(null!=n)return this.convertAndCacheOnCPU(e);if(Xe().getBool("DEBUG")&&!Xe().getBool("WEBGL_DOWNLOAD_FLOAT_ENABLED")&&2===Xe().getNumber("WEBGL_VERSION"))throw new Error("tensor.data() with WEBGL_DOWNLOAD_FLOAT_ENABLED=false and WEBGL_VERSION=2 not yet supported.");let l,u,c=null;if("complex64"!==a&&Xe().get("WEBGL_BUFFER_SUPPORTED")){l=this.decode(e);const t=this.texData.get(l.dataId);c=this.gpgpu.createBufferFromTexture(t.texture.texture,...GD(s))}if(this.pendingRead.set(e,[]),"complex64"!==a&&await this.gpgpu.createAndWaitForFence(),"complex64"===a){const e=await Promise.all([this.read(i.real.dataId),this.read(i.imag.dataId)]);u=dm(e[0],e[1])}else if(null==c)u=this.getValuesFromTexture(e);else{const e=ue(s);u=this.gpgpu.downloadFloat32MatrixFromBuffer(c,e)}if(null!=l&&this.disposeIntermediateTensorInfo(l),null!=c){const e=this.gpgpu.gl;qD(e,(()=>e.deleteBuffer(c)))}const h=this.convertAndCacheOnCPU(e,u),p=this.pendingRead.get(e);return this.pendingRead.delete(e),p.forEach((e=>e(h))),this.pendingDisposal.has(e)&&(this.pendingDisposal.delete(e),this.disposeData(e)&&co().removeDataId(e,this),this.pendingDeletes--),h}readToGPU(e,t={}){const n=this.texData.get(e),{values:s,shape:r,slice:a,dtype:i,isPacked:o,texture:l}=n;if("complex64"===i)throw new Error("Does not support reading texture for complex64 dtype.");if(null!=a){let n;n=o?new uz(r,nz):new XL(r,nz);const s=this.runWebGLProgram(n,[{dataId:e,shape:r,dtype:i}],i),a=this.readToGPU(s,t);return this.disposeIntermediateTensorInfo(s),a}if(null==l)throw null!=s?new Error("Data is not on GPU but on CPU."):new Error("There is no data on GPU or CPU.");const u=this.decode(e,t.customTexShape),c=co().makeTensorFromTensorInfo(u),h=this.texData.get(u.dataId);return Object.assign({tensorRef:c},h.texture)}bufferSync(e){const t=this.readSync(e.dataId);if("string"===e.dtype)try{const n=t.map((e=>Jr(e)));return to(e.shape,e.dtype,n)}catch(e){throw new Error("Failed to decode encoded string bytes into utf-8")}return to(e.shape,e.dtype,t)}checkNumericalProblems(e){if(null!=e)for(let t=0;t<e.length;t++){const n=e[t];if(!YD(n)){if(Xe().getBool("WEBGL_RENDER_FLOAT32_CAPABLE"))throw Error(`The value ${n} cannot be represented with your current settings. Consider enabling float32 rendering: 'tf.env().set('WEBGL_RENDER_FLOAT32_ENABLED', true);'`);throw Error(`The value ${n} cannot be represented on this device.`)}}}getValuesFromTexture(e){const{shape:t,dtype:n,isPacked:s}=this.texData.get(e),r=ue(t);if(Xe().getBool("WEBGL_DOWNLOAD_FLOAT_ENABLED")){const n=this.decode(e),s=this.texData.get(n.dataId),a=this.gpgpu.downloadMatrixFromPackedTexture(s.texture.texture,...GD(t)).subarray(0,r);return this.disposeIntermediateTensorInfo(n),a}const a=Xe().getBool("WEBGL_PACK")&&!0===s,i=a?CO(t):t,o=a?new xM(i):new bM(i),l=this.runWebGLProgram(o,[{shape:i,dtype:n,dataId:e}],"float32"),u=this.texData.get(l.dataId),c=this.gpgpu.downloadByteEncodedFloatMatrixFromOutputTexture(u.texture.texture,u.texShape[0],u.texShape[1]).subarray(0,r);return this.disposeIntermediateTensorInfo(l),c}timerAvailable(){return Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_RELIABLE")>0}time(e){const t=this.activeTimers,n=[];let s=!1;null==this.programTimersStack?(this.programTimersStack=n,s=!0):this.activeTimers.push(n),this.activeTimers=n,e();const r=ea(this.activeTimers.map((e=>e.query))).filter((e=>null!=e)),a=ea(this.activeTimers.map((e=>e.name))).filter((e=>null!=e));this.activeTimers=t,s&&(this.programTimersStack=null);const i={uploadWaitMs:this.uploadWaitMs,downloadWaitMs:this.downloadWaitMs,kernelMs:null,wallMs:null};return(async()=>{if(Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_RELIABLE")>0){const e=await Promise.all(r);i.kernelMs=se(e),i.getExtraProfileInfo=()=>e.map(((e,t)=>({name:a[t],ms:e}))).map((e=>`${e.name}: ${e.ms}`)).join(", ")}else i.kernelMs={error:"WebGL query timers are not supported in this environment."};return this.uploadWaitMs=0,this.downloadWaitMs=0,i})()}memory(){return{unreliable:!1,numBytesInGPU:this.numBytesInGPU,numBytesInGPUAllocated:this.textureManager.numBytesAllocated,numBytesInGPUFree:this.textureManager.numBytesFree}}startTimer(){return Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_RELIABLE")>0?this.gpgpu.beginQuery():{startMs:Xr(),endMs:null}}endTimer(e){return Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_RELIABLE")>0?(this.gpgpu.endQuery(),e):(e.endMs=Xr(),e)}async getQueryTime(e){if(Xe().getNumber("WEBGL_DISJOINT_QUERY_TIMER_EXTENSION_RELIABLE")>0)return this.gpgpu.waitForQueryAndGetTime(e);const t=e;return t.endMs-t.startMs}disposeData(e,t=!1){if(this.pendingDisposal.has(e))return!1;if(!this.texData.has(e))return!0;if(t?this.texData.get(e).refCount=0:this.texData.get(e).refCount--,!t&&this.texData.get(e).refCount>0)return!1;if(this.pendingRead.has(e))return this.pendingDisposal.add(e),this.pendingDeletes++,!1;this.releaseGPUData(e);const{complexTensorInfos:n}=this.texData.get(e);return null!=n&&(this.disposeData(n.real.dataId,t),this.disposeData(n.imag.dataId,t)),this.texData.delete(e),!0}releaseGPUData(e){const{texture:t,dtype:n,texShape:s,usage:r,isPacked:a,slice:i}=this.texData.get(e),o=i&&i.origDataId||e,l=this.dataRefCount.get(o);l>1?this.dataRefCount.set(o,l-1):(this.dataRefCount.delete(o),null!=t&&(this.numBytesInGPU-=this.computeBytes(s,n),this.textureManager.releaseTexture(t,s,r,a)));const u=this.texData.get(e);u.texture=null,u.texShape=null,u.isPacked=!1,u.slice=null}getTexture(e){return this.uploadToGPU(e),this.texData.get(e).texture.texture}getDataInfo(e){return this.texData.get(e)}shouldExecuteOnCPU(e,t=dz){return Xe().getBool("WEBGL_CPU_FORWARD")&&e.every((e=>null==this.texData.get(e.dataId).texture&&ue(e.shape)<t))}getGPGPUContext(){return this.gpgpu}where(e){xr("tf.where() in webgl locks the UI thread. Call tf.whereAsync() instead");const t=e.dataSync();return hz(e.shape,t)}packedUnaryOp(e,t,n){const s=new uz(e.shape,t),r=this.compileAndRun(s,[e],n);return co().makeTensorFromTensorInfo(r)}abs(e){if(this.shouldExecuteOnCPU([e])&&"complex64"!==e.dtype){const t=SL(this.texData.get(e.dataId).values);return this.makeOutput(e.shape,e.dtype,t)}if(Xe().getBool("WEBGL_PACK_UNARY_OPERATIONS"))return this.packedUnaryOp(e,JL,e.dtype);const t=new XL(e.shape,JL),n=this.compileAndRun(t,[e]);return co().makeTensorFromTensorInfo(n)}makeTensorInfo(e,t,n){let s;if("string"===t&&null!=n&&n.length>0&&Ee(n[0])){const r=n.map((e=>Zr(e)));s=this.write(r,e,t)}else s=this.write(n,e,t);return this.texData.get(s).usage=null,{dataId:s,shape:e,dtype:t}}makeOutput(e,t,n){return co().makeTensorFromTensorInfo(this.makeTensorInfo(e,t,n),this)}unpackTensor(e){const t=new cz(e.shape);return this.runWebGLProgram(t,[e],e.dtype)}packTensor(e){const t=new UL(e.shape);return this.runWebGLProgram(t,[e],e.dtype,null,!0)}packedReshape(e,t){const n=[SO(e.shape),...TO(e.shape)],s={dtype:e.dtype,shape:n,dataId:e.dataId},r=[SO(t),...TO(t)],a=new GL(r,n),i=[n],o=this.runWebGLProgram(a,[s],e.dtype,i,!0);return{dataId:o.dataId,shape:t,dtype:o.dtype}}decode(e,t){const n=this.texData.get(e),{isPacked:s,shape:r,dtype:a}=n;if(null!=t){ie(ue(r)<=t[0]*t[1]*4,(()=>"customTexShape is too small. Row * Column * 4 should be equal or larger than the size of the tensor data."))}const i=CO(r);let o;o=s?new yM(i):new gM(i);const l=[null!=t?t:GD(i)];return{dtype:a,shape:r,dataId:this.runWebGLProgram(o,[{shape:i,dtype:a,dataId:e}],a,l,!0,t).dataId}}runWebGLProgram(e,t,n,s,r=!1,a){const i=this.makeTensorInfo(e.outputShape,n),o=this.texData.get(i.dataId);if(e.packedOutput&&(o.isPacked=!0),e.outPackingScheme===BD.DENSE){const t=null!=a?a:GD(e.outputShape);o.texShape=t.map((e=>2*e))}if(null!=e.outTexUsage&&(o.usage=e.outTexUsage),0===ue(i.shape))return o.values=ke(i.dtype,0),i;const l=[],u=t.map((t=>{if("complex64"===t.dtype)throw new Error("GPGPUProgram does not support complex64 input. For complex64 dtypes, please separate the program into real and imaginary parts.");let n=this.texData.get(t.dataId);if(null==n.texture){if(!e.packedInputs&&ue(t.shape)<=Xe().getNumber("WEBGL_SIZE_UPLOAD_UNIFORM"))return{shape:t.shape,texData:null,isUniform:!0,uniformValues:n.values};e.packedInputs&&(n.isPacked=!0,n.shape=t.shape)}if(this.uploadToGPU(t.dataId),!!n.isPacked!=!!e.packedInputs)t=n.isPacked?this.unpackTensor(t):this.packTensor(t),l.push(t),n=this.texData.get(t.dataId);else if(n.isPacked&&!AO(n.shape,t.shape)){const e=t,s=t.shape;t.shape=n.shape,t=this.packedReshape(t,s),l.push(t),n=this.texData.get(t.dataId),e.shape=s}return{shape:t.shape,texData:n,isUniform:!1}}));this.uploadToGPU(i.dataId);const c={shape:i.shape,texData:o,isUniform:!1},h=function(e,t,n){let s="";t.concat(n).forEach((t=>{const r=null!=t.texData&&null!=t.texData.slice&&t.texData.slice.flatOffset>0;if(e.enableShapeUniforms&&!t.isUniform){const a=t.texData.texShape,{useSqueezeShape:i,uniformShape:o,keptDims:l}=cM(e.packedInputs,t.shape,a);let u="",c="",h="";if(1===o.length&&e.packedInputs){const e=[Math.ceil(a[0]/2),Math.ceil(a[1]/2)];u=`${e[0]>1}_${e[1]>1}`}else if(2!==o.length||e.packedInputs){if(o.length>2&&!e.packedInputs){const e=Oe(o);h=`${e[0]===a[1]}_${e[e.length-1]===a[1]}`}}else c=`${o[0]>1}_${o[1]>1}`;const p=t.shape.length,d=2===o.length&&pe(t.shape,a),f=1===ue(t.shape),m=Qo(t.shape,n.shape),g=!e.packedInputs&&p===n.shape.length&&pe(a,n.texData.texShape),y=e.packedInputs||o.length>2?"":`${a[0]>1}_${a[1]>1}`;s+=`${p}_${g}_${i?l:""}_${o.length}_${f}_${m}_${d}_${u}_${c}_${h}_${y}_${r}`}else{const e=t.isUniform?"uniform":t.texData.texShape;s+=`${t.shape}_${e}_${r}`}}));const r=e.userCode;let a=e.constructor.name;return a+="_"+s+"_"+r+`${Xe().getNumber("WEBGL_VERSION")}`,a}(e,u,c),p=this.getAndSaveBinary(h,(()=>function(e,t,n,s){const r=n.map(((e,n)=>{const s={logicalShape:e.shape,texShape:e.isUniform?null:e.texData.texShape,isUniform:e.isUniform,isPacked:!e.isUniform&&e.texData.isPacked,flatOffset:null};return null!=e.texData&&null!=e.texData.slice&&e.texData.slice.flatOffset>0&&(s.flatOffset=e.texData.slice.flatOffset),{name:t.variableNames[n],shapeInfo:s}})),a=r.map((e=>e.shapeInfo)),i={logicalShape:s.shape,texShape:s.texData.texShape,isUniform:!1,isPacked:s.texData.isPacked,flatOffset:null},o=QO(r,i,t),l=eO(e.gl,o),u=e.createProgram(l);return Xe().get("ENGINE_COMPILE_ONLY")?{program:t,fragmentShader:l,source:o,webGLProgram:u,inShapeInfos:a,outShapeInfo:i,variablesLocations:null,customUniformLocations:null,infLoc:null,nanLoc:null,outShapeLocation:null,outShapeStridesLocation:null,outTexShapeLocation:null}:(e.buildVao(u),Object.assign({program:t,fragmentShader:l,source:o,webGLProgram:u,inShapeInfos:a,outShapeInfo:i},dM(e,t,u)))}(this.gpgpu,e,u,c))),d=null!=this.activeTimers;let f;d&&(f=this.startTimer()),Xe().get("ENGINE_COMPILE_ONLY")||function(e,t,n,s,r){t.program.enableShapeUniforms||(fM(t.inShapeInfos,n),fM([t.outShapeInfo],[s]));const a=s.texData.texture,i=s.texData.texShape;s.texData.isPacked?e.setOutputPackedMatrixTexture(a.texture,i[0],i[1]):e.setOutputMatrixTexture(a.texture,i[0],i[1]),e.setProgram(t.webGLProgram),e.bindVertexArray(t.webGLProgram.vao),1===Xe().getNumber("WEBGL_VERSION")&&null!==t.infLoc&&e.gl.uniform1f(t.infLoc,1/0),null!==t.nanLoc&&e.gl.uniform1f(t.nanLoc,NaN);for(let s=0;s<n.length;++s){const r=n[s],{uniform:a,offset:i,shape:o,texShape:l}=t.variablesLocations[s];if(o){const{uniformShape:n}=cM(t.program.packedInputs,r.shape,r.texData.texShape);switch(n.length){case 1:e.gl.uniform1iv(o,new Int32Array(n));break;case 2:e.gl.uniform2iv(o,new Int32Array(n));break;case 3:e.gl.uniform3iv(o,new Int32Array(n));break;case 4:e.gl.uniform4iv(o,new Int32Array(n))}}if(l&&e.gl.uniform2i(l,r.texData.texShape[0],r.texData.texShape[1]),null!=a)if(r.isUniform)if(ue(r.shape)<2)e.gl.uniform1f(a,r.uniformValues[0]);else{let t=r.uniformValues;t instanceof Float32Array||(t=new Float32Array(t)),e.gl.uniform1fv(a,t)}else null!=r.texData.slice&&null!=i&&e.gl.uniform1i(i,r.texData.slice.flatOffset),e.setInputMatrixTexture(r.texData.texture.texture,a,s)}const o=t.outShapeLocation;if(o)switch(s.shape.length){case 1:e.gl.uniform1iv(o,new Int32Array(s.shape));break;case 2:e.gl.uniform2iv(o,new Int32Array(s.shape));break;case 3:e.gl.uniform3iv(o,new Int32Array(s.shape));break;case 4:e.gl.uniform4iv(o,new Int32Array(s.shape))}if(t.outShapeStridesLocation){const n=Oe(s.shape);switch(s.shape.length){case 2:e.gl.uniform1iv(t.outShapeStridesLocation,new Int32Array(n));break;case 3:e.gl.uniform2iv(t.outShapeStridesLocation,new Int32Array(n));break;case 4:e.gl.uniform3iv(t.outShapeStridesLocation,new Int32Array(n))}}if(t.outTexShapeLocation&&e.gl.uniform2i(t.outTexShapeLocation,s.texData.texShape[0],s.texData.texShape[1]),t.program.customUniforms&&r)for(let n=0;n<t.program.customUniforms.length;++n){const s=t.program.customUniforms[n],a=t.customUniformLocations[n],i=r[n];if("float"===s.type)e.gl.uniform1fv(a,i);else if("vec2"===s.type)e.gl.uniform2fv(a,i);else if("vec3"===s.type)e.gl.uniform3fv(a,i);else if("vec4"===s.type)e.gl.uniform4fv(a,i);else if("int"===s.type)e.gl.uniform1iv(a,i);else if("ivec2"===s.type)e.gl.uniform2iv(a,i);else if("ivec3"===s.type)e.gl.uniform3iv(a,i);else{if("ivec4"!==s.type)throw Error(`uniform type ${s.type} is not supported yet.`);e.gl.uniform4iv(a,i)}}e.executeProgram()}(this.gpgpu,p,u,c,s),l.forEach((e=>this.disposeIntermediateTensorInfo(e))),d&&(f=this.endTimer(f),this.activeTimers.push({name:e.constructor.name,query:this.getQueryTime(f)}));const m=Xe().get("WEBGL_FLUSH_THRESHOLD");if(m>0){const e=Xr();e-this.lastGlFlushTime>m&&(this.gpgpu.gl.flush(),this.lastGlFlushTime=e)}if(!Xe().getBool("WEBGL_LAZILY_UNPACK")&&o.isPacked&&!1===r){const e=this.unpackTensor(i);return this.disposeIntermediateTensorInfo(i),e}return i}compileAndRun(e,t,n,s,r=!1){n=n||t[0].dtype;return this.runWebGLProgram(e,t,n,s,r)}getAndSaveBinary(e,t){return e in this.binaryCache||(this.binaryCache[e]=t()),this.binaryCache[e]}getTextureManager(){return this.textureManager}dispose(){if(!this.disposed){if(!Xe().getBool("IS_TEST")){Object.keys(this.binaryCache).forEach((e=>{this.gpgpu.deleteProgram(this.binaryCache[e].webGLProgram),delete this.binaryCache[e]}))}this.textureManager.dispose(),null!=this.canvas&&"undefined"!=typeof HTMLCanvasElement&&this.canvas instanceof HTMLCanvasElement?this.canvas.remove():this.canvas=null,this.gpgpuCreatedLocally&&(this.gpgpu.program=null,this.gpgpu.dispose()),this.disposed=!0}}floatPrecision(){return null==this.floatPrecisionValue&&(this.floatPrecisionValue=fo((()=>{if(!Xe().get("WEBGL_RENDER_FLOAT32_ENABLED")){const e=Xe().getBool("DEBUG");Xe().set("DEBUG",!1);const t=this.abs(Wo(1e-8)).dataSync()[0];if(Xe().set("DEBUG",e),t>0)return 32}return 16}))),this.floatPrecisionValue}epsilon(){return 32===this.floatPrecision()?1e-7:1e-4}uploadToGPU(e){const t=this.texData.get(e),{shape:n,dtype:s,values:r,texture:a,usage:i,isPacked:o}=t;if(null!=a)return;const l=null!=this.activeTimers;let u;l&&(u=Xr());let c=t.texShape;if(null==c&&(c=$O(n,o),t.texShape=c),null!=r){const e=CO(n);let a,i=c[1],h=c[0];const p=r instanceof Uint8Array||r instanceof Uint8ClampedArray;!o&&p||([i,h]=HD(c[0],c[1])),a=o?new kM(e,p):new vM(e,p);const d=p?[h,i]:c,f=this.makeTensorInfo(d,s),m=this.texData.get(f.dataId);m.usage=p?WD.PIXELS:WD.UPLOAD,m.texShape=d,this.gpgpu.uploadDenseMatrixToTexture(this.getTexture(f.dataId),i,h,r);const g=[[h,i]],y=!0,b=this.runWebGLProgram(a,[f],s,g,y),x=this.texData.get(b.dataId);t.texShape=x.texShape,t.isPacked=x.isPacked,t.usage=x.usage,Xe().get("ENGINE_COMPILE_ONLY")?this.disposeData(b.dataId):(t.texture=x.texture,t.values=null,this.texData.delete(b.dataId)),this.disposeIntermediateTensorInfo(f),l&&(this.uploadWaitMs+=Xr()-u)}else{const e=this.acquireTexture(c,i,s,o);t.texture=e}}convertAndCacheOnCPU(e,t){const n=this.texData.get(e),{dtype:s}=n;return null!=t&&(n.values=function(e,t){if("float32"===t||"complex64"===t)return e;if("int32"===t||"bool"===t){const n="int32"===t?new Int32Array(e.length):new Uint8Array(e.length);for(let t=0;t<n.length;++t)n[t]=Math.round(e[t]);return n}throw new Error(`Unknown dtype ${t}`)}(t,s)),n.values}acquireTexture(e,t,n,s){if(this.numBytesInGPU+=this.computeBytes(e,n),!this.warnedAboutMemory&&this.numBytesInGPU>1024*this.numMBBeforeWarning*1024){const e=(this.numBytesInGPU/1024/1024).toFixed(2);this.warnedAboutMemory=!0,console.warn(`High memory usage in GPU: ${e} MB, most likely due to a memory leak`)}return this.textureManager.acquireTexture(e,t,s)}computeBytes(e,t){return e[0]*e[1]*Ce(t)}checkCompileCompletion(){for(const[,e]of Object.entries(this.binaryCache))this.checkCompletion_(e)}async checkCompileCompletionAsync(){const e=[];if(this.gpgpu.parallelCompilationExtension){for(const[,t]of Object.entries(this.binaryCache))e.push(this.checkCompletionAsync_(t));return Promise.all(e)}for(const[,t]of Object.entries(this.binaryCache)){const n=new Promise((e=>{try{this.checkCompletion_(t),e(!0)}catch(e){throw e}}));e.push(n)}return Promise.all(e)}async checkCompletionAsync_(e){return this.gpgpu.gl.getProgramParameter(e.webGLProgram,this.gpgpu.parallelCompilationExtension.COMPLETION_STATUS_KHR)?this.checkCompletion_(e):(await Uf(),this.checkCompletionAsync_(e))}checkCompletion_(e){if(!1===this.gpgpu.gl.getProgramParameter(e.webGLProgram,this.gpgpu.gl.LINK_STATUS)){if(console.log(this.gpgpu.gl.getProgramInfoLog(e.webGLProgram)),!1===this.gpgpu.gl.getShaderParameter(e.fragmentShader,this.gpgpu.gl.COMPILE_STATUS))throw nO(e.source,this.gpgpu.gl.getShaderInfoLog(e.fragmentShader)),new Error("Failed to compile fragment shader.");throw new Error("Failed to link vertex and fragment shaders.")}return!0}getUniformLocations(){for(const e of Object.values(this.binaryCache)){this.gpgpu.buildVao(e.webGLProgram);const{variablesLocations:t,customUniformLocations:n,infLoc:s,nanLoc:r,outShapeLocation:a,outShapeStridesLocation:i,outTexShapeLocation:o}=dM(this.gpgpu,e.program,e.webGLProgram);e.variablesLocations=t,e.customUniformLocations=n,e.infLoc=s,e.nanLoc=r,e.outShapeLocation=a,e.outShapeStridesLocation=i,e.outTexShapeLocation=o}}createTensorFromGPUData(e,t,n){e.channels=e.channels||"RGBA";const{texture:s,height:r,width:a,channels:i}=e,o=co().backend;if(!o.gpgpu.gl.isTexture(s))throw new Error("The texture is invalid. Also, please make sure the texture and the TFJS WebGL backend are using the same canvas. If you want to use your own custom canvas, you have to create and use the custom TFJS WebGL backend created from the canvas through 'new tf.MathBackendWebGL(customCanvas)'.");const l=o.writeTexture(s,t,n,r,a,i);return co().makeTensorFromDataId(l,t,n,o)}}fz.nextDataId=0;const mz="4.6.0";function gz(){Xe().set("WEBGL_FORCE_F16_TEXTURES",!0)}Ua()&&No("webgl",(()=>new fz),2);const yz={forceHalfFloat:gz},bz="\n  if (isnan(a)) return a;\n  if (isnan(b)) return b;\n";class xz{constructor(e,t,n){this.variableNames=["A","B"],this.outputShape=tl(t,n),this.enableShapeUniforms=mM(this.outputShape.length),this.userCode=`\n      float binaryOperation(float a, float b) {\n        ${e}\n      }\n\n      void main() {\n        float a = getAAtOutCoords();\n        float b = getBAtOutCoords();\n        setOutput(binaryOperation(a, b));\n      }\n    `}}const wz="\n  result.r = isNaN.r ? NAN : result.r;\n  result.g = isNaN.g ? NAN : result.g;\n  result.b = isNaN.b ? NAN : result.b;\n  result.a = isNaN.a ? NAN : result.a;\n";class vz{constructor(e,t,n,s=!1){this.variableNames=["A","B"],this.supportsBroadcasting=!0,this.packedInputs=!0,this.packedOutput=!0,this.outputShape=tl(t,n);const r=this.outputShape.length;this.enableShapeUniforms=mM(r);let a="";if(s)if(0===r||1===ue(this.outputShape))a="\n          result.y = 0.;\n          result.z = 0.;\n          result.w = 0.;\n        ";else{if(a=`\n          ${uM(r)} coords = getOutputCoords();\n        `,1===r)this.enableShapeUniforms?a+="\n            result.y = (coords + 1) >= outShape ? 0. : result.y;\n            result.z = 0.;\n            result.w = 0.;\n          ":a+=`\n            result.y = (coords + 1) >= ${this.outputShape[0]} ? 0. : result.y;\n            result.z = 0.;\n            result.w = 0.;\n          `;else{const e=VL("coords",r);this.enableShapeUniforms?a+=`\n            bool nextRowOutOfBounds =\n              (${e[r-2]} + 1) >= outShape[${r} - 2];\n            bool nextColOutOfBounds =\n              (${e[r-1]} + 1) >= outShape[${r} - 1];\n            result.y = nextColOutOfBounds ? 0. : result.y;\n            result.z = nextRowOutOfBounds ? 0. : result.z;\n            result.w = nextColOutOfBounds || nextRowOutOfBounds ? 0. : result.w;\n          `:a+=`\n            bool nextRowOutOfBounds =\n              (${e[r-2]} + 1) >= ${this.outputShape[r-2]};\n            bool nextColOutOfBounds =\n              (${e[r-1]} + 1) >= ${this.outputShape[r-1]};\n            result.y = nextColOutOfBounds ? 0. : result.y;\n            result.z = nextRowOutOfBounds ? 0. : result.z;\n            result.w = nextColOutOfBounds || nextRowOutOfBounds ? 0. : result.w;\n          `}}this.userCode=`\n      vec4 binaryOperation(vec4 a, vec4 b) {\n        ${e}\n      }\n\n      void main() {\n        vec4 a = getAAtOutCoords();\n        vec4 b = getBAtOutCoords();\n\n        vec4 result = binaryOperation(a, b);\n        ${a}\n\n        setOutput(result);\n      }\n    `}}function kz(e){const{inputs:t,backend:n}=e,{x:s}=t;return n.incRef(s.dataId),{dataId:s.dataId,shape:s.shape,dtype:s.dtype}}const Iz={kernelName:yn,backendName:"webgl",kernelFunc:kz};function Nz(e){const{inputs:t,backend:n}=e,{real:s,imag:r}=t,a=n.makeTensorInfo(s.shape,"complex64"),i=n.texData.get(a.dataId),o=kz({inputs:{x:s},backend:n}),l=kz({inputs:{x:r},backend:n});return i.complexTensorInfos={real:o,imag:l},a}const Sz={kernelName:Ct,backendName:"webgl",kernelFunc:Nz},Tz="return (a < 0.) ? b * a : a;",Cz="\n  vec4 aLessThanZero = vec4(lessThan(a, vec4(0.)));\n  return (aLessThanZero * (b * a)) + ((vec4(1.0) - aLessThanZero) * a);\n";const $z={kernelName:In,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{alpha:a}=s,i=n.makeTensorInfo([],"float32",qr(a,"float32")),o=Xe().getBool("WEBGL_PACK_BINARY_OPERATIONS")?new vz(Cz,r.shape,i.shape):new xz(Tz,r.shape,i.shape),l=n.runWebGLProgram(o,[r,i],"float32");return n.disposeIntermediateTensorInfo(i),l}},Ez="return (a < 0.) ? b * a : a;",Az="\n  vec4 aLessThanZero = vec4(lessThan(a, vec4(0.)));\n  return (aLessThanZero * (b * a)) + ((vec4(1.0) - aLessThanZero) * a);\n";const Rz={kernelName:us,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{x:s,alpha:r}=t,a=Xe().getBool("WEBGL_PACK_BINARY_OPERATIONS")?new vz(Az,s.shape,r.shape):new xz(Ez,s.shape,r.shape);return n.runWebGLProgram(a,[s,r],"float32")}},Fz="if (isnan(x)) return x;";function _z({opSnippet:e,packedOpSnippet:t,cpuKernelImpl:n,dtype:s}){return({inputs:r,backend:a})=>{const{x:i}=r,o=a,l=s||i.dtype;if(o.shouldExecuteOnCPU([i])&&null!=n){const e=o.texData.get(i.dataId),t=n(e.values,l);return o.makeTensorInfo(i.shape,l,t)}let u;return u=Xe().getBool("WEBGL_PACK_UNARY_OPERATIONS")&&null!=t?new uz(i.shape,t):new XL(i.shape,e),o.runWebGLProgram(u,[i],l)}}function Dz({opSnippet:e,packedOpSnippet:t,checkOutOfBounds:n=!1,supportsComplex:s=!1,cpuKernelImpl:r,dtype:a}){return({inputs:i,backend:o})=>{const{a:l,b:u}=i,c=o;if(s&&"complex64"===l.dtype){const t=c.texData.get(l.dataId),n=c.texData.get(u.dataId),[s,r]=[[t.complexTensorInfos.real,n.complexTensorInfos.real],[t.complexTensorInfos.imag,n.complexTensorInfos.imag]].map((t=>{const[n,s]=t,r={dataId:n.dataId,dtype:n.dtype,shape:l.shape},a={dataId:s.dataId,dtype:s.dtype,shape:u.shape},i=new xz(e,l.shape,u.shape);return c.runWebGLProgram(i,[r,a],Sa(n.dtype,s.dtype))})),a=Nz({inputs:{real:s,imag:r},backend:c});return c.disposeIntermediateTensorInfo(s),c.disposeIntermediateTensorInfo(r),a}const h=a||Sa(l.dtype,u.dtype);if(("string"===l.dtype||"string"===u.dtype||c.shouldExecuteOnCPU([l,u]))&&null!=r){const e=c.texData.get(l.dataId).values,t=c.texData.get(u.dataId).values,n="string"===l.dtype?qm(e):e,s="string"===l.dtype?qm(t):t,[a,i]=r(l.shape,u.shape,n,s,h),o=c.makeTensorInfo(i,h);return c.texData.get(o.dataId).values=a,o}let p;return p=Xe().getBool("WEBGL_PACK_BINARY_OPERATIONS")&&null!=t?new vz(t,l.shape,u.shape,n):new xz(e,l.shape,u.shape),c.runWebGLProgram(p,[l,u],h)}}function Oz(e,t=!1){if("linear"===e)return t?rz:ZL;if("relu"===e)return t?iz:ez;if("elu"===e)return t?az:QL;if("relu6"===e)return t?oz:tz;if("prelu"===e)return t?Az:Ez;if("leakyrelu"===e)return t?Cz:Tz;if("sigmoid"===e)return t?lz:sz;throw new Error(`Activation ${e} has not been implemented for the WebGL backend.`)}class Mz{constructor(e,t,n,s=!1,r=!1,a=!1,i=null,o=!1,l=!1){this.variableNames=["matrixA","matrixB"],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=n,this.enableShapeUniforms=mM(this.outputShape.length);const u=s?e[1]:e[2],c=Math.ceil(u/2),h=s?"i * 2, rc.y":"rc.y, i * 2",p=r?"rc.z, i * 2":"i * 2, rc.z",d=s?["a.xxyy","a.zzww"]:["a.xxzz","a.yyww"],f=r?["b.xzxz","b.ywyw"]:["b.xyxy","b.zwzw"];let m="",g="";i&&(m=o?`vec4 activation(vec4 a) {\n          vec4 b = getPreluActivationWeightsAtOutCoords();\n          ${i}\n        }`:l?`vec4 activation(vec4 a) {\n          vec4 b = getLeakyreluAlphaAtOutCoords();\n          ${i}\n        }`:`vec4 activation(vec4 x) {\n          ${i}\n        }`,g="result = activation(result);");const y=a?"result += getBiasAtOutCoords();":"";a&&this.variableNames.push("bias"),o&&this.variableNames.push("preluActivationWeights"),l&&this.variableNames.push("leakyreluAlpha");let b="rc.x",x="rc.x";e[0]<t[0]?b=`imod(rc.x, ${e[0]})`:t[0]<e[0]&&(x=`imod(rc.x, ${t[0]})`),this.userCode=`\n      ${m}\n      // Don't use uniform for sharedDimensionPacked for performance.\n      const float sharedDimension = ${c}.0;\n\n      vec4 dot2x2ARowBCol(ivec3 rc) {\n        vec4 result = vec4(0);\n        int batchA = ${b};\n        int batchB = ${x};\n        for (int i = 0; i < ${c}; i++) {\n          vec4 a = getMatrixA(batchA, ${h});\n          vec4 b = getMatrixB(batchB, ${p});\n\n          // These swizzled products need to be separately added.\n          // See: https://github.com/tensorflow/tfjs/issues/1735\n          result += (${d[0]} * ${f[0]});\n          result += (${d[1]} * ${f[1]});\n        }\n        return result;\n      }\n\n      void main() {\n        ivec3 rc = getOutputCoords();\n        vec4 result = dot2x2ARowBCol(rc);\n\n        ${y}\n\n        ${g}\n\n        setOutput(result);\n      }\n    `}}const Lz={REAL:"return areal * breal - aimag * bimag;",IMAG:"return areal * bimag + aimag * breal;"};class zz{constructor(e,t,n){this.variableNames=["AReal","AImag","BReal","BImag"],this.outputShape=tl(t,n),this.userCode=`\n      float binaryOpComplex(\n          float areal, float aimag, float breal, float bimag) {\n        ${e}\n      }\n\n      void main() {\n        float areal = getARealAtOutCoords();\n        float aimag = getAImagAtOutCoords();\n        float breal = getBRealAtOutCoords();\n        float bimag = getBImagAtOutCoords();\n        setOutput(binaryOpComplex(areal, aimag, breal, bimag));\n      }\n    `}}const Pz="return a * b;";function Bz(e){const{inputs:t,backend:n}=e,{a:s,b:r}=t,a=Sa(s.dtype,r.dtype);if("complex64"===s.dtype){const e=n.texData.get(s.dataId),t=n.texData.get(r.dataId),a=new zz(Lz.REAL,s.shape,r.shape),i=new zz(Lz.IMAG,s.shape,r.shape),o=[{dataId:e.complexTensorInfos.real.dataId,dtype:e.complexTensorInfos.real.dtype,shape:s.shape},{dataId:e.complexTensorInfos.imag.dataId,dtype:e.complexTensorInfos.imag.dtype,shape:s.shape},{dataId:t.complexTensorInfos.real.dataId,dtype:t.complexTensorInfos.real.dtype,shape:r.shape},{dataId:t.complexTensorInfos.imag.dataId,dtype:t.complexTensorInfos.imag.dtype,shape:r.shape}],l=n.runWebGLProgram(a,o,"float32"),u=n.runWebGLProgram(i,o,"float32"),c=Nz({inputs:{real:l,imag:u},backend:n});return n.disposeIntermediateTensorInfo(l),n.disposeIntermediateTensorInfo(u),c}if(n.shouldExecuteOnCPU([s,r])){const e=n.texData.get(s.dataId),t=n.texData.get(r.dataId),[i,o]=fL(s.shape,r.shape,e.values,t.values,a),l=n.makeTensorInfo(o,a);return n.texData.get(l.dataId).values=i,l}let i;return i=Xe().getBool("WEBGL_PACK_BINARY_OPERATIONS")?new vz(Pz,s.shape,r.shape):new xz(Pz,s.shape,r.shape),n.runWebGLProgram(i,[s,r],a)}const Wz={kernelName:Zn,backendName:"webgl",kernelFunc:Bz};function Vz(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{shape:a}=s,i=n,o=ue(r.shape),l=xe(a,o),u=ue(l);ie(o===u,(()=>`The new shape (${l}) has ${u} elements and the old shape (${r.shape}) has ${o} elements. The new shape and old shape must have the same number of elements.`));const c=i.texData.get(r.dataId);return!c.isPacked||AO(r.shape,l)||null!==c.texture&&AO(c.shape,l)?(i.incRef(r.dataId),{dataId:r.dataId,shape:l,dtype:r.dtype}):function(e,t,n){const s=[SO(e.shape),...TO(e.shape)],r={dtype:e.dtype,shape:s,dataId:e.dataId},a=[SO(t),...TO(t)],i=new GL(a,s),o=[s],l=n.runWebGLProgram(i,[r],e.dtype,o,!0);return{dataId:l.dataId,shape:t,dtype:l.dtype}}(r,l,i)}const Uz={kernelName:bs,backendName:"webgl",kernelFunc:Vz};class Gz{constructor(e,t){this.variableNames=["x"];const{windowSize:n,batchSize:s,inSize:r,outSize:a}=e;this.outputShape=[s,a];const i=4*Math.floor(n/4),o=n%4;let l="sumValue += dot(values, ones);";if(null!=t){const e=1/t;l=`sumValue += dot(values * ${de(e)?e.toPrecision(2):e}, ones);`}let u="";r%n>0&&(u=`\n        if (inIdx < 0 || inIdx >= ${r}) {\n          return 0.0;\n        }\n      `),this.userCode=`\n      const vec4 ones = vec4(1.0, 1.0, 1.0, 1.0);\n\n      float getValue(int batch, int inIdx) {\n        ${u}\n        return getX(batch, inIdx);\n      }\n\n      void main() {\n        ivec2 coords = getOutputCoords();\n        int batch = coords[0];\n        int outIdx = coords[1];\n        int inOffset = outIdx * ${n};\n\n        float sumValue = 0.0;\n\n        for (int i = 0; i < ${i}; i += 4) {\n          int inIdx = inOffset + i;\n          vec4 values = vec4(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            getValue(batch, inIdx + 2),\n            getValue(batch, inIdx + 3)\n          );\n\n          ${l}\n        }\n\n        int inIdx = inOffset + ${i};\n        if (${1===o}) {\n          vec4 values = vec4(getValue(batch, inIdx), 0.0, 0.0, 0.0);\n\n          ${l}\n        } else if (${2===o}) {\n          vec4 values = vec4(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1), 0.0, 0.0);\n\n          ${l}\n        } else if (${3===o}) {\n          vec4 values = vec4(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            getValue(batch, inIdx + 2), 0.0);\n\n          ${l}\n        }\n        setOutput(sumValue);\n      }\n    `}}class Hz{constructor(e,t){this.variableNames=["x"];const{windowSize:n,batchSize:s,inSize:r,outSize:a}=e;this.outputShape=[s,a];let i="0.0",o="";"prod"===t?i="1.0":"min"===t?(i="1.0 / 1e-20",o="min"):"max"===t&&(i="-1.0 / 1e-20",o="max");let l=`${t}(${t}(${t}(minMaxValue[0], minMaxValue[1]), minMaxValue[2]), minMaxValue[3])`;"sum"===t?l="sumValue":"prod"===t?l="prodValue":"all"===t?l="allValue":"any"===t&&(l="anyValue");const u=4*Math.floor(n/4),c=n%4;let h=`\n      if (${"sum"===t}) {\n        sumValue += dot(values, ones);\n      } else if (${"prod"===t}) {\n        vec2 tmp = vec2(values[0], values[1]) * vec2(values[2], values[3]);\n        prodValue *= tmp[0] * tmp[1];\n      } else {\n        minMaxValue = ${o}(values, minMaxValue);\n        if (${"min"===t} || ${"max"===t}) {\n          minMaxValue = ${o}(values, minMaxValue);\n          bvec4 isNaN = isnan(values);\n          if (isNaN.r || isNaN.g || isNaN.b || isNaN.a) {\n            minMaxValue = vec4(NAN);\n          }\n        }\n      }\n    `,p="vec4";"all"===t?(i="1.0",h="\n        bool reducedAllValue = all(values);\n        float floatedReducedAllValue = float(reducedAllValue);\n        allValue = float(allValue >= 1.0 && floatedReducedAllValue >= 1.0);\n      ",p="bvec4"):"any"===t&&(i="0.0",h="\n        bool reducedAnyValue = any(values);\n        float floatedReducedAnyValue = float(reducedAnyValue);\n        anyValue = float(anyValue >= 1.0 || floatedReducedAnyValue >= 1.0);\n      ",p="bvec4");let d="";r%n>0&&(d=`\n        if (inIdx < 0 || inIdx >= ${r}) {\n          return initializationValue;\n        }\n      `),this.userCode=`\n      const float initializationValue = ${i};\n      const vec4 ones = vec4(1.0, 1.0, 1.0, 1.0);\n\n      float getValue(int batch, int inIdx) {\n        ${d}\n        return getX(batch, inIdx);\n      }\n\n      void main() {\n        ivec2 coords = getOutputCoords();\n        int batch = coords[0];\n        int outIdx = coords[1];\n        int inOffset = outIdx * ${n};\n\n        vec4 minMaxValue = vec4(${i});\n        float prodValue = 1.0;\n        float sumValue = 0.0;\n        float allValue = 1.0;\n        float anyValue = 0.0;\n\n        for (int i = 0; i < ${u}; i += 4) {\n          int inIdx = inOffset + i;\n          ${p} values = ${p}(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            getValue(batch, inIdx + 2),\n            getValue(batch, inIdx + 3)\n          );\n\n          ${h}\n        }\n\n        int inIdx = inOffset + ${u};\n        if (${1===c}) {\n          ${p} values = ${p}(\n            getValue(batch, inIdx),\n            initializationValue,\n            initializationValue,\n            initializationValue\n          );\n\n          ${h}\n        } else if (${2===c}) {\n          ${p} values = ${p}(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            initializationValue,\n            initializationValue\n          );\n\n          ${h}\n        } else if (${3===c}) {\n          ${p} values = ${p}(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            getValue(batch, inIdx + 2),\n            initializationValue\n          );\n\n          ${h}\n        }\n        setOutput(${l});\n      }\n    `}}function jz(e,t,n,s){const r=function(e){const t=[];for(;0===t.length||1!==t[t.length-1].outSize;){const n=t.length?t[t.length-1].outSize:e[1],s=Jf(n);t.push({inSize:n,windowSize:s,outSize:Math.ceil(n/s)})}return t}(e.shape);let a=e;for(let i=0;i<r.length;i++){const{inSize:o,windowSize:l,outSize:u}=r[i];let c,h;c="mean"===n?0===i?new Gz({windowSize:l,inSize:o,batchSize:e.shape[0],outSize:u},o):new Gz({windowSize:l,inSize:o,batchSize:e.shape[0],outSize:u}):new Hz({windowSize:l,inSize:o,batchSize:e.shape[0],outSize:u},n),h=a,a=s.runWebGLProgram(c,[a],t),h.dataId!==e.dataId&&s.disposeIntermediateTensorInfo(h)}return a}class qz{constructor(e,t){this.variableNames=["A"];const n=new Array(e.length);for(let s=0;s<n.length;s++)n[s]=e[t[s]];this.outputShape=n,this.rank=n.length;const s=uM(this.rank),r=function(e){const t=e.length;if(t>6)throw Error(`Transpose for rank ${t} is not yet supported`);const n=["resRC.x","resRC.y","resRC.z","resRC.w","resRC.u","resRC.v"],s=new Array(t);for(let t=0;t<e.length;t++)s[e[t]]=n[t];return s.join()}(t);this.userCode=`\n    void main() {\n      ${s} resRC = getOutputCoords();\n      setOutput(getA(${r}));\n    }\n    `}}class Kz{constructor(e,t){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0;const n=new Array(e.length);for(let s=0;s<n.length;s++)n[s]=e[t[s]];if(this.outputShape=n,this.rank=n.length,this.rank>6)throw Error(`Packed transpose for rank ${this.rank} is not yet supported.`);const s=uM(this.rank),r=WL("rc",this.rank),a=new Array(this.rank);for(let e=0;e<t.length;e++)a[t[e]]=r[e];const i=`vec2(${a.slice(-2).join()})`,o=`++${r[this.rank-1]} < ${n[this.rank-1]}`,l=`getChannel(getA(${a.join()}), ${i})`;this.userCode=`\n    void main() {\n      ${s} rc = getOutputCoords();\n      vec4 result = vec4(0.);\n      result[0] = ${l};\n      if(${o}) {\n        result[1] = ${l};\n      }\n      --${r[this.rank-1]};\n      if(++${r[this.rank-2]} < ${n[this.rank-2]}) {\n        result[2] = ${l};\n        if(${o}) {\n          result[3] = ${l};\n        }\n      }\n      setOutput(result);\n    }\n    `}}function Xz(e,t,n){const s=Xe().getBool("WEBGL_PACK_ARRAY_OPERATIONS")?new Kz(e.shape,t):new qz(e.shape,t);return n.runWebGLProgram(s,[e],e.dtype)}function Yz(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s;return function(e,t,n,s){const r=t,a=e.shape.length,i=we(r,e.shape);let o=i;const l=th(o,a),u=null!=l;let c=e;u&&(c=Xz(e,l,s),o=sh(o.length,a)),eh("sum",o,a);const[h,p]=Jc(c.shape,o);let d=h;n&&(d=Qc(h,i));const f=ue(p),m=Vz({inputs:{x:c},attrs:{shape:[ue(e.shape)/f,f]},backend:s}),g=jz(m,Ta(e.dtype),"sum",s),y=Vz({inputs:{x:g},attrs:{shape:d},backend:s});return s.disposeIntermediateTensorInfo(m),s.disposeIntermediateTensorInfo(g),u&&s.disposeIntermediateTensorInfo(c),y}(r,a,i,n)}const Zz={kernelName:Ps,backendName:"webgl",kernelFunc:Yz};function Jz(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{perm:a}=s,i=n,o=r.shape.length,l=new Array(o);for(let e=0;e<l.length;e++)l[e]=r.shape[a[e]];let u;if(i.shouldExecuteOnCPU([r])){const e=i.texData.get(r.dataId).values,t=PL(e,r.shape,r.dtype,a,l);u=i.makeTensorInfo(l,r.dtype);i.texData.get(u.dataId).values=t}else u=Xz(r,a,i);return u}const Qz={kernelName:or,backendName:"webgl",kernelFunc:Jz},eP=1e3;function tP({a:e,b:t,transposeA:n,transposeB:s,backend:r,bias:a=null,preluActivationWeights:i=null,leakyreluAlpha:o=0,activation:l=null}){const u=e.shape.length,c=t.shape.length,h=n?e.shape[u-2]:e.shape[u-1],p=s?t.shape[c-1]:t.shape[c-2],d=n?e.shape[u-1]:e.shape[u-2],f=s?t.shape[c-2]:t.shape[c-1],m=e.shape.slice(0,-2),g=t.shape.slice(0,-2),y=ue(m),b=ue(g),x=tl(e.shape.slice(0,-2),t.shape.slice(0,-2)).concat([d,f]);ie(h===p,(()=>`Error in matMul: inner shapes (${h}) and (${p}) of Tensors with shapes ${e.shape} and ${t.shape} and transposeA=${n} and transposeB=${s} must match.`));const w=n?[y,h,d]:[y,d,h],v=s?[b,f,p]:[b,p,f],k=Vz({inputs:{x:e},backend:r,attrs:{shape:w}}),I=Vz({inputs:{x:t},backend:r,attrs:{shape:v}}),N=[k,I],S=Math.max(y,b),T=n?k.shape[1]:k.shape[2],C=null!=a,$=null!=i,E="leakyrelu"===l,A=null!=l?Oz(l,!0):null;let R;if((1===d||1===f)&&T>eP&&!1===(C||$||E||null!=A)){let e=k,t=I;n&&(e=Jz({inputs:{x:k},backend:r,attrs:{perm:[0,2,1]}}),N.push(e)),s&&(t=Jz({inputs:{x:I},backend:r,attrs:{perm:[0,2,1]}}),N.push(t));const a=1===f;let i=e;1!==f&&(i=Vz({inputs:{x:e},backend:r,attrs:{shape:[S,T,1]}}),N.push(i));const o=1===f?2:1;let l=t;a&&(l=Vz({inputs:{x:t},backend:r,attrs:{shape:[S,1,T]}}),N.push(l));const u=Bz({inputs:{a:i,b:l},backend:r});R=Yz({inputs:{x:u},backend:r,attrs:{axis:o,keepDims:!0}}),N.push(u)}else{const l=Sa(e.dtype,t.dtype),u=new Mz(w,v,[S,d,f],n,s,C,A,$,E),c=[k,I];if(null!=a&&c.push(a),$&&c.push(i),E){const e=r.makeTensorInfo([],"float32",qr(o,"float32"));c.push(e),N.push(e)}R=r.runWebGLProgram(u,c,l)}const F=Vz({inputs:{x:R},backend:r,attrs:{shape:x}});N.push(R);for(const e of N)r.disposeIntermediateTensorInfo(e);return F}const nP={kernelName:gr,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{a:r,b:a,bias:i,preluActivationWeights:o}=t,{transposeA:l,transposeB:u,activation:c,leakyreluAlpha:h}=s;return tP({a:r,b:a,transposeA:l,transposeB:u,backend:n,bias:i,preluActivationWeights:o,leakyreluAlpha:h,activation:c})}},sP="return abs(x);";const rP={kernelName:et,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{x:s}=t;if(n.shouldExecuteOnCPU([s])&&"complex64"!==s.dtype){const e=n.texData.get(s.dataId),t=SL(e.values);return n.makeTensorInfo(s.shape,s.dtype,t)}let r;return r=Xe().getBool("WEBGL_PACK_UNARY_OPERATIONS")?new uz(s.shape,sP):new XL(s.shape,sP),n.runWebGLProgram(r,[s],s.dtype)}},aP=_z({opSnippet:YL+"\n  if (abs(x) > 1.) {\n    return NAN;\n  }\n  return acos(x);\n"}),iP={kernelName:tt,backendName:"webgl",kernelFunc:aP},oP=_z({opSnippet:YL+"\n  if (x < 1.0) return NAN;\nreturn log(x + sqrt(x * x - 1.0));"}),lP={kernelName:nt,backendName:"webgl",kernelFunc:oP},uP="return a + b;",cP=Dz({opSnippet:uP,packedOpSnippet:uP,supportsComplex:!0,cpuKernelImpl:jM}),hP={kernelName:st,backendName:"webgl",kernelFunc:cP};class pP{constructor(e,t){this.outputShape=[],this.outputShape=e,this.variableNames=t.map(((e,t)=>`T${t}`));const n=[];this.variableNames.forEach((e=>{n.push(`float v${e} = get${e}AtOutCoords();`)}));const s=this.variableNames.map((e=>`v${e}`)).join(" + ");this.userCode=`\n      void main() {\n        ${n.join("\n        ")}\n\n        float result = ${s};\n        setOutput(result);\n      }\n    `}}class dP{constructor(e,t){this.outputShape=[],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=e,this.variableNames=t.map(((e,t)=>`T${t}`));const n=[];this.variableNames.forEach((e=>{n.push(`vec4 v${e} = get${e}AtOutCoords();`)}));const s=this.variableNames.map((e=>`v${e}`)).join(" + ");this.userCode=`\n      void main() {\n        ${n.join("\n        ")}\n\n        vec4 result = ${s};\n        setOutput(result);\n      }\n    `}}const fP={kernelName:rt,backendName:"webgl",kernelFunc:function e(t){const{inputs:n,backend:s}=t,r=n;if(1===r.length)return kz({inputs:{x:r[0]},backend:s});if(r.length>Xe().get("WEBGL_MAX_TEXTURES_IN_SHADER")){const t=Math.floor(r.length/2),n=e({inputs:r.slice(0,t),backend:s}),a=e({inputs:r.slice(t),backend:s});return e({inputs:[n,a],backend:s})}const a=r.map((e=>e.dtype)).reduce(((e,t)=>Sa(e,t))),i=r.map((e=>e.shape)),o=Xe().getBool("WEBGL_PACK")?new dP(r[0].shape,i):new pP(r[0].shape,i);return s.runWebGLProgram(o,r,a)}};const mP={kernelName:at,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s,o=r.shape.length,l=we(a,r.shape);let u=l;const c=th(u,o);let h=r;null!=c&&(h=Jz({inputs:{x:r},backend:n,attrs:{perm:c}}),u=sh(u.length,o)),eh("all",u,o);const[p,d]=Jc(h.shape,u),f=Vz({inputs:{x:h},backend:n,attrs:{shape:[-1,ue(d)]}}),m=jz(f,f.dtype,"all",n);let g;if(i){g=Vz({inputs:{x:m},backend:n,attrs:{shape:Qc(p,l)}})}else g=Vz({inputs:{x:m},backend:n,attrs:{shape:p}});return n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(m),null!=c&&n.disposeIntermediateTensorInfo(h),g}};const gP={kernelName:it,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s,o=r.shape.length,l=we(a,r.shape);let u=l;const c=th(u,o);let h=r;null!=c&&(h=Jz({inputs:{x:r},backend:n,attrs:{perm:c}}),u=sh(u.length,o)),eh("any",u,o);const[p,d]=Jc(h.shape,u),f=Vz({inputs:{x:h},backend:n,attrs:{shape:[-1,ue(d)]}}),m=jz(f,f.dtype,"any",n);let g;if(i){g=Vz({inputs:{x:m},backend:n,attrs:{shape:Qc(p,l)}})}else g=Vz({inputs:{x:m},backend:n,attrs:{shape:p}});return n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(m),null!=c&&n.disposeIntermediateTensorInfo(h),g}};class yP{constructor(e,t,n){this.variableNames=["A"];const{windowSize:s,batchSize:r,outSize:a}=e;n||this.variableNames.push("bestIndicesA"),this.outputShape=[r,a];const i="max"===t?">":"<",o=n?"inOffset + i;":"round(getBestIndicesA(batch, inOffset + i));";this.userCode=`\n      void main() {\n        ivec2 coords = getOutputCoords();\n        int batch = coords[0];\n        int outIdx = coords[1];\n        int inOffset = outIdx * ${s};\n\n        int bestIndex = inOffset;\n        float bestValue = getA(batch, bestIndex);\n\n        for (int i = 0; i < ${s}; i++) {\n          int inIdx = ${o};\n          float candidate = getA(batch, inIdx);\n          if (candidate ${i} bestValue) {\n            bestValue = candidate;\n            bestIndex = inIdx;\n          }\n        }\n        setOutput(float(bestIndex));\n      }\n    `}}class bP{constructor(e,t,n,s){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,ie(e.length>2,(()=>`Packed arg${n.charAt(0).toUpperCase()+n.slice(1)} supports only inputs with rank above 2.`));const r=e[e.length-1],a=Math.ceil(r/t);this.outputShape=e.slice(0,-1),a>1&&this.outputShape.push(a),s||this.variableNames.push("bestIndicesA");const i=this.outputShape,o=i.length,l=uM(o),u=VL("coords",o);let c,h;if(1===a){h=o+1;const e=uM(h);c=`\n        ${e} sourceLocR = ${e}(${u.join()}, 0);\n        ++${u[o-1]};\n        ${e} sourceLocG = ${e}(${u.join()}, 0);\n        ++${u[o-2]};\n        ${e} sourceLocA = ${e}(${u.join()}, 0);\n        --${u[o-1]};\n        ${e} sourceLocB = ${e}(${u.join()}, 0);\n        --${u[o-2]};`}else h=o,c=`\n        ${l} sourceLocR = coords;\n        ++${u[o-1]};\n        ${l} sourceLocG = coords;\n        ++${u[o-2]};\n        ${l} sourceLocA = coords;\n        --${u[o-1]};\n        ${l} sourceLocB = coords;\n        --${u[o-2]};`;const p=["x","y","z","w","u","v"].slice(0,h),d="."+p[h-1],f=p.map((e=>"int "+e)),m=VL("sourceLocR",h-1).concat("inIdx.r"),g=VL("sourceLocG",h-1).concat("inIdx.g"),y=VL("sourceLocB",h-1).concat("inIdx.b"),b=VL("sourceLocA",h-1).concat("inIdx.a"),x="max"===n?"greaterThan":"lessThan",w=s?"":`\n          inIdx = round(vec4(getBestIndicesAChannel(${m.join()}),\n                             getBestIndicesAChannel(${g.join()}),\n                             getBestIndicesAChannel(${y.join()}),\n                             getBestIndicesAChannel(${b.join()})));`,v=`vec4(\n            getAChannel(${m.join()}),\n            hasNextCol ? getAChannel(${g.join()}) : 0.,\n            hasNextRow ? getAChannel(${y.join()}) : 0.,\n            hasNextRow && hasNextCol ? getAChannel(${b.join()}) : 0.)`,k=s?"":`\n      float getBestIndicesAChannel(${f.join()}) {\n        return getChannel(getBestIndicesA(${p.join()}),\n                                          vec2(${p.slice(-2).join()}));\n      }`;this.userCode=`\n      float getAChannel(${f.join()}) {\n        return getChannel(getA(${p.join()}),\n                               vec2(${p.slice(-2).join()}));\n      }\n      ${k}\n      void main() {\n        ${l} coords = getOutputCoords();\n        bool hasNextCol = ${u[o-1]} < ${i[o-1]-1};\n        bool hasNextRow = ${u[o-2]} < ${i[o-2]-1};\n        ${c}\n        ivec4 srcIdx = ivec4(sourceLocR${d}, sourceLocG${d},\n          sourceLocB${d}, sourceLocA${d}) * ${t};\n        ivec4 inIdx = srcIdx;\n        vec4 bestIndex = vec4(inIdx);\n        vec4 bestValue = ${v};\n\n        for (int i = 0; i < ${t}; i++) {\n          inIdx = srcIdx;\n          ${w}\n          vec4 candidate = ${v};\n          bvec4 nan = isnan(candidate);\n          bvec4 replace = bvec4(\n            vec4(${x}(candidate, bestValue)) * (vec4(1.0) - vec4(nan)));\n\n          bestValue = vec4(replace.x  ? candidate.x : bestValue.x,\n                           replace.y  ? candidate.y : bestValue.y,\n                           replace.z  ? candidate.z : bestValue.z,\n                           replace.w  ? candidate.w : bestValue.w);\n          bestIndex = mix(bestIndex, vec4(inIdx), vec4(replace));\n          srcIdx++;\n        }\n        setOutput(bestIndex);\n      }\n    `}}function xP(e,t,n,s=null){let r=t.shape[0],a=t.shape[1];null!=s&&(r=s.shape[0],a=s.shape[1]);const i=Jf(a),o={windowSize:i,inSize:a,batchSize:r,outSize:Math.ceil(a/i)},l=new yP(o,n,null==s),u=[t];null!=s&&u.push(s);const c=e.runWebGLProgram(l,u,"int32");if(1===c.shape[1])return c;const h=xP(e,t,n,c);return e.disposeIntermediateTensorInfo(c),h}function wP(e,t,n,s=null){const r=null!=s?s.shape:t.shape,a=Jf(r[r.length-1]),i=new bP(r,a,n,null==s),o=null==s?[t]:[t,s],l=e.runWebGLProgram(i,o,"int32");if(l.shape.length===t.shape.length){const s=wP(e,t,n,l);return e.disposeIntermediateTensorInfo(l),s}return l}function vP(e,t,n,s){const r=[n];if(eh("arg"+s.charAt(0).toUpperCase()+s.slice(1),r,t.shape.length),!Xe().getBool("WEBGL_PACK_REDUCE")||t.shape.length<=2){const n=[],a=e.texData.get(t.dataId);let i=t;null!==a&&a.isPacked&&(i=e.unpackTensor(t),n.push(i));const[o,l]=Jc(i.shape,r),u=ue(l),c=Vz({inputs:{x:i},backend:e,attrs:{shape:[-1,u]}});n.push(c);const h=xP(e,c,s);n.push(h);const p=Vz({inputs:{x:h},backend:e,attrs:{shape:o}});return n.forEach((t=>e.disposeIntermediateTensorInfo(t))),p}return wP(e,t,s)}const kP={kernelName:ot,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a}=s;let i=we(a,r.shape);const o=th(i,r.shape.length);let l=r;const u=[];null!=o&&(l=Jz({inputs:{x:r},backend:n,attrs:{perm:o}}),u.push(l),i=sh(i.length,l.shape.length)),eh("argMax",[i[0]],l.shape.length);const c=vP(n,l,i[0],"max");return u.forEach((e=>n.disposeIntermediateTensorInfo(e))),c}};const IP={kernelName:lt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a}=s;let i=we(a,r.shape);const o=th(i,r.shape.length);let l=r;const u=[];null!=o&&(l=Jz({inputs:{x:r},backend:n,attrs:{perm:o}}),u.push(l),i=sh(i.length,l.shape.length)),eh("argMin",[i[0]],l.shape.length);const c=vP(n,l,i[0],"min");return u.forEach((e=>n.disposeIntermediateTensorInfo(e))),c}},NP=_z({opSnippet:YL+"\n  if (abs(x) > 1.) {\n    return NAN;\n  }\n  return asin(x);\n"}),SP={kernelName:ut,backendName:"webgl",kernelFunc:NP},TP=_z({opSnippet:YL+"return log(x + sqrt(x * x + 1.0));"}),CP={kernelName:ct,backendName:"webgl",kernelFunc:TP},$P=_z({opSnippet:YL+"\n  return atan(x);\n"}),EP={kernelName:ht,backendName:"webgl",kernelFunc:$P},AP=Dz({opSnippet:bz+"\n  return atan(a, b);\n",packedOpSnippet:"\n  vec4 result = atan(a, b);\n  bvec4 isNaNA = isnan(a);\n  bvec4 isNaNB = isnan(b);\n  bvec4 isNaN = bvec4(isNaNA.x || isNaNB.x, isNaNA.y || isNaNB.y, isNaNA.z || isNaNB.z, isNaNA.w || isNaNB.w);\n  "+wz+"\n  return result;\n"}),RP={kernelName:dt,backendName:"webgl",kernelFunc:AP},FP=_z({opSnippet:YL+"\n  if ((x < -1.0) || (x > 1.0)) return NAN;\nreturn (log(1.0 + x) - log(1.0 - x)) / 2.0;"}),_P={kernelName:pt,backendName:"webgl",kernelFunc:FP};class DP{constructor(e,t,n,s=!1,r=!1){if(this.variableNames=["x"],"avg"===t&&n)throw new Error("Cannot compute positions for average pool.");const a=e.filterWidth,i=e.strideHeight,o=e.strideWidth,l=e.dilationHeight,u=e.dilationWidth,c=e.effectiveFilterHeight,h=e.effectiveFilterWidth,p=e.padInfo.top,d=e.padInfo.left;this.outputShape=e.outShape;const f="avg"===t,m=`((batch  * ${e.inHeight} + xR) * ${e.inWidth} + xC) * ${e.inChannels} + d`,g=`(xR * ${e.inWidth} + xC) * ${e.inChannels} + d`;let y="0.0";if(f||(y="-1.0 / 1e-20"),n){const t=">=";return void(this.userCode=`\n        const ivec2 strides = ivec2(${i}, ${o});\n        const ivec2 pads = ivec2(${p}, ${d});\n\n        void main() {\n          ivec4 coords = getOutputCoords();\n          int batch = coords[0];\n          int d = coords[3];\n\n          ivec2 xRCCorner = coords.yz * strides - pads;\n          int xRCorner = xRCCorner.x;\n          int xCCorner = xRCCorner.y;\n\n          // max/min x(?, ?, d) to get y(yR, yC, d).\n          // ? = to be determined\n          float minMaxValue = 0.0;\n          float minMaxValueFound = 0.0;\n          int minMaxPosition = 0;\n          float avgValue = 0.0;\n\n          for (int wR = 0; wR < ${c};\n              wR += ${l}) {\n            int xR = xRCorner + wR;\n\n            if (xR < 0 || xR >= ${e.inHeight}) {\n              continue;\n            }\n\n            for (int wC = 0; wC < ${h};\n                wC += ${u}) {\n              int xC = xCCorner + wC;\n\n              if (xC < 0 || xC >= ${e.inWidth}) {\n                continue;\n              }\n\n              float value = getX(batch, xR, xC, d);\n\n              // If a min / max value has already been found, use it. If not,\n              // use the current value.\n              float currMinMaxValue = mix(\n                  value, minMaxValue, minMaxValueFound);\n              if (value ${t} currMinMaxValue) {\n                minMaxValue = value;\n                minMaxValueFound = 1.0;\n                minMaxPosition = ${s?r?m:g:`wR * ${h} + wC`};\n              }\n            }\n          }\n          setOutput(float(minMaxPosition));\n        }\n      `)}let b=`${t}(${t}(${t}(minMaxValue[0], minMaxValue[1]), minMaxValue[2]), minMaxValue[3])`;"avg"===t&&(b="avgValue / max(count, 1.0)");const x=4*Math.floor(a/4),w=a%4,v=`\n      if (${f}) {\n        avgValue += dot(values, ones);\n      } else {\n        minMaxValue = max(values, minMaxValue);\n      }\n    `;this.userCode=`\n      const ivec2 strides = ivec2(${i}, ${o});\n      const ivec2 pads = ivec2(${p}, ${d});\n      const float initializationValue = ${y};\n      const vec4 ones = vec4(1.0, 1.0, 1.0, 1.0);\n\n      float count = 0.0;\n\n      float getValue(int batch, int xR, int xC, int d) {\n        if (xC < 0 || xC >= ${e.inWidth}) {\n          return initializationValue;\n        }\n        count += 1.0;\n        return getX(batch, xR, xC, d);\n      }\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords[0];\n        int d = coords[3];\n\n        ivec2 xRCCorner = coords.yz * strides - pads;\n        int xRCorner = xRCCorner.x;\n        int xCCorner = xRCCorner.y;\n\n        // max/min x(?, ?, d) to get y(yR, yC, d).\n        // ? = to be determined\n        vec4 minMaxValue = vec4(${y});\n        float avgValue = 0.0;\n        count = 0.0;\n\n        for (int wR = 0; wR < ${c};\n            wR += ${l}) {\n          int xR = xRCorner + wR;\n\n          if (xR < 0 || xR >= ${e.inHeight}) {\n            continue;\n          }\n\n          for (int wC = 0; wC < ${x}; wC += 4) {\n            int xC = xCCorner + wC * ${u};\n\n            vec4 values = vec4(\n              getValue(batch, xR, xC, d),\n              getValue(batch, xR, xC + ${u}, d),\n              getValue(batch, xR, xC + 2 * ${u}, d),\n              getValue(batch, xR, xC + 3 * ${u}, d)\n            );\n\n            ${v}\n          }\n\n          int xC = xCCorner + ${x};\n          if (${1===w}) {\n            vec4 values = vec4(\n              getValue(batch, xR, xC, d),\n              initializationValue,\n              initializationValue,\n              initializationValue\n            );\n\n            ${v}\n          } else if (${2===w}) {\n            vec4 values = vec4(\n              getValue(batch, xR, xC, d),\n              getValue(batch, xR, xC + ${u}, d),\n              initializationValue,\n              initializationValue\n            );\n\n            ${v}\n          } else if (${3===w}) {\n            vec4 values = vec4(\n              getValue(batch, xR, xC, d),\n              getValue(batch, xR, xC + ${u}, d),\n              getValue(batch, xR, xC + 2 * ${u}, d),\n              initializationValue\n            );\n\n            ${v}\n          }\n        }\n        setOutput(${b});\n      }\n    `}}class OP{constructor(e,t,n,s=!1,r=!1){if(this.variableNames=["x"],"avg"===t&&n)throw new Error("Cannot compute positions for average pool.");const a=e.filterWidth,i=e.strideDepth,o=e.strideHeight,l=e.strideWidth,u=e.dilationDepth,c=e.dilationHeight,h=e.dilationWidth,p=e.effectiveFilterDepth,d=e.effectiveFilterHeight,f=e.effectiveFilterWidth,m=e.padInfo.front,g=e.padInfo.top,y=e.padInfo.left;this.outputShape=e.outShape;const b="avg"===t;let x="0.0";if(b||(x="-1.0 / 1e-20"),n){const t=">=";return void(this.userCode=`\n        const ivec3 strides =\n            ivec3(${i}, ${o}, ${l});\n        const ivec3 pads = ivec3(${m}, ${g}, ${y});\n\n        void main() {\n          ivec5 coords = getOutputCoords();\n          int batch = coords.x;\n          int ch = coords.u;\n\n          ivec3 xCorner = ivec3(coords.y, coords.z, coords.w) * strides - pads;\n          int xDCorner = xCorner.x;\n          int xRCorner = xCorner.y;\n          int xCCorner = xCorner.z;\n\n          // max/min x(?, ?, ?, ch) to get y(yD, yR, yC, ch).\n          // ? = to be determined\n          float minMaxValue = 0.0;\n          float minMaxValueFound = 0.0;\n          int minMaxPosition = 0;\n\n          for (int wD = 0; wD < ${p};\n              wD += ${u}) {\n            int xD = xDCorner + wD;\n\n            if (xD < 0 || xD >= ${e.inDepth}) {\n              continue;\n            }\n\n            for (int wR = 0; wR < ${d};\n                wR += ${c}) {\n              int xR = xRCorner + wR;\n\n              if (xR < 0 || xR >= ${e.inHeight}) {\n                continue;\n              }\n\n              for (int wC = 0; wC < ${f};\n                  wC += ${h}) {\n                int xC = xCCorner + wC;\n\n                if (xC < 0 || xC >= ${e.inWidth}) {\n                  continue;\n                }\n\n                float value = getX(batch, xD, xR, xC, ch);\n\n                // If a min / max value has already been found, use it. If not,\n                // use the current value.\n                float currMinMaxValue = mix(\n                    value, minMaxValue, minMaxValueFound);\n                if (value ${t} currMinMaxValue) {\n                  minMaxValue = value;\n                  minMaxValueFound = 1.0;\n                  minMaxPosition = ${s?r?`(((batch * ${e.inDepth} + xD) * ${e.inHeight} + xR) * ${e.inWidth} + xC) * ${e.inChannels} + ch`:`((xD * ${e.inHeight} + xR) * ${e.inWidth} + xC) * ${e.inChannels} + ch`:`wD * ${d} * ${f} +\n                      wR * ${f} + wC`};\n                }\n              }\n            }\n          }\n          setOutput(float(minMaxPosition));\n        }\n      `)}let w=`${t}(${t}(${t}(minMaxValue[0], minMaxValue[1]), minMaxValue[2]), minMaxValue[3])`;"avg"===t&&(w="avgValue / max(count, 1.0)");const v=4*Math.floor(a/4),k=a%4,I=`\n      if (${b}) {\n        avgValue += dot(values, ones);\n      } else {\n        minMaxValue = max(values, minMaxValue);\n      }\n    `;this.userCode=`\n      const ivec3 strides =\n        ivec3(${i}, ${o}, ${l});\n      const ivec3 pads = ivec3(${m}, ${g}, ${y});\n      const float initializationValue = ${x};\n      const vec4 ones = vec4(1.0, 1.0, 1.0, 1.0);\n\n      float count = 0.0;\n\n      float getValue(int batch, int xD, int xR, int xC, int ch) {\n        if (xC < 0 || xC >= ${e.inWidth}) {\n          return initializationValue;\n        }\n        count += 1.0;\n        return getX(batch, xD, xR, xC, ch);\n      }\n\n      void main() {\n        ivec5 coords = getOutputCoords();\n        int batch = coords.x;\n        int ch = coords.u;\n\n        ivec3 xCorner = ivec3(coords.y, coords.z, coords.w) * strides - pads;\n        int xDCorner = xCorner.x;\n        int xRCorner = xCorner.y;\n        int xCCorner = xCorner.z;\n\n        // max/min x(?, ?, ?, d) to get y(yD, yR, yC, ch).\n        // ? = to be determined\n        vec4 minMaxValue = vec4(${x});\n        float avgValue = 0.0;\n        count = 0.0;\n\n        for (int wD = 0; wD < ${p};\n            wD += ${u}) {\n          int xD = xDCorner + wD;\n\n          if (xD < 0 || xD >= ${e.inDepth}) {\n            continue;\n          }\n\n          for (int wR = 0; wR < ${d};\n            wR += ${c}) {\n            int xR = xRCorner + wR;\n\n            if (xR < 0 || xR >= ${e.inHeight}) {\n              continue;\n            }\n\n            for (int wC = 0; wC < ${v}; wC += 4) {\n              int xC = xCCorner + wC * ${h};\n\n              vec4 values = vec4(\n                getValue(batch, xD, xR, xC, ch),\n                getValue(batch, xD, xR, xC + ${h}, ch),\n                getValue(batch, xD, xR, xC + 2 * ${h}, ch),\n                getValue(batch, xD, xR, xC + 3 * ${h}, ch)\n              );\n\n              ${I}\n            }\n\n            int xC = xCCorner + ${v};\n            if (${1===k}) {\n              vec4 values = vec4(\n                getValue(batch, xD, xR, xC, ch),\n                initializationValue,\n                initializationValue,\n                initializationValue\n              );\n\n              ${I}\n            } else if (${2===k}) {\n              vec4 values = vec4(\n                getValue(batch, xD, xR, xC, ch),\n                getValue(batch, xD, xR, xC + ${h}, ch),\n                initializationValue,\n                initializationValue\n              );\n\n              ${I}\n            } else if (${3===k}) {\n              vec4 values = vec4(\n                getValue(batch, xD, xR, xC, ch),\n                getValue(batch, xD, xR, xC + ${h}, ch),\n                getValue(batch, xD, xR, xC + 2 * ${h}, ch),\n                initializationValue\n              );\n\n              ${I}\n            }\n          }\n        }\n        setOutput(${w});\n      }\n    `}}const MP={kernelName:ft,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t;GO(r,"avgPool");const{filterSize:a,strides:i,pad:o,dimRoundingMode:l}=s;ie(Qu(i,1),(()=>`Error in avgPool: Either strides or dilations must be 1. Got strides ${i} and dilations '1'`));const u=Uu(r.shape,a,i,1,o,l);if(1===u.filterWidth&&1===u.filterHeight&&pe(u.inShape,u.outShape))return kz({inputs:{x:r},backend:n});const c=new DP(u,"avg",!1);return n.runWebGLProgram(c,[r],"float32")}};const LP={kernelName:gt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{filterSize:a,strides:i,pad:o,dimRoundingMode:l,dataFormat:u}=s,c=Gu(r.shape,a,i,[1,1,1],o,l,u),h=new OP(c,"avg",!1);return n.runWebGLProgram(h,[r],"float32")}};class zP{constructor(e){this.variableNames=["dy"],this.outputShape=e.inShape;const t=e.filterHeight,n=e.filterWidth,s=e.strideHeight,r=e.strideWidth,a=e.dilationHeight,i=e.dilationWidth,o=e.effectiveFilterHeight,l=e.effectiveFilterWidth,u=o-1-e.padInfo.top,c=l-1-e.padInfo.left,h=1/(t*n);this.userCode=`\n      const ivec2 pads = ivec2(${u}, ${c});\n      const float avgMultiplier = float(${h});\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n\n        ivec2 dyRCCorner = coords.yz - pads;\n        int dyRCorner = dyRCCorner.x;\n        int dyCCorner = dyRCCorner.y;\n\n        // Convolve dy(?, ?, d) with pos mask(:, :, d) to get dx(xR, xC, d).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n        for (int wR = 0; wR < ${o};\n            wR += ${a}) {\n          float dyR = float(dyRCorner + wR) / ${s}.0;\n\n          if (dyR < 0.0 || dyR >= ${e.outHeight}.0 || fract(dyR) > 0.0) {\n            continue;\n          }\n          int idyR = int(dyR);\n\n          for (int wC = 0; wC < ${l};\n            wC+= ${i}) {\n            float dyC = float(dyCCorner + wC) / ${r}.0;\n\n            if (dyC < 0.0 || dyC >= ${e.outWidth}.0 ||\n                fract(dyC) > 0.0) {\n              continue;\n            }\n            int idyC = int(dyC);\n\n            float dyValue = getDy(b, idyR, idyC, d);\n\n            dotProd += dyValue * avgMultiplier;\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}class PP{constructor(e){this.variableNames=["dy"],this.outputShape=e.inShape;const t=e.filterDepth,n=e.filterHeight,s=e.filterWidth,r=e.strideDepth,a=e.strideHeight,i=e.strideWidth,o=e.dilationDepth,l=e.dilationHeight,u=e.dilationWidth,c=e.effectiveFilterDepth,h=e.effectiveFilterHeight,p=e.effectiveFilterWidth,d=c-1-e.padInfo.front,f=h-1-e.padInfo.top,m=p-1-e.padInfo.left,g=1/(t*n*s);this.userCode=`\n      const ivec3 pads = ivec3(${d}, ${f}, ${m});\n      const float avgMultiplier = float(${g});\n\n      void main() {\n        ivec5 coords = getOutputCoords();\n        int batch = coords.x;\n        int ch = coords.u;\n\n        ivec3 dyCorner = ivec3(coords.y, coords.z, coords.w) - pads;\n        int dyDCorner = dyCorner.x;\n        int dyRCorner = dyCorner.y;\n        int dyCCorner = dyCorner.z;\n\n        // Convolve dy(?, ?, ?, d) with pos mask(:, :, :, ch) to get\n        // dx(xD, xR, xC, ch).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n\n        for (int wD = 0; wD < ${c};\n            wD += ${o}) {\n          float dyD = float(dyDCorner + wD) / ${r}.0;\n\n          if (dyD < 0.0 || dyD >= ${e.outDepth}.0 || fract(dyD) > 0.0) {\n            continue;\n          }\n          int idyD = int(dyD);\n\n          for (int wR = 0; wR < ${h};\n              wR += ${l}) {\n            float dyR = float(dyRCorner + wR) / ${a}.0;\n\n            if (dyR < 0.0 || dyR >= ${e.outHeight}.0 ||\n                fract(dyR) > 0.0) {\n              continue;\n            }\n            int idyR = int(dyR);\n\n            for (int wC = 0; wC < ${p};\n                wC += ${u}) {\n              float dyC = float(dyCCorner + wC) / ${i}.0;\n\n              if (dyC < 0.0 || dyC >= ${e.outWidth}.0 ||\n                  fract(dyC) > 0.0) {\n                continue;\n              }\n              int idyC = int(dyC);\n\n              float dyValue = getDy(batch, idyD, idyR, idyC, ch);\n\n              dotProd += dyValue * avgMultiplier;\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}const BP={kernelName:yt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a}=t,i=a,{filterSize:o,strides:l,pad:u,dimRoundingMode:c}=s,h=Gu(i.shape,o,l,[1,1,1],u,c),p=new PP(h);return n.runWebGLProgram(p,[r],i.dtype)}};const WP={kernelName:mt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a}=t,i=a;GO([r,a],"avgPoolGrad");const{filterSize:o,strides:l,pad:u}=s,c=Uu(i.shape,o,l,1,u),h=new zP(c);return n.runWebGLProgram(h,[r],i.dtype)}};const VP={kernelName:bt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{a:r,b:a}=t,{transposeA:i,transposeB:o}=s;return tP({a:r,b:a,transposeA:i,transposeB:o,backend:n})}};class UP{constructor(e,t,n,s,r,a){this.outputShape=[],this.variableNames=["x","mean","variance"],tl(e,t),tl(e,n);let i="0.0";null!=s&&(tl(e,s),this.variableNames.push("offset"),i="getOffsetAtOutCoords()");let o="1.0";null!=r&&(tl(e,r),this.variableNames.push("scale"),o="getScaleAtOutCoords()"),this.outputShape=e,this.userCode=`\n      void main() {\n        float x = getXAtOutCoords();\n        float mean = getMeanAtOutCoords();\n        float variance = getVarianceAtOutCoords();\n        float offset = ${i};\n        float scale = ${o};\n        float inv = scale * inversesqrt(variance + float(${a}));\n        setOutput(dot(vec3(x, -mean, offset), vec3(inv, inv, 1)));\n      }\n    `}}class GP{constructor(e,t,n,s,r,a){this.packedInputs=!0,this.packedOutput=!0,this.variableNames=["x","mean","variance"],tl(e,t),tl(e,n);let i="vec4(0.0)";null!=s&&(tl(e,s),this.variableNames.push("offset"),i="getOffsetAtOutCoords()");let o="vec4(1.0)";null!=r&&(tl(e,r),this.variableNames.push("scale"),o="getScaleAtOutCoords()"),this.outputShape=e,this.userCode=`\n      void main() {\n        vec4 offset = ${i};\n        vec4 scale = ${o};\n\n        vec4 x = getXAtOutCoords();\n        vec4 mean = getMeanAtOutCoords();\n        vec4 variance = getVarianceAtOutCoords();\n\n        vec4 inv = scale * inversesqrt(variance + vec4(${a}));\n\n        setOutput((x - mean) * inv + offset);\n      }\n    `}}const HP={kernelName:pn,backendName:"webgl",kernelFunc:({inputs:e,backend:t,attrs:n})=>{const{x:s,mean:r,variance:a,offset:i,scale:o}=e;ie(r.shape.length===a.shape.length,(()=>"Batch normalization gradient requires mean and variance to have equal ranks.")),ie(null==i||r.shape.length===i.shape.length,(()=>"Batch normalization gradient requires mean and offset to have equal ranks.")),ie(null==o||r.shape.length===o.shape.length,(()=>"Batch normalization gradient requires mean and scale to have equal ranks."));let{varianceEpsilon:l}=n;null==l&&(l=.001);const u=[s,r,a];let c=null;null!=i&&(c=i.shape,u.push(i));let h=null;null!=o&&(h=o.shape,u.push(o));const p=Xe().getBool("WEBGL_PACK_NORMALIZATION")?new GP(s.shape,r.shape,a.shape,c,h,l):new UP(s.shape,r.shape,a.shape,c,h,l);return t.runWebGLProgram(p,u,u[0].dtype)}};class jP{constructor(e){this.variableNames=["source"],this.outputShape=e,this.rank=e.length;const t=uM(this.rank);this.customUniforms=[{name:"start",arrayIndex:this.rank,type:"int"}];const n=function(e){if(1===e)return"sourceLoc";if(e<=6)return qP.slice(0,e).map((e=>"sourceLoc."+e)).join(",");throw Error(`Slicing for rank ${e} is not yet supported`)}(this.rank);let s;s=`\n        ${t} sourceLoc;\n        ${t} coords = getOutputCoords();\n        ${e.map(((e,t)=>`sourceLoc.${qP[t]} = start[${t}] + coords.${qP[t]};`)).join("\n")}\n      `,this.userCode=`\n      void main() {\n        ${s}\n        setOutput(getSource(${n}));\n      }\n    `}}const qP=["x","y","z","w","u","v"];class KP{constructor(e){this.variableNames=["source"],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=e,this.rank=e.length,this.customUniforms=[{name:"start",arrayIndex:this.rank,type:"int"}];const t=uM(this.rank),n=VL("coords",this.rank),s=VL("sourceLoc",this.rank),r=1===this.rank?"sourceLoc":`vec2(${s.slice(-2).join()})`,a=`getChannel(getSource(${s.join()}), ${r})`,i=`\n      result.x = ${a};\n      if (++${n[this.rank-1]} < ${e[this.rank-1]}) {\n        ++${s[this.rank-1]};\n        result.y = ${a};\n        --${s[this.rank-1]};\n      }\n    `,o=1===this.rank?"":`\n      --${n[this.rank-1]};\n      if (++${n[this.rank-2]} < ${e[this.rank-2]}) {\n        ++${s[this.rank-2]};\n        result.z = ${a};\n        if (++${n[this.rank-1]} < ${e[this.rank-1]}) {\n          ++${s[this.rank-1]};\n          result.w = ${a};\n        }\n      }\n    `,l=this.rank<=4?`sourceLoc = coords +\n            ${t}(${e.map(((e,t)=>`start[${t}]`)).join()});`:e.map(((e,t)=>`${s[t]} = ${n[t]} + start[${t}];`)).join("\n");this.userCode=`\n      void main() {\n        ${t} coords = getOutputCoords();\n        ${t} sourceLoc;\n        ${l}\n        vec4 result = vec4(0.);\n        ${i}\n        ${o}\n        setOutput(result);\n      }\n    `}}function XP(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{begin:a,size:i}=s,[o,l]=hu(r,a,i);if(Zl(r,o,l),0===ue(l))return n.makeTensorInfo(l,r.dtype,[]);if(n.shouldExecuteOnCPU([r])||"string"===r.dtype){const e=n.texData.get(r.dataId),t=TL(e.values,o,l,r.shape,r.dtype);return n.makeTensorInfo(l,r.dtype,t)}const{isPacked:u}=n.texData.get(r.dataId),c=uu(r.shape,o,l);if(u||!c){const e=Xe().getBool("WEBGL_PACK_ARRAY_OPERATIONS")?new KP(l):new jP(l),t=[o];return n.runWebGLProgram(e,[r],r.dtype,t)}return n.uploadToGPU(r.dataId),function(e,t,n,s){const r=s.texData.get(e.dataId),a=s.makeTensorInfo(n,e.dtype),i=s.texData.get(a.dataId);Object.assign(i,r),i.refCount=1,i.shape=n,i.dtype=e.dtype;let o=cu(t,Oe(e.shape));r.slice&&(o+=r.slice.flatOffset),i.slice={flatOffset:o,origDataId:r.slice&&r.slice.origDataId||e.dataId};const l=s.dataRefCount.get(i.slice.origDataId)||1;return s.dataRefCount.set(i.slice.origDataId,l+1),a}(r,o,l,n)}const YP={kernelName:Fs,backendName:"webgl",kernelFunc:XP},ZP={kernelName:xt,backendName:"webgl",kernelFunc:e=>{const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{blockShape:a,crops:i}=s;ie(r.shape.length<=4,(()=>"batchToSpaceND for rank > 4 with a WebGL backend not implemented yet"));const o=a.reduce(((e,t)=>e*t)),l=em(r.shape,a,o),u=tm(l.length,a.length),c=nm(r.shape,a,o),h=sm(i,a.length),p=rm(c,i,a.length),d=[],f=Vz({inputs:{x:r},backend:n,attrs:{shape:l}}),m=Jz({inputs:{x:f},backend:n,attrs:{perm:u}}),g=Vz({inputs:{x:m},backend:n,attrs:{shape:c}}),y=XP({inputs:{x:g},backend:n,attrs:{begin:h,size:p}});return d.push(f),d.push(m),d.push(g),d.forEach((e=>n.disposeIntermediateTensorInfo(e))),y}};const JP={kernelName:wt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,weights:a}=t,{size:i}=s,o=n.readSync(r.dataId),l=n.readSync(a.dataId),u=qM(o,l,a.dtype,a.shape,i);return n.makeTensorInfo([i],a.dtype,u)}};const QP={kernelName:vt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{a:s,b:r}=t,a=Xe().getBool("WEBGL_PACK_BINARY_OPERATIONS"),i=Xe().getNumber("WEBGL_VERSION");if(n.shouldExecuteOnCPU([s,r])||1===i){const e=n.texData.get(s.dataId).values,t=n.texData.get(r.dataId).values,[a,i]=XM(s.shape,r.shape,e,t,s.dtype),o=n.makeTensorInfo(i,s.dtype);return n.texData.get(o.dataId).values=a,o}let o;return o=a?new vz("\n  int r = int(a.r) & int(b.r);\n  int g = int(a.g) & int(b.g);\n  int rb = int(a.b) & int(b.b);\n  int ra = int(a.a) & int(b.a);\n  return vec4(r, g, rb, ra);\n",s.shape,r.shape,!1):new xz("\n  return float(int(a.r) & int(b.r));\n",s.shape,r.shape),n.runWebGLProgram(o,[s,r],s.dtype)}};const eB={kernelName:It,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{s0:s,s1:r}=t,a=n.readSync(s.dataId),i=n.readSync(r.dataId),o=tl(Array.from(a),Array.from(i));return n.makeTensorInfo([o.length],"int32",Int32Array.from(o))}},tB=Dz({opSnippet:"return float(a != b);",cpuKernelImpl:gL,dtype:"bool"}),nB={kernelName:Qn,backendName:"webgl",kernelFunc:tB};function sB(e){const{inputs:t,backend:n}=e,{input:s}=t;return kz({inputs:{x:n.texData.get(s.dataId).complexTensorInfos.real},backend:n})}const rB={kernelName:ms,backendName:"webgl",kernelFunc:sB},aB="return float(int(x));";const iB={kernelName:Nt,backendName:"webgl",kernelFunc:function e(t){const{inputs:n,backend:s,attrs:r}=t,{x:a}=n,{dtype:i}=r;if("complex64"===i){if("complex64"===a.dtype)return kz({inputs:{x:a},backend:s});const t=Gh(a.shape),n=e({inputs:{x:a},backend:s,attrs:{dtype:"float32"}}),r=Nz({inputs:{real:n,imag:t},backend:s});return t.dispose(),s.disposeIntermediateTensorInfo(n),r}if("complex64"===a.dtype){const t=sB({inputs:{input:a},backend:s}),n=e({inputs:{x:t},backend:s,attrs:{dtype:i}});return s.disposeIntermediateTensorInfo(t),n}if(!Te(a.dtype,i)){const e=kz({inputs:{x:a},backend:s});return{dataId:e.dataId,shape:e.shape,dtype:i}}if(s.shouldExecuteOnCPU([a])){const e=s.texData.get(a.dataId).values,[t,n,r]=YM(e,a.shape,a.dtype,i);return s.makeTensorInfo(t,n,r)}if("int32"===i)return function(e,t){const n=new XL(e.shape,aB),s=t.runWebGLProgram(n,[e],"int32");return{dataId:s.dataId,shape:s.shape,dtype:s.dtype}}(a,s);if("bool"===i){const e=s.makeTensorInfo([],"bool",ke("bool",1)),t=tB({inputs:{a,b:e},backend:s});return s.disposeIntermediateTensorInfo(e),t}throw new Error(`Error in Cast: failed to cast ${a.dtype} to ${i}`)}},oB="return ceil(x);",lB=_z({opSnippet:oB,packedOpSnippet:oB,cpuKernelImpl:ZM}),uB={kernelName:St,backendName:"webgl",kernelFunc:lB};class cB{constructor(e){this.variableNames=["A"],this.customUniforms=[{name:"minVal",type:"float"},{name:"maxVal",type:"float"}],this.outputShape=e,this.userCode="\n\n      void main() {\n        float value = getAAtOutCoords();\n        if (isnan(value)) {\n          setOutput(value);\n          return;\n        }\n\n        setOutput(clamp(value, minVal, maxVal));\n      }\n    "}}class hB{constructor(e){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,this.customUniforms=[{name:"minVal",type:"float"},{name:"maxVal",type:"float"}],this.outputShape=e,this.userCode="\n      void main() {\n        vec4 value = getAAtOutCoords();\n\n        if (any(isnan(value))) {\n          setOutput(value);\n          return;\n        }\n\n        setOutput(clamp(value, vec4(minVal), vec4(maxVal)));\n      }\n    "}}const pB={kernelName:Tt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{clipValueMin:a,clipValueMax:i}=s;let o;o=Xe().getBool("WEBGL_PACK_CLIP")?new hB(r.shape):new cB(r.shape);const l=[[a],[i]];return n.runWebGLProgram(o,[r],r.dtype,l)}};class dB{constructor(e){this.variableNames=["real","imag"],this.outputShape=e,this.userCode="\n      void main() {\n        float re = abs(getRealAtOutCoords());\n        float im = abs(getImagAtOutCoords());\n        float mx = max(re, im);\n\n        // sadly the length function in glsl is not underflow-safe\n        // (at least not on Intel GPUs). So the safe solution is\n        // to ensure underflow-safety in all cases.\n        setOutput(\n          mx == 0.0 ? 0.0 : mx * length(vec2(1, min(re, im)/mx))\n        );\n      }\n    "}}function fB(e,t){return{dataId:t.dataId,dtype:t.dtype,shape:e.shape}}const mB={kernelName:$t,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{x:s}=t,r=n.texData.get(s.dataId),a=new dB(s.shape),i=[fB(s,r.complexTensorInfos.real),fB(s,r.complexTensorInfos.imag)];return n.runWebGLProgram(a,i,i[0].dtype)}};class gB{constructor(e){this.outputShape=[],this.outputShape=Hf(e,1),this.variableNames=e.map(((e,t)=>`T${t}`));const t=new Array(e.length-1);t[0]=e[0][1];for(let n=1;n<t.length;n++)t[n]=t[n-1]+e[n][1];const n=[`if (yC < ${t[0]}) setOutput(getT0(yR, yC));`];for(let e=1;e<t.length;e++){const s=t[e-1];n.push(`else if (yC < ${t[e]}) setOutput(getT${e}(yR, yC-${s}));`)}const s=t.length,r=t[t.length-1];n.push(`else setOutput(getT${s}(yR, yC-${r}));`),this.userCode=`\n      void main() {\n        ivec2 coords = getOutputCoords();\n        int yR = coords.x;\n        int yC = coords.y;\n\n        ${n.join("\n        ")}\n      }\n    `}}class yB{constructor(e,t){this.packedInputs=!0,this.packedOutput=!0,this.outputShape=[],this.outputShape=Hf(e,t);const n=this.outputShape,s=n.length,r=uM(s),a=VL("coords",s),i=["x","y","z","w","u","v"].slice(0,s);this.variableNames=e.map(((e,t)=>`T${t}`));const o=new Array(e.length-1);o[0]=e[0][t];for(let n=1;n<o.length;n++)o[n]=o[n-1]+e[n][t];const l=i[t],u=i.slice(-2),c=i.join();let h=`if (${l} < ${o[0]}) {\n        return getChannel(\n            getT0(${c}), vec2(${u.join()}));\n        }`;for(let e=1;e<o.length;e++){const t=o[e-1];h+=`\n        if (${l} < ${o[e]}  && ${l} >= ${o[e-1]}) {\n          return getChannel(\n            getT${e}(${bB(i,l,t)}),\n            vec2(${bB(u,l,t)}));\n        }`}const p=o.length,d=o[o.length-1];h+=`\n        return getChannel(\n          getT${p}(${bB(i,l,d)}),\n          vec2(${bB(u,l,d)}));`,this.userCode=`\n      float getValue(${i.map((e=>"int "+e))}) {\n        ${h}\n      }\n\n      void main() {\n        ${r} coords = getOutputCoords();\n        vec4 result = vec4(getValue(${a}), 0., 0., 0.);\n\n        ${a[s-1]} = ${a[s-1]} + 1;\n        if (${a[s-1]} < ${n[s-1]}) {\n          result.g = getValue(${a});\n        }\n\n        ${a[s-2]} = ${a[s-2]} + 1;\n        if (${a[s-2]} < ${n[s-2]}) {\n          result.a = getValue(${a});\n        }\n\n        ${a[s-1]} = ${a[s-1]} - 1;\n        if (${a[s-2]} < ${n[s-2]} &&\n            ${a[s-1]} < ${n[s-1]}) {\n          result.b = getValue(${a});\n        }\n        setOutput(result);\n      }\n    `}}function bB(e,t,n){const s=e.indexOf(t);return e.map(((e,t)=>t===s?`${e} - ${n}`:e)).join()}function xB(e){const{inputs:t,backend:n}=e,{input:s}=t;return kz({inputs:{x:n.texData.get(s.dataId).complexTensorInfos.imag},backend:n})}const wB={kernelName:xn,backendName:"webgl",kernelFunc:xB};function vB(e,t,n){const s=e[0].dtype;if("complex64"===s){const s=e.map((e=>sB({inputs:{input:e},backend:n}))),r=e.map((e=>xB({inputs:{input:e},backend:n}))),a=vB(s,t,n),i=vB(r,t,n),o=Nz({inputs:{real:a,imag:i},backend:n});return s.forEach((e=>n.disposeIntermediateTensorInfo(e))),r.forEach((e=>n.disposeIntermediateTensorInfo(e))),n.disposeIntermediateTensorInfo(a),n.disposeIntermediateTensorInfo(i),o}let r=n.shouldExecuteOnCPU(e);if("string"===s&&(r=!0),r){const r=e.map((e=>{const s=ue(e.shape.slice(t));return Vz({inputs:{x:e},backend:n,attrs:{shape:[-1,s]}})})),a=r.map((e=>({vals:n.readSync(e.dataId),shape:e.shape}))),i=Hf(r.map((e=>e.shape)),1),o=1===r[0].shape[0],l=JM(a,i,s,o),u=Hf(e.map((e=>e.shape)),t),c=n.makeTensorInfo(u,s,l);return r.forEach((e=>n.disposeIntermediateTensorInfo(e))),c}const a=e.filter((e=>ue(e.shape)>0)),i=Xe().getBool("WEBGL_PACK_ARRAY_OPERATIONS")&&a[0].shape.length>1;if(1===a.length){const t=i?new XL(e[0].shape,nz):new uz(e[0].shape,nz);return n.runWebGLProgram(t,e,s)}const o=Xe().getNumber("WEBGL_MAX_TEXTURES_IN_SHADER");if(a.length>o){const e=[];for(let s=0;s<a.length;s+=o){const r=a.slice(s,s+o);e.push(vB(r,t,n))}const s=vB(e,t,n);for(const t of e)n.disposeIntermediateTensorInfo(t);return s}if(i){const e=new yB(a.map((e=>e.shape)),t);return n.runWebGLProgram(e,a,s)}const{tensors2D:l,outShape:u}=function(e,t,n){const s=Hf(e.map((e=>e.shape)),t),r=e.map((e=>Vz({inputs:{x:e},attrs:{shape:[-1,ue(e.shape.slice(t))]},backend:n})));return{tensors2D:r,outShape:s}}(a,t,n),c=new gB(l.map((e=>e.shape))),h=n.runWebGLProgram(c,l,s);l.forEach((e=>n.disposeIntermediateTensorInfo(e)));const p=Vz({inputs:{x:h},attrs:{shape:u},backend:n});return n.disposeIntermediateTensorInfo(h),p}function kB(e){const{inputs:t,backend:n,attrs:s}=e,{axis:r}=s,a=we(r,t[0].shape)[0];Gf(t.map((e=>e.shape)),a);const i=Hf(t.map((e=>e.shape)),a);if(0===ue(i))return n.makeTensorInfo(i,t[0].dtype,[]);const o=t.filter((e=>ue(e.shape)>0));return 1===o.length?kz({inputs:{x:o[0]},backend:n}):vB(o,a,n)}const IB={kernelName:Et,backendName:"webgl",kernelFunc:kB};class NB{constructor(e,t=!1,n=null,s=!1,r=!1){this.variableNames=["x","W"],this.outputShape=e.outShape;const a=e.padInfo.top,i=e.padInfo.left,o=e.strideHeight,l=e.strideWidth,u=e.dilationHeight,c=e.dilationWidth,h=e.filterHeight,p=e.filterWidth,d=4*Math.floor(e.inChannels/4),f=e.inChannels%4,m="channelsLast"===e.dataFormat,g=m?1:2,y=m?2:3,b=m?3:1;let x="",w="";n&&(x=s?`float activation(float a) {\n          float b = getPreluActivationWeightsAtOutCoords();\n          ${n}\n        }`:r?`float activation(float a) {\n          float b = getLeakyreluAlphaAtOutCoords();\n          ${n}\n        }`:`\n          float activation(float x) {\n            ${n}\n          }\n        `,w="result = activation(result);");const v=t?"result += getBiasAtOutCoords();":"";t&&this.variableNames.push("bias"),s&&this.variableNames.push("preluActivationWeights"),r&&this.variableNames.push("leakyreluAlpha"),this.userCode=`\n      ${x}\n\n      const ivec2 strides = ivec2(${o}, ${l});\n      const ivec2 pads = ivec2(${a}, ${i});\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords[0];\n        int d2 = coords[${b}];\n\n        ivec2 xRCCorner =\n            ivec2(coords[${g}], coords[${y}]) * strides - pads;\n        int xRCorner = xRCCorner.x;\n        int xCCorner = xRCCorner.y;\n\n        // Convolve x(?, ?, d1) with w(:, :, d1, d2) to get y(yR, yC, d2).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n        for (int wR = 0; wR < ${h}; wR++) {\n          int xR = xRCorner + wR * ${u};\n\n          if (xR < 0 || xR >= ${e.inHeight}) {\n            continue;\n          }\n\n          for (int wC = 0; wC < ${p}; wC++) {\n            int xC = xCCorner + wC * ${c};\n\n            if (xC < 0 || xC >= ${e.inWidth}) {\n              continue;\n            }\n\n            for (int d1 = 0; d1 < ${d}; d1 += 4) {\n              vec4 wValues = vec4(\n                getW(wR, wC, d1, d2),\n                getW(wR, wC, d1 + 1, d2),\n                getW(wR, wC, d1 + 2, d2),\n                getW(wR, wC, d1 + 3, d2)\n              );\n\n              if (${m}) {\n                vec4 xValues = vec4(\n                  getX(batch, xR, xC, d1),\n                  getX(batch, xR, xC, d1 + 1),\n                  getX(batch, xR, xC, d1 + 2),\n                  getX(batch, xR, xC, d1 + 3)\n                );\n                dotProd += dot(xValues, wValues);\n              } else {\n                vec4 xValues = vec4(\n                  getX(batch, d1, xR, xC),\n                  getX(batch, d1 + 1, xR, xC),\n                  getX(batch, d1 + 2, xR, xC),\n                  getX(batch, d1 + 3, xR, xC)\n                );\n                dotProd += dot(xValues, wValues);\n              }\n            }\n\n            if (${1===f}) {\n\n              if (${m}) {\n                dotProd +=\n                    getX(batch, xR, xC, ${d}) *\n                    getW(wR, wC, ${d}, d2);\n              } else {\n                dotProd +=\n                    getX(batch, ${d}, xR, xC) *\n                    getW(wR, wC, ${d}, d2);\n              }\n\n            } else if (${2===f}) {\n              vec2 wValues = vec2(\n                getW(wR, wC, ${d}, d2),\n                getW(wR, wC, ${d} + 1, d2)\n              );\n\n              if (${m}) {\n                vec2 xValues = vec2(\n                  getX(batch, xR, xC, ${d}),\n                  getX(batch, xR, xC, ${d} + 1)\n                );\n                dotProd += dot(xValues, wValues);\n              } else {\n                vec2 xValues = vec2(\n                  getX(batch, ${d}, xR, xC),\n                  getX(batch, ${d} + 1, xR, xC)\n                );\n                dotProd += dot(xValues, wValues);\n              }\n\n            } else if (${3===f}) {\n              vec3 wValues = vec3(\n                getW(wR, wC, ${d}, d2),\n                getW(wR, wC, ${d} + 1, d2),\n                getW(wR, wC, ${d} + 2, d2)\n              );\n\n              if (${m}) {\n                vec3 xValues = vec3(\n                  getX(batch, xR, xC, ${d}),\n                  getX(batch, xR, xC, ${d} + 1),\n                  getX(batch, xR, xC, ${d} + 2)\n                );\n                dotProd += dot(xValues, wValues);\n              } else {\n                vec3 xValues = vec3(\n                  getX(batch, ${d}, xR, xC),\n                  getX(batch, ${d} + 1, xR, xC),\n                  getX(batch, ${d} + 2, xR, xC)\n                );\n                dotProd += dot(xValues, wValues);\n              }\n\n            }\n          }\n        }\n\n        float result = dotProd;\n        ${v}\n        ${w}\n        setOutput(result);\n      }\n    `}}class SB{constructor(e){this.variableNames=["x","W"],this.outputShape=e.outShape;const t=e.padInfo.front,n=e.padInfo.top,s=e.padInfo.left,r=e.strideDepth,a=e.strideHeight,i=e.strideWidth,o=e.dilationDepth,l=e.dilationHeight,u=e.dilationWidth,c=e.filterDepth,h=e.filterHeight,p=e.filterWidth,d=4*Math.floor(e.inChannels/4),f=e.inChannels%4;this.userCode=`\n      const ivec3 strides = ivec3(${r}, ${a}, ${i});\n      const ivec3 pads = ivec3(${t}, ${n}, ${s});\n\n      void main() {\n        ivec5 coords = getOutputCoords();\n        int batch = coords.x;\n        int d2 = coords.u;\n\n        ivec3 xFRCCorner = ivec3(coords.y, coords.z, coords.w) * strides - pads;\n        int xFCorner = xFRCCorner.x;\n        int xRCorner = xFRCCorner.y;\n        int xCCorner = xFRCCorner.z;\n\n        // Convolve x(?, ?, ?, d1) with w(:, :, :, d1, d2) to get\n        // y(yF, yR, yC, d2). ? = to be determined. : = across all\n        // values in that axis.\n        float dotProd = 0.0;\n        for (int wF = 0; wF < ${c}; wF++) {\n          int xF = xFCorner + wF * ${o};\n\n          if (xF < 0 || xF >= ${e.inDepth}) {\n            continue;\n          }\n\n          for (int wR = 0; wR < ${h}; wR++) {\n            int xR = xRCorner + wR * ${l};\n\n            if (xR < 0 || xR >= ${e.inHeight}) {\n              continue;\n            }\n\n            for (int wC = 0; wC < ${p}; wC++) {\n              int xC = xCCorner + wC * ${u};\n\n              if (xC < 0 || xC >= ${e.inWidth}) {\n                continue;\n              }\n\n              for (int d1 = 0; d1 < ${d}; d1 += 4) {\n                vec4 xValues = vec4(\n                  getX(batch, xF, xR, xC, d1),\n                  getX(batch, xF, xR, xC, d1 + 1),\n                  getX(batch, xF, xR, xC, d1 + 2),\n                  getX(batch, xF, xR, xC, d1 + 3)\n                );\n                vec4 wValues = vec4(\n                  getW(wF, wR, wC, d1, d2),\n                  getW(wF, wR, wC, d1 + 1, d2),\n                  getW(wF, wR, wC, d1 + 2, d2),\n                  getW(wF, wR, wC, d1 + 3, d2)\n                );\n\n                dotProd += dot(xValues, wValues);\n              }\n\n              if (${1===f}) {\n                dotProd +=\n                  getX(batch, xF, xR, xC, ${d}) *\n                  getW(wF, wR, wC, ${d}, d2);\n              } else if (${2===f}) {\n                vec2 xValues = vec2(\n                  getX(batch, xF, xR, xC, ${d}),\n                  getX(batch, xF, xR, xC, ${d} + 1)\n                );\n                vec2 wValues = vec2(\n                  getW(wF, wR, wC, ${d}, d2),\n                  getW(wF, wR, wC, ${d} + 1, d2)\n                );\n                dotProd += dot(xValues, wValues);\n              } else if (${3===f}) {\n                vec3 xValues = vec3(\n                  getX(batch, xF, xR, xC, ${d}),\n                  getX(batch, xF, xR, xC, ${d} + 1),\n                  getX(batch, xF, xR, xC, ${d} + 2)\n                );\n                vec3 wValues = vec3(\n                  getW(wF, wR, wC, ${d}, d2),\n                  getW(wF, wR, wC, ${d} + 1, d2),\n                  getW(wF, wR, wC, ${d} + 2, d2)\n                );\n                dotProd += dot(xValues, wValues);\n              }\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}class TB{constructor(e,t=!1,n=null,s=!1,r=!1){this.variableNames=["x","W"],this.packedInputs=!0,this.packedOutput=!0,this.customUniforms=[{name:"pads",type:"ivec2"},{name:"strides",type:"ivec2"},{name:"dilations",type:"ivec2"},{name:"inDims",type:"ivec2"}],this.outputShape=e.outShape,this.enableShapeUniforms=mM(this.outputShape.length);const a=e.padInfo.left,i=e.strideWidth,o=e.dilationWidth,l=e.filterHeight,u=e.filterWidth,c=u;let h="\n       int xR; int xC; int xCOffset;\n       vec4 wTexel; vec4 previous; vec4 final;";for(let e=0;e<u;e++)h+=`\n           vec4 xTexelC${2*e};\n           int xTexelC${2*e}Ready;\n           vec4 xTexelC${2*e+1};\n           int xTexelC${2*e+1}Ready;\n           vec4 xC${e};`;h+=`\n     for (int r = 0; r < ${l}; r++) {\n      for (int d1 = 0; d1 < ${e.inChannels}; d1 += 2) {\n       `;for(let e=0;e<u;e++)h+=`\n           xTexelC${2*e} = vec4(0.0);\n           xTexelC${2*e}Ready = 0;\n           xTexelC${2*e+1} = vec4(0.0);\n           xTexelC${2*e+1}Ready = 0;\n           xC${e} = vec4(0.0);`;h+="\n         xR = xRCorner + r * dilations[0];\n         if (xR >=0 && xR < inDims[0]) {\n       ";for(let t=0;t<(c+1)/2;t++){const n=2*t;if(h+=`\n           xC = xCCorner + ${n*o};\n           `,1===i){if(n<u&&(a%2==1?(h+=`\n                 xCOffset = xC + 1;\n                 if (xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${n}Ready == 0) {\n                   xTexelC${n} = getX(batch, xR, xCOffset, d1);\n\n                   // Need to manually clear unused channels in case\n                   // we're reading from recycled texture.\n                   if (xCOffset + 1 >= inDims[1]) {\n                     xTexelC${n}.zw = vec2(0.0);\n                   }\n                   xTexelC${n}Ready = 1;\n                 }\n               `,h+=1===o&&n>0?`\n                 xC${n} = vec4(xTexelC${n-2}.zw, xTexelC${n}.xy);\n                 `:`\n                   xCOffset = xC + 1 - 2;\n\n                   if (xCOffset >= 0 && xCOffset < inDims[1]) {\n                     previous = getX(batch, xR, xCOffset, d1);\n\n                     // Need to manually clear unused channels in case\n                     // we're reading from recycled texture.\n                     if (xCOffset + 1 >= inDims[1]) {\n                       previous.zw = vec2(0.0);\n                     }\n\n                     xC${n} = vec4(previous.zw, xTexelC${n}.xy);\n                   } else {\n                     xC${n} = vec4(0.0, 0.0, xTexelC${n}.xy);\n                   }\n                   `):h+=`\n                 if (xC >= 0 && xC < inDims[1] && xTexelC${n}Ready == 0) {\n                   xTexelC${n} = getX(batch, xR, xC, d1);\n                   if (xC + 1 >= inDims[1]) {\n                     xTexelC${n}.zw = vec2(0.0);\n                   }\n                   xTexelC${n}Ready = 1;\n                 }\n\n                 xC${n} = xTexelC${n};\n                 `,n+1<u)){const e=a%2==0?te(o):o;o%2==0&&a%2==1||o%2!=0&&a%2!=1?(h+=`\n                   xCOffset = xC + imod(pads[1], 2) + ${e};\n\n                   if (xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${n+1}Ready == 0) {\n                     xTexelC${n+1} = getX(batch, xR, xCOffset, d1);\n\n                     // Need to manually clear unused channels in case\n                     // we're reading from recycled texture.\n                     if (xCOffset + 1 >= inDims[1]) {\n                       xTexelC${n+1}.zw = vec2(0.0);\n                     }\n                     xTexelC${n+1}Ready = 1;\n                   }\n                   `,h+=o>1?`\n                     xCOffset -= 2;\n                     if (xCOffset >= 0 && xCOffset < inDims[1]) {\n                      previous = getX(batch, xR, xCOffset, d1);\n                      xC${n+1} = vec4(previous.zw, xTexelC${n+1}.xy);\n                     } else {\n                      xC${n+1} = vec4(0.0, 0.0, xTexelC${n+1}.xy);\n                     }\n                     `:`\n                     xC${n+1} = vec4(xTexelC${n}.zw, xTexelC${n+1}.xy);\n                     `):h+=1===e?`\n                     xC${n+1} = xTexelC${n};\n                     `:`\n                     xCOffset = xC + ${e};\n\n                     if (xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${n+1}Ready == 0) {\n                       xTexelC${n+1} = getX(batch, xR, xCOffset, d1);\n                       if (xCOffset + 1 >= inDims[1]) {\n                         xTexelC${n+1}.zw = vec2(0.0);\n                       }\n                       xTexelC${n+1}Ready = 1;\n                     }\n\n                     xC${n+1} = xTexelC${n+1};\n                     `}}else n<u&&(a%2==1?(h+=`\n                 xCOffset = xC + 1 - strides[1];\n                 if(xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${n}Ready == 0) {\n                   xTexelC${n} = getX(batch, xR, xCOffset, d1);\n                   // Need to manually clear unused channels in case\n                   // we're reading from recycled texture.\n                   if (xCOffset + 1 >= inDims[1]) {\n                     xTexelC${n}.zw = vec2(0.0);\n                   }\n                   xTexelC${n}Ready = 1;\n                 }\n\n                 if(xC + 1 >= 0 && xC + 1 < inDims[1] && xTexelC${n+1}Ready == 0) {\n                   xTexelC${n+1} = getX(batch, xR, xC + 1, d1);\n                   // Need to manually clear unused channels in case\n                   // we're reading from recycled texture.\n                   if (xC + 2 >= inDims[1]) {\n                     xTexelC${n+1}.zw = vec2(0.0);\n                   }\n                   xTexelC${n+1}Ready = 1;\n                 }\n\n                 xC${n} = vec4(xTexelC${n}.zw, xTexelC${n+1}.zw);\n               `,n+1<u&&(h+=`\n                   final = vec4(0.0);\n                   xCOffset = xC + 1 + strides[1];\n                   if(xCOffset >= 0 && xCOffset < inDims[1]) {\n                     final = getX(batch, xR, xCOffset, d1);\n                   }\n                   xC${n+1} = vec4(xTexelC${n+1}.xy, final.xy);\n                 `)):(h+=`\n                 if(xC >= 0 && xC < inDims[1] && xTexelC${n}Ready == 0) {\n                   xTexelC${n} = getX(batch, xR, xC, d1);\n                   if (xC + 1 >= inDims[1]) {\n                     xTexelC${n}.zw = vec2(0.0);\n                   }\n                   xTexelC${n}Ready = 1;\n                 }\n\n                 xCOffset = xC + strides[1];\n                 if(xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${n+1}Ready == 0) {\n                   xTexelC${n+1} = getX(batch, xR, xCOffset, d1);\n                   if (xCOffset + 1 >= inDims[1]) {\n                     xTexelC${n+1}.zw = vec2(0.);\n                   }\n                   xTexelC${n+1}Ready = 1;\n                 }\n\n                 xC${n} = vec4(\n                   xTexelC${n}.xy, xTexelC${n+1}.xy);\n               `,n+1<u&&(h+=`\n                   xC${n+1} = vec4(xTexelC${n}.zw, xTexelC${n+1}.zw);\n                 `)));n<u&&(h+=`\n             wTexel = getW(r, ${n}, d1, d2);\n             dotProd += xC${n}.xxzz * vec4(wTexel.xy, wTexel.xy);\n             if(d1 + 1 < ${e.inChannels}) {\n               dotProd += xC${n}.yyww * vec4(wTexel.zw, wTexel.zw);\n             }\n           `,n+1<u&&(h+=`\n               wTexel = getW(r, ${n+1}, d1, d2);\n               dotProd += xC${n+1}.xxzz * vec4(wTexel.xy, wTexel.xy);\n               if(d1 + 1 < ${e.inChannels}) {\n                 dotProd += xC${n+1}.yyww * vec4(wTexel.zw, wTexel.zw);\n               }\n             `))}h+="\n     }\n   ",h+="\n     }\n   ",h+="\n     }\n   ";let p="",d="";n&&(p=s?`vec4 activation(vec4 a) {\n           vec4 b = getPreluActivationWeightsAtOutCoords();\n           ${n}\n         }`:r?`vec4 activation(vec4 a) {\n           vec4 b = getLeakyreluAlphaAtOutCoords();\n           ${n}\n         }`:`vec4 activation(vec4 x) {\n           ${n}\n         }`,d="result = activation(result);");const f=t?"result += getBiasAtOutCoords();":"";t&&this.variableNames.push("bias"),s&&this.variableNames.push("preluActivationWeights"),r&&this.variableNames.push("leakyreluAlpha"),this.userCode=`\n       ${p}\n\n       void main() {\n         ivec4 coords = getOutputCoords();\n         int batch = coords.x;\n         ivec2 xRCCorner = coords.yz * strides - pads;\n         int d2 = coords.w;\n         int xRCorner = xRCCorner.x;\n         int xCCorner = xRCCorner.y;\n\n         //intialize dotProd with a small epsilon seems to reduce GPU accuracy loss.\n         vec4 dotProd = vec4(0.000000000000001);\n\n         ${h}\n\n         vec4 result = dotProd - vec4(0.000000000000001);\n         ${f}\n         ${d}\n         setOutput(result);\n       }\n     `}}class CB{constructor(e,t){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,this.customUniforms=[{name:"inputShape",type:"ivec4"},{name:"pad",type:"ivec2"},{name:"stride",type:"ivec2"},{name:"dilation",type:"ivec2"},{name:"inChannels",type:"int"},{name:"itemsPerBlockRow",type:"int"},{name:"outWidth",type:"int"}],this.outputShape=e,this.enableShapeUniforms=mM(this.outputShape.length);const{dataFormat:n}=t,s=jO(),r="channelsLast"===n,a=r?1:2,i=r?2:3,o=this.enableShapeUniforms?"if(blockIndex < outShape[2] && pos < outShape[1]) {":`if(blockIndex < ${e[2]} && pos < ${e[1]}) {`;let l="";for(let e=0;e<=1;e++)for(let t=0;t<=1;t++)l+=`\n          blockIndex = rc.z + ${t};\n          pos = rc.y + ${e};\n\n          ${o}\n            offsetY = int(blockIndex / outWidth) * stride[0] - pad[0];\n            d0 = offsetY + dilation[0] * (pos / itemsPerBlockRow);\n\n            if(d0 < inputShape[${a}] && d0 >= 0) {\n              // Use custom imod instead mod. On Intel GPU, mod may generate\n              // unexpected value.\n              // https://github.com/tensorflow/tfjs/issues/5447\n              offsetX = imod(blockIndex, outWidth) * stride[1] - pad[1];\n              d1 = offsetX + dilation[1] * (imod(pos, itemsPerBlockRow) /\n                  inChannels);\n\n              if(d1 < inputShape[${i}] && d1 >= 0) {\n\n                ch = imod(pos, inChannels);\n\n                if (${r}) {\n                  innerDims = vec2(d1, ch);\n                  result[${2*e+t}] = getChannel(\n                    getA(rc.x, d0, int(innerDims.x),\n                    int(innerDims.y)), innerDims);\n                } else {\n                  innerDims = vec2(d0, d1);\n                  result[${2*e+t}] = getChannel(\n                    getA(rc.x, ch, int(innerDims.x),\n                    int(innerDims.y)), innerDims);\n                }\n              }\n            }\n          }\n        `;this.userCode=`\n      void main() {\n        ivec3 rc = getOutputCoords();\n\n        vec4 result = vec4(0);\n\n        int blockIndex, pos, offsetY, d0, offsetX, d1, ch;\n        vec2 innerDims;\n\n        ${l}\n\n        ${s.output} = result;\n      }\n    `}}function $B(e,t){const n=e.length;return n>=3?t?[...e.slice(0,-3),e[n-3]*e[n-2],e[n-1]]:[...e.slice(0,-3),e[n-3],e[n-2]*e[n-1]]:!t&&1===n&&e[0]>1?[e[0],1]:null}function EB({x:e,filter:t,convInfo:n,backend:s,bias:r=null,preluActivationWeights:a=null,leakyreluAlpha:i=0,activation:o=null}){const l=e.shape,u=s.texData.get(e.dataId),c=n.inChannels,h=l[0]*l[1]*l[2],p=n.outChannels,d="channelsLast"===n.dataFormat;let f;const m=[];if(null!=a){const e=$B(a.shape,d);null!=e&&(a=Vz({inputs:{x:a},backend:s,attrs:{shape:e}}),m.push(a))}if(null!=r){const e=$B(r.shape,d);null!=e&&(r=Vz({inputs:{x:r},backend:s,attrs:{shape:e}}),m.push(r))}if(!((1===h||1===p)&&c>eP)&&u.isPacked&&d&&null!=u.texture&&l[2]%2!=0&&pe(u.shape.slice(-3),l.slice(-3))){const c=l[0]*l[1]*(l[2]+1),h={dataId:e.dataId,shape:[1,c,n.inChannels],dtype:e.dtype},p=u.shape;u.shape=u.shape.slice(),u.shape[u.shape.length-2]++,ie(AO(u.shape,h.shape),(()=>`packed reshape ${u.shape} to ${h.shape} isn't free`));const d=Vz({inputs:{x:t},backend:s,attrs:{shape:[1,n.inChannels,n.outChannels]}});m.push(d);const g=tP({a:h,b:d,backend:s,transposeA:false,transposeB:false,bias:r,activation:o,preluActivationWeights:a,leakyreluAlpha:i}),y=s.texData.get(g.dataId);ie(y.isPacked,(()=>"batchMatMul result is expected to be packed")),u.shape=p,y.shape=n.outShape,f=kz({inputs:{x:g},backend:s}),f.shape=n.outShape,m.push(g)}else{const l=n.outHeight*n.outWidth,u=Vz({inputs:{x:e},backend:s,attrs:{shape:d?[n.batchSize,l,n.inChannels]:[n.batchSize,n.inChannels,l]}}),c=Vz({inputs:{x:t},backend:s,attrs:{shape:[1,n.inChannels,n.outChannels]}}),h=tP({a:d?u:c,b:d?c:u,transposeA:!d,transposeB:false,backend:s,bias:r,activation:o,preluActivationWeights:a,leakyreluAlpha:i});f=Vz({inputs:{x:h},backend:s,attrs:{shape:n.outShape}}),m.push(u),m.push(c),m.push(h)}for(const e of m)s.disposeIntermediateTensorInfo(e);return f}function AB({x:e,filter:t,convInfo:n,backend:s,bias:r=null,preluActivationWeights:a=null,leakyreluAlpha:i=0,activation:o=null}){const{filterWidth:l,filterHeight:u,inChannels:c,outWidth:h,outHeight:p,dataFormat:d}=n,f="channelsLast"===d,m=l*u*c,g=p*h,y=[n.batchSize,m,g],b=[];if(null!=a){const e=$B(a.shape,f);null!=e&&(a=Vz({inputs:{x:a},backend:s,attrs:{shape:e}}),b.push(a))}if(null!=r){const e=$B(r.shape,f);null!=e&&(r=Vz({inputs:{x:r},backend:s,attrs:{shape:e}}),b.push(r))}const x=Vz({inputs:{x:t},backend:s,attrs:{shape:[1,m,ue(t.shape)/m]}});b.push(x);const w=new CB(y,n),v=[e.shape,[n.padInfo.top,n.padInfo.left],[n.strideHeight,n.strideWidth],[n.dilationHeight,n.dilationWidth],[n.inChannels],[n.filterWidth*n.inChannels],[n.outWidth]],k=s.runWebGLProgram(w,[e],"float32",v),I=Vz({inputs:{x:k},backend:s,attrs:{shape:y}});b.push(k),b.push(I);const N=null!=r,S=null!=a,T="leakyrelu"===o,C=o?Oz(o,!0):null,$=new Mz(f?I.shape:x.shape,f?x.shape:I.shape,f?[n.batchSize,g,n.outChannels]:[n.batchSize,n.outChannels,g],!0,!1,N,C,S,T),E=f?[I,x]:[x,I];if(r&&E.push(r),S&&E.push(a),T){const e=s.makeTensorInfo([],"float32",qr(i,"float32"));E.push(e),b.push(e)}const A=s.runWebGLProgram($,E,"float32"),R=Vz({inputs:{x:A},backend:s,attrs:{shape:n.outShape}});b.push(A);for(const e of b)s.disposeIntermediateTensorInfo(e);return R}const RB={kernelName:At,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a}=t,{strides:i,pad:o,dataFormat:l,dilations:u,dimRoundingMode:c}=s,h=tc(l),p=Hu(r.shape,a.shape,i,u,o,c,!1,h);let d;if(1!==p.filterHeight||1!==p.filterWidth||1!==p.dilationHeight||1!==p.dilationWidth||1!==p.strideHeight||1!==p.strideWidth||"SAME"!==p.padInfo.type&&"VALID"!==p.padInfo.type)if(p.strideWidth<=2&&"channelsLast"===h&&Xe().getBool("WEBGL_EXP_CONV")){const e=new TB(p),t=[[p.padInfo.top,p.padInfo.left],[p.strideHeight,p.strideWidth],[p.dilationHeight,p.dilationWidth],[p.inHeight,p.inWidth]];d=n.runWebGLProgram(e,[r,a],"float32",t)}else if(Xe().getBool("WEBGL_CONV_IM2COL"))d=AB({x:r,filter:a,convInfo:p,backend:n});else{const e=new NB(p);d=n.runWebGLProgram(e,[r,a],"float32")}else d=EB({x:r,filter:a,convInfo:p,backend:n});const f=Vz({inputs:{x:d},backend:n,attrs:{shape:p.outShape}});return n.disposeIntermediateTensorInfo(d),f}};class FB{constructor(e){this.variableNames=["x","dy"],this.outputShape=e.filterShape;const t=e.strideHeight,n=e.strideWidth,s=e.padInfo.top,r=e.padInfo.left,a="channelsLast"===e.dataFormat;this.userCode=`\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int wR = coords.x;\n        int wC = coords.y;\n        int d1 = coords.z;\n        int d2 = coords.w;\n\n        // Convolve x(?, ?, d1) with dy(:, :, d2) to get dw(wR, wC, d1, d2).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n\n        for (int b = 0; b < ${e.batchSize}; b++) {\n          for (int yR = 0; yR < ${e.outHeight}; yR++) {\n            int xR = wR + yR * ${t} - ${s};\n\n            if (xR < 0 || xR >= ${e.inHeight}) {\n              continue;\n            }\n\n            for (int yC = 0; yC < ${e.outWidth}; yC++) {\n              int xC = wC + yC * ${n} - ${r};\n\n              if (xC < 0 || xC >= ${e.inWidth}) {\n                continue;\n              }\n\n              ${a?"float dyValue = getDy(b, yR, yC, d2);\n              float xValue = getX(b, xR, xC, d1);\n              dotProd += (xValue * dyValue);":"float dyValue = getDy(b, d2, yR, yC);\n              float xValue = getX(b, d1, xR, xC);\n              dotProd += (xValue * dyValue);"}\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}class _B{constructor(e){this.variableNames=["dy","W"],this.outputShape=e.inShape;const t=e.filterHeight,n=e.filterWidth,s=e.strideHeight,r=e.strideWidth,a="channelsLast"===e.dataFormat,i=t-1-e.padInfo.top,o=n-1-e.padInfo.left,l=a?1:2,u=a?2:3,c=a?3:1;this.userCode=`\n      const ivec2 pads = ivec2(${i}, ${o});\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords[0];\n        int d1 = coords[${c}];\n\n        ivec2 dyCorner = ivec2(coords[${l}], coords[${u}]) - pads;\n        int dyRCorner = dyCorner.x;\n        int dyCCorner = dyCorner.y;\n\n        // Convolve dy(?, ?, d2) with w(:, :, d1, d2) to compute dx(xR, xC, d1).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n        for (int wR = 0; wR < ${t}; wR++) {\n          float dyR = float(dyRCorner + wR) / ${s}.0;\n\n          if (dyR < 0.0 || dyR >= ${e.outHeight}.0 || fract(dyR) > 0.0) {\n            continue;\n          }\n          int idyR = int(dyR);\n\n          int wRPerm = ${t} - 1 - wR;\n\n          for (int wC = 0; wC < ${n}; wC++) {\n            float dyC = float(dyCCorner + wC) / ${r}.0;\n\n            if (dyC < 0.0 || dyC >= ${e.outWidth}.0 ||\n                fract(dyC) > 0.0) {\n              continue;\n            }\n            int idyC = int(dyC);\n\n            int wCPerm = ${n} - 1 - wC;\n\n            for (int d2 = 0; d2 < ${e.outChannels}; d2++) {\n\n              if (${a}) {\n                float xValue = getDy(batch, idyR, idyC, d2);\n                float wValue = getW(wRPerm, wCPerm, d1, d2);\n                dotProd += xValue * wValue;\n              } else {\n                float xValue = getDy(batch, d2, idyR, idyC);\n                float wValue = getW(wRPerm, wCPerm, d1, d2);\n                dotProd += xValue * wValue;\n              }\n\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}class DB{constructor(e){this.variableNames=["x","dy"],this.outputShape=e.filterShape;const t=e.strideDepth,n=e.strideHeight,s=e.strideWidth,r=e.padInfo.front,a=e.padInfo.top,i=e.padInfo.left;this.userCode=`\n      void main() {\n        ivec5 coords = getOutputCoords();\n        int wF = coords.x;\n        int wR = coords.y;\n        int wC = coords.z;\n        int d1 = coords.w;\n        int d2 = coords.u;\n\n        float dotProd = 0.0;\n\n        for (int b = 0; b < ${e.batchSize}; b++) {\n          for (int yF = 0; yF < ${e.outDepth}; yF++) {\n            int xF = wF + yF * ${t} - ${r};\n\n            if (xF < 0 || xF >= ${e.inDepth}) {\n              continue;\n            }\n\n            for (int yR = 0; yR < ${e.outHeight}; yR++) {\n              int xR = wR + yR * ${n} - ${a};\n\n              if (xR < 0 || xR >= ${e.inHeight}) {\n                continue;\n              }\n\n              for (int yC = 0; yC < ${e.outWidth}; yC++) {\n                int xC = wC + yC * ${s} - ${i};\n\n                if (xC < 0 || xC >= ${e.inWidth}) {\n                  continue;\n                }\n\n                float dyValue = getDy(b, yF, yR, yC, d2);\n                float xValue = getX(b, xF, xR, xC, d1);\n                dotProd += (xValue * dyValue);\n              }\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}class OB{constructor(e){this.variableNames=["dy","W"],this.outputShape=e.inShape;const t=e.filterDepth,n=e.filterHeight,s=e.filterWidth,r=e.strideDepth,a=e.strideHeight,i=e.strideWidth,o=t-1-e.padInfo.front,l=n-1-e.padInfo.top,u=s-1-e.padInfo.left;this.userCode=`\n      const ivec3 pads = ivec3(${o}, ${l}, ${u});\n\n      void main() {\n        ivec5 coords = getOutputCoords();\n        int batch = coords.x;\n        int d1 = coords.u;\n\n\n        ivec3 dyCorner = ivec3(coords.y, coords.z, coords.w) - pads;\n        int dyFCorner = dyCorner.x;\n        int dyRCorner = dyCorner.y;\n        int dyCCorner = dyCorner.z;\n\n        float dotProd = 0.0;\n        for (int wF = 0; wF < ${t}; wF++) {\n          float dyF = float(dyFCorner + wF) / ${r}.0;\n\n          if (dyF < 0.0 || dyF >= ${e.outDepth}.0 || fract(dyF) > 0.0) {\n            continue;\n          }\n          int idyF = int(dyF);\n\n          int wFPerm = ${t} - 1 - wF;\n\n          for (int wR = 0; wR < ${n}; wR++) {\n            float dyR = float(dyRCorner + wR) / ${a}.0;\n\n            if (dyR < 0.0 || dyR >= ${e.outHeight}.0 ||\n              fract(dyR) > 0.0) {\n              continue;\n            }\n            int idyR = int(dyR);\n\n            int wRPerm = ${n} - 1 - wR;\n\n            for (int wC = 0; wC < ${s}; wC++) {\n              float dyC = float(dyCCorner + wC) / ${i}.0;\n\n              if (dyC < 0.0 || dyC >= ${e.outWidth}.0 ||\n                  fract(dyC) > 0.0) {\n                continue;\n              }\n              int idyC = int(dyC);\n\n              int wCPerm = ${s} - 1 - wC;\n\n              for (int d2 = 0; d2 < ${e.outChannels}; d2++) {\n                float xValue = getDy(batch, idyF, idyR, idyC, d2);\n                float wValue = getW(wFPerm, wRPerm, wCPerm, d1, d2);\n                dotProd += xValue * wValue;\n              }\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}const MB={kernelName:Rt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,dy:a}=t,{strides:i,pad:o,dataFormat:l,dimRoundingMode:u,filterShape:c}=s,h=tc(l),p=Hu(r.shape,c,i,1,o,u,!1,h),d=new FB(p);return n.runWebGLProgram(d,[r,a],"float32")}};class LB{constructor(e){this.variableNames=["dy","W"],this.packedInputs=!0,this.packedOutput=!0,this.customUniforms=[{name:"strides",type:"vec2"}],this.outputShape=e.inShape,this.enableShapeUniforms=mM(this.outputShape.length);const t=e.filterHeight,n=e.filterWidth,s=t-1-e.padInfo.top,r=n-1-e.padInfo.left;this.userCode=`\n      const ivec2 pads = ivec2(${s}, ${r});\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords[0];\n        int d1 = coords[3];\n\n        ivec2 dyCorner = ivec2(coords[1], coords[2]) - pads;\n        int dyRCorner = dyCorner.x;\n        int dyCCorner = dyCorner.y;\n\n        vec4 result = vec4(0.);\n        for (int wR = 0; wR < ${t}; wR++) {\n          float dyR = float(dyRCorner + wR) / strides[0];\n          if (dyR < 0.0 || dyR >= ${e.outHeight}.0 || fract(dyR) > 0.0) {\n            continue;\n          }\n          int idyR = int(dyR);\n          int wRPerm = ${t} - 1 - wR;\n\n          for (int wC = 0; wC < ${n}; wC++) {\n            int wCPerm = ${n} - 1 - wC;\n\n            float dyC = float(dyCCorner + wC) / strides[1];\n            bool idyCVal = (dyC >= 0.0) && (dyC < ${e.outWidth}.0)\n              && (fract(dyC) == 0.0);\n            int idyC = int(dyC);\n\n            float dyC2 = float(dyCCorner + wC + 1) / strides[1];\n            bool idyCVal2 = (dyC2 >= 0.0) && (dyC2 < ${e.outWidth}.0)\n              && (fract(dyC2) == 0.0);\n            int idyC2 = int(dyC2);\n\n            if (idyCVal && idyCVal2) {\n              for (int d2 = 0; d2 < ${e.outChannels}; d2 += 2) {\n                vec4 wValue = getW(wRPerm, wCPerm, d1, d2);\n                vec4 dySample = getDy(batch, idyR, idyC, d2);\n                vec4 dySample2 = (idyC / 2 == idyC2 / 2) ?\n                  dySample : getDy(batch, idyR, idyC2, d2);\n\n                vec2 dyValue = mod(float(idyC), 2.) == 0. ?\n                  dySample.xy : dySample.zw;\n                result.xy += vec2(dot(dyValue, wValue.xy),\n                  dot(dyValue, wValue.zw));\n\n                dyValue = mod(float(idyC2), 2.) == 0. ?\n                  dySample2.xy : dySample2.zw;\n                result.zw += vec2(dot(dyValue, wValue.xy),\n                  dot(dyValue, wValue.zw));\n              }\n            } else if (idyCVal) {\n              for (int d2 = 0; d2 < ${e.outChannels}; d2 += 2) {\n                vec4 wValue = getW(wRPerm, wCPerm, d1, d2);\n                vec4 dySample = getDy(batch, idyR, idyC, d2);\n                vec2 dyValue = mod(float(idyC), 2.) == 0. ?\n                  dySample.xy : dySample.zw;\n                result.xy += vec2(dot(dyValue, wValue.xy),\n                  dot(dyValue, wValue.zw));\n              }\n            } else if (idyCVal2) {\n              for (int d2 = 0; d2 < ${e.outChannels}; d2 += 2) {\n                vec4 wValue = getW(wRPerm, wCPerm, d1, d2);\n                vec4 dySample = getDy(batch, idyR, idyC2, d2);\n                vec2 dyValue = mod(float(idyC2), 2.) == 0. ?\n                  dySample.xy : dySample.zw;\n                result.zw += vec2(dot(dyValue, wValue.xy),\n                  dot(dyValue, wValue.zw));\n              }\n            }\n          }\n        }\n        setOutput(result);\n      }\n    `}}const zB={kernelName:Ft,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,filter:a}=t,{inputShape:i,strides:o,pad:l,dataFormat:u,dimRoundingMode:c}=s,h=tc(u),p=Hu(i,a.shape,o,1,l,c,!1,h);if(Xe().getBool("WEBGL_PACK")&&"channelsLast"===h){const e=[[p.strideHeight,p.strideWidth]],t=new LB(p);return n.runWebGLProgram(t,[r,a],"float32",e)}{const e=new _B(p);return n.runWebGLProgram(e,[r,a],"float32")}}};const PB={kernelName:_t,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a}=t,{strides:i,pad:o,dilations:l}=s,u=ju(r.shape,a.shape,i,l,o),c=new SB(u);return n.runWebGLProgram(c,[r,a],"float32")}};const BB={kernelName:Dt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,dy:a}=t,{strides:i,pad:o,filterShape:l}=s,u=ju(r.shape,l,i,1,o),c=new DB(u);return n.runWebGLProgram(c,[r,a],"float32")}};const WB={kernelName:Ot,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,filter:a}=t,{pad:i,strides:o,inputShape:l}=s,u=ju(l,a.shape,o,1,i),c=new OB(u);return n.runWebGLProgram(c,[r,a],"float32")}},VB=_z({opSnippet:Fz+"\n  return cos(x);\n",packedOpSnippet:`\n  vec4 result = cos(x);\n  bvec4 isNaN = isnan(x);\n  ${wz}\n  return result;\n`}),UB={kernelName:Mt,backendName:"webgl",kernelFunc:VB},GB=_z({opSnippet:"\n  float e2x = exp(-x);\n  return (e2x + 1.0 / e2x) / 2.0;\n"}),HB={kernelName:Lt,backendName:"webgl",kernelFunc:GB};class jB{constructor(e,t,n,s,r){this.variableNames=["Image","Boxes","BoxInd"],this.outputShape=[];const[a,i,o,l]=e,[u]=t,[c,h]=n;this.outputShape=[u,c,h,l];const p="bilinear"===s?1:0,[d,f]=[i-1+".0",o-1+".0"],[m,g,y]=c>1?[""+(i-1)/(c-1),"(y2-y1) * height_ratio",`y1*${d} + float(y)*(height_scale)`]:["0.0","0.0",`0.5 * (y1+y2) * ${d}`],[b,x,w]=h>1?[""+(o-1)/(h-1),"(x2-x1) * width_ratio",`x1*${f} + float(x)*(width_scale)`]:["0.0","0.0",`0.5 * (x1+x2) * ${f}`];this.userCode=`\n      const float height_ratio = float(${m});\n      const float width_ratio = float(${b});\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int y = coords[1];\n        int x = coords[2];\n        int d = coords[3];\n\n        // get box vals\n        float y1 = getBoxes(b,0);\n        float x1 = getBoxes(b,1);\n        float y2 = getBoxes(b,2);\n        float x2 = getBoxes(b,3);\n\n        // get image in batch index\n        int bInd = round(getBoxInd(b));\n        if(bInd < 0 || bInd >= ${a}) {\n          return;\n        }\n\n        float height_scale = ${g};\n        float width_scale = ${x};\n\n        float in_y = ${y};\n        if( in_y < 0.0 || in_y > ${d} ) {\n          setOutput(float(${r}));\n          return;\n        }\n        float in_x = ${w};\n        if( in_x < 0.0 || in_x > ${f} ) {\n          setOutput(float(${r}));\n          return;\n        }\n\n        vec2 sourceFracIndexCR = vec2(in_x,in_y);\n        if(${p} == 1) {\n          // Compute the four integer indices.\n          ivec2 sourceFloorCR = ivec2(sourceFracIndexCR);\n          ivec2 sourceCeilCR = ivec2(ceil(sourceFracIndexCR));\n\n          float topLeft = getImage(b, sourceFloorCR.y, sourceFloorCR.x, d);\n          float bottomLeft = getImage(b, sourceCeilCR.y, sourceFloorCR.x, d);\n          float topRight = getImage(b, sourceFloorCR.y, sourceCeilCR.x, d);\n          float bottomRight = getImage(b, sourceCeilCR.y, sourceCeilCR.x, d);\n\n          vec2 fracCR = sourceFracIndexCR - vec2(sourceFloorCR);\n\n          float top = topLeft + (topRight - topLeft) * fracCR.x;\n          float bottom = bottomLeft + (bottomRight - bottomLeft) * fracCR.x;\n          float newValue = top + (bottom - top) * fracCR.y;\n          setOutput(newValue);\n        } else {\n          // Compute the coordinators of nearest neighbor point.\n          ivec2 sourceNearestCR = ivec2(floor(\n            sourceFracIndexCR + vec2(0.5,0.5)));\n          float newValue = getImage(b, sourceNearestCR.y, sourceNearestCR.x, d);\n          setOutput(newValue);\n        }\n      }\n    `}}const qB={kernelName:Bt,backendName:"webgl",kernelFunc:e=>{const{inputs:t,backend:n,attrs:s}=e,{image:r,boxes:a,boxInd:i}=t,{cropSize:o,method:l,extrapolationValue:u}=s,c=new jB(r.shape,a.shape,o,l,u);return n.runWebGLProgram(c,[r,a,i],"float32")}};var KB;!function(e){e.Prod="*",e.Sum="+"}(KB||(KB={}));class XB{constructor(e,t,n,s){this.op=e,this.outputShape=t,this.variableNames=["x"],this.customUniforms=[{name:"index",type:"float"}];const r=this.outputShape.length,a=this.op===KB.Prod?"1.0":"0.0",i=n?a:`getX(${YB(r,"coords",this.op)})`,o=this.outputShape[this.outputShape.length-1];let l="",u="";n?(l=s?"end != "+(o-1):"end != 0",u=s?"end + 1":"end - 1"):(l=s?`end + pow2 < ${o}`:"end >= pow2",u=s?"end + pow2":"end - pow2"),this.userCode=`\n      void main() {\n        ${uM(r)} coords = getOutputCoords();\n        int end = ${ZB(r,"coords",this.op)};\n        float val = ${i};\n        int pow2 = int(pow(2.0, index));\n        if (${l}) {\n          int idx = ${u};\n          ${ZB(r,"coords",this.op)} = idx;\n          val ${this.op}= getX(${YB(r,"coords",this.op)});\n        }\n        setOutput(val);\n      }\n    `}}function YB(e,t,n){if(1===e)return`${t}`;if(2===e)return`${t}.x, ${t}.y`;if(3===e)return`${t}.x, ${t}.y, ${t}.z`;if(4===e)return`${t}.x, ${t}.y, ${t}.z, ${t}.w`;throw new Error(`Cumulative ${n} for rank ${e} is not yet supported`)}function ZB(e,t,n){if(1===e)return`${t}`;if(2===e)return`${t}.y`;if(3===e)return`${t}.z`;if(4===e)return`${t}.w`;throw new Error(`Cumulative ${n} for rank ${e} is not yet supported`)}function JB(e,t,n,s,r,a){const i=t.shape.length,o=th([s],i);let l=t;null!=o&&(l=Jz({inputs:{x:t},backend:n,attrs:{perm:o}}));const u=sh(1,i)[0];if(u!==i-1)throw new Error(`WebGL cumprod shader expects an inner-most axis=${t.shape.length-1} but got axis=${s}`);const c=l.shape[u];let h=kz({inputs:{x:l},backend:n});for(let t=0;t<=Math.ceil(Math.log2(c))-1;t++){const s=new XB(e,l.shape,!1,a),r=[[t]],i=h;h=n.runWebGLProgram(s,[h],h.dtype,r),n.disposeIntermediateTensorInfo(i)}if(r){const t=new XB(e,l.shape,r,a),s=h;h=n.runWebGLProgram(t,[h],h.dtype),n.disposeIntermediateTensorInfo(s)}if(null!=o){const e=Jz({inputs:{x:h},backend:n,attrs:{perm:nh(o)}});return n.disposeIntermediateTensorInfo(h),n.disposeIntermediateTensorInfo(l),e}return h}const QB={kernelName:zt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,exclusive:i,reverse:o}=s;return JB(KB.Prod,r,n,a,i,o)}};const eW={kernelName:Pt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,exclusive:i,reverse:o}=s;return JB(KB.Sum,r,n,a,i,o)}};const tW={kernelName:Wt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,weights:a}=t,{size:i,binaryOutput:o}=s;if(1===r.shape.length){const e=n.readSync(r.dataId),t=n.readSync(a.dataId),s=qM(e,t,a.dtype,a.shape,i);return n.makeTensorInfo([i],a.dtype,s)}if(2===r.shape.length){const e=n.bufferSync(r),t=n.bufferSync(a),s=KM(e,t,i,o);return n.makeTensorInfo(s.shape,a.dtype,s.values)}throw new Error(`Error in denseBincount: input must be at most rank 2, but got rank${r.shape.length}.`)}};class nW{constructor(e,t,n){this.variableNames=["x"],this.outputShape=[],this.outputShape=e,this.blockSize=t,this.dataFormat=n,this.userCode=`\n    void main() {\n      ivec4 coords = getOutputCoords();\n      int b = coords[0];\n      int h = ${this.getHeightCoordString()};\n      int w = ${this.getWidthCoordString()};\n      int d = ${this.getDepthCoordString()};\n\n      int in_h = h / ${t};\n      int offset_h = imod(h, ${t});\n      int in_w = w / ${t};\n      int offset_w = imod(w, ${t});\n      int offset_d = (offset_h * ${t} + offset_w) *\n        ${this.getOutputDepthSize()};\n      int in_d = d + offset_d;\n\n      float result = ${this.getInputSamplingString()};\n      setOutput(result);\n    }\n  `}getHeightCoordString(){return"NHWC"===this.dataFormat?"coords[1]":"coords[2]"}getWidthCoordString(){return"NHWC"===this.dataFormat?"coords[2]":"coords[3]"}getDepthCoordString(){return"NHWC"===this.dataFormat?"coords[3]":"coords[1]"}getOutputDepthSize(){return"NHWC"===this.dataFormat?this.outputShape[3]:this.outputShape[1]}getInputSamplingString(){return"NHWC"===this.dataFormat?"getX(b, in_h, in_w, in_d)":"getX(b, in_d, in_h, in_w)"}}const sW={kernelName:Vt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{blockSize:a,dataFormat:i}=s,o=r.shape[0],l=("NHWC"===i?r.shape[1]:r.shape[2])*a,u=("NHWC"===i?r.shape[2]:r.shape[3])*a,c=("NHWC"===i?r.shape[3]:r.shape[1])/(a*a),h=new nW("NHWC"===i?[o,l,u,c]:[o,c,l,u],a,i);return n.runWebGLProgram(h,[r],r.dtype)}};class rW{constructor(e,t=!1,n=null,s=!1,r=!1){this.variableNames=["x","W"],this.customUniforms=[{name:"pads",type:"ivec2"},{name:"strides",type:"ivec2"},{name:"dilations",type:"ivec2"},{name:"inDims",type:"ivec2"}],this.outputShape=e.outShape,this.enableShapeUniforms=mM(this.outputShape.length);const a=e.filterHeight,i=e.filterWidth,o=e.outChannels/e.inChannels;let l="",u="";n&&(l=s?`float activation(float a) {\n          float b = getPreluActivationWeightsAtOutCoords();\n          ${n}\n        }`:r?`float activation(float a) {\n          float b = getLeakyreluAlphaAtOutCoords();\n          ${n}\n        }`:`\n          float activation(float x) {\n            ${n}\n          }\n        `,u="result = activation(result);");const c=t?"result += getBiasAtOutCoords();":"";t&&this.variableNames.push("bias"),s&&this.variableNames.push("preluActivationWeights"),r&&this.variableNames.push("leakyreluAlpha"),this.userCode=`\n      ${l}\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords.x;\n        ivec2 xRCCorner = coords.yz * strides - pads;\n        int d2 = coords.w;\n        int d1 = d2 / ${o};\n        int q = d2 - d1 * ${o};\n\n        int xRCorner = xRCCorner.x;\n        int xCCorner = xRCCorner.y;\n\n        // Convolve x(?, ?, d1) with w(:, :, d1, q) to get y(yR, yC, d2).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n        // TO DO(dsmilkov): Flatten the two for loops and vec4 the operations.\n        for (int wR = 0; wR < ${a}; wR++) {\n          int xR = xRCorner + wR * dilations[0];\n\n          if (xR < 0 || xR >= inDims[0]) {\n            continue;\n          }\n\n          for (int wC = 0; wC < ${i}; wC++) {\n            int xC = xCCorner + wC * dilations[1];\n\n            if (xC < 0 || xC >= inDims[1]) {\n              continue;\n            }\n\n            float xVal = getX(batch, xR, xC, d1);\n            float wVal = getW(wR, wC, d1, q);\n            dotProd += xVal * wVal;\n          }\n        }\n\n        float result = dotProd;\n        ${c}\n        ${u}\n        setOutput(result);\n      }\n    `}}class aW{constructor(e,t=!1,n=null,s=!1,r=!1){this.variableNames=["x","W"],this.packedInputs=!0,this.packedOutput=!0,this.customUniforms=[{name:"pads",type:"ivec2"},{name:"strides",type:"ivec2"},{name:"dilations",type:"ivec2"},{name:"inDims",type:"ivec2"}],this.outputShape=e.outShape,this.enableShapeUniforms=mM(this.outputShape.length);const a=e.outChannels/e.inChannels,i=e.padInfo.left,o=e.strideWidth,l=e.dilationWidth,u=e.filterHeight,c=e.filterWidth,h=c;let p="\n      int xR; int xC; int xCOffset;\n      vec4 wTexel; vec4 previous; vec4 final;";for(let e=0;e<c;e++)p+=`\n          vec4 xTexelC${2*e};\n          int xTexelC${2*e}Ready;\n          vec4 xTexelC${2*e+1};\n          int xTexelC${2*e+1}Ready;\n          vec4 xC${e};`;p+=`\n    for (int r = 0; r < ${u}; r++) {\n      `;for(let e=0;e<c;e++)p+=`\n          xTexelC${2*e} = vec4(0.0);\n          xTexelC${2*e}Ready = 0;\n          xTexelC${2*e+1} = vec4(0.0);\n          xTexelC${2*e+1}Ready = 0;\n          xC${e} = vec4(0.0);`;p+="\n        xR = xRCorner + r * dilations[0];\n        if (xR >=0 && xR < inDims[0]) {\n      ";for(let e=0;e<(h+1)/2;e++){const t=2*e;if(p+=`\n          xC = xCCorner + ${t*l};\n          `,1===o){if(t<c&&(i%2==1?(p+=`\n                xCOffset = xC + 1;\n                if (xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${t}Ready == 0) {\n                  xTexelC${t} = getX(batch, xR, xCOffset, d1);\n\n                  // Need to manually clear unused channels in case\n                  // we're reading from recycled texture.\n                  if (xCOffset + 1 >= inDims[1]) {\n                    xTexelC${t}.zw = vec2(0.0);\n                  }\n                  xTexelC${t}Ready = 1;\n                }\n              `,p+=1===l&&t>0?`\n                xC${t} = vec4(xTexelC${t-2}.zw, xTexelC${t}.xy);\n                `:`\n                  xCOffset = xC + 1 - 2;\n\n                  if (xCOffset >= 0 && xCOffset < inDims[1]) {\n                    previous = getX(batch, xR, xCOffset, d1);\n\n                    // Need to manually clear unused channels in case\n                    // we're reading from recycled texture.\n                    if (xCOffset + 1 >= inDims[1]) {\n                      previous.zw = vec2(0.0);\n                    }\n\n                    xC${t} = vec4(previous.zw, xTexelC${t}.xy);\n                  } else {\n                    xC${t} = vec4(0.0, 0.0, xTexelC${t}.xy);\n                  }\n                  `):p+=`\n                if (xC >= 0 && xC < inDims[1] && xTexelC${t}Ready == 0) {\n                  xTexelC${t} = getX(batch, xR, xC, d1);\n                  if (xC + 1 >= inDims[1]) {\n                    xTexelC${t}.zw = vec2(0.0);\n                  }\n                  xTexelC${t}Ready = 1;\n                }\n\n                xC${t} = xTexelC${t};\n                `,t+1<c)){const e=i%2==0?te(l):l;l%2==0&&i%2==1||l%2!=0&&i%2!=1?(p+=`\n                  xCOffset = xC + imod(pads[1], 2) + ${e};\n\n                  if (xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${t+1}Ready == 0) {\n                    xTexelC${t+1} = getX(batch, xR, xCOffset, d1);\n\n                    // Need to manually clear unused channels in case\n                    // we're reading from recycled texture.\n                    if (xCOffset + 1 >= inDims[1]) {\n                      xTexelC${t+1}.zw = vec2(0.0);\n                    }\n                    xTexelC${t+1}Ready = 1;\n                  }\n                  `,p+=l>1?`\n                    xCOffset -= 2;\n                    if (xCOffset >= 0 && xCOffset < inDims[1]) {\n                     previous = getX(batch, xR, xCOffset, d1);\n                     xC${t+1} = vec4(previous.zw, xTexelC${t+1}.xy);\n                    } else {\n                     xC${t+1} = vec4(0.0, 0.0, xTexelC${t+1}.xy);\n                    }\n                    `:`\n                    xC${t+1} = vec4(xTexelC${t}.zw, xTexelC${t+1}.xy);\n                    `):p+=1===e?`\n                    xC${t+1} = xTexelC${t};\n                    `:`\n                    xCOffset = xC + ${e};\n\n                    if (xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${t+1}Ready == 0) {\n                      xTexelC${t+1} = getX(batch, xR, xCOffset, d1);\n                      if (xCOffset + 1 >= inDims[1]) {\n                        xTexelC${t+1}.zw = vec2(0.0);\n                      }\n                      xTexelC${t+1}Ready = 1;\n                    }\n\n                    xC${t+1} = xTexelC${t+1};\n                    `}}else t<c&&(i%2==1?(p+=`\n                xCOffset = xC + 1 - strides[1];\n                if(xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${t}Ready == 0) {\n                  xTexelC${t} = getX(batch, xR, xCOffset, d1);\n                  // Need to manually clear unused channels in case\n                  // we're reading from recycled texture.\n                  if (xCOffset + 1 >= inDims[1]) {\n                    xTexelC${t}.zw = vec2(0.0);\n                  }\n                  xTexelC${t}Ready = 1;\n                }\n\n                if(xC + 1 >= 0 && xC + 1 < inDims[1] && xTexelC${t+1}Ready == 0) {\n                  xTexelC${t+1} = getX(batch, xR, xC + 1, d1);\n                  // Need to manually clear unused channels in case\n                  // we're reading from recycled texture.\n                  if (xC + 2 >= inDims[1]) {\n                    xTexelC${t+1}.zw = vec2(0.0);\n                  }\n                  xTexelC${t+1}Ready = 1;\n                }\n\n                xC${t} = vec4(xTexelC${t}.zw, xTexelC${t+1}.zw);\n              `,t+1<c&&(p+=`\n                  final = vec4(0.0);\n                  xCOffset = xC + 1 + strides[1];\n                  if(xCOffset >= 0 && xCOffset < inDims[1]) {\n                    final = getX(batch, xR, xCOffset, d1);\n                  }\n                  xC${t+1} = vec4(xTexelC${t+1}.xy, final.xy);\n                `)):(p+=`\n                if(xC >= 0 && xC < inDims[1] && xTexelC${t}Ready == 0) {\n                  xTexelC${t} = getX(batch, xR, xC, d1);\n                  if (xC + 1 >= inDims[1]) {\n                    xTexelC${t}.zw = vec2(0.0);\n                  }\n                  xTexelC${t}Ready = 1;\n                }\n\n                xCOffset = xC + strides[1];\n                if(xCOffset >= 0 && xCOffset < inDims[1] && xTexelC${t+1}Ready == 0) {\n                  xTexelC${t+1} = getX(batch, xR, xCOffset, d1);\n                  if (xCOffset + 1 >= inDims[1]) {\n                    xTexelC${t+1}.zw = vec2(0.);\n                  }\n                  xTexelC${t+1}Ready = 1;\n                }\n\n                xC${t} = vec4(\n                  xTexelC${t}.xy, xTexelC${t+1}.xy);\n              `,t+1<c&&(p+=`\n                  xC${t+1} = vec4(xTexelC${t}.zw, xTexelC${t+1}.zw);\n                `)));t<c&&(p+=`\n            wTexel = getW(r, ${t}, d1, q);\n            dotProd += xC${t} * vec4(wTexel.xz, wTexel.xz);\n          `,t+1<c&&(p+=`\n              wTexel = getW(r, ${t+1}, d1, q);\n              dotProd += xC${t+1} * vec4(wTexel.xz, wTexel.xz);\n            `))}p+="\n    }\n  ",p+="\n      }\n    ";let d="",f="";n&&(d=s?`vec4 activation(vec4 a) {\n          vec4 b = getPreluActivationWeightsAtOutCoords();\n          ${n}\n        }`:r?`vec4 activation(vec4 a) {\n          vec4 b = getLeakyreluAlphaAtOutCoords();\n          ${n}\n        }`:`vec4 activation(vec4 x) {\n          ${n}\n        }`,f="result = activation(result);");const m=t?"result += getBiasAtOutCoords();":"";t&&this.variableNames.push("bias"),s&&this.variableNames.push("preluActivationWeights"),r&&this.variableNames.push("leakyreluAlpha"),this.userCode=`\n      ${d}\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords.x;\n        ivec2 xRCCorner = coords.yz * strides - pads;\n        int d2 = coords.w;\n        int d1 = d2 / ${a};\n        int q = d2 - d1 * ${a};\n        int xRCorner = xRCCorner.x;\n        int xCCorner = xRCCorner.y;\n\n        //intialize dotProd with a small epsilon seems to reduce GPU accuracy loss.\n        vec4 dotProd = vec4(0.000000000000001);\n\n        ${p}\n\n        vec4 result = dotProd - vec4(0.000000000000001);\n        ${m}\n        ${f}\n        setOutput(result);\n      }\n    `}}const iW={kernelName:Ut,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a}=t,{strides:i,pad:o,dilations:l,dimRoundingMode:u}=s;let c=l;null==c&&(c=[1,1]),ie(Qu(i,c),(()=>`Error in depthwiseConv2d: Either strides or dilations must be 1. Got strides ${i} and dilations '${c}'`));const h=Hu(r.shape,a.shape,i,c,o,u,!0);let p;p=Xe().getBool("WEBGL_PACK_DEPTHWISECONV")&&h.strideWidth<=2&&h.outChannels/h.inChannels==1?new aW(h):new rW(h);const d=[[h.padInfo.top,h.padInfo.left],[h.strideHeight,h.strideWidth],[h.dilationHeight,h.dilationWidth],[h.inHeight,h.inWidth]];return n.runWebGLProgram(p,[r,a],"float32",d)}};class oW{constructor(e){this.variableNames=["x","dy"],this.outputShape=e.filterShape;const t=e.strideHeight,n=e.strideWidth,s=e.padInfo.top,r=e.padInfo.left,a=e.outChannels/e.inChannels;this.userCode=`\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int wR = coords.x;\n        int wC = coords.y;\n        int d1 = coords.z;\n        int dm = coords.w;\n        int d2 = d1 * ${a} + dm;\n\n        float dotProd = 0.0;\n\n        // TO DO: Vec4 over the batch size\n        for (int b = 0; b < ${e.batchSize}; b++) {\n          for (int yR = 0; yR < ${e.outHeight}; yR++) {\n            int xR = wR + yR * ${t} - ${s};\n\n            if (xR < 0 || xR >= ${e.inHeight}) {\n              continue;\n            }\n\n            for (int yC = 0; yC < ${e.outWidth}; yC++) {\n              int xC = wC + yC * ${n} - ${r};\n\n              if (xC < 0 || xC >= ${e.inWidth}) {\n                continue;\n              }\n\n              float dyValue = getDy(b, yR, yC, d2);\n              float xValue = getX(b, xR, xC, d1);\n              dotProd += (xValue * dyValue);\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}class lW{constructor(e){this.variableNames=["dy","W"],this.outputShape=e.inShape;const t=e.filterHeight,n=e.filterWidth,s=e.strideHeight,r=e.strideWidth,a=t-1-e.padInfo.top,i=n-1-e.padInfo.left,o=e.outChannels/e.inChannels;this.userCode=`\n      const ivec2 pads = ivec2(${a}, ${i});\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords[0];\n        int d1 = coords[3];\n        ivec2 dyCorner = coords.yz - pads;\n        int dyRCorner = dyCorner.x;\n        int dyCCorner = dyCorner.y;\n\n        float dotProd = 0.0;\n\n        for (int wR = 0; wR < ${t}; wR++) {\n          float dyR = float(dyRCorner + wR) / ${s}.0;\n\n          if (dyR < 0.0 || dyR >= ${e.outHeight}.0 || fract(dyR) > 0.0) {\n            continue;\n          }\n          int idyR = int(dyR);\n\n          int wRPerm = ${t} - 1 - wR;\n\n          for (int wC = 0; wC < ${n}; wC++) {\n            float dyC = float(dyCCorner + wC) / ${r}.0;\n\n            if (dyC < 0.0 || dyC >= ${e.outWidth}.0 ||\n                fract(dyC) > 0.0) {\n              continue;\n            }\n            int idyC = int(dyC);\n\n            int wCPerm = ${n} - 1 - wC;\n\n            // TO DO: Vec4 over the channelMul\n            for (int dm = 0; dm < ${o}; dm++) {\n              int d2 = d1 * ${o} + dm;\n              float xValue = getDy(batch, idyR, idyC, d2);\n              float wValue = getW(wRPerm, wCPerm, d1, dm);\n              dotProd += xValue * wValue;\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}const uW={kernelName:Gt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,dy:a}=t,{strides:i,dilations:o,pad:l,dimRoundingMode:u,filterShape:c}=s,h=Hu(r.shape,c,i,o,l,u,!0),p=new oW(h);return n.runWebGLProgram(p,[r,a],"float32")}};const cW={kernelName:Ht,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,filter:a}=t,{strides:i,dilations:o,pad:l,dimRoundingMode:u,inputShape:c}=s,h=Hu(c,a.shape,i,o,l,u,!0),p=new lW(h);return n.runWebGLProgram(p,[r,a],"float32")}};class hW{constructor(e){this.variableNames=["X"],this.outputShape=[e,e],this.userCode="\n      void main() {\n          ivec2 coords = getOutputCoords();\n          float val = coords[0] == coords[1] ? getX(coords[0]) : 0.0;\n          setOutput(val);\n      }\n    "}}const pW={kernelName:jt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{x:s}=t,r=[...s.shape,...s.shape],a=ue(s.shape),i=Vz({inputs:{x:s},backend:n,attrs:{shape:[a]}}),o=new hW(a),l=n.runWebGLProgram(o,[i],i.dtype),u=Vz({inputs:{x:l},backend:n,attrs:{shape:r}});return n.disposeIntermediateTensorInfo(i),n.disposeIntermediateTensorInfo(l),u}};class dW{constructor(e){this.variableNames=["x","W"],this.outputShape=e.outShape;const{inHeight:t,inWidth:n,padInfo:s,strideHeight:r,strideWidth:a,filterHeight:i,filterWidth:o,dilationHeight:l,dilationWidth:u}=e,{top:c,left:h}=s;this.userCode=`\n      const ivec2 strides = ivec2(${r}, ${a});\n      const ivec2 pads = ivec2(${c}, ${h});\n      const float neg_infinity = -3.4e38;\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int batch = coords.x;\n        int d1 = coords.w;\n        ivec2 outTopLeftCorner =\n            coords.yz * strides - pads;\n        int hBeg = outTopLeftCorner.x;\n        int wBeg = outTopLeftCorner.y;\n\n        float curVal = neg_infinity;\n        for (int h = 0; h < ${i}; h++) {\n          int hIn = hBeg + h * ${l};\n\n          if (hIn >= 0 && hIn < ${t}) {\n            for (int w = 0; w < ${o}; w++) {\n              int wIn = wBeg + w * ${u};\n\n              if (wIn >= 0 && wIn < ${n}) {\n                float xVal = getX(batch, hIn, wIn, d1);\n                float wVal = getW(h, w, d1);\n\n                float val = xVal + wVal;\n                if (val > curVal) {\n                  curVal = val;\n                }\n              }\n            }\n          }\n        }\n\n        float result = curVal;\n        setOutput(result);\n      }\n    `}}const fW={kernelName:qt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a}=t,{strides:i,pad:o,dilations:l}=s,u=Vu(r.shape,a.shape,i,o,"NHWC",l);let c;const h=new dW(u);c=n.runWebGLProgram(h,[r,a],"float32");const p=Vz({inputs:{x:c},backend:n,attrs:{shape:u.outShape}});return n.disposeIntermediateTensorInfo(c),p}};const mW={kernelName:Jt,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{equation:r}=s,a=t,{allDims:i,summedDims:o,idDims:l}=Sm(r,a.length);Cm(i.length,l,a);const{path:u,steps:c}=$m(o,l),h=c.length;let p=null,d=i.length;const f=[];for(let e=0;e<h;++e){for(const t of c[e]){const{permutationIndices:e,expandDims:s}=Tm(d,l[t]);let r;Em(e)?r=a[t]:(r=Jz({inputs:{x:a[t]},backend:n,attrs:{perm:e}}),f.push(r));const i=r.shape.slice();for(let e=0;e<s.length;++e)i.splice(s[e],0,1);pe(r.shape,i)||(r=Vz({inputs:{x:r},backend:n,attrs:{shape:i}}),f.push(r)),null===p?p=r:(p=Bz({inputs:{a:r,b:p},backend:n}),f.push(p))}e<h-1&&(u[e]>=0&&(p=Yz({inputs:{x:p},backend:n,attrs:{axis:u[e]-(i.length-d),keepDims:!1}}),f.push(p)),d--)}for(const e of f)e!==p&&n.disposeIntermediateTensorInfo(e);return p}},gW=_z({opSnippet:"return (x >= 0.0) ? x : (exp(x) - 1.0);",packedOpSnippet:"\n  vec4 result;\n\n  result.r = (x.r >= 0.0) ? x.r : (exp(x.r) - 1.0);\n  result.g = (x.g >= 0.0) ? x.g : (exp(x.g) - 1.0);\n  result.b = (x.b >= 0.0) ? x.b : (exp(x.b) - 1.0);\n  result.a = (x.a >= 0.0) ? x.a : (exp(x.a) - 1.0);\n\n  return result;\n"}),yW={kernelName:Qt,backendName:"webgl",kernelFunc:gW},bW={kernelName:en,backendName:"webgl",kernelFunc:e=>{const{inputs:t,backend:n}=e,{dy:s,y:r}=t,a=Xe().getBool("WEBGL_PACK_BINARY_OPERATIONS")?new vz("\n  vec4 bGTEZero = vec4(greaterThanEqual(b, vec4(0.)));\n  return (bGTEZero * a) + ((vec4(1.0) - bGTEZero) * (a * (b + vec4(1.0))));\n",s.shape,r.shape):new xz("return (b >= 0.0) ? a : a * (b + 1.0);",s.shape,r.shape);return n.runWebGLProgram(a,[s,r],s.dtype)}},xW=Dz({opSnippet:"return float(a == b);",packedOpSnippet:"\n  return vec4(equal(a, b));\n",dtype:"bool",cpuKernelImpl:QM}),wW={kernelName:nn,backendName:"webgl",kernelFunc:xW},vW=_z({opSnippet:`\n  // Error function is calculated approximately with elementary function.\n  // See "Handbook of Mathematical Functions with Formulas,\n  // Graphs, and Mathematical Tables", Abramowitz and Stegun.\n  float p = ${om};\n  float a1 = ${lm};\n  float a2 = ${um};\n  float a3 = ${cm};\n  float a4 = ${hm};\n  float a5 = ${pm};\n\n  float sign = sign(x);\n  x = abs(x);\n  float t = 1.0 / (1.0 + p * x);\n  return sign * (1.0 - (((((a5*t + a4)*t) + a3)*t + a2)*t + a1)*t*exp(-x*x));\n`}),kW={kernelName:tn,backendName:"webgl",kernelFunc:vW},IW=_z({opSnippet:Fz+"\n  return exp(x);\n",packedOpSnippet:"\n  vec4 result = exp(x);\n  bvec4 isNaN = isnan(x);\n  result.r = isNaN.r ? x.r : result.r;\n  result.g = isNaN.g ? x.g : result.g;\n  result.b = isNaN.b ? x.b : result.b;\n  result.a = isNaN.a ? x.a : result.a;\n\n  return result;\n",cpuKernelImpl:eL,dtype:"float32"}),NW={kernelName:sn,backendName:"webgl",kernelFunc:IW};function SW(e){const{inputs:t,attrs:n,backend:s}=e,{dim:r}=n,{input:a}=t,i=a.shape.length,o=a.shape.slice();let l=r;return r<0&&(ie(-(i+1)<=r,(()=>`Axis must be in the interval [${-(i+1)}, ${i}]`)),l=i+r+1),o.splice(l,0,1),Vz({inputs:{x:a},backend:s,attrs:{shape:o}})}const TW={kernelName:rn,backendName:"webgl",kernelFunc:SW},CW="return exp(x) - 1.0;",$W=_z({opSnippet:CW,packedOpSnippet:CW,cpuKernelImpl:tL}),EW={kernelName:an,backendName:"webgl",kernelFunc:$W};class AW{constructor(e,t,n){this.variableNames=["real","imag"];const s=t[1];this.outputShape=t;const r=n?`2.0 * ${Math.PI}`:`-2.0 * ${Math.PI}`,a=n?`${s}.0`:"1.0";let i;if("real"===e)i="return real * expR - imag * expI;";else{if("imag"!==e)throw new Error(`FFT component must be either "real" or "imag", got ${e}.`);i="return real * expI + imag * expR;"}this.userCode=`\n      const float exponentMultiplier = ${r};\n\n      float unaryOpComplex(float real, float expR, float imag, float expI) {\n        ${i}\n      }\n\n      float mulMatDFT(int batch, int index) {\n        float indexRatio = float(index) / float(${s});\n        float exponentMultiplierTimesIndexRatio =\n            exponentMultiplier * indexRatio;\n\n        float result = 0.0;\n\n        for (int i = 0; i < ${s}; i++) {\n          // x = (-2|2 * PI / N) * index * i;\n          float x = exponentMultiplierTimesIndexRatio * float(i);\n          float expR = cos(x);\n          float expI = sin(x);\n          float real = getReal(batch, i);\n          float imag = getImag(batch, i);\n\n          result +=\n              unaryOpComplex(real, expR, imag, expI) / ${a};\n        }\n\n        return result;\n      }\n\n      void main() {\n        ivec2 coords = getOutputCoords();\n        setOutput(mulMatDFT(coords[0], coords[1]));\n      }\n    `}}function RW(e,t,n){const s=n.texData.get(e.dataId),r=ue(e.shape),a=e.shape[e.shape.length-1],i=Vz({inputs:{x:e},backend:n,attrs:{shape:[r/a,a]}}),o=i.shape,l=new AW("real",o,t),u=new AW("imag",o,t),c=[{dataId:s.complexTensorInfos.real.dataId,dtype:s.complexTensorInfos.real.dtype,shape:o},{dataId:s.complexTensorInfos.imag.dataId,dtype:s.complexTensorInfos.imag.dtype,shape:o}],h=n.runWebGLProgram(l,c,"float32"),p=n.runWebGLProgram(u,c,"float32"),d=Nz({inputs:{real:h,imag:p},backend:n});n.disposeIntermediateTensorInfo(h),n.disposeIntermediateTensorInfo(p);const f=Vz({inputs:{x:d},backend:n,attrs:{shape:e.shape}});return n.disposeIntermediateTensorInfo(i),n.disposeIntermediateTensorInfo(d),f}const FW={kernelName:on,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{input:s}=t;return RW(s,!1,n)}};class _W{constructor(e,t){this.outputShape=[],this.customUniforms=[{name:"value",type:"float"}],this.variableNames=["x"],this.outputShape=e,this.userCode="\n      void main() {\n        // Input can be obtained from uniform value.\n        setOutput(value);\n      }\n    "}}function DW(e){const{backend:t,attrs:n}=e,{shape:s,value:r}=n;let{dtype:a}=n;if(a=a||Fe(r),"string"===a){const e=Ie(a,ue(s));return e.fill(r),t.makeTensorInfo(s,a,e)}{const e=new _W(s,r),n=[[r]];return t.runWebGLProgram(e,[],a,n)}}const OW={kernelName:ln,backendName:"webgl",kernelFunc:DW};class MW{constructor(e){this.variableNames=["Image"],this.outputShape=[];const t=e[2];this.outputShape=e,this.userCode=`\n        void main() {\n          ivec4 coords = getOutputCoords();\n          int x = coords[2];\n\n          int coordX = ${t} - x - 1;\n          float outputValue;\n          if(coordX >= 0 && coordX < ${t}) {\n            outputValue = getImage(coords[0], coords[1], coordX, coords[3]);\n          } else {\n            outputValue = getImage(coords[0], coords[1], coords[2], coords[3]);\n          }\n          setOutput(outputValue);\n        }\n    `}}const LW={kernelName:un,backendName:"webgl",kernelFunc:({inputs:e,backend:t})=>{const{image:n}=e,s=t,r=new MW(n.shape);return s.runWebGLProgram(r,[n],n.dtype)}},zW="return floor(x);",PW=_z({opSnippet:zW,packedOpSnippet:zW,cpuKernelImpl:nL}),BW={kernelName:cn,backendName:"webgl",kernelFunc:PW},WW=Dz({opSnippet:"\n  float s = sign(a) * sign(b);\n  int ia = round(a);\n  int ib = round(b);\n  if (ib != 0) {\n    // Windows (D3D) wants guaranteed non-zero int division at compile-time.\n    return float(idiv(ia, ib, s));\n  } else {\n    return NAN;\n  }\n",packedOpSnippet:"\n  ivec4 ia = round(a);\n  ivec4 ib = round(b);\n  bvec4 cond = notEqual(ib, ivec4(0));\n  ivec4 result = ivec4(0);\n  vec4 s = sign(a) * sign(b);\n\n  // Windows (D3D) wants guaranteed non-zero int division at compile-time.\n  if (cond[0]) {\n    result[0] = idiv(ia[0], ib[0], s[0]);\n  }\n  if (cond[1]) {\n    result[1] = idiv(ia[1], ib[1], s[1]);\n  }\n  if (cond[2]) {\n    result[2] = idiv(ia[2], ib[2], s[2]);\n  }\n  if (cond[3]) {\n    result[3] = idiv(ia[3], ib[3], s[3]);\n  }\n  return vec4(result);\n",dtype:"int32"}),VW={kernelName:hn,backendName:"webgl",kernelFunc:WW};class UW{constructor(e){this.variableNames=["A"];const t=jO(),[n,s]=e;this.outputShape=e,this.userCode=`\n      void main() {\n        ivec3 coords = getOutputCoords();\n        int texR = coords[0];\n        int texC = coords[1];\n        int depth = coords[2];\n        vec2 uv = (vec2(texC, texR) + halfCR) / vec2(${s}.0, ${n}.0);\n\n        vec4 values = ${t.texture2D}(A, uv);\n        float value;\n        if (depth == 0) {\n          value = values.r;\n        } else if (depth == 1) {\n          value = values.g;\n        } else if (depth == 2) {\n          value = values.b;\n        } else if (depth == 3) {\n          value = values.a;\n        }\n\n        setOutput(floor(value * 255.0 + 0.5));\n      }\n    `}}class GW{constructor(e){this.variableNames=["A"],this.packedInputs=!1,this.packedOutput=!0;const t=jO(),[n,s]=e;this.outputShape=e,this.userCode=`\n      void main() {\n        ivec3 coords = getOutputCoords();\n        int texR = coords[0];\n        int texC = coords[1];\n        int depth = coords[2];\n\n        vec4 result = vec4(0.);\n\n        for(int row=0; row<=1; row++) {\n          for(int col=0; col<=1; col++) {\n            texC = coords[1] + row;\n            depth = coords[2] + col;\n\n            vec2 uv = (vec2(texC, texR) + halfCR) /\n                       vec2(${s}.0, ${n}.0);\n            vec4 values = ${t.texture2D}(A, uv);\n            float value;\n            if (depth == 0) {\n              value = values.r;\n            } else if (depth == 1) {\n              value = values.g;\n            } else if (depth == 2) {\n              value = values.b;\n            } else if (depth == 3) {\n              value = values.a;\n            }\n\n            result[row * 2 + col] = floor(value * 255.0 + 0.5);\n          }\n        }\n\n        ${t.output} = result;\n      }\n    `}}const HW={kernelName:fr,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e;let{pixels:r}=t;const{numChannels:a}=s,i="undefined"!=typeof HTMLVideoElement&&r instanceof HTMLVideoElement,o="undefined"!=typeof HTMLImageElement&&r instanceof HTMLImageElement,[l,u]=i?[r.videoWidth,r.videoHeight]:[r.width,r.height],c=[u,l],h=[u,l,a];if(o||i){const e=Xe().getBool("CANVAS2D_WILL_READ_FREQUENTLY_FOR_GPU");null!=jW&&e===qW||(qW=e,jW=document.createElement("canvas").getContext("2d",{willReadFrequently:qW})),jW.canvas.width=l,jW.canvas.height=u,jW.drawImage(r,0,0,l,u),r=jW.canvas}const p=n.makeTensorInfo(c,"int32");n.texData.get(p.dataId).usage=WD.PIXELS,n.gpgpu.uploadPixelDataToTexture(n.getTexture(p.dataId),r);const d=Xe().getBool("WEBGL_PACK")?new GW(h):new UW(h),f=n.runWebGLProgram(d,[p],"int32");return n.disposeData(p.dataId),f}};let jW,qW=Xe().getBool("CANVAS2D_WILL_READ_FREQUENTLY_FOR_GPU");const KW={kernelName:yr,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a,bias:i,preluActivationWeights:o}=t,{strides:l,pad:u,dataFormat:c,dilations:h,dimRoundingMode:p,activation:d,leakyreluAlpha:f}=s,m=tc(c),g=Hu(r.shape,a.shape,l,h,u,p,!1,m);let y;const b=[],x=null!=i,w=null!=o,v="leakyrelu"===d,k=()=>{const e=[r,a],t=(e,t)=>{if("NCHW"===t&&1===e.shape.length&&1!==e.shape[0]){const t=Vz({inputs:{x:e},backend:n,attrs:{shape:[e.shape[0],1,1]}});return b.push(t),t}return e};if(x&&e.push(t(i,c)),w&&e.push(t(o,c)),v){const t=n.makeTensorInfo([],"float32",qr(f,"float32"));e.push(t),b.push(t)}return e};if(1!==g.filterHeight||1!==g.filterWidth||1!==g.dilationHeight||1!==g.dilationWidth||1!==g.strideHeight||1!==g.strideWidth||"SAME"!==g.padInfo.type&&"VALID"!==g.padInfo.type)if(g.strideWidth<=2&&"channelsLast"===m&&Xe().getBool("WEBGL_EXP_CONV")){const e=d?Oz(d,!0):null,t=new TB(g,x,e,w,v),s=[[g.padInfo.top,g.padInfo.left],[g.strideHeight,g.strideWidth],[g.dilationHeight,g.dilationWidth],[g.inHeight,g.inWidth]],r=k();y=n.runWebGLProgram(t,r,"float32",s)}else if(Xe().getBool("WEBGL_CONV_IM2COL"))y=AB({x:r,filter:a,convInfo:g,backend:n,bias:i,activation:d,preluActivationWeights:o,leakyreluAlpha:f});else{const e=d?Oz(d,!1):null,t=new NB(g,x,e,w,v),s=k();y=n.runWebGLProgram(t,s,"float32")}else y=EB({x:r,filter:a,convInfo:g,backend:n,bias:i,activation:d,preluActivationWeights:o,leakyreluAlpha:f});const I=Vz({inputs:{x:y},backend:n,attrs:{shape:g.outShape}});return b.push(y),b.forEach((e=>n.disposeIntermediateTensorInfo(e))),I}};const XW={kernelName:br,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,filter:a,bias:i,preluActivationWeights:o}=t,{strides:l,pad:u,dilations:c,dimRoundingMode:h,activation:p,leakyreluAlpha:d}=s,f=[];let m=c;null==m&&(m=[1,1]),ie(Qu(l,m),(()=>`Error in depthwiseConv2d: Either strides or dilations must be 1. Got strides ${l} and dilations '${m}'`));const g=Hu(r.shape,a.shape,l,m,u,h,!0),y=Xe().getBool("WEBGL_PACK_DEPTHWISECONV")&&g.strideWidth<=2&&g.outChannels/g.inChannels==1,b=p?Oz(p,y):null,x=[r,a],w=null!=i,v=null!=o,k="leakyrelu"===p;if(w&&x.push(i),v&&x.push(o),k){const e=n.makeTensorInfo([],"float32",qr(d,"float32"));x.push(e),f.push(e)}let I;I=y?new aW(g,w,b,v,k):new rW(g,w,b,v,k);const N=[[g.padInfo.top,g.padInfo.left],[g.strideHeight,g.strideWidth],[g.dilationHeight,g.dilationWidth],[g.inHeight,g.inWidth]],S=n.runWebGLProgram(I,x,"float32",N);return f.forEach((e=>n.disposeIntermediateTensorInfo(e))),S}};class YW{constructor(e,t,n,s){this.sliceDim=e,this.strides=t,this.paramsShape=s,this.variableNames=["x","indices"],this.outputShape=n;const r=uM(n.length);let a="\n    int index;";for(let e=0;e<this.sliceDim;e++)a+=`\n          index = round(getIndices(coords[0], ${e}));\n          out_of_bounds = out_of_bounds || index < 0;\n          out_of_bounds = out_of_bounds || index >= ${this.paramsShape[e]};\n          flattenIndex += index * ${this.strides[e]};`;this.userCode=`\n         void main() {\n          ${r} coords = getOutputCoords();\n          int flattenIndex = 0;\n          bool out_of_bounds = false;\n\n          ${a}\n\n          setOutput(out_of_bounds ? 0.0 : getX(flattenIndex, coords[1]));\n        }\n      `}}const ZW={kernelName:fn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{params:s,indices:r}=t,a=r.shape,i=a[a.length-1],o=ue(s.shape),[l,u,c,h]=Hl(s,r),p=Vz({inputs:{x:r},backend:n,attrs:{shape:[u,i]}}),d=Vz({inputs:{x:s},backend:n,attrs:{shape:[ue(s.shape)/c,c]}});if(n.shouldExecuteOnCPU([s,r])||"string"===s.dtype){const e=n.readSync(r.dataId),t=n.bufferSync(s),a=sL(e,t,s.dtype,u,i,c,h,s.shape,o);return n.makeTensorInfo(l,s.dtype,a.values)}const f=new YW(i,h,[u,c],s.shape),m=n.runWebGLProgram(f,[d,p],d.dtype),g=Vz({inputs:{x:m},backend:n,attrs:{shape:l}});return n.disposeIntermediateTensorInfo(p),n.disposeIntermediateTensorInfo(d),n.disposeIntermediateTensorInfo(m),g}};class JW{constructor(e,t){this.variableNames=["A","indices"],this.outputShape=t,this.rank=t.length;const n=uM(this.rank),s=function(e,t){const n=["resRC.x","resRC.y","resRC.z","resRC.w"],s=[];for(let t=0;t<e.length;t++)2===t?s.push("index"):s.push(`${n[t]}`);return s.join()}(e);this.userCode=`\n      void main() {\n        ${n} resRC = getOutputCoords();\n        int index = int(getIndices(resRC.x, resRC.z));\n        float inBounds = (index >= 0) && (index < ${e[2]}) ? 1.0 : 0.0;\n        setOutput(inBounds * getA(${s}));\n      }\n    `}}function QW(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,indices:a}=t,{axis:i,batchDims:o}=s,l=we(i,r.shape)[0];if(Xe().get("DEBUG")){const e=n.readSync(a.dataId),t=r.shape[l];for(let n=0;n<e.length;++n){const s=e[n];ie(s<=t-1&&s>=0,(()=>`GatherV2: the index value ${s} is not in [0, ${t-1}]`))}}const u=jm(r,a,l,o),c=ue(a.shape),h=[],p=Vz({inputs:{x:r},backend:n,attrs:{shape:[u.batchSize,u.outerSize,u.dimSize,u.sliceSize]}}),d=Vz({inputs:{x:a},backend:n,attrs:{shape:[u.batchSize,c/u.batchSize]}});h.push(p),h.push(d);const f=[u.batchSize,u.outerSize,c/u.batchSize,u.sliceSize];if(n.shouldExecuteOnCPU([r,a])||"string"===r.dtype){const e=n.bufferSync(d),t=n.bufferSync(p),s=rL(t,e,f);return h.forEach((e=>n.disposeIntermediateTensorInfo(e))),n.makeTensorInfo(u.outputShape,s.dtype,s.values)}const m=new JW(p.shape,f),g=n.runWebGLProgram(m,[p,d],p.dtype);h.push(g);const y=Vz({inputs:{x:g},backend:n,attrs:{shape:u.outputShape}});return h.forEach((e=>n.disposeIntermediateTensorInfo(e))),y}const eV={kernelName:dn,backendName:"webgl",kernelFunc:QW},tV=Dz({opSnippet:"return float(a > b);",packedOpSnippet:"\n  return vec4(greaterThan(a, b));\n",cpuKernelImpl:aL,dtype:"bool"}),nV={kernelName:mn,backendName:"webgl",kernelFunc:tV},sV=Dz({opSnippet:"return float(a >= b);",packedOpSnippet:"\n  return vec4(greaterThanEqual(a, b));\n",dtype:"bool",cpuKernelImpl:iL}),rV={kernelName:gn,backendName:"webgl",kernelFunc:sV};const aV={kernelName:bn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{input:s}=t;return RW(s,!0,n)}},iV=_z({opSnippet:"return float(!isnan(x) && !isinf(x));",dtype:"bool"}),oV={kernelName:wn,backendName:"webgl",kernelFunc:iV},lV=_z({opSnippet:"return float(isinf(x));",dtype:"bool"}),uV={kernelName:vn,backendName:"webgl",kernelFunc:lV},cV=_z({opSnippet:"return float(isnan(x));",dtype:"bool"}),hV={kernelName:kn,backendName:"webgl",kernelFunc:cV},pV=Dz({opSnippet:"return float(a < b);",packedOpSnippet:"\n  return vec4(lessThan(a, b));\n",cpuKernelImpl:oL,dtype:"bool"}),dV={kernelName:Nn,backendName:"webgl",kernelFunc:pV},fV=Dz({opSnippet:"return float(a <= b);",packedOpSnippet:"\n  return vec4(lessThanEqual(a, b));\n",cpuKernelImpl:lL,dtype:"bool"}),mV={kernelName:Sn,backendName:"webgl",kernelFunc:fV};const gV={kernelName:Tn,backendName:"webgl",kernelFunc:function(e){const{backend:t,attrs:n}=e,{start:s,stop:r,num:a}=n,i=uL(s,r,a);return t.makeTensorInfo([i.length],"float32",i)}},yV=_z({opSnippet:Fz+"\n  return x < 0.0 ? 0./0. : log(x);\n",packedOpSnippet:"\n  vec4 result = log(x);\n  bvec4 isNaN = isnan(x);\n  result.r = isNaN.r ? x.r : (x.r < 0.0 ? 0./0. : result.r);\n  result.g = isNaN.g ? x.g : (x.g < 0.0 ? 0./0. : result.g);\n  result.b = isNaN.b ? x.b : (x.b < 0.0 ? 0./0. : result.b);\n  result.a = isNaN.a ? x.a : (x.a < 0.0 ? 0./0. : result.a);\n  return result;\n",cpuKernelImpl:cL}),bV={kernelName:Cn,backendName:"webgl",kernelFunc:yV},xV=_z({opSnippet:Fz+"\n  return log(1.0 + x);\n"}),wV={kernelName:$n,backendName:"webgl",kernelFunc:xV},vV=Dz({opSnippet:"return float(a >= 1.0 && b >= 1.0);",packedOpSnippet:"\n  return vec4(\n    vec4(greaterThanEqual(a, vec4(1.0))) *\n    vec4(greaterThanEqual(b, vec4(1.0))));\n",dtype:"bool"}),kV={kernelName:En,backendName:"webgl",kernelFunc:vV},IV=_z({opSnippet:"return float(!(x >= 1.0));"}),NV={kernelName:An,backendName:"webgl",kernelFunc:IV},SV=Dz({opSnippet:"return float(a >= 1.0 || b >= 1.0);",packedOpSnippet:"\n  return min(\n    vec4(greaterThanEqual(a, vec4(1.0))) +\n    vec4(greaterThanEqual(b, vec4(1.0))),\n    vec4(1.0));\n",dtype:"bool"}),TV={kernelName:Rn,backendName:"webgl",kernelFunc:SV};class CV{constructor(e,t,n,s,r){this.variableNames=["x"],this.outputShape=[];const a=t,i=e[3]-1;let o;this.outputShape=e;const l=`float(${n}) + float(${s}) * sum`;o=.5===r?`inversesqrt(${l})`:1===r?`1.0/(${l})`:`exp(log(${l}) * float(-${r}));`,this.userCode=`\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int r = coords[1];\n        int c = coords[2];\n        int d = coords[3];\n        float x = getX(b, r, c, d);\n        float sum = 0.0;\n        for (int j = -${a}; j <= ${a}; j++) {\n          int idx = d + j;\n          if (idx >= 0 && idx <=  ${i}) {\n            float z = getX(b, r, c, idx);\n            sum += z * z;\n          }\n        }\n        float val = x * ${o};\n        setOutput(val);\n      }\n    `}}class $V{constructor(e,t,n,s,r){this.variableNames=["x"],this.outputShape=[],this.packedInputs=!0,this.packedOutput=!0;const a=t,i=e[3]-1;let o;this.outputShape=e;const l=`float(${n}) + float(${s}) * sum`;o=.5===r?`inversesqrt(${l})`:1===r?`1.0/(${l})`:`exp(log(${l}) * float(-${r}));`,this.userCode=`\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords.x;\n        int r = coords.y;\n        int c = coords.z;\n        int d = coords.w;\n\n        bool hasNextCol = d < ${this.outputShape[3]};\n        bool hasNextRow = c < ${this.outputShape[2]};\n\n        vec4 sum = vec4(0.);\n        vec4 xFragAtOutputCoords = getX(b, r, c, d);\n\n        vec4 xAtOutputCoords = vec4(\n          getChannel(xFragAtOutputCoords, vec2(c, d)),\n          hasNextCol ?\n            getChannel(xFragAtOutputCoords, vec2(c, d + 1)) : 0.0,\n          hasNextRow ?\n            getChannel(xFragAtOutputCoords , vec2(c + 1, d)) : 0.0,\n          (hasNextRow && hasNextCol) ?\n            getChannel(xFragAtOutputCoords, vec2(c + 1, d + 1)) : 0.0\n        );\n\n        int firstChannel = d - ${a};\n        vec2 cache = vec2(0.);\n        if(firstChannel >= 0){\n          vec4 firstChannelFrag = getX(b, r, c, firstChannel);\n          cache.x = getChannel(firstChannelFrag, vec2(c, firstChannel));\n            if(hasNextRow){\n              cache.y = getChannel(firstChannelFrag, vec2(c + 1, firstChannel));\n            }\n        }\n\n        ivec2 depth = ivec2(d, d + 1);\n        for (int j = - ${a}; j <= ${a}; j++) {\n          ivec2 idx = depth + j;\n          bvec2 aboveLowerBound = greaterThanEqual(idx, ivec2(0));\n          bvec2 belowUpperBound = lessThanEqual(idx, ivec2(${i}));\n\n          bool depthInRange = aboveLowerBound.x && belowUpperBound.x;\n          bool depthPlusOneInRange = aboveLowerBound.y && belowUpperBound.y;\n\n          if(depthInRange || depthPlusOneInRange){\n            vec4 z = vec4(0.);\n            vec4 xFragAtCurrentDepth;\n            z.xz = cache.xy;\n            if(depthPlusOneInRange && hasNextCol){\n              xFragAtCurrentDepth = idx.y != d ?\n                getX(b, r, c, idx.y) : xFragAtOutputCoords;\n              z.y = getChannel(xFragAtCurrentDepth, vec2(c, idx.y));\n              if(hasNextRow){\n                z.w = getChannel(xFragAtCurrentDepth, vec2(c + 1, idx.y));\n              }\n            }\n            cache.xy = z.yw;\n            sum += z * z;\n          }\n        }\n        vec4 result = xAtOutputCoords * ${o};\n        setOutput(result);\n      }\n    `}}const EV={kernelName:On,backendName:"webgl",kernelFunc:e=>{const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{depthRadius:a,bias:i,alpha:o,beta:l}=s,u=Xe().getBool("WEBGL_PACK_NORMALIZATION")?new $V(r.shape,a,i,o,l):new CV(r.shape,a,i,o,l);return n.runWebGLProgram(u,[r],r.dtype)}};class AV{constructor(e,t,n,s,r){this.variableNames=["inputImage","outputImage","dy"],this.outputShape=[],this.outputShape=e,this.depth=e[3],this.depthRadius=t,this.bias=n,this.alpha=s,this.beta=r,this.userCode=`\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int r = coords[1];\n        int c = coords[2];\n\n        float result = 0.0;\n        for (int d = 0; d < ${this.depth}; ++d) {\n          int depthBegin = int(max(0.0, float(d - ${t})));\n          int depthEnd = int(min(float(${this.depth}),\n              float(d + ${t} + 1)));\n\n          const int MIN_DEPTH_BEGIN = 0;\n          const int MAX_DEPTH_END = ${this.depth};\n\n          float norm = 0.0;\n          for (int k = MIN_DEPTH_BEGIN; k < MAX_DEPTH_END; ++k) {\n            if (k < depthBegin){\n              continue;\n            }\n            else if (k >= depthBegin && k < depthEnd) {\n              norm += getInputImage(b, r, c, k) * getInputImage(b, r, c, k);\n            }\n            else {\n              break;\n            }\n          }\n\n          norm = float(${s}) * norm + float(${n});\n\n          for(int k = MIN_DEPTH_BEGIN; k < MAX_DEPTH_END; ++k){\n            if (k < depthBegin){\n              continue;\n            }\n            else if (k >= depthBegin && k < depthEnd){\n              float dyi = -2.0 * float(${s})\n                * float(${r})\n                * getInputImage(b, r, c, k) * getOutputImage(b, r, c, d)\n                / norm;\n              if (k == d) {\n                dyi += pow(norm, -1.0 * ${r});\n              }\n              if (k == coords[3]) {\n                dyi *= getDy(b, r, c, d);\n                result += dyi;\n              }\n            }\n            else {\n              break;\n            }\n          }\n      }\n      setOutput(result);\n      }\n    `}}const RV={kernelName:Mn,backendName:"webgl",kernelFunc:e=>{const{inputs:t,backend:n,attrs:s}=e,{x:r,y:a,dy:i}=t,{depthRadius:o,bias:l,alpha:u,beta:c}=s,h=new AV(r.shape,o,l,u,c);return n.runWebGLProgram(h,[r,a,i],r.dtype)}};function FV(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{reductionIndices:a,keepDims:i}=s,o=r.shape.length,l=we(a,r.shape);let u=l;const c=th(u,o),h=null!=c,p=n.shouldExecuteOnCPU([r]);let d=r;if(h){if(p){const e=n.texData.get(d.dataId).values,t=new Array(o);for(let e=0;e<t.length;e++)t[e]=r.shape[c[e]];const s=PL(e,r.shape,r.dtype,c,t);d=n.makeTensorInfo(t,r.dtype);n.texData.get(d.dataId).values=s}else d=Xz(r,c,n);u=sh(u.length,o)}eh("max",u,o);const[f,m]=Jc(d.shape,u);let g,y=f;if(i&&(y=Qc(f,l)),p){const e=n.texData.get(d.dataId).values,t=hL(e,ue(m),y,r.dtype);g=n.makeTensorInfo(y,r.dtype);n.texData.get(g.dataId).values=t}else g=function(e,t,n,s){const r=ue(t),a=Vz({inputs:{x:e},attrs:{shape:[ue(e.shape)/r,r]},backend:s}),i=jz(a,e.dtype,"max",s),o=Vz({inputs:{x:i},attrs:{shape:n},backend:s});return s.disposeIntermediateTensorInfo(a),s.disposeIntermediateTensorInfo(i),o}(d,m,y,n);return h&&n.disposeIntermediateTensorInfo(d),g}const _V={kernelName:zn,backendName:"webgl",kernelFunc:FV},DV=Dz({opSnippet:bz+"\n  return max(a, b);\n",packedOpSnippet:"\n  vec4 result = vec4(max(a, b));\n  bvec4 isNaNA = isnan(a);\n  bvec4 isNaNB = isnan(b);\n  bvec4 isNaN = bvec4(isNaNA.x || isNaNB.x, isNaNA.y || isNaNB.y, isNaNA.z || isNaNB.z, isNaNA.w || isNaNB.w);\n  "+wz+"\n  return result;\n",cpuKernelImpl:pL}),OV={kernelName:Pn,backendName:"webgl",kernelFunc:DV};const MV={kernelName:Bn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t;GO(r,"maxPool");const{filterSize:a,strides:i,pad:o,dimRoundingMode:l}=s;ie(Qu(i,1),(()=>`Error in maxPool: Either strides or dilations must be 1. Got strides ${i} and dilations '1'`));const u=Uu(r.shape,a,i,1,o,l);if(1===u.filterWidth&&1===u.filterHeight&&pe(u.inShape,u.outShape))return kz({inputs:{x:r},backend:n});const c=new DP(u,"max",!1);return n.runWebGLProgram(c,[r],r.dtype)}};const LV={kernelName:Vn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{filterSize:a,strides:i,pad:o,dataFormat:l,dimRoundingMode:u}=s,c=Gu(r.shape,a,i,[1,1,1],o,u,l),h=new OP(c,"max",!1);return n.runWebGLProgram(h,[r],r.dtype)}};class zV{constructor(e){this.variableNames=["dy","maxPos"],this.outputShape=e.inShape;const t=e.strideHeight,n=e.strideWidth,s=e.dilationHeight,r=e.effectiveFilterHeight,a=e.effectiveFilterWidth,i=r-1-e.padInfo.top,o=a-1-e.padInfo.left,l=r*a-1;this.userCode=`\n      const ivec2 pads = ivec2(${i}, ${o});\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n\n        ivec2 dyRCCorner = coords.yz - pads;\n        int dyRCorner = dyRCCorner.x;\n        int dyCCorner = dyRCCorner.y;\n\n        // Convolve dy(?, ?, d) with pos mask(:, :, d) to get dx(xR, xC, d).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n        for (int wR = 0; wR < ${r};\n          wR += ${s}) {\n          float dyR = float(dyRCorner + wR) / ${t}.0;\n\n          if (dyR < 0.0 || dyR >= ${e.outHeight}.0 || fract(dyR) > 0.0) {\n            continue;\n          }\n          int idyR = int(dyR);\n\n          for (int wC = 0; wC < ${a}; wC++) {\n            float dyC = float(dyCCorner + wC) / ${n}.0;\n\n            if (dyC < 0.0 || dyC >= ${e.outWidth}.0 ||\n                fract(dyC) > 0.0) {\n              continue;\n            }\n            int idyC = int(dyC);\n\n            float dyValue = getDy(b, idyR, idyC, d);\n            int maxPosValue = ${l} - int(getMaxPos(b, idyR, idyC, d));\n\n            // Get the current value, check it against the value from the\n            // position matrix.\n            int curPosValue = wR * ${a} + wC;\n            float mask = float(maxPosValue == curPosValue ? 1.0 : 0.0);\n\n            dotProd += dyValue * mask;\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}class PV{constructor(e){this.variableNames=["dy","maxPos"],this.outputShape=e.inShape;const t=e.strideDepth,n=e.strideHeight,s=e.strideWidth,r=e.dilationDepth,a=e.dilationHeight,i=e.dilationWidth,o=e.effectiveFilterDepth,l=e.effectiveFilterHeight,u=e.effectiveFilterWidth,c=o-1-e.padInfo.front,h=l-1-e.padInfo.top,p=u-1-e.padInfo.left,d=o*l*u-1;this.userCode=`\n      const ivec3 pads = ivec3(${c}, ${h}, ${p});\n\n      void main() {\n        ivec5 coords = getOutputCoords();\n        int batch = coords.x;\n        int ch = coords.u;\n\n        ivec3 dyCorner = ivec3(coords.y, coords.z, coords.w) - pads;\n        int dyDCorner = dyCorner.x;\n        int dyRCorner = dyCorner.y;\n        int dyCCorner = dyCorner.z;\n\n        // Convolve dy(?, ?, ?, ch) with pos mask(:, :, :, d) to get\n        // dx(xD, xR, xC, ch).\n        // ? = to be determined. : = across all values in that axis.\n        float dotProd = 0.0;\n\n        for (int wD = 0; wD < ${o};\n           wD += ${r}) {\n          float dyD = float(dyDCorner + wD) / ${t}.0;\n\n          if (dyD < 0.0 || dyD >= ${e.outDepth}.0 || fract(dyD) > 0.0) {\n            continue;\n          }\n          int idyD = int(dyD);\n\n          for (int wR = 0; wR < ${l};\n              wR += ${a}) {\n            float dyR = float(dyRCorner + wR) / ${n}.0;\n\n            if (dyR < 0.0 || dyR >= ${e.outHeight}.0 ||\n                fract(dyR) > 0.0) {\n              continue;\n            }\n            int idyR = int(dyR);\n\n            for (int wC = 0; wC < ${u};\n                wC += ${i}) {\n              float dyC = float(dyCCorner + wC) / ${s}.0;\n\n              if (dyC < 0.0 || dyC >= ${e.outWidth}.0 ||\n                  fract(dyC) > 0.0) {\n                continue;\n              }\n              int idyC = int(dyC);\n\n              float dyValue = getDy(batch, idyD, idyR, idyC, ch);\n              int maxPosValue = ${d} -\n                  int(getMaxPos(batch, idyD, idyR, idyC, ch));\n\n              // Get the current value, check it against the value from the\n              // position matrix.\n              int curPosValue =\n                  wD * ${l} * ${u} +\n                  wR * ${u} + wC;\n              float mask = float(maxPosValue == curPosValue ? 1.0 : 0.0);\n\n              dotProd += dyValue * mask;\n            }\n          }\n        }\n        setOutput(dotProd);\n      }\n    `}}const BV={kernelName:Un,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a}=t,i=a,{filterSize:o,strides:l,pad:u,dimRoundingMode:c}=s,h=Gu(i.shape,o,l,[1,1,1],u,c),p=new OP(h,"max",!0),d=n.runWebGLProgram(p,[i],i.dtype),f=new PV(h),m=n.runWebGLProgram(f,[r,d],i.dtype);return n.disposeIntermediateTensorInfo(d),m}};const WV={kernelName:Wn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{dy:r,input:a,output:i}=t,o=a;GO([a,i],"maxPoolGrad");const{filterSize:l,strides:u,pad:c,dimRoundingMode:h}=s,p=Uu(o.shape,l,u,1,c,h),d=new DP(p,"max",!0),f=n.runWebGLProgram(d,[o],o.dtype),m=new zV(p),g=n.runWebGLProgram(m,[r,f],o.dtype);return n.disposeIntermediateTensorInfo(f),g}};const VV={kernelName:Gn,backendName:"webgl",kernelFunc:({inputs:e,attrs:t,backend:n})=>{const{x:s}=e,{filterSize:r,strides:a,pad:i,includeBatchInIndex:o}=t,l=n;ie(4===s.shape.length,(()=>`Error in maxPool: input must be rank 4 but got rank ${s.shape.length}.`));const u=[1,1];ie(Qu(a,u),(()=>`Error in maxPool: Either strides or dilations must be 1. Got strides ${a} and dilations '${u}'`));const c=Uu(s.shape,r,a,u,i),[h,p]=function(e,t,n,s){let r=new DP(n,"max",!1);const a=s.runWebGLProgram(r,[e],"float32");return r=new DP(n,"max",!0,!0,t),[a,s.runWebGLProgram(r,[e],"float32")]}(s,o,c,l);return[h,p]}};const UV={kernelName:Hn,backendName:"webgl",kernelFunc:({inputs:e,attrs:t,backend:n})=>{const{x:s}=e,{keepDims:r,axis:a}=t,i=n,o=s.shape.length,l=we(a,s.shape);let u=l;const c=th(u,o),h=null!=c,p=i.shouldExecuteOnCPU([s]),d=[];let f=s;if(h){if(p){const e=i.texData.get(f.dataId).values,t=new Array(o);for(let e=0;e<t.length;e++)t[e]=s.shape[c[e]];const n=PL(e,s.shape,s.dtype,c,t);f=i.makeTensorInfo(t,s.dtype);i.texData.get(f.dataId).values=n}else f=Xz(s,c,i);d.push(f),u=sh(u.length,o)}eh("sum",u,o);const[m,g]=Jc(f.shape,u);let y=m;r&&(y=Qc(m,l));const b=function(e,t,n,s){const r=ue(t),a=Vz({inputs:{x:e},attrs:{shape:[ue(e.shape)/r,r]},backend:s}),i=jz(a,"float32","mean",s),o=Vz({inputs:{x:i},attrs:{shape:n},backend:s});return s.disposeIntermediateTensorInfo(a),s.disposeIntermediateTensorInfo(i),o}(f,g,y,i);for(const e of d)i.disposeIntermediateTensorInfo(e);return b}};const GV={kernelName:jn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s,o=r.shape.length,l=we(a,r.shape);let u=l;const c=th(u,o);let h=r;null!=c&&(h=Jz({inputs:{x:r},backend:n,attrs:{perm:c}}),u=sh(u.length,r.shape.length)),eh("min",u,o);const[p,d]=Jc(h.shape,u),f=Vz({inputs:{x:h},backend:n,attrs:{shape:[-1,ue(d)]}}),m=jz(f,f.dtype,"min",n);let g;if(i){g=Vz({inputs:{x:m},backend:n,attrs:{shape:Qc(p,l)}})}else g=Vz({inputs:{x:m},backend:n,attrs:{shape:p}});return n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(m),null!=c&&n.disposeIntermediateTensorInfo(h),g}},HV=Dz({opSnippet:bz+"\n  return min(a, b);\n",packedOpSnippet:"\n  vec4 result = vec4(min(a, b));\n  bvec4 isNaNA = isnan(a);\n  bvec4 isNaNB = isnan(b);\n  bvec4 isNaN = bvec4(isNaNA.x || isNaNB.x, isNaNA.y || isNaNB.y, isNaNA.z || isNaNB.z, isNaNA.w || isNaNB.w);\n  "+wz+"\n  return result;\n",cpuKernelImpl:dL}),jV={kernelName:qn,backendName:"webgl",kernelFunc:HV};class qV{constructor(e,t,n){this.variableNames=["x"],this.outputShape=t.map(((t,n)=>t[0]+e[n]+t[1]));const s=e.length,r=uM(s),a=t.map((e=>e[0])).join(","),i=t.map(((t,n)=>t[0]+e[n])).join(","),o=["coords[0]","coords[1]","coords[2]","coords[3]"].slice(0,s),l="reflect"===n?0:1;this.userCode=1!==s?`\n      ${r} start = ${r}(${a});\n      ${r} end = ${r}(${i});\n\n      void main() {\n        ${r} outC = getOutputCoords();\n        for (int i = 0; i < ${s}; i++) {\n          if (outC[i] < start[i]) {\n            outC[i] = start[i] * 2 - outC[i] - ${l};\n          } else if(outC[i] >= end[i]) {\n            outC[i] = (end[i] - 1) * 2 - outC[i] + ${l};\n          }\n        }\n        ${r} coords = outC - start;\n        setOutput(getX(${o}));\n      }\n    `:`\n        int start = ${a};\n        int end = ${i};\n\n        void main() {\n          int outC = getOutputCoords();\n          if (outC < start) {\n            outC = start * 2 - outC - ${l};\n          } else if(outC >= end) {\n            outC = (end - 1) * 2 - outC + ${l};\n          }\n          setOutput(getX(outC - start));\n        }\n      `}}class KV{constructor(e,t,n){this.variableNames=["x"],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=t.map(((t,n)=>t[0]+e[n]+t[1]));const s=e.length,r=uM(s),a=t.map((e=>e[0])).join(","),i=t.map(((t,n)=>t[0]+e[n])).join(","),o=VL("rc",s),l=VL("source",s),u=`${o[s-1]} < ${this.outputShape[s-1]}`,c=1===s?"source":`vec2(${l.slice(-2).join()})`,h="reflect"===n?0:1;let p="";if(1===s){const e=`\n        ${r} source = rc;\n        if (source < start) {\n          source = start * 2 - source - ${h};\n        } else if (source >= end) {\n          source = (end - 1) * 2 - source + ${h};\n        }\n        source -= start;\n      `;p=`\n        ${r} rc = outputLoc;\n        ${e}\n        result[0] = getChannel(getX(${l.join()}), ${c});\n        ${o[s-1]} += 1;\n        if(${u}) {\n          ${e}\n          result[1] = getChannel(getX(${l.join()}), ${c});\n        }\n      `}else{const e=`\n        ${r} source = rc;\n        ${r} lt = ${r}(lessThan(source, start));\n        ${r} gte = ${r}(greaterThanEqual(source, end));\n        ${r} orig = 1 - (lt + gte);\n        source = orig * source +\n                lt * (start * 2 - source - ${h}) +\n                gte * ((end - 1) * 2 - source + ${h});\n        source -= start;\n      `;p=`\n        ${r} rc = outputLoc;\n        ${e}\n        result[0] = getChannel(getX(${l.join()}), ${c});\n        ${o[s-1]} += 1;\n        if(${u}) {\n          ${e}\n          result[1] = getChannel(getX(${l.join()}), ${c});\n        }\n        rc = outputLoc;\n        ${o[s-2]} += 1;\n        if(${o[s-2]} < ${this.outputShape[s-2]}) {\n          ${e}\n          result[2] = getChannel(getX(${l.join()}), ${c});\n          ${o[s-1]} += 1;\n          if(${u}) {\n            ${e}\n            result[3] = getChannel(getX(${l.join()}), ${c});\n          }\n        }\n      `}this.userCode=`\n      const ${r} start = ${r}(${a});\n      const ${r} end = ${r}(${i});\n\n      void main() {\n        ${r} outputLoc = getOutputCoords();\n        vec4 result = vec4(0.);\n        ${p}\n        setOutput(result);\n      }\n    `}}const XV={kernelName:Kn,backendName:"webgl",kernelFunc:({inputs:e,backend:t,attrs:n})=>{const{x:s}=e,{paddings:r,mode:a}=n,i=Xe().getBool("WEBGL_PACK_ARRAY_OPERATIONS")?new KV(s.shape,r,a):new qV(s.shape,r,a);return t.runWebGLProgram(i,[s],s.dtype)}},YV=Dz({opSnippet:"if (b == 0.0) return NAN;\n  return mod(a, b);",packedOpSnippet:"\n  vec4 result = mod(a, b);\n  bvec4 isNaN = equal(b, vec4(0.0));\n  "+wz+"\n  return result;\n"}),ZV={kernelName:Xn,backendName:"webgl",kernelFunc:YV};class JV{constructor(e,t,n){this.variableNames=["probs"],this.customUniforms=[{name:"seed",type:"float"}],this.outputShape=[e,n],this.userCode=`\n      void main() {\n        ivec2 coords = getOutputCoords();\n        int batch = coords[0];\n\n        float r = random(seed);\n        float cdf = 0.0;\n\n        for (int i = 0; i < ${t-1}; i++) {\n          cdf += getProbs(batch, i);\n\n          if (r < cdf) {\n            setOutput(float(i));\n            return;\n          }\n        }\n\n        // If no other event happened, last event happened.\n        setOutput(float(${t-1}));\n      }\n    `}}const QV=Dz({opSnippet:"\nif (a == b) {\n  return 1.0;\n};\nreturn a / b;",packedOpSnippet:"\n  // vec4 one = vec4(equal(a, b));\n  // return one + (vec4(1.0) - one) * a / b;\n  vec4 result = a / b;\n  if(a.x == b.x) {\n    result.x = 1.;\n  }\n  if(a.y == b.y) {\n    result.y = 1.;\n  }\n  if(a.z == b.z) {\n    result.z = 1.;\n  }\n  if(a.w == b.w) {\n    result.w = 1.;\n  }\n\n  return result;\n",checkOutOfBounds:!0}),eU={kernelName:Zt,backendName:"webgl",kernelFunc:QV},tU="return a - b;",nU=Dz({opSnippet:tU,packedOpSnippet:tU,supportsComplex:!0,cpuKernelImpl:ML}),sU={kernelName:tr,backendName:"webgl",kernelFunc:nU};function rU(e){const{inputs:t,backend:n,attrs:s}=e,{logits:r}=t,{dim:a}=s,i=we([a],r.shape),o=FV({inputs:{x:r},backend:n,attrs:{reductionIndices:i,keepDims:!1}}),l=Qc(o.shape,i),u=Vz({inputs:{x:o},backend:n,attrs:{shape:l}}),c=nU({inputs:{a:r,b:u},backend:n}),h=IW({inputs:{x:c},backend:n}),p=Yz({inputs:{x:h},backend:n,attrs:{axis:i,keepDims:!1}}),d=Vz({inputs:{x:p},backend:n,attrs:{shape:l}}),f=QV({inputs:{a:h,b:d},backend:n});return n.disposeIntermediateTensorInfo(o),n.disposeIntermediateTensorInfo(u),n.disposeIntermediateTensorInfo(c),n.disposeIntermediateTensorInfo(h),n.disposeIntermediateTensorInfo(p),n.disposeIntermediateTensorInfo(d),f}const aU={kernelName:Vs,backendName:"webgl",kernelFunc:rU};const iU={kernelName:Yn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{logits:r}=t,{numSamples:a,seed:i,normalized:o}=s,l=o?r:rU({inputs:{logits:r},backend:n,attrs:{dim:r.shape.length-1}}),u=l.shape[0],c=l.shape[1],h=new JV(u,c,a),p=[[i]],d=n.runWebGLProgram(h,[l],"int32",p);return o||n.disposeIntermediateTensorInfo(l),d}},oU=YL+"\n  return -x;\n";const lU={kernelName:Jn,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{x:s}=t;if(n.shouldExecuteOnCPU([s])){const e=n.texData.get(s.dataId),[t,r]=mL(e.values,s.shape,s.dtype);return n.makeTensorInfo(r,s.dtype,t)}let r;return r=Xe().getBool("WEBGL_PACK_UNARY_OPERATIONS")?new uz(s.shape,"\n  vec4 result = -x;\n  bvec4 isNaN = isnan(x);\n\n  result.r = isNaN.r ? x.r : result.r;\n  result.g = isNaN.g ? x.g : result.g;\n  result.b = isNaN.b ? x.b : result.b;\n  result.a = isNaN.a ? x.a : result.a;\n\n  return result;\n"):new XL(s.shape,oU),n.runWebGLProgram(r,[s],s.dtype)}},uU=Xd;const cU={kernelName:es,backendName:"webgl",kernelFunc:function(e){xr("tf.nonMaxSuppression() in webgl locks the UI thread. Call tf.nonMaxSuppressionAsync() instead");const{inputs:t,backend:n,attrs:s}=e,{boxes:r,scores:a}=t,{maxOutputSize:i,iouThreshold:o,scoreThreshold:l}=s,u=n.readSync(r.dataId),c=n.readSync(a.dataId),{selectedIndices:h}=uU(u,c,i,o,l);return n.makeTensorInfo([h.length],"int32",new Int32Array(h))}},hU=Yd;const pU={kernelName:ts,backendName:"webgl",kernelFunc:function(e){xr("tf.nonMaxSuppression() in webgl locks the UI thread. Call tf.nonMaxSuppressionAsync() instead");const{inputs:t,backend:n,attrs:s}=e,{boxes:r,scores:a}=t,{maxOutputSize:i,iouThreshold:o,scoreThreshold:l,padToMaxOutputSize:u}=s,c=n.readSync(r.dataId),h=n.readSync(a.dataId),{selectedIndices:p,validOutputs:d}=hU(c,h,i,o,l,u);return[n.makeTensorInfo([p.length],"int32",new Int32Array(p)),n.makeTensorInfo([],"int32",new Int32Array([d]))]}},dU=Zd;const fU={kernelName:ns,backendName:"webgl",kernelFunc:function(e){xr("tf.nonMaxSuppression() in webgl locks the UI thread. Call tf.nonMaxSuppressionAsync() instead");const{inputs:t,backend:n,attrs:s}=e,{boxes:r,scores:a}=t,{maxOutputSize:i,iouThreshold:o,scoreThreshold:l,softNmsSigma:u}=s,c=n.readSync(r.dataId),h=n.readSync(a.dataId),p=i,d=o,f=l,m=u,{selectedIndices:g,selectedScores:y}=dU(c,h,p,d,f,m);return[n.makeTensorInfo([g.length],"int32",new Int32Array(g)),n.makeTensorInfo([y.length],"float32",new Float32Array(y))]}};class mU{constructor(e,t,n,s){this.variableNames=["indices"],this.outputShape=[e,t],this.userCode=`\n      void main() {\n        ivec2 coords = getOutputCoords();\n        int index = round(getIndices(coords.x));\n        setOutput(mix(float(${s}), float(${n}),\n                      float(index == coords.y)));\n      }\n    `}}const gU={kernelName:rs,backendName:"webgl",kernelFunc:e=>{const{inputs:t,backend:n,attrs:s}=e,{indices:r}=t,{dtype:a,depth:i,onValue:o,offValue:l}=s,u=ue(r.shape),c=new mU(u,i,o,l),h=Vz({inputs:{x:r},backend:n,attrs:{shape:[u]}}),p=n.runWebGLProgram(c,[h],a);n.disposeIntermediateTensorInfo(h);const d=Vz({inputs:{x:p},backend:n,attrs:{shape:[...r.shape,i]}});return n.disposeIntermediateTensorInfo(p),d}};function yU(e){const{inputs:t,backend:n}=e,{x:s}=t;if("complex64"===s.dtype){const e=sB({inputs:{input:s},backend:n}),t=yU({inputs:{x:e},backend:n}),r=xB({inputs:{input:s},backend:n}),a=yU({inputs:{x:r},backend:n}),i=Nz({inputs:{real:t,imag:a},backend:n});return n.disposeIntermediateTensorInfo(e),n.disposeIntermediateTensorInfo(t),n.disposeIntermediateTensorInfo(r),n.disposeIntermediateTensorInfo(a),i}return DW({attrs:{shape:s.shape,dtype:s.dtype,value:"string"===s.dtype?"":0},backend:n})}const bU={kernelName:pr,backendName:"webgl",kernelFunc:yU};const xU={kernelName:ss,backendName:"webgl",kernelFunc:function e(t){const{inputs:n,backend:s}=t,{x:r}=n;if("string"===r.dtype)throw new Error("onesLike is not supported under string dtype");if("complex64"===r.dtype){const t=sB({inputs:{input:r},backend:s}),n=e({inputs:{x:t},backend:s}),a=xB({inputs:{input:r},backend:s}),i=yU({inputs:{x:a},backend:s}),o=Nz({inputs:{real:n,imag:i},backend:s});return s.disposeIntermediateTensorInfo(t),s.disposeIntermediateTensorInfo(n),s.disposeIntermediateTensorInfo(a),s.disposeIntermediateTensorInfo(i),o}return DW({attrs:{shape:r.shape,dtype:r.dtype,value:1},backend:s})}};const wU={kernelName:as,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{axis:r}=s;if(1===t.length)return SW({inputs:{input:t[0]},backend:n,attrs:{dim:r}});const a=t[0].shape,i=t[0].dtype;t.forEach((e=>{oe(a,e.shape,"All tensors passed to stack must have matching shapes"),ie(i===e.dtype,(()=>"All tensors passed to stack must have matching dtypes"))}));const o=[],l=kB({inputs:t.map((e=>{const t=SW({inputs:{input:e},backend:n,attrs:{dim:r}});return o.push(t),t})),backend:n,attrs:{axis:r}});return o.forEach((e=>n.disposeIntermediateTensorInfo(e))),l}};class vU{constructor(e,t,n){this.variableNames=["x"],this.customUniforms=[{name:"value",type:"float"}],this.outputShape=t.map(((t,n)=>t[0]+e[n]+t[1]));const s=e.length,r=uM(s),a=t.map((e=>e[0])).join(","),i=t.map(((t,n)=>t[0]+e[n])).join(","),o=["coords[0]","coords[1]","coords[2]","coords[3]"].slice(0,s);this.userCode=1!==s?`\n      ${r} start = ${r}(${a});\n      ${r} end = ${r}(${i});\n\n      void main() {\n        ${r} outC = getOutputCoords();\n        if (any(lessThan(outC, start)) || any(greaterThanEqual(outC, end))) {\n          setOutput(value);\n        } else {\n          ${r} coords = outC - start;\n          setOutput(getX(${o}));\n        }\n      }\n    `:`\n        int start = ${a};\n        int end = ${i};\n\n        void main() {\n          int outC = getOutputCoords();\n          if (outC < start || outC >= end) {\n            setOutput(value);\n          } else {\n            setOutput(getX(outC - start));\n          }\n        }\n      `}}class kU{constructor(e,t,n){this.variableNames=["x"],this.packedInputs=!0,this.packedOutput=!0,this.customUniforms=[{name:"value",type:"float"}],this.outputShape=t.map(((t,n)=>t[0]+e[n]+t[1]));const s=e.length,r=uM(s),a=t.map((e=>e[0])).join(","),i=t.map(((t,n)=>t[0]+e[n])).join(","),o=VL("rc",s),l=VL("source",s),u=`${o[s-1]} < ${this.outputShape[s-1]}`,c=1===s?"source":`vec2(${l.slice(-2).join()})`,h=[`${r} rc = outputLoc;`,`${o[s-1]} += 1;\n       if(${u}) {\n      `,1===s?"":`}\n       rc = outputLoc;\n       ${o[s-2]} += 1;\n       if(${o[s-2]} < ${this.outputShape[s-2]}) {`,1===s?"":`  ${o[s-1]} += 1;\n         if(${u}) {`],p=1===s?"rc < start || rc >= end":"any(lessThan(rc, start)) || any(greaterThanEqual(rc, end))";let d="";for(let e=0,t=1===s?2:4;e<t;e++)d+=`\n        ${h[e]}\n        if (${p}) {\n          result[${e}] = float(value);\n        } else {\n          ${r} source = rc - start;\n          result[${e}] = getChannel(getX(${l.join()}), ${c});\n        }\n      `;d+=1===s?"} ":"}}",this.userCode=`\n      const ${r} start = ${r}(${a});\n      const ${r} end = ${r}(${i});\n\n      void main() {\n        ${r} outputLoc = getOutputCoords();\n        vec4 result = vec4(0.);\n        ${d}\n        setOutput(result);\n      }\n    `}}const IU=e=>{const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{paddings:a,constantValue:i}=s;if(0===ue(r.shape)){const e=a.map(((e,t)=>e[0]+r.shape[t]+e[1]));return DW({backend:n,attrs:{shape:e,value:i,dtype:r.dtype}})}const o=Xe().getBool("WEBGL_PACK_ARRAY_OPERATIONS")?new kU(r.shape,a,i):new vU(r.shape,a,i),l=[[i]];return n.runWebGLProgram(o,[r],r.dtype,l)},NU={kernelName:is,backendName:"webgl",kernelFunc:IU},SU=Dz({opSnippet:"\n  if(a < 0.0 && floor(b) < b){\n    return NAN;\n  }\n  if (b == 0.0) {\n    return 1.0;\n  }\n  return (round(mod(b, 2.0)) != 1) ?\n      pow(abs(a), b) : sign(a) * pow(abs(a), b);\n",packedOpSnippet:"\n  // isModRound1 has 1 for components with round(mod(b, 2.0)) == 1, 0 otherwise.\n  vec4 isModRound1 = vec4(equal(round(mod(b, 2.0)), ivec4(1)));\n  vec4 multiplier = sign(a) * isModRound1 + (vec4(1.0) - isModRound1);\n  vec4 result = multiplier * pow(abs(a), b);\n\n  // Ensure that a^0 = 1, including 0^0 = 1 as this correspond to TF and JS\n  bvec4 isExpZero = equal(b, vec4(0.0));\n  result.r = isExpZero.r ? 1.0 : result.r;\n  result.g = isExpZero.g ? 1.0 : result.g;\n  result.b = isExpZero.b ? 1.0 : result.b;\n  result.a = isExpZero.a ? 1.0 : result.a;\n\n  bvec4 isNaN1 = lessThan(a, vec4(0.0));\n  bvec4 isNaN2 = lessThan(floor(b), b);\n  bvec4 isNaN = bvec4(isNaN1.x && isNaN2.x, isNaN1.y && isNaN2.y, isNaN1.z && isNaN2.z, isNaN1.w && isNaN2.w);\n  "+wz+"\n  return result;\n"}),TU={kernelName:ls,backendName:"webgl",kernelFunc:SU};const CU={kernelName:cs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{axis:a,keepDims:i}=s,o=r.shape.length,l=[],u=we(a,r.shape);let c=u;const h=th(c,o);let p,d=r;if(null!=h&&(d=Jz({inputs:{x:r},backend:n,attrs:{perm:h}}),c=sh(c.length,o),l.push(d)),eh("prod",c,o),n.shouldExecuteOnCPU([d])){const e=n.texData.get(d.dataId).values,{outVals:t,outShape:s,outDtype:r}=yL(d.shape,d.dtype,e,c);p=n.makeTensorInfo(s,r,t)}else{const[e,t]=Jc(d.shape,c),s=ue(t),a=Vz({inputs:{x:d},backend:n,attrs:{shape:[-1,s]}}),i=jz(a,Ta(r.dtype),"prod",n);p=Vz({inputs:{x:i},backend:n,attrs:{shape:e}}),l.push(a),l.push(i)}if(i){l.push(p);const e=Qc(p.shape,u);p=Vz({inputs:{x:p},backend:n,attrs:{shape:e}})}return l.forEach((e=>n.disposeIntermediateTensorInfo(e))),p}};const $U={kernelName:hs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{paramsNestedSplits:r,paramsDenseValues:a,indices:i}=t,{outputRaggedRank:o}=s,l=r.map((e=>n.readSync(e.dataId))),u=r.map((e=>e.shape)),c=n.readSync(a.dataId),h=n.readSync(i.dataId),[p,d,f]=bL(l,u,c,a.shape,a.dtype,h,i.shape,o),m=p.map((e=>n.makeTensorInfo([e.length],"int32",e))),g=n.makeTensorInfo(f,a.dtype,d);return m.concat([g])}};const EU={kernelName:ps,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{starts:s,limits:r,deltas:a}=t,i=n.readSync(s.dataId),o=n.readSync(r.dataId),l=n.readSync(a.dataId),[u,c]=xL(i,s.shape,s.dtype,o,r.shape,l,a.shape);return[n.makeTensorInfo([u.length],"int32",u),n.makeTensorInfo([c.length],s.dtype,c)]}};const AU={kernelName:ds,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{shape:r,values:a,defaultValue:i,rowPartitionTensors:o}=t,{rowPartitionTypes:l}=s,u=n.readSync(r.dataId),c=n.readSync(a.dataId),h=n.readSync(i.dataId),p=o.map((e=>n.readSync(e.dataId))),d=o.map((e=>e.shape)),[f,m]=wL(u,r.shape,c,a.shape,a.dtype,h,i.shape,p,d,l);return n.makeTensorInfo(f,a.dtype,m)}},RU=e=>{const{backend:t,attrs:n}=e,{start:s,stop:r,step:a,dtype:i}=n,o=vL(s,r,a,i);return t.makeTensorInfo([o.length],i,o)},FU={kernelName:fs,backendName:"webgl",kernelFunc:RU},_U=_z({opSnippet:"return 1.0 / x;"}),DU={kernelName:gs,backendName:"webgl",kernelFunc:_U},OU=_z({opSnippet:YL+"\n  return (x < 0.0) ? 0.0 : x;\n",packedOpSnippet:"\n  vec4 result = x * vec4(greaterThanEqual(x, vec4(0.0)));\n  bvec4 isNaN = isnan(x);\n\n  result.r = isNaN.r ? x.r : result.r;\n  result.g = isNaN.g ? x.g : result.g;\n  result.b = isNaN.b ? x.b : result.b;\n  result.a = isNaN.a ? x.a : result.a;\n\n  return result;\n"}),MU={kernelName:ys,backendName:"webgl",kernelFunc:OU},LU=_z({opSnippet:YL+"\n  return (x < 0.0) ? 0.0 : min(6.0, x);\n",packedOpSnippet:"\n  vec4 result = min(x, vec4(6.)) * vec4(greaterThanEqual(x, vec4(0.0)));\n  bvec4 isNaN = isnan(x);\n\n  result.r = isNaN.r ? x.r : result.r;\n  result.g = isNaN.g ? x.g : result.g;\n  result.b = isNaN.b ? x.b : result.b;\n  result.a = isNaN.a ? x.a : result.a;\n\n  return result;\n"}),zU={kernelName:Is,backendName:"webgl",kernelFunc:LU};class PU{constructor(e,t,n,s,r){this.variableNames=["A"],this.outputShape=[];const[a,i,o,l]=e;this.outputShape=[a,t,n,l];const u=[s&&t>1?i-1:i,s&&n>1?o-1:o],c=[s&&t>1?t-1:t,s&&n>1?n-1:n];let h;h=r?"(vec2(yRC) + vec2(0.5)) * effectiveInputOverOutputRatioRC - vec2(0.5)":"vec2(yRC) * effectiveInputOverOutputRatioRC",this.userCode=`\n      const vec2 effectiveInputOverOutputRatioRC = vec2(\n          ${u[0]/c[0]},\n          ${u[1]/c[1]});\n      const vec2 inputShapeRC = vec2(${i}.0, ${o}.0);\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n        ivec2 yRC = coords.yz;\n\n        // Fractional source index.\n        vec2 sourceFracIndexRC = ${h};\n\n        // Compute the four integer indices.\n        ivec2 sourceFloorRC = ivec2(max(sourceFracIndexRC, vec2(0.0)));\n        ivec2 sourceCeilRC = ivec2(\n          min(inputShapeRC - 1.0, ceil(sourceFracIndexRC)));\n\n        float topLeft = getA(b, sourceFloorRC.x, sourceFloorRC.y, d);\n        float bottomLeft = getA(b, sourceCeilRC.x, sourceFloorRC.y, d);\n        float topRight = getA(b, sourceFloorRC.x, sourceCeilRC.y, d);\n        float bottomRight = getA(b, sourceCeilRC.x, sourceCeilRC.y, d);\n\n        vec2 fracRC = sourceFracIndexRC - vec2(sourceFloorRC);\n\n        float top = topLeft + (topRight - topLeft) * fracRC.y;\n        float bottom = bottomLeft + (bottomRight - bottomLeft) * fracRC.y;\n        float newValue = top + (bottom - top) * fracRC.x;\n\n        setOutput(newValue);\n      }\n    `}}class BU{constructor(e,t,n,s,r){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=[];const[a,i,o,l]=e;this.outputShape=[a,t,n,l];const u=[s&&t>1?i-1:i,s&&n>1?o-1:o],c=[s&&t>1?t-1:t,s&&n>1?n-1:n];let h;h=r?"(vec3(yRC) + vec3(0.5)) * effectiveInputOverOutputRatioRC - vec3(0.5)":"vec3(yRC) * effectiveInputOverOutputRatioRC",this.userCode=`\n      const vec3 effectiveInputOverOutputRatioRC = vec3(\n          ${u[0]/c[0]},\n          ${u[1]/c[1]},\n          ${u[1]/c[1]});\n      const vec3 inputShapeRC = vec3(${i}.0, ${o}.0,\n                                     ${o}.0);\n\n      float getAValue(int b, int r, int c, int d) {\n        return getChannel(getA(b, r, c, d), vec2(c, d));\n      }\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n        // Calculate values for next column in yRC.z.\n        ivec3 yRC = coords.yzz + ivec3(0, 0, 1);\n\n        // Fractional source index.\n        vec3 sourceFracIndexRC = ${h};\n\n        // Compute the four integer indices.\n        ivec3 sourceFloorRC = ivec3(max(sourceFracIndexRC, vec3(0.0)));\n        ivec3 sourceCeilRC = ivec3(\n          min(inputShapeRC - 1.0, ceil(sourceFracIndexRC)));\n\n        // Should we calculate next column and row elements in 2x2 packed cell.\n        bool hasNextCol = d < ${l-1};\n        bool hasNextRow = coords.z < ${n-1};\n\n        // In parallel, construct four corners for all four components in\n        // packed 2x2 cell.\n        vec4 topLeft = vec4(\n          getAValue(b, sourceFloorRC.x, sourceFloorRC.y, d),\n          hasNextCol ? getAValue(b, sourceFloorRC.x, sourceFloorRC.y, d + 1)\n                     : 0.0,\n          hasNextRow ? getAValue(b, sourceFloorRC.x, sourceFloorRC.z, d)\n                     : 0.0,\n          (hasNextRow && hasNextCol) ?\n            getAValue(b, sourceFloorRC.x, sourceFloorRC.z, d + 1) : 0.0);\n\n        vec4 bottomLeft = vec4(\n          getAValue(b, sourceCeilRC.x, sourceFloorRC.y, d),\n          hasNextCol ? getAValue(b, sourceCeilRC.x, sourceFloorRC.y, d + 1)\n                     : 0.0,\n          hasNextRow ? getAValue(b, sourceCeilRC.x, sourceFloorRC.z, d)\n                     : 0.0,\n          (hasNextRow && hasNextCol) ?\n            getAValue(b, sourceCeilRC.x, sourceFloorRC.z, d + 1) : 0.0);\n\n        vec4 topRight = vec4(\n          getAValue(b, sourceFloorRC.x, sourceCeilRC.y, d),\n          hasNextCol ? getAValue(b, sourceFloorRC.x, sourceCeilRC.y, d + 1)\n                     : 0.0,\n          hasNextRow ? getAValue(b, sourceFloorRC.x, sourceCeilRC.z, d)\n                     : 0.0,\n          (hasNextRow && hasNextCol) ?\n            getAValue(b, sourceFloorRC.x, sourceCeilRC.z, d + 1) : 0.0);\n\n        vec4 bottomRight = vec4(\n          getAValue(b, sourceCeilRC.x, sourceCeilRC.y, d),\n          hasNextCol ? getAValue(b, sourceCeilRC.x, sourceCeilRC.y, d + 1)\n                     : 0.0,\n          hasNextRow ? getAValue(b, sourceCeilRC.x, sourceCeilRC.z, d)\n                     : 0.0,\n          (hasNextRow && hasNextCol) ?\n            getAValue(b, sourceCeilRC.x, sourceCeilRC.z, d + 1) : 0.0);\n\n        vec3 fracRC = sourceFracIndexRC - vec3(sourceFloorRC);\n\n        vec4 top = mix(topLeft, topRight, fracRC.yyzz);\n        vec4 bottom = mix(bottomLeft, bottomRight, fracRC.yyzz);\n        vec4 newValue = mix(top, bottom, fracRC.x);\n\n        setOutput(newValue);\n      }\n    `}}const WU={kernelName:vs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r}=t,{alignCorners:a,halfPixelCenters:i,size:o}=s,[l,u]=o,c=Xe().getBool("WEBGL_PACK_IMAGE_OPERATIONS")?new BU(r.shape,l,u,a,i):new PU(r.shape,l,u,a,i);return n.runWebGLProgram(c,[r],"float32")}};class VU{constructor(e,t,n){this.variableNames=["dy"],this.outputShape=[],this.outputShape=t;const[,s,r]=t,[,a,i]=e,o=[n&&a>1?s-1:s,n&&i>1?r-1:r],l=[n&&a>1?a-1:a,n&&i>1?i-1:i],u=o[0]/l[0],c=o[1]/l[1],h=1/u,p=1/c,d=2*Math.ceil(h)+2,f=2*Math.ceil(p)+2;this.userCode=`\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n        int r = coords[1];\n        int c = coords[2];\n\n        float accumulator = 0.0;\n\n        const float heightScale = float(${u});\n        const float widthScale = float(${c});\n\n        const float invHeightScale = float(${h});\n        const float invWidthScale = float(${p});\n\n        const int winHeight = int(${d});\n        const int winWidth = int(${f});\n\n        // Compute bounds for where in dy we will look\n        float startRLerp = floor(float(r) * invHeightScale);\n        int startDyR = int(startRLerp - float(winHeight / 2));\n\n        float startCLerp = floor(float(c) * invWidthScale);\n        int startDyC = int(startCLerp - float(winWidth / 2));\n\n        // Loop over dy\n        for (int dyROffset = 0; dyROffset < winHeight; dyROffset++) {\n          int dyR = dyROffset + startDyR;\n\n          // Guard against the window exceeding the bounds of dy\n          if (dyR < 0 || dyR >= ${a}) {\n            continue;\n          }\n\n          for (int dyCOffset = 0; dyCOffset < winWidth; dyCOffset++) {\n            int dyC = dyCOffset + startDyC;\n\n            // Guard against the window exceeding the bounds of dy\n            if (dyC < 0 || dyC >= ${i}) {\n              continue;\n            }\n\n            float dxR = float(dyR) * heightScale;\n            int topDxRIndex = int(floor(dxR));\n            int bottomDxRIndex = int(min(ceil(dxR), ${s-1}.0));\n            float dxRLerp = dxR - float(topDxRIndex);\n            float inverseDxRLerp = 1.0 - dxRLerp;\n\n            float dxC = float(dyC) * widthScale;\n            int leftDxCIndex = int(floor(dxC));\n            int rightDxCIndex = int(min(ceil(dxC), ${r-1}.0));\n            float dxCLerp = dxC - float(leftDxCIndex);\n            float inverseDxCLerp = 1.0 - dxCLerp;\n\n            if (r == topDxRIndex && c == leftDxCIndex) {\n              // topLeft\n              accumulator +=\n                getDy(b, dyR, dyC, d) * inverseDxRLerp * inverseDxCLerp;\n            }\n\n            if (r == topDxRIndex && c == rightDxCIndex) {\n              // topRight\n              accumulator += getDy(b, dyR, dyC, d) * inverseDxRLerp * dxCLerp;\n            }\n\n            if (r == bottomDxRIndex && c == leftDxCIndex) {\n              // bottomLeft\n              accumulator += getDy(b, dyR, dyC, d) * dxRLerp * inverseDxCLerp;\n            }\n\n            if (r == bottomDxRIndex && c == rightDxCIndex) {\n              // bottomRight\n              accumulator += getDy(b, dyR, dyC, d) * dxRLerp * dxCLerp;\n            }\n          }\n        }\n        // End loop over dy\n\n        setOutput(accumulator);\n      }\n    `}}const UU={kernelName:ks,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r,dy:a}=t,{alignCorners:i}=s,o=new VU(a.shape,r.shape,i);return n.runWebGLProgram(o,[a],a.dtype)}};class GU{constructor(e,t,n,s,r){this.variableNames=["A"],this.outputShape=[];const[a,i,o,l]=e;this.outputShape=[a,t,n,l];const u=[s&&t>1?i-1:i,s&&n>1?o-1:o],c=[s&&t>1?t-1:t,s&&n>1?n-1:n],h=s?"0.5":"0.0";let p;p=r?"max((vec2(yRC) + vec2(0.5)) * effectiveInputOverOutputRatioRC, vec2(0.0))":"vec2(yRC) * effectiveInputOverOutputRatioRC",this.userCode=`\n      const vec2 effectiveInputOverOutputRatioRC = vec2(\n          ${u[0]/c[0]},\n          ${u[1]/c[1]});\n      const vec2 inputShapeRC = vec2(${i}.0, ${o}.0);\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n        ivec2 yRC = coords.yz;\n\n        // Fractional source index.\n        vec2 sourceFracIndexRC = ${p};\n\n        // Compute the coordinators of nearest neighbor point.\n        ivec2 sourceNearestRC = ivec2(\n          min(inputShapeRC - 1.0, floor(sourceFracIndexRC + ${h})));\n        float newValue = getA(b, sourceNearestRC.x, sourceNearestRC.y, d);\n\n        setOutput(newValue);\n      }\n    `}}class HU{constructor(e,t,n,s,r){this.variableNames=["A"],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=[];const[a,i,o,l]=e;this.outputShape=[a,t,n,l];const u=[s&&t>1?i-1:i,s&&n>1?o-1:o],c=[s&&t>1?t-1:t,s&&n>1?n-1:n],h=s?"0.5":"0.0";let p;p=r?"max((vec3(yRC) + vec3(0.5)) * effectiveInputOverOutputRatioRC, vec3(0.0))":"vec3(yRC) * effectiveInputOverOutputRatioRC",this.userCode=`\n      const vec3 effectiveInputOverOutputRatioRC = vec3(\n          ${u[0]/c[0]},\n          ${u[1]/c[1]},\n          ${u[1]/c[1]});\n      const vec3 inputShapeRC = vec3(${i}.0, ${o}.0,\n                                     ${o}.0);\n\n      float getAValue(int b, int r, int c, int d) {\n        return getChannel(getA(b, r, c, d), vec2(c, d));\n      }\n\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n        // Calculate values for next column in yRC.z.\n        ivec3 yRC = coords.yzz + ivec3(0, 0, 1);\n\n        // Fractional source index.\n        vec3 sourceFracIndexRC = ${p};\n\n        // Compute the coordinators of nearest neighbor point.\n        ivec3 sourceNearestRC = ivec3(\n          min(inputShapeRC - 1.0, floor(sourceFracIndexRC + ${h})));\n\n        // Should we calculate next column and row elements in 2x2 packed cell.\n        bool hasNextCol = d < ${l-1};\n        bool hasNextRow = coords.z < ${n-1};\n\n        vec4 newValue = vec4(\n          getAValue(b, sourceNearestRC.x, sourceNearestRC.y, d),\n          hasNextCol ? getAValue(b, sourceNearestRC.x, sourceNearestRC.y, d + 1)\n                     : 0.0,\n          hasNextRow ? getAValue(b, sourceNearestRC.x, sourceNearestRC.z, d)\n                     : 0.0,\n          (hasNextRow && hasNextCol) ?\n            getAValue(b, sourceNearestRC.x, sourceNearestRC.z, d + 1) : 0.0);\n\n        setOutput(newValue);\n      }\n    `}}const jU={kernelName:xs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r}=t,{alignCorners:a,halfPixelCenters:i,size:o}=s,[l,u]=o,c=Xe().getBool("WEBGL_PACK_IMAGE_OPERATIONS")?new HU(r.shape,l,u,a,i):new GU(r.shape,l,u,a,i);return n.runWebGLProgram(c,[r],r.dtype)}};class qU{constructor(e,t,n){this.variableNames=["dy"],this.outputShape=[],this.outputShape=t;const[,s,r]=t,[,a,i]=e,o=[n&&a>1?s-1:s,n&&i>1?r-1:r],l=[n&&a>1?a-1:a,n&&i>1?i-1:i],u=o[0]/l[0],c=o[1]/l[1],h=1/u,p=1/c,d=2*Math.ceil(h)+2,f=2*Math.ceil(p)+2;this.userCode=`\n      void main() {\n        ivec4 coords = getOutputCoords();\n        int b = coords[0];\n        int d = coords[3];\n        int r = coords[1];\n        int c = coords[2];\n\n        float accumulator = 0.0;\n\n        const float heightScale = float(${u});\n        const float widthScale = float(${c});\n\n        const float invHeightScale = float(${h});\n        const float invWidthScale = float(${p});\n\n        const int winHeight = int(${d});\n        const int winWidth = int(${f});\n\n        // Compute bounds for where in dy we will look\n        float startRLerp = floor(float(r) * invHeightScale);\n        int startDyR = int(floor(startRLerp - float(winHeight / 2)));\n\n        float startCLerp = floor(float(c) * invWidthScale);\n        int startDyC = int(floor(startCLerp - float(winWidth / 2)));\n\n        // Loop over dy\n        for (int dyROffset = 0; dyROffset < winHeight; dyROffset++) {\n          int dyR = dyROffset + startDyR;\n\n          // Guard against the window exceeding the bounds of dy\n          if (dyR < 0 || dyR >= ${a}) {\n            continue;\n          }\n\n          for (int dyCOffset = 0; dyCOffset < winWidth; dyCOffset++) {\n            int dyC = dyCOffset + startDyC;\n\n            // Guard against the window exceeding the bounds of dy\n            if (dyC < 0 || dyC >= ${i}) {\n              continue;\n            }\n\n            float sourceFracRow =\n              float(${o[0]}) *\n                (float(dyR) / float(${l[0]}));\n\n            float sourceFracCol =\n                float(${o[1]}) *\n                  (float(dyC) / float(${l[1]}));\n\n            int sourceNearestRow = int(min(\n                float(int(${s}) - 1),\n                ${n} ? float(round(sourceFracRow)) :\n                                  float(floor(sourceFracRow))));\n\n            int sourceNearestCol = int(min(\n                float(int(${r}) - 1),\n                ${n} ? float(round(sourceFracCol)) :\n                                  float(floor(sourceFracCol))));\n\n            if (r == sourceNearestRow && c == sourceNearestCol) {\n              accumulator += getDy(b, dyR, dyC, d);\n            }\n          }\n        }\n        // End loop over dy\n\n        setOutput(accumulator);\n      }\n    `}}const KU={kernelName:ws,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{images:r,dy:a}=t,{alignCorners:i}=s,o=new qU(a.shape,r.shape,i);return n.runWebGLProgram(o,[a],a.dtype)}};class XU{constructor(e,t){this.variableNames=["x"];const n=e.length;if(n>4)throw new Error(`WebGL backend: Reverse of rank-${n} tensor is not yet supported`);if(this.outputShape=e,1===n)return void(this.userCode=`\n        void main() {\n          int coord = getOutputCoords();\n          setOutput(getX(${e[0]} - coord - 1));\n        }\n      `);const s=e.map(((n,s)=>(n=>-1!==t.indexOf(n)&&1!==e[n]?`${e[n]} - coords[${n}] - 1`:`coords[${n}]`)(s))).join(","),r=uM(n);this.userCode=`\n      void main() {\n        ${r} coords = getOutputCoords();\n        setOutput(getX(${s}));\n      }\n    `}}class YU{constructor(e,t){this.variableNames=["x"],this.packedInputs=!0,this.packedOutput=!0;const n=e.length;if(n>4)throw new Error(`WebGL backend: Reverse of rank-${n} tensor is not yet supported`);this.outputShape=e;const s=VL("rc",n),r=`${s[n-1]} + 1 < ${this.outputShape[n-1]}`,a=`${s[n-2]} + 1 < ${this.outputShape[n-2]}`,i=uM(n);function o(n){const s=e.map(((s,r)=>function(n,s){return-1!==t.indexOf(n)&&1!==e[n]?`${e[n]} - ${s[n]} - 1`:`${s[n]}`}(r,n)));return`getChannel(getX(${s.join(",")}), vec2(${s.slice(-2).join(",")}))`}this.userCode=1===n?`\n        void main(){\n          int rc = getOutputCoords();\n          vec4 result = vec4(0.);\n          result.r = getChannel(getX(${e[0]} - rc - 1),\n            ${e[0]} - rc - 1);\n          if(${r}){\n              result.g = getChannel(getX(${e[0]} - (rc  + 1) - 1),\n                ${e[0]} - (rc  + 1) - 1);\n          }\n          setOutput(result);\n        }\n      `:`\n        void main() {\n          ${i} rc = getOutputCoords();\n          vec4 result = vec4(0.);\n          result.r = ${function(e){return o(e)}(s.slice())};\n          if(${r}){\n            result.g = ${function(e){return e[n-1]="("+e[n-1]+" + 1)",o(e)}(s.slice())};\n          }\n          if(${a}) {\n            result.b = ${function(e){return e[n-2]="("+e[n-2]+" + 1)",o(e)}(s.slice())};\n            if(${r}) {\n              result.a = ${function(e){return e[n-1]="("+e[n-1]+" + 1)",e[n-2]="("+e[n-2]+" + 1)",o(e)}(s.slice())};\n            }\n          }\n          setOutput(result);\n        }\n    `}}const ZU={kernelName:Ns,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{dims:a}=s,i=r.shape.length,o=we(a,r.shape);if(0===i)return kz({inputs:{x:r},backend:n});const l=Xe().getBool("WEBGL_PACK_ARRAY_OPERATIONS")?new YU(r.shape,o):new XU(r.shape,o);return n.runWebGLProgram(l,[r],r.dtype)}};class JU{constructor(e,t){this.variableNames=["Image"],this.outputShape=[],this.customUniforms=[{name:"params",type:"vec4"}];const n=e[1],s=e[2];this.outputShape=e;let r="";r="number"==typeof t?`float outputValue = ${t.toFixed(2)};`:`\n        vec3 fill = vec3(${t.join(",")});\n        float outputValue = fill[coords[3]];`,this.userCode=`\n        void main() {\n          ivec4 coords = getOutputCoords();\n          int x = coords[2];\n          int y = coords[1];\n          float coordXFloat = (float(x) - params[0]) * params[3] -\n            (float(y) - params[1]) * params[2];\n          float coordYFloat = (float(x) - params[0]) * params[2] +\n            (float(y) - params[1]) * params[3];\n          int coordX = int(round(coordXFloat + params[0]));\n          int coordY = int(round(coordYFloat + params[1]));\n          ${r}\n          if(coordX >= 0 && coordX < ${s} && coordY >= 0 && coordY < ${n}) {\n            outputValue = getImage(coords[0], coordY, coordX, coords[3]);\n          }\n          setOutput(outputValue);\n        }\n    `}}const QU={kernelName:mr,backendName:"webgl",kernelFunc:({inputs:e,attrs:t,backend:n})=>{const{image:s}=e,{radians:r,fillValue:a,center:i}=t,o=n,l=new JU(s.shape,a),[u,c]=Qf(i,s.shape[1],s.shape[2]),h=[[u,c,Math.sin(r),Math.cos(r)]];return o.runWebGLProgram(l,[s],s.dtype,h)}},eG=_z({opSnippet:"\n  // OpenGL ES does not support round function.\n  // The algorithm is based on banker's rounding.\n  float base = floor(x);\n  if ((x - base) < 0.5) {\n    return floor(x);\n  } else if ((x - base) > 0.5) {\n    return ceil(x);\n  } else {\n    if (mod(base, 2.0) == 0.0) {\n      return base;\n    } else {\n      return base + 1.0;\n    }\n  }\n"}),tG={kernelName:Ss,backendName:"webgl",kernelFunc:eG},nG=_z({opSnippet:"return inversesqrt(x);",cpuKernelImpl:kL}),sG={kernelName:Ts,backendName:"webgl",kernelFunc:nG};class rG{constructor(e,t,n,s,r,a,i=!0,o=!1){this.variableNames=["updates","indices","defaultValue"],this.outputShape=a;const l=uM(r.length),u=uM(a.length);let c="";1===n?c="i":2===n&&(c="i, j");const h=`getIndices(${c})`;let p="";1===s?p="i":2===s&&(p="i, coords[1]");const d=`getUpdates(${p})`;let f="";o&&(f="coords[0], coords[1]");const m=`getDefaultValue(${f})`,g=t>1?"strides[j]":"strides";this.userCode=`\n        ${l} strides = ${l}(${r});\n\n        void main() {\n          ${u} coords = getOutputCoords();\n          float sum = 0.0;\n          bool found = false;\n          for (int i = 0; i < ${e}; i++) {\n            int flattenedIndex = 0;\n            for (int j = 0; j < ${t}; j++) {\n              int index = round(${h});\n              flattenedIndex += index * ${g};\n            }\n            if (flattenedIndex == coords[0]) {\n              sum += ${d};\n              found = true;\n            }\n          }\n          setOutput(mix(${m}, sum, float(found)));\n        }\n      `}}class aG{constructor(e,t,n,s,r,a,i=!0,o=!1){this.variableNames=["updates","indices","defaultValue"],this.packedInputs=!0,this.packedOutput=!0,this.outputShape=a;const l=uM(r.length),u=uM(a.length);let c="";1===n?c="i":2===n&&(c="i, j");const h=`getIndices(${c})`;let p="";1===s?p="i":2===s&&(p="i, coords[1]");const d=`getUpdates(${p})`;let f="";o&&(f="coords[0], coords[1]");const m=`getDefaultValue(${f})`,g=t>1?"strides[j]":"strides",y=t>1?"strides[j + 1]":"strides";this.userCode=`\n        ${l} strides = ${l}(${r});\n\n        void main() {\n          ${u} coords = getOutputCoords();\n          vec4 sum = vec4(0.);\n          vec4 found = vec4(0.);\n          for (int i = 0; i < ${e}; i+=2) {\n            ivec2 flattenedIndex = ivec2(0);\n            for (int j = 0; j < ${t}; j+=2) {\n              ivec4 index = round(${h});\n              flattenedIndex += index.xz * ${g};\n              if (j + 1 < ${t}) {\n                flattenedIndex += index.yw * ${y};\n              }\n            }\n            if (flattenedIndex[0] == coords[0] || flattenedIndex[1] == coords[0] ||\n                flattenedIndex[0] == coords[0] + 1 || flattenedIndex[1] == coords[0] + 1) {\n              vec4 updVals = ${d};\n              if (flattenedIndex[0] == coords[0]) {\n                sum.xy += updVals.xy;\n                found.xy = vec2(1.);\n              } else if (flattenedIndex[0] == coords[0] + 1) {\n                sum.zw += updVals.xy;\n                found.zw = vec2(1.);\n              }\n              if (flattenedIndex[1] == coords[0]) {\n                sum.xy += updVals.zw;\n                found.xy = vec2(1.);\n              } else if (flattenedIndex[1] == coords[0] + 1) {\n                sum.zw += updVals.zw;\n                found.zw = vec2(1.);\n              }\n            }\n          }\n          setOutput(mix(${m}, sum, found));\n        }\n      `}}const iG={kernelName:Cs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{indices:r,updates:a}=t,{shape:i}=s,{sliceRank:o,numUpdates:l,sliceSize:u,strides:c,outputSize:h}=Kl(0,r,i),p=[h/u,u];if(0===h)return n.makeTensorInfo(i,r.dtype);const d=Vz({inputs:{x:r},backend:n,attrs:{shape:[l,o]}}),f=Vz({inputs:{x:a},backend:n,attrs:{shape:[l,u]}}),m=n.makeTensorInfo([],"float32",new Float32Array([0]));let g;g=Xe().getBool("WEBGL_PACK")?new aG(l,o,d.shape.length,f.shape.length,c,p):new rG(l,o,d.shape.length,f.shape.length,c,p);const y=n.runWebGLProgram(g,[f,d,m],f.dtype),b=Vz({inputs:{x:y},backend:n,attrs:{shape:i}});return n.disposeIntermediateTensorInfo(d),n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(y),n.disposeIntermediateTensorInfo(m),b}};class oG{constructor(e,t,n,s){this.variableNames=["sortedSequence","values"],this.customUniforms=[{name:"numInputs",type:"int"}],this.outputShape=[e,n];const r=`for (int i = 0; i < ${Math.ceil(Math.log2(t+1))}; ++i) { if (left >= right) break;`,a=2===Xe().getNumber("WEBGL_VERSION")?"while (left < right) {":r,i="left"===s?"<":"<=";this.userCode=`\n       int findBound(int batch, float value) {\n         int left = 0;\n         int right = numInputs;\n         int mid;\n         ${a}\n           mid = (left + right) / 2;\n           if (getSortedSequence(batch, mid) ${i} value) {\n             left = mid + 1;\n           } else {\n             right = mid;\n           }\n         }\n         return right;\n       }\n\n       void main() {\n         ivec2 coords = getOutputCoords();\n         int batch = coords[0];\n         int valueIndex = coords[1];\n\n         float value = getValues(batch, valueIndex);\n\n         setOutput(float(findBound(batch, value)));\n       }\n     `}}const lG={kernelName:Es,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{sortedSequence:r,values:a}=t,{side:i}=s,o=new oG(r.shape[0],r.shape[1],a.shape[1],i),l=[[r.shape[1]]];return n.runWebGLProgram(o,[r,a],"int32",l)}};class uG{constructor(e,t,n){let s,r;if(this.variableNames=["c","a","b"],this.outputShape=t,n>4)throw Error(`Where for rank ${n} is not yet supported`);if(1===n)r="resRC",s="resRC";else{const n=["resRC.x","resRC.y","resRC.z","resRC.w"],a=[],i=[];for(let s=0;s<t.length;s++)i.push(`${n[s]}`),s<e&&a.push(`${n[s]}`);s=a.join(),r=i.join()}const a=uM(n);this.userCode=`\n      void main() {\n        ${a} resRC = getOutputCoords();\n        float cVal = getC(${s});\n        if (cVal >= 1.0) {\n          setOutput(getA(${r}));\n        } else {\n          setOutput(getB(${r}));\n        }\n      }\n    `}}const cG={kernelName:As,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{condition:s,t:r,e:a}=t,i=new uG(s.shape.length,r.shape,r.shape.length);return n.runWebGLProgram(i,[s,r,a],Sa(r.dtype,a.dtype))}},hG=_z({opSnippet:`\n  // Stable and Attracting Fixed Point (0, 1) for Normalized Weights.\n  // see: https://arxiv.org/abs/1706.02515\n  float scaleAlpha = ${am};\n  float scale = ${im};\n  return (x >= 0.0) ? scale * x : scaleAlpha * (exp(x) - 1.0);\n`}),pG={kernelName:Rs,backendName:"webgl",kernelFunc:hG},dG=_z({opSnippet:Fz+"\n  return 1.0 / (1.0 + exp(-1.0 * x));\n",packedOpSnippet:"\n  vec4 result = 1.0 / (1.0 + exp(-1.0 * x));\n  bvec4 isNaN = isnan(x);\n\n  result.r = isNaN.r ? x.r : result.r;\n  result.g = isNaN.g ? x.g : result.g;\n  result.b = isNaN.b ? x.b : result.b;\n  result.a = isNaN.a ? x.a : result.a;\n\n  return result;\n",cpuKernelImpl:NL}),fG={kernelName:Ms,backendName:"webgl",kernelFunc:dG},mG=_z({opSnippet:"\n  if (isnan(x)) { return 0.0; }\n  return sign(x);\n"}),gG={kernelName:Os,backendName:"webgl",kernelFunc:mG},yG=_z({opSnippet:Fz+"\n  return sin(x);\n",packedOpSnippet:`\n  vec4 result = sin(x);\n  bvec4 isNaN = isnan(x);\n  ${wz}\n  return result;\n`}),bG={kernelName:_s,backendName:"webgl",kernelFunc:yG},xG=_z({opSnippet:"\n  float e2x = exp(x);\n  return (e2x - 1.0 / e2x) / 2.0;\n"}),wG={kernelName:Ds,backendName:"webgl",kernelFunc:xG},vG=_z({opSnippet:"\n  float epsilon = 1.1920928955078125e-7;\n  float threshold = log(epsilon) + 2.0;\n\n  bool too_large = x > -threshold;\n  bool too_small = x < threshold;\n\n  float result;\n  float exp_x = exp(x);\n\n  if (too_large){\n    result = x;\n  }\n  else if (too_small){\n    result = exp_x;\n  }\n  else{\n    result = log(exp_x + 1.0);\n  }\n  return result;\n"}),kG={kernelName:Ls,backendName:"webgl",kernelFunc:vG},IG={kernelName:Bs,backendName:"webgl",kernelFunc:e=>{const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{blockShape:a,paddings:i}=s;ie(r.shape.length<=4,(()=>"spaceToBatchND for rank > 4 with a WebGL backend not implemented yet"));const o=a.reduce(((e,t)=>e*t)),l=[[0,0]];l.push(...i);for(let e=1+a.length;e<r.shape.length;++e)l.push([0,0]);const u=[],c=IU({inputs:{x:r},backend:n,attrs:{paddings:l,constantValue:0}}),h=em(c.shape,a,o,!1),p=tm(h.length,a.length,!1),d=nm(c.shape,a,o,!1),f=Vz({inputs:{x:c},backend:n,attrs:{shape:h}}),m=Jz({inputs:{x:f},backend:n,attrs:{perm:p}}),g=Vz({inputs:{x:m},backend:n,attrs:{shape:d}});return u.push(c),u.push(f),u.push(m),u.forEach((e=>n.disposeIntermediateTensorInfo(e))),g}};const NG={kernelName:Us,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{indices:s,values:r,denseShape:a,defaultValue:i}=t;if(1!==a.shape.length)throw new Error(`Dense shape must be a vector, saw:\n         ${a.shape}`);if(2!==s.shape.length)throw new Error(`Indices must be a matrix, saw:\n         ${s.shape}`);if(1!==r.shape.length)throw new Error(`Values must be a vector, saw:\n         ${r.shape}`);if(0!==i.shape.length)throw new Error(`Default value must be a scalar, saw:\n        ${i.shape}`);const o=n.readSync(s.dataId),l=n.readSync(r.dataId),u=n.readSync(a.dataId),c=n.readSync(i.dataId)[0],[h,p,d,f,m]=CL(o,s.shape,s.dtype,l,r.dtype,u,c);return[n.makeTensorInfo(p,s.dtype,h),n.makeTensorInfo([p[0]],r.dtype,d),n.makeTensorInfo([f.length],"bool",new Uint8Array(f.map((e=>Number(e))))),n.makeTensorInfo([m.length],s.dtype,new Int32Array(m))]}};const SG={kernelName:Gs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{inputIndices:s,inputShape:r,newShape:a}=t;if(2!==s.shape.length)throw new Error(`Input indices should be a matrix but received shape ${s.shape}`);if(1!==r.shape.length)throw new Error(`Input shape should be a vector but received shape ${r.shape}`);if(1!==a.shape.length)throw new Error(`Target shape should be a vector but received shape ${a.shape}`);const i=Array.from(n.readSync(r.dataId)),o=n.readSync(s.dataId),l=Array.from(n.readSync(a.dataId)),[u,c,h]=$L(o,s.shape,s.dtype,i,l);return[n.makeTensorInfo(c,s.dtype,u),n.makeTensorInfo([h.length],a.dtype,new Int32Array(h))]}};const TG={kernelName:Hs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{data:s,indices:r,segmentIds:a}=t;if(s.shape.length<1)throw new Error("Data should be at least 1 dimensional but received scalar");if(1!==r.shape.length)throw new Error(`Indices should be a vector but received shape\n              ${r.shape}`);if(1!==a.shape.length)throw new Error(`Segment ids should be a vector but received shape\n              ${a.shape}`);const i=n.readSync(s.dataId),o=n.readSync(r.dataId),l=n.readSync(a.dataId),[u,c]=EL(i,s.shape,s.dtype,o,l,!0);return n.makeTensorInfo(c,s.dtype,u)}};const CG={kernelName:js,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n}=e,{data:s,indices:r,segmentIds:a}=t;if(s.shape.length<1)throw new Error("Data should be at least 1 dimensional but received scalar");if(1!==r.shape.length)throw new Error(`Indices should be a vector but received shape\n             ${r.shape}`);if(1!==a.shape.length)throw new Error(`Segment ids should be a vector but received shape\n             ${a.shape}`);const i=n.readSync(s.dataId),o=n.readSync(r.dataId),l=n.readSync(a.dataId),[u,c]=EL(i,s.shape,s.dtype,o,l);return n.makeTensorInfo(c,s.dtype,u)}};const $G={kernelName:qs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{sparseIndices:r,sparseValues:a,defaultValue:i}=t,{outputShape:o}=s,{sliceRank:l,numUpdates:u,sliceSize:c,strides:h,outputSize:p}=Kl(0,r,o);if("string"===a.dtype){const e=n.bufferSync(r),t=n.bufferSync(a),s=Jr(n.readSync(i.dataId)[0]),d=IL(e,t,o,p,c,u,l,h,s,false);return n.makeTensorInfo(o,d.dtype,d.values)}const d=new rG(u,l,r.shape.length,a.shape.length,h,[p,1],false),f=n.runWebGLProgram(d,[a,r,i],a.dtype),m=Vz({inputs:{x:f},backend:n,attrs:{shape:o}});return n.disposeIntermediateTensorInfo(f),m}};const EG={kernelName:Ws,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{numOrSizeSplits:a,axis:i}=s,o=we(i,r.shape)[0],l=Rm(r,a,o),u=r.shape.length,c=new Array(u).fill(0),h=r.shape.slice();return l.map((e=>{const t=[...h];t[o]=e;const s=XP({inputs:{x:r},backend:n,attrs:{begin:c,size:t}});return c[o]+=e,s}))}},AG="return sqrt(x);",RG=_z({opSnippet:AG,packedOpSnippet:AG,cpuKernelImpl:AL}),FG={kernelName:zs,backendName:"webgl",kernelFunc:RG},_G=_z({opSnippet:"return x * x;"}),DG={kernelName:Xs,backendName:"webgl",kernelFunc:_G},OG="return (a - b) * (a - b);",MG=Dz({opSnippet:OG,packedOpSnippet:OG}),LG={kernelName:Ks,backendName:"webgl",kernelFunc:MG};const zG={kernelName:Ys,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t;if("string"!==r.dtype)throw new Error("Input must be of datatype string");const a=qm(n.readSync(r.dataId)),i=RL(a,"string",s);return n.makeTensorInfo(r.shape,"string",i)}};const PG={kernelName:dr,backendName:"webgl",kernelFunc:function({inputs:e,attrs:t,backend:n}){const{x:s}=e,r=YL+`\n    return x > 0.0 ? 1.0 : float(${t.alpha});\n  `,a=new XL(s.shape,r);return n.runWebGLProgram(a,[s],s.dtype)}};class BG{constructor(e,t,n){this.variableNames=["x"],this.outputShape=n;const s=n.length,r=uM(n.length),a=uM(n.length);let i="";if(1===s)i="coords * strides + begin";else{let e=0;i=n.map(((t,s)=>(e++,1===n.length?`coords * strides[${s}] + begin[${s}]`:`coords[${e-1}] * strides[${s}] + begin[${s}]`))).join(",")}this.userCode=`\n      ${r} begin = ${r}(${e});\n      ${r} strides = ${r}(${t});\n\n      void main() {\n        ${a} coords = getOutputCoords();\n        setOutput(getX(${i}));\n      }\n    `}}const WG={kernelName:Zs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{begin:a,end:i,strides:o,beginMask:l,endMask:u,ellipsisMask:c,newAxisMask:h,shrinkAxisMask:p}=s,{finalShapeSparse:d,finalShape:f,isIdentity:m,sliceDim0:g,isSimpleSlice:y,begin:b,end:x,strides:w}=pu(r.shape,a,i,o,l,u,c,h,p);let v;if(m)v=Vz({inputs:{x:r},backend:n,attrs:{shape:f}});else if(g||y){ie(r.shape.length>=1,(()=>`Input must have rank at least 1, got: ${r.shape.length}`));const e=Ql(b,x,w),t=XP({inputs:{x:r},backend:n,attrs:{begin:b,size:e}});v=Vz({inputs:{x:t},backend:n,attrs:{shape:f}}),n.disposeIntermediateTensorInfo(t)}else{if(n.shouldExecuteOnCPU([r])){const e=n.readSync(r.dataId),t=to(r.shape,r.dtype,e),s=FL(d,t,w,b);v=n.makeTensorInfo(f,r.dtype,s.values)}else{const e=new BG(b,w,d);v=n.runWebGLProgram(e,[r],r.dtype)}}const k=Vz({inputs:{x:v},backend:n,attrs:{shape:f}});return n.disposeIntermediateTensorInfo(v),k}};const VG={kernelName:Js,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{separator:r,nGramWidths:a,leftPad:i,rightPad:o,padWidth:l,preserveShortSequences:u}=s,{data:c,dataSplits:h}=t,p=n.readSync(c.dataId),d=n.readSync(h.dataId),[f,m]=_L(p,d,r,a,i,o,l,u);return[n.makeTensorInfo([f.length],"string",f),n.makeTensorInfo(h.shape,"int32",m)]}};const UG={kernelName:Qs,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{skipEmpty:r}=s,{input:a,delimiter:i}=t;if("string"!==a.dtype)throw new Error("Input must be of datatype string");if(1!==a.shape.length)throw new Error(`Input must be a vector, got shape: ${a.shape}`);if(0!==i.shape.length)throw new Error(`Delimiter must be a scalar, got shape: ${i.shape}`);const o=n.readSync(a.dataId),l=n.readSync(i.dataId)[0],[u,c,h]=DL(o,l,r),p=c.length;return[n.makeTensorInfo([p,2],"int32",u),n.makeTensorInfo([p],"string",c),n.makeTensorInfo([2],"int32",new Int32Array(h))]}};const GG={kernelName:er,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{numBuckets:r}=s,{input:a}=t;if("string"!==a.dtype)throw new Error("Input must be of datatype string");if(r<=0)throw new Error("Number of buckets must be at least 1");const i=n.readSync(a.dataId),o=OL(i,r);return n.makeTensorInfo(a.shape,"int32",o)}},HG=_z({opSnippet:"return tan(x);"}),jG={kernelName:nr,backendName:"webgl",kernelFunc:HG},qG=_z({opSnippet:"\n  float e2x = exp(-2.0 * abs(x));\n  return sign(x) * (1.0 - e2x) / (1.0 + e2x);\n"}),KG={kernelName:sr,backendName:"webgl",kernelFunc:qG};const XG={kernelName:$s,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{tensor:r,indices:a,updates:i}=t,{}=s,{sliceRank:o,numUpdates:l,sliceSize:u,strides:c,outputSize:h}=Kl(0,a,r.shape),p=[h/u,u];if(0===h)return n.makeTensorInfo(r.shape,a.dtype);const d=Vz({inputs:{x:a},backend:n,attrs:{shape:[l,o]}}),f=Vz({inputs:{x:i},backend:n,attrs:{shape:[l,u]}}),m=Vz({inputs:{x:r},backend:n,attrs:{shape:p}}),g=new rG(l,o,d.shape.length,f.shape.length,c,p,!1,!0),y=n.runWebGLProgram(g,[f,d,m],m.dtype),b=Vz({inputs:{x:y},backend:n,attrs:{shape:r.shape}});return n.disposeIntermediateTensorInfo(d),n.disposeIntermediateTensorInfo(f),n.disposeIntermediateTensorInfo(m),n.disposeIntermediateTensorInfo(y),b}};class YG{constructor(e,t){this.variableNames=["A"];const n=new Array(e.length);for(let s=0;s<n.length;s++)n[s]=e[s]*t[s];this.outputShape=n,this.rank=n.length;const s=uM(this.rank),r=function(e){const t=e.length;if(t>5)throw Error(`Tile for rank ${t} is not yet supported`);if(1===t)return`imod(resRC, ${e[0]})`;const n=["resRC.x","resRC.y","resRC.z","resRC.w","resRC.u"],s=[];for(let t=0;t<e.length;t++)s.push(`imod(${n[t]}, ${e[t]})`);return s.join()}(e);this.userCode=`\n      void main() {\n        ${s} resRC = getOutputCoords();\n        setOutput(getA(${r}));\n      }\n    `}}function ZG(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{reps:a}=s;if("string"===r.dtype||r.shape.length>5){const e=n.readSync(r.dataId),t="string"===r.dtype?e.map((e=>Jr(e))):e,s=to(r.shape,r.dtype,t),i=LL(s,a);return n.makeTensorInfo(i.shape,i.dtype,i.values)}const i=new YG(r.shape,a);return n.runWebGLProgram(i,[r],r.dtype)}const JG={kernelName:rr,backendName:"webgl",kernelFunc:ZG};class QG{constructor(e){this.variableNames=["x","indices"],this.customUniforms=[{name:"n",type:"int"},{name:"firstPass",type:"int"},{name:"negativeInf",type:"float"},{name:"dir",type:"int"},{name:"inc",type:"int"}],this.outputShape=e,this.userCode="\n       void main() {\n         ivec2 coords = getOutputCoords();\n         int batch = coords[0];\n         int elemIdx = coords[1];\n\n         // We compare elements pair-wise within a group of size 2 * inc.\n         // The comparing rule for each group alternates between ascending\n         // and descending. Within each group, we compare each pair at\n         // positions i and i+inc. To decide whether an element at position i\n         // is x0 or x1, we mod it by 2 * inc, if the result is smaller than\n         // inc, it is in the first half of the group, we denote it as x0,\n         // otherwise we denote it as x1.\n         // For example, as shown in the Bitonic top K paper referenced above,\n         // Figure5(a) shows that element[1] is in the\n         // second half of the group when group size is 2, but it is in the\n         // first half of the group when group size is 4.\n\n         bool isFirstInPair = imod(elemIdx, 2 * inc) < inc;\n         int i = isFirstInPair ? elemIdx : elemIdx - inc;\n\n         int i0 = firstPass == 1 ? i : int(getIndices(batch, i));\n         int i1 = firstPass == 1 ? i + inc : int(getIndices(batch, i + inc));\n         float x0 = i0 < n ? getX(batch, i0) : negativeInf;\n         float x1 = i1 < n ? getX(batch, i1) : negativeInf;\n\n         // Denotes which direction indices are in (ascending or descending).\n         bool reverse = imod(elemIdx, 2 * dir) >= dir;\n         bool isGreater = x0 > x1 || (x0 == x1 && i1 > i0);\n         if (reverse == isGreater) { // Elements in opposite order of direction\n           int iTemp = i0;\n           i0 = i1;\n           i1 = iTemp;\n         }\n         if (isFirstInPair) {\n            setOutput(float(i0));\n         } else {\n            setOutput(float(i1));\n         }\n       }\n     "}}class eH{constructor(e){this.variableNames=["x","indices"],this.customUniforms=[{name:"n",type:"int"},{name:"firstPass",type:"int"},{name:"k",type:"int"}],this.outputShape=e,this.userCode="\n    void main() {\n         // Takes max of indices (0, k), (1, k + 1), (2, k + 2) ...\n         ivec2 coords = getOutputCoords();\n         int batch = coords[0];\n         int elemIdx = coords[1];\n\n         // The output size is half of the previous size.\n         // If the previous sequence is | | | | _ _ _ _  | | | |  _ _ _ _ (k=4),\n         // we only need to output the indices at positions |, the indices at\n         // positions _ can be thrown away, see Figure5(b) After Phase 2\n         // (Merge phase) in the Bitonic Top K paper referenced above.\n         // For example, the paper shows we only need to output the orange bars.\n         // The output sequence should look like this | | | | | | | |.\n         // Because the sequence is halved, to map the output index back\n         // to the previous sequence to find the corresponding value,\n         // we need to double the index. When we double the index,\n         // we basically interpolate a position, so 2i looks like\n         // | _ | _ | _ | _ | _ | _ | _. We move the | to the first k position\n         // of each 2k positions by - elemIdx % k. E.g. for output at\n         // index 4,5,6,7, we want to get the corresponding element at\n         // original index 8,9,10,11, for output at index 8,9,10,11,\n         // we want to get the corresponding element at original index\n         // 16,17,18,19, so on and so forth.\n\n         int i = elemIdx < k ? elemIdx : (elemIdx * 2 - imod(elemIdx, k));\n         int i0 = firstPass == 1 ? i : int(getIndices(batch, i));\n         int i1 = firstPass == 1 ? i + k : int(getIndices(batch, i + k));\n\n         float x0 = getX(batch, i0);\n         float x1 = i1 < n ? getX(batch, i1) : x0;\n\n         setOutput(x0 >= x1 ? float(i0) : float(i1));\n       }\n     "}}function tH(e,t){null!==t&&e.disposeIntermediateTensorInfo(t)}function nH(e){let t=1;for(;t<e;)t*=2;return t}const sH={kernelName:ar,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r}=t,{k:a,sorted:i}=s,o=Xe().getNumber("TOPK_LAST_DIM_CPU_HANDOFF_SIZE_THRESHOLD"),l=Xe().getNumber("TOPK_K_CPU_HANDOFF_THRESHOLD"),u=r.shape,c=u[u.length-1];if(n.shouldExecuteOnCPU([r])||c<o||a>l){const e=n.readSync(r.dataId),[t,s]=zL(e,u,r.dtype,a,i);return[n.makeTensorInfo(t.shape,t.dtype,t.values),n.makeTensorInfo(s.shape,s.dtype,s.values)]}if(0===a)return u[u.length-1]=0,[n.makeTensorInfo(u,r.dtype,[]),n.makeTensorInfo(u,"int32",[])];if(1===c)return[r,DW({attrs:{shape:u,dtype:"int32",value:0},backend:n})];const h=n.texData.get(r.dataId),p=null!==h&&h.isPacked,d=p?n.unpackTensor(r):r,f=ue(u)/c,m=Vz({inputs:{x:d},attrs:{shape:[f,c]},backend:n});p&&tH(n,d);const g=nH(a),y=nH(c);let b=null;const x=()=>null===b?[m,m]:[m,b],w=(e,t,s)=>{const r=x(),a=new QG(s),i=[[c],[null===b?1:0],[Number.NEGATIVE_INFINITY],[e],[t]],o=b;b=n.runWebGLProgram(a,r,"int32",i),tH(n,o)};for(let e=1;e<g;e*=2){const t=2*e;for(let n=e;n>=1;n/=2)w(t,n,[f,y])}for(let e=y;e>g;e/=2){const t=x(),s=new eH([f,e/2]),r=[[c],[null===b?1:0],[g]],a=b;b=n.runWebGLProgram(s,t,"int32",r),tH(n,a);const i=g/2,o=2*i;for(let e=i;e>=1;e/=2)w(o,e,b.shape)}let v=b;b=XP({inputs:{x:b},backend:n,attrs:{begin:0,size:[f,a]}}),tH(n,v);let k=QW({inputs:{x:m,indices:b},backend:n,attrs:{axis:1,batchDims:1}});tH(n,m);const I=u.slice(0,-1);I.push(a),v=b,b=Vz({inputs:{x:b},attrs:{shape:I},backend:n}),tH(n,v);const N=k;return k=Vz({inputs:{x:k},attrs:{shape:I},backend:n}),tH(n,N),[k,b]}};class rH{constructor(e,t,n,s,r,a){this.variableNames=["Image","Transforms"],this.outputShape=a;const i="nearest"===n?1:2;let o;switch(s){case"constant":default:o=1;break;case"reflect":o=2;break;case"wrap":o=3;break;case"nearest":o=4}this.userCode=`\n            float mapCoord(float outCoord, float len) {\n              float inCoord = outCoord;\n              if(${o} == 2) {\n                if (inCoord < 0.0) {\n                  if (len <= 1.0) {\n                    inCoord = 0.0;\n                  } else {\n                    float sz2 = 2.0 * len;\n                    if (inCoord < sz2) {\n                      inCoord = sz2 * float(int(float(-inCoord / sz2))) +\n                      inCoord;\n                    }\n                    inCoord = inCoord < -len ? inCoord + sz2 : -inCoord - 1.0;\n                  }\n                } else if (inCoord > len - 1.0) {\n                  if (len <= 1.0) {\n                    inCoord = 0.0;\n                  } else {\n                    float sz2 = 2.0 * len;\n                    inCoord -= sz2 * float(int(float(inCoord / sz2)));\n                    if (inCoord >= len) {\n                      inCoord = sz2 - inCoord - 1.0;\n                    }\n                  }\n                }\n                return clamp(inCoord, 0.0, len - 1.0);\n              } else if (${o} == 3) {\n                if (inCoord < 0.0) {\n                  if (len <= 1.0) {\n                    inCoord = 0.0;\n                  } else {\n                    float sz = len - 1.0;\n                    inCoord += len * (float(int(float(-inCoord / sz))) + 1.0);\n                  }\n                } else if (inCoord > len - 1.0) {\n                  if (len <= 1.0) {\n                    inCoord = 0.0;\n                  } else {\n                    float sz = len - 1.0;\n                    inCoord -= len * float(int(float(inCoord / sz)));\n                  }\n                }\n                return clamp(inCoord, 0.0, len - 1.0);\n              } else if (${o} == 4) {\n                return clamp(outCoord, 0.0, len - 1.0);\n              } else {\n                return outCoord;\n              }\n            }\n\n            float readWithFillValue(int batch, int coordY, int coordX,\n              int channel) {\n              float outputValue;\n              if (0 <= coordY && coordY < ${e} && 0 <= coordX && coordX < ${t}) {\n                  outputValue = getImage(batch, coordY, coordX, channel);\n              } else {\n                outputValue = float(${r});\n              }\n              return outputValue;\n            }\n\n            void main() {\n              ivec4 coords = getOutputCoords();\n              float outputValue;\n              int batch = coords[0];\n              int x = coords[2];\n              int y = coords[1];\n              int channel = coords[3];\n              float xf = float(x);\n              float yf = float(y);\n              float a1 = getTransforms(batch, 0);\n              float a2 = getTransforms(batch, 1);\n              float a3 = getTransforms(batch, 2);\n              float b1 = getTransforms(batch, 3);\n              float b2 = getTransforms(batch, 4);\n              float b3 = getTransforms(batch, 5);\n              float c1 = getTransforms(batch, 6);\n              float c2 = getTransforms(batch, 7);\n              float projection = c1 * xf + c2 * yf + 1.0;\n              if (projection == 0.0) {\n                outputValue = float(${r});\n              } else {\n                float inX = (a1 * xf + a2 * yf + a3) / projection;\n                float inY = (b1 * xf + b2 * yf + b3) / projection;\n                float mapX = mapCoord(inX, float(${t}));\n                float mapY = mapCoord(inY, float(${e}));\n\n                if (${i} == 1) {\n                  int coordY = int(round(mapY));\n                  int coordX = int(round(mapX));\n                  outputValue = readWithFillValue(batch, coordY, coordX,\n                    channel);\n                } else {\n                  float yFloor = floor(mapY);\n                  float xFloor = floor(mapX);\n                  float yCeil = yFloor + 1.0;\n                  float xCeil = xFloor + 1.0;\n                  float valueYFloor = (xCeil - mapX) *\n                  readWithFillValue(batch, int(yFloor), int(xFloor), channel) +\n                  (mapX - xFloor) *\n                  readWithFillValue(batch, int(yFloor), int(xCeil), channel);\n                  float valueYCeil = (xCeil - mapX) *\n                  readWithFillValue(batch, int(yCeil), int(xFloor), channel) +\n                  (mapX - xFloor) *\n                  readWithFillValue(batch, int(yCeil), int(xCeil), channel);\n                  outputValue = (yCeil - mapY) * valueYFloor +\n                  (mapY - yFloor) * valueYCeil;\n                }\n              }\n              setOutput(outputValue);\n            }\n        `}}const aH={kernelName:ir,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{image:r,transforms:a}=t,{interpolation:i,fillMode:o,fillValue:l,outputShape:u}=s,[c,h,p,d]=r.shape,[f,m]=null!=u?u:[h,p],g=new rH(h,p,i,o,l,[c,f,m,d]);return n.runWebGLProgram(g,[r,a],"float32")}};const iH={kernelName:lr,backendName:"webgl",kernelFunc:function(e){const{inputs:t,attrs:n,backend:s}=e,{axis:r}=n,{x:a}=t;GO(a,"unique"),console.warn("WARNING: ","UI might be locked temporarily as data is being downloaded");const i=s.readSync(a.dataId),{outputValues:o,outputShape:l,indices:u}=BL(i,r,a.shape,a.dtype);return[s.makeTensorInfo(l,a.dtype,o),s.makeTensorInfo([u.length],"int32",u)]}};const oH={kernelName:ur,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{value:r}=t;let{axis:a}=s;a<0&&(a+=r.shape.length);const i=r,o=i.shape.length,l=r.shape[a],u=new Array(o-1);let c=0;for(let e=0;e<o;e++)e!==a&&(u[c++]=i.shape[e]);const h=[],p=new Array(o).fill(0),d=i.shape.slice();d[a]=1;const f=new Array(l);for(let e=0;e<f.length;e++){p[a]=e;const t=XP({inputs:{x:i},backend:n,attrs:{begin:p,size:d}}),s=Vz({inputs:{x:t},backend:n,attrs:{shape:u}});f[e]=s,h.push(t)}return h.forEach((e=>n.disposeIntermediateTensorInfo(e))),f}};class lH{constructor(e,t){this.variableNames=["x","segmentIds"];const n=e.windowSize,s=e.batchSize,r=e.inSize,a=e.numSegments,i=a*Math.ceil(r/n);this.outputShape=[s,i];const o=4*Math.floor(n/4),l=n%4,u="\n        sumValue += dot(values, segFilter);\n    ";let c="";r%n>0&&(c=`\n        if (inIdx < 0 || inIdx >= ${r}) {\n          return initializationValue;\n        }\n      `);let h="";r%n>0&&(h=`\n        if (inIdx < 0 || inIdx >= ${r}) {\n          return -1.0;\n        }\n      `),this.userCode=`\n      const float initializationValue = 0.0;\n\n      float getValue(int batch, int inIdx) {\n        ${c}\n        return getX(batch, inIdx);\n      }\n\n      float getSegmentIdAtIndex(int inIdx) {\n        ${h}\n        return getSegmentIds(inIdx);\n      }\n\n      void main() {\n        ivec2 coords = getOutputCoords();\n        int batch = coords[0];\n        int outIdx = coords[1];\n        int inOffset = int(floor(float(outIdx) / float(\n          ${a})) * float(${n}));\n        int currentSeg = int(mod(float(outIdx), float(${a})));\n\n        float sumValue = 0.0;\n\n        for (int i = 0; i < ${o}; i += 4) {\n          int inIdx = inOffset + i;\n          vec4 values = vec4(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            getValue(batch, inIdx + 2),\n            getValue(batch, inIdx + 3)\n          );\n\n          vec4 segFilter = vec4(\n            int(getSegmentIdAtIndex(inIdx)) == currentSeg ? 1 : 0,\n            int(getSegmentIdAtIndex(inIdx + 1)) == currentSeg ? 1 : 0,\n            int(getSegmentIdAtIndex(inIdx + 2)) == currentSeg ? 1 : 0,\n            int(getSegmentIdAtIndex(inIdx + 3)) == currentSeg ? 1 : 0\n          );\n\n          ${u}\n        }\n\n        int inIdx = inOffset + ${o};\n        if (${1===l}) {\n          vec4 values = vec4(\n            getValue(batch, inIdx),\n            initializationValue,\n            initializationValue,\n            initializationValue\n          );\n\n          int inIdxSeg = int(getSegmentIdAtIndex(inIdx));\n\n          vec4 segFilter = vec4(\n            int(getSegmentIdAtIndex(inIdx)) == currentSeg ? 1 : 0,\n            0,\n            0,\n            0\n          );\n\n          ${u}\n        } else if (${2===l}) {\n          vec4 values = vec4(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            initializationValue,\n            initializationValue\n          );\n\n          vec4 segFilter = vec4(\n            int(getSegmentIdAtIndex(inIdx)) == currentSeg ? 1 : 0,\n            int(getSegmentIdAtIndex(inIdx + 1)) == currentSeg ? 1 : 0,\n              0,\n              0\n          );\n\n          ${u}\n        } else if (${3===l}) {\n          vec4 values = vec4(\n            getValue(batch, inIdx),\n            getValue(batch, inIdx + 1),\n            getValue(batch, inIdx + 2),\n            initializationValue\n          );\n\n          vec4 segFilter = vec4(\n            int(getSegmentIdAtIndex(inIdx)) == currentSeg ? 1 : 0,\n            int(getSegmentIdAtIndex(inIdx + 1)) == currentSeg ? 1 : 0,\n            int(getSegmentIdAtIndex(inIdx + 2)) == currentSeg ? 1 : 0,\n            0\n          );\n\n          ${u}\n        }\n        setOutput(sumValue);\n      }\n    `}}const uH={kernelName:cr,backendName:"webgl",kernelFunc:function(e){const{inputs:t,backend:n,attrs:s}=e,{x:r,segmentIds:a}=t,{numSegments:i}=s,o=r.shape.length,l=[];let u=0;const c=th([u],o);let h=r;null!=c&&(h=Jz({inputs:{x:r},backend:n,attrs:{perm:c}}),l.push(h),u=sh(1,o)[0]);const p=Hm(h.shape,u,i),d=ue([h.shape[u]]),f=Vz({inputs:{x:h},backend:n,attrs:{shape:[-1,d]}});l.push(f);const m=Ta(r.dtype),g=(e,t,s,r,a)=>{const i=e.shape[0],o=e.shape[1],u=Gm(o,a),c=new lH({windowSize:u,inSize:o,batchSize:i,numSegments:a},t),h=n.compileAndRun(c,[e,s],r);if(l.push(h),h.shape[1]===a)return h;const p=RU({backend:n,attrs:{start:0,stop:a,step:1,dtype:"float32"}}),d=ZG({inputs:{x:p},backend:n,attrs:{reps:[o/u]}});l.push(p),l.push(d);return g(h,t,d,r,a)},y=Vz({inputs:{x:g(f,"unsortedSegmentSum",a,m,i)},backend:n,attrs:{shape:p}});let b=y;if(null!=c){l.push(y);const e=nh(c);b=Jz({inputs:{x:b},backend:n,attrs:{perm:e}})}return l.forEach((e=>n.disposeIntermediateTensorInfo(e))),b}},cH=[nP,rP,iP,lP,hP,fP,mP,gP,kP,IP,SP,CP,EP,RP,_P,MP,LP,BP,WP,VP,HP,ZP,JP,QP,eB,iB,uB,pB,Sz,mB,IB,RB,MB,zB,PB,BB,WB,UB,HB,qB,QB,eW,tW,sW,iW,uW,cW,pW,fW,mW,yW,bW,wW,kW,NW,TW,EW,FW,OW,LW,BW,VW,HW,KW,XW,ZW,eV,nV,rV,Iz,aV,wB,oV,uV,hV,$z,dV,mV,gV,bV,wV,kV,NV,TV,EV,RV,_V,OV,MV,LV,BV,WV,VV,UV,GV,jV,XV,ZV,iU,Wz,lU,cU,pU,fU,nB,gU,xU,wU,NU,TU,Rz,CU,$U,EU,AU,FU,rB,eU,DU,MU,zU,Uz,WU,UU,jU,KU,ZU,QU,tG,sG,iG,lG,cG,pG,fG,gG,bG,wG,YP,aU,kG,IG,NG,SG,TG,CG,$G,EG,FG,DG,LG,zG,PG,WG,VG,UG,GG,sU,Zz,jG,KG,XG,JG,sH,aH,Qz,iH,oH,uH,bU];for(const e of cH)Tr(e);const hH={"tfjs-core":$u,"tfjs-backend-cpu":AA,"tfjs-backend-webgl":mz,"tfjs-data":e$,"tfjs-layers":zw,"tfjs-converter":GT,tfjs:"4.6.0"}},720:e=>{e.exports=n;var t=null;try{t=new WebAssembly.Instance(new WebAssembly.Module(new Uint8Array([0,97,115,109,1,0,0,0,1,13,2,96,0,1,127,96,4,127,127,127,127,1,127,3,7,6,0,1,1,1,1,1,6,6,1,127,1,65,0,11,7,50,6,3,109,117,108,0,1,5,100,105,118,95,115,0,2,5,100,105,118,95,117,0,3,5,114,101,109,95,115,0,4,5,114,101,109,95,117,0,5,8,103,101,116,95,104,105,103,104,0,0,10,191,1,6,4,0,35,0,11,36,1,1,126,32,0,173,32,1,173,66,32,134,132,32,2,173,32,3,173,66,32,134,132,126,34,4,66,32,135,167,36,0,32,4,167,11,36,1,1,126,32,0,173,32,1,173,66,32,134,132,32,2,173,32,3,173,66,32,134,132,127,34,4,66,32,135,167,36,0,32,4,167,11,36,1,1,126,32,0,173,32,1,173,66,32,134,132,32,2,173,32,3,173,66,32,134,132,128,34,4,66,32,135,167,36,0,32,4,167,11,36,1,1,126,32,0,173,32,1,173,66,32,134,132,32,2,173,32,3,173,66,32,134,132,129,34,4,66,32,135,167,36,0,32,4,167,11,36,1,1,126,32,0,173,32,1,173,66,32,134,132,32,2,173,32,3,173,66,32,134,132,130,34,4,66,32,135,167,36,0,32,4,167,11])),{}).exports}catch(e){}function n(e,t,n){this.low=0|e,this.high=0|t,this.unsigned=!!n}function s(e){return!0===(e&&e.__isLong__)}n.prototype.__isLong__,Object.defineProperty(n.prototype,"__isLong__",{value:!0}),n.isLong=s;var r={},a={};function i(e,t){var n,s,i;return t?(i=0<=(e>>>=0)&&e<256)&&(s=a[e])?s:(n=l(e,(0|e)<0?-1:0,!0),i&&(a[e]=n),n):(i=-128<=(e|=0)&&e<128)&&(s=r[e])?s:(n=l(e,e<0?-1:0,!1),i&&(r[e]=n),n)}function o(e,t){if(isNaN(e))return t?y:g;if(t){if(e<0)return y;if(e>=d)return k}else{if(e<=-f)return I;if(e+1>=f)return v}return e<0?o(-e,t).neg():l(e%p|0,e/p|0,t)}function l(e,t,s){return new n(e,t,s)}n.fromInt=i,n.fromNumber=o,n.fromBits=l;var u=Math.pow;function c(e,t,n){if(0===e.length)throw Error("empty string");if("NaN"===e||"Infinity"===e||"+Infinity"===e||"-Infinity"===e)return g;if("number"==typeof t?(n=t,t=!1):t=!!t,(n=n||10)<2||36<n)throw RangeError("radix");var s;if((s=e.indexOf("-"))>0)throw Error("interior hyphen");if(0===s)return c(e.substring(1),t,n).neg();for(var r=o(u(n,8)),a=g,i=0;i<e.length;i+=8){var l=Math.min(8,e.length-i),h=parseInt(e.substring(i,i+l),n);if(l<8){var p=o(u(n,l));a=a.mul(p).add(o(h))}else a=(a=a.mul(r)).add(o(h))}return a.unsigned=t,a}function h(e,t){return"number"==typeof e?o(e,t):"string"==typeof e?c(e,t):l(e.low,e.high,"boolean"==typeof t?t:e.unsigned)}n.fromString=c,n.fromValue=h;var p=4294967296,d=p*p,f=d/2,m=i(1<<24),g=i(0);n.ZERO=g;var y=i(0,!0);n.UZERO=y;var b=i(1);n.ONE=b;var x=i(1,!0);n.UONE=x;var w=i(-1);n.NEG_ONE=w;var v=l(-1,2147483647,!1);n.MAX_VALUE=v;var k=l(-1,-1,!0);n.MAX_UNSIGNED_VALUE=k;var I=l(0,-2147483648,!1);n.MIN_VALUE=I;var N=n.prototype;N.toInt=function(){return this.unsigned?this.low>>>0:this.low},N.toNumber=function(){return this.unsigned?(this.high>>>0)*p+(this.low>>>0):this.high*p+(this.low>>>0)},N.toString=function(e){if((e=e||10)<2||36<e)throw RangeError("radix");if(this.isZero())return"0";if(this.isNegative()){if(this.eq(I)){var t=o(e),n=this.div(t),s=n.mul(t).sub(this);return n.toString(e)+s.toInt().toString(e)}return"-"+this.neg().toString(e)}for(var r=o(u(e,6),this.unsigned),a=this,i="";;){var l=a.div(r),c=(a.sub(l.mul(r)).toInt()>>>0).toString(e);if((a=l).isZero())return c+i;for(;c.length<6;)c="0"+c;i=""+c+i}},N.getHighBits=function(){return this.high},N.getHighBitsUnsigned=function(){return this.high>>>0},N.getLowBits=function(){return this.low},N.getLowBitsUnsigned=function(){return this.low>>>0},N.getNumBitsAbs=function(){if(this.isNegative())return this.eq(I)?64:this.neg().getNumBitsAbs();for(var e=0!=this.high?this.high:this.low,t=31;t>0&&0==(e&1<<t);t--);return 0!=this.high?t+33:t+1},N.isZero=function(){return 0===this.high&&0===this.low},N.eqz=N.isZero,N.isNegative=function(){return!this.unsigned&&this.high<0},N.isPositive=function(){return this.unsigned||this.high>=0},N.isOdd=function(){return 1==(1&this.low)},N.isEven=function(){return 0==(1&this.low)},N.equals=function(e){return s(e)||(e=h(e)),(this.unsigned===e.unsigned||this.high>>>31!=1||e.high>>>31!=1)&&(this.high===e.high&&this.low===e.low)},N.eq=N.equals,N.notEquals=function(e){return!this.eq(e)},N.neq=N.notEquals,N.ne=N.notEquals,N.lessThan=function(e){return this.comp(e)<0},N.lt=N.lessThan,N.lessThanOrEqual=function(e){return this.comp(e)<=0},N.lte=N.lessThanOrEqual,N.le=N.lessThanOrEqual,N.greaterThan=function(e){return this.comp(e)>0},N.gt=N.greaterThan,N.greaterThanOrEqual=function(e){return this.comp(e)>=0},N.gte=N.greaterThanOrEqual,N.ge=N.greaterThanOrEqual,N.compare=function(e){if(s(e)||(e=h(e)),this.eq(e))return 0;var t=this.isNegative(),n=e.isNegative();return t&&!n?-1:!t&&n?1:this.unsigned?e.high>>>0>this.high>>>0||e.high===this.high&&e.low>>>0>this.low>>>0?-1:1:this.sub(e).isNegative()?-1:1},N.comp=N.compare,N.negate=function(){return!this.unsigned&&this.eq(I)?I:this.not().add(b)},N.neg=N.negate,N.add=function(e){s(e)||(e=h(e));var t=this.high>>>16,n=65535&this.high,r=this.low>>>16,a=65535&this.low,i=e.high>>>16,o=65535&e.high,u=e.low>>>16,c=0,p=0,d=0,f=0;return d+=(f+=a+(65535&e.low))>>>16,p+=(d+=r+u)>>>16,c+=(p+=n+o)>>>16,c+=t+i,l((d&=65535)<<16|(f&=65535),(c&=65535)<<16|(p&=65535),this.unsigned)},N.subtract=function(e){return s(e)||(e=h(e)),this.add(e.neg())},N.sub=N.subtract,N.multiply=function(e){if(this.isZero())return g;if(s(e)||(e=h(e)),t)return l(t.mul(this.low,this.high,e.low,e.high),t.get_high(),this.unsigned);if(e.isZero())return g;if(this.eq(I))return e.isOdd()?I:g;if(e.eq(I))return this.isOdd()?I:g;if(this.isNegative())return e.isNegative()?this.neg().mul(e.neg()):this.neg().mul(e).neg();if(e.isNegative())return this.mul(e.neg()).neg();if(this.lt(m)&&e.lt(m))return o(this.toNumber()*e.toNumber(),this.unsigned);var n=this.high>>>16,r=65535&this.high,a=this.low>>>16,i=65535&this.low,u=e.high>>>16,c=65535&e.high,p=e.low>>>16,d=65535&e.low,f=0,y=0,b=0,x=0;return b+=(x+=i*d)>>>16,y+=(b+=a*d)>>>16,b&=65535,y+=(b+=i*p)>>>16,f+=(y+=r*d)>>>16,y&=65535,f+=(y+=a*p)>>>16,y&=65535,f+=(y+=i*c)>>>16,f+=n*d+r*p+a*c+i*u,l((b&=65535)<<16|(x&=65535),(f&=65535)<<16|(y&=65535),this.unsigned)},N.mul=N.multiply,N.divide=function(e){if(s(e)||(e=h(e)),e.isZero())throw Error("division by zero");var n,r,a;if(t)return this.unsigned||-2147483648!==this.high||-1!==e.low||-1!==e.high?l((this.unsigned?t.div_u:t.div_s)(this.low,this.high,e.low,e.high),t.get_high(),this.unsigned):this;if(this.isZero())return this.unsigned?y:g;if(this.unsigned){if(e.unsigned||(e=e.toUnsigned()),e.gt(this))return y;if(e.gt(this.shru(1)))return x;a=y}else{if(this.eq(I))return e.eq(b)||e.eq(w)?I:e.eq(I)?b:(n=this.shr(1).div(e).shl(1)).eq(g)?e.isNegative()?b:w:(r=this.sub(e.mul(n)),a=n.add(r.div(e)));if(e.eq(I))return this.unsigned?y:g;if(this.isNegative())return e.isNegative()?this.neg().div(e.neg()):this.neg().div(e).neg();if(e.isNegative())return this.div(e.neg()).neg();a=g}for(r=this;r.gte(e);){n=Math.max(1,Math.floor(r.toNumber()/e.toNumber()));for(var i=Math.ceil(Math.log(n)/Math.LN2),c=i<=48?1:u(2,i-48),p=o(n),d=p.mul(e);d.isNegative()||d.gt(r);)d=(p=o(n-=c,this.unsigned)).mul(e);p.isZero()&&(p=b),a=a.add(p),r=r.sub(d)}return a},N.div=N.divide,N.modulo=function(e){return s(e)||(e=h(e)),t?l((this.unsigned?t.rem_u:t.rem_s)(this.low,this.high,e.low,e.high),t.get_high(),this.unsigned):this.sub(this.div(e).mul(e))},N.mod=N.modulo,N.rem=N.modulo,N.not=function(){return l(~this.low,~this.high,this.unsigned)},N.and=function(e){return s(e)||(e=h(e)),l(this.low&e.low,this.high&e.high,this.unsigned)},N.or=function(e){return s(e)||(e=h(e)),l(this.low|e.low,this.high|e.high,this.unsigned)},N.xor=function(e){return s(e)||(e=h(e)),l(this.low^e.low,this.high^e.high,this.unsigned)},N.shiftLeft=function(e){return s(e)&&(e=e.toInt()),0==(e&=63)?this:e<32?l(this.low<<e,this.high<<e|this.low>>>32-e,this.unsigned):l(0,this.low<<e-32,this.unsigned)},N.shl=N.shiftLeft,N.shiftRight=function(e){return s(e)&&(e=e.toInt()),0==(e&=63)?this:e<32?l(this.low>>>e|this.high<<32-e,this.high>>e,this.unsigned):l(this.high>>e-32,this.high>=0?0:-1,this.unsigned)},N.shr=N.shiftRight,N.shiftRightUnsigned=function(e){if(s(e)&&(e=e.toInt()),0===(e&=63))return this;var t=this.high;return e<32?l(this.low>>>e|t<<32-e,t>>>e,this.unsigned):l(32===e?t:t>>>e-32,0,this.unsigned)},N.shru=N.shiftRightUnsigned,N.shr_u=N.shiftRightUnsigned,N.toSigned=function(){return this.unsigned?l(this.low,this.high,!1):this},N.toUnsigned=function(){return this.unsigned?this:l(this.low,this.high,!0)},N.toBytes=function(e){return e?this.toBytesLE():this.toBytesBE()},N.toBytesLE=function(){var e=this.high,t=this.low;return[255&t,t>>>8&255,t>>>16&255,t>>>24,255&e,e>>>8&255,e>>>16&255,e>>>24]},N.toBytesBE=function(){var e=this.high,t=this.low;return[e>>>24,e>>>16&255,e>>>8&255,255&e,t>>>24,t>>>16&255,t>>>8&255,255&t]},n.fromBytes=function(e,t,s){return s?n.fromBytesLE(e,t):n.fromBytesBE(e,t)},n.fromBytesLE=function(e,t){return new n(e[0]|e[1]<<8|e[2]<<16|e[3]<<24,e[4]|e[5]<<8|e[6]<<16|e[7]<<24,t)},n.fromBytesBE=function(e,t){return new n(e[4]<<24|e[5]<<16|e[6]<<8|e[7],e[0]<<24|e[1]<<16|e[2]<<8|e[3],t)}},377:(e,t,n)=>{var s=n(832),r=n(652),a=n(801),i=n(30),o=n(618),l=n(49),u=n(971);u.alea=s,u.xor128=r,u.xorwow=a,u.xorshift7=i,u.xor4096=o,u.tychei=l,e.exports=u},832:function(e,t,n){var s;!function(e,r,a){function i(e){var t=this,n=function(){var e=4022871197,t=function(t){t=String(t);for(var n=0;n<t.length;n++){var s=.02519603282416938*(e+=t.charCodeAt(n));s-=e=s>>>0,e=(s*=e)>>>0,e+=4294967296*(s-=e)}return 2.3283064365386963e-10*(e>>>0)};return t}();t.next=function(){var e=2091639*t.s0+2.3283064365386963e-10*t.c;return t.s0=t.s1,t.s1=t.s2,t.s2=e-(t.c=0|e)},t.c=1,t.s0=n(" "),t.s1=n(" "),t.s2=n(" "),t.s0-=n(e),t.s0<0&&(t.s0+=1),t.s1-=n(e),t.s1<0&&(t.s1+=1),t.s2-=n(e),t.s2<0&&(t.s2+=1),n=null}function o(e,t){return t.c=e.c,t.s0=e.s0,t.s1=e.s1,t.s2=e.s2,t}function l(e,t){var n=new i(e),s=t&&t.state,r=n.next;return r.int32=function(){return 4294967296*n.next()|0},r.double=function(){return r()+11102230246251565e-32*(2097152*r()|0)},r.quick=r,s&&("object"==typeof s&&o(s,n),r.state=function(){return o(n,{})}),r}r&&r.exports?r.exports=l:n.amdD&&n.amdO?void 0===(s=function(){return l}.call(t,n,t,r))||(r.exports=s):this.alea=l}(0,e=n.nmd(e),n.amdD)},49:function(e,t,n){var s;!function(e,r,a){function i(e){var t=this,n="";t.next=function(){var e=t.b,n=t.c,s=t.d,r=t.a;return e=e<<25^e>>>7^n,n=n-s|0,s=s<<24^s>>>8^r,r=r-e|0,t.b=e=e<<20^e>>>12^n,t.c=n=n-s|0,t.d=s<<16^n>>>16^r,t.a=r-e|0},t.a=0,t.b=0,t.c=-1640531527,t.d=1367130551,e===Math.floor(e)?(t.a=e/4294967296|0,t.b=0|e):n+=e;for(var s=0;s<n.length+20;s++)t.b^=0|n.charCodeAt(s),t.next()}function o(e,t){return t.a=e.a,t.b=e.b,t.c=e.c,t.d=e.d,t}function l(e,t){var n=new i(e),s=t&&t.state,r=function(){return(n.next()>>>0)/4294967296};return r.double=function(){do{var e=((n.next()>>>11)+(n.next()>>>0)/4294967296)/(1<<21)}while(0===e);return e},r.int32=n.next,r.quick=r,s&&("object"==typeof s&&o(s,n),r.state=function(){return o(n,{})}),r}r&&r.exports?r.exports=l:n.amdD&&n.amdO?void 0===(s=function(){return l}.call(t,n,t,r))||(r.exports=s):this.tychei=l}(0,e=n.nmd(e),n.amdD)},652:function(e,t,n){var s;!function(e,r,a){function i(e){var t=this,n="";t.x=0,t.y=0,t.z=0,t.w=0,t.next=function(){var e=t.x^t.x<<11;return t.x=t.y,t.y=t.z,t.z=t.w,t.w^=t.w>>>19^e^e>>>8},e===(0|e)?t.x=e:n+=e;for(var s=0;s<n.length+64;s++)t.x^=0|n.charCodeAt(s),t.next()}function o(e,t){return t.x=e.x,t.y=e.y,t.z=e.z,t.w=e.w,t}function l(e,t){var n=new i(e),s=t&&t.state,r=function(){return(n.next()>>>0)/4294967296};return r.double=function(){do{var e=((n.next()>>>11)+(n.next()>>>0)/4294967296)/(1<<21)}while(0===e);return e},r.int32=n.next,r.quick=r,s&&("object"==typeof s&&o(s,n),r.state=function(){return o(n,{})}),r}r&&r.exports?r.exports=l:n.amdD&&n.amdO?void 0===(s=function(){return l}.call(t,n,t,r))||(r.exports=s):this.xor128=l}(0,e=n.nmd(e),n.amdD)},618:function(e,t,n){var s;!function(e,r,a){function i(e){var t=this;t.next=function(){var e,n,s=t.w,r=t.X,a=t.i;return t.w=s=s+1640531527|0,n=r[a+34&127],e=r[a=a+1&127],n^=n<<13,e^=e<<17,n^=n>>>15,e^=e>>>12,n=r[a]=n^e,t.i=a,n+(s^s>>>16)|0},function(e,t){var n,s,r,a,i,o=[],l=128;for(t===(0|t)?(s=t,t=null):(t+="\0",s=0,l=Math.max(l,t.length)),r=0,a=-32;a<l;++a)t&&(s^=t.charCodeAt((a+32)%t.length)),0===a&&(i=s),s^=s<<10,s^=s>>>15,s^=s<<4,s^=s>>>13,a>=0&&(i=i+1640531527|0,r=0==(n=o[127&a]^=s+i)?r+1:0);for(r>=128&&(o[127&(t&&t.length||0)]=-1),r=127,a=512;a>0;--a)s=o[r+34&127],n=o[r=r+1&127],s^=s<<13,n^=n<<17,s^=s>>>15,n^=n>>>12,o[r]=s^n;e.w=i,e.X=o,e.i=r}(t,e)}function o(e,t){return t.i=e.i,t.w=e.w,t.X=e.X.slice(),t}function l(e,t){null==e&&(e=+new Date);var n=new i(e),s=t&&t.state,r=function(){return(n.next()>>>0)/4294967296};return r.double=function(){do{var e=((n.next()>>>11)+(n.next()>>>0)/4294967296)/(1<<21)}while(0===e);return e},r.int32=n.next,r.quick=r,s&&(s.X&&o(s,n),r.state=function(){return o(n,{})}),r}r&&r.exports?r.exports=l:n.amdD&&n.amdO?void 0===(s=function(){return l}.call(t,n,t,r))||(r.exports=s):this.xor4096=l}(0,e=n.nmd(e),n.amdD)},30:function(e,t,n){var s;!function(e,r,a){function i(e){var t=this;t.next=function(){var e,n,s=t.x,r=t.i;return e=s[r],n=(e^=e>>>7)^e<<24,n^=(e=s[r+1&7])^e>>>10,n^=(e=s[r+3&7])^e>>>3,n^=(e=s[r+4&7])^e<<7,e=s[r+7&7],n^=(e^=e<<13)^e<<9,s[r]=n,t.i=r+1&7,n},function(e,t){var n,s=[];if(t===(0|t))s[0]=t;else for(t=""+t,n=0;n<t.length;++n)s[7&n]=s[7&n]<<15^t.charCodeAt(n)+s[n+1&7]<<13;for(;s.length<8;)s.push(0);for(n=0;n<8&&0===s[n];++n);for(8==n?s[7]=-1:s[n],e.x=s,e.i=0,n=256;n>0;--n)e.next()}(t,e)}function o(e,t){return t.x=e.x.slice(),t.i=e.i,t}function l(e,t){null==e&&(e=+new Date);var n=new i(e),s=t&&t.state,r=function(){return(n.next()>>>0)/4294967296};return r.double=function(){do{var e=((n.next()>>>11)+(n.next()>>>0)/4294967296)/(1<<21)}while(0===e);return e},r.int32=n.next,r.quick=r,s&&(s.x&&o(s,n),r.state=function(){return o(n,{})}),r}r&&r.exports?r.exports=l:n.amdD&&n.amdO?void 0===(s=function(){return l}.call(t,n,t,r))||(r.exports=s):this.xorshift7=l}(0,e=n.nmd(e),n.amdD)},801:function(e,t,n){var s;!function(e,r,a){function i(e){var t=this,n="";t.next=function(){var e=t.x^t.x>>>2;return t.x=t.y,t.y=t.z,t.z=t.w,t.w=t.v,(t.d=t.d+362437|0)+(t.v=t.v^t.v<<4^e^e<<1)|0},t.x=0,t.y=0,t.z=0,t.w=0,t.v=0,e===(0|e)?t.x=e:n+=e;for(var s=0;s<n.length+64;s++)t.x^=0|n.charCodeAt(s),s==n.length&&(t.d=t.x<<10^t.x>>>4),t.next()}function o(e,t){return t.x=e.x,t.y=e.y,t.z=e.z,t.w=e.w,t.v=e.v,t.d=e.d,t}function l(e,t){var n=new i(e),s=t&&t.state,r=function(){return(n.next()>>>0)/4294967296};return r.double=function(){do{var e=((n.next()>>>11)+(n.next()>>>0)/4294967296)/(1<<21)}while(0===e);return e},r.int32=n.next,r.quick=r,s&&("object"==typeof s&&o(s,n),r.state=function(){return o(n,{})}),r}r&&r.exports?r.exports=l:n.amdD&&n.amdO?void 0===(s=function(){return l}.call(t,n,t,r))||(r.exports=s):this.xorwow=l}(0,e=n.nmd(e),n.amdD)},971:function(e,t,n){var s;!function(r,a,i){var o,l=256,u=i.pow(l,6),c=i.pow(2,52),h=2*c,p=l-1;function d(e,t,n){var s=[],p=y(g((t=1==t?{entropy:!0}:t||{}).entropy?[e,b(a)]:null==e?function(){try{var e;return o&&(e=o.randomBytes)?e=e(l):(e=new Uint8Array(l),(r.crypto||r.msCrypto).getRandomValues(e)),b(e)}catch(e){var t=r.navigator,n=t&&t.plugins;return[+new Date,r,n,r.screen,b(a)]}}():e,3),s),d=new f(s),x=function(){for(var e=d.g(6),t=u,n=0;e<c;)e=(e+n)*l,t*=l,n=d.g(1);for(;e>=h;)e/=2,t/=2,n>>>=1;return(e+n)/t};return x.int32=function(){return 0|d.g(4)},x.quick=function(){return d.g(4)/4294967296},x.double=x,y(b(d.S),a),(t.pass||n||function(e,t,n,s){return s&&(s.S&&m(s,d),e.state=function(){return m(d,{})}),n?(i.random=e,t):e})(x,p,"global"in t?t.global:this==i,t.state)}function f(e){var t,n=e.length,s=this,r=0,a=s.i=s.j=0,i=s.S=[];for(n||(e=[n++]);r<l;)i[r]=r++;for(r=0;r<l;r++)i[r]=i[a=p&a+e[r%n]+(t=i[r])],i[a]=t;(s.g=function(e){for(var t,n=0,r=s.i,a=s.j,i=s.S;e--;)t=i[r=p&r+1],n=n*l+i[p&(i[r]=i[a=p&a+t])+(i[a]=t)];return s.i=r,s.j=a,n})(l)}function m(e,t){return t.i=e.i,t.j=e.j,t.S=e.S.slice(),t}function g(e,t){var n,s=[],r=typeof e;if(t&&"object"==r)for(n in e)try{s.push(g(e[n],t-1))}catch(e){}return s.length?s:"string"==r?e:e+"\0"}function y(e,t){for(var n,s=e+"",r=0;r<s.length;)t[p&r]=p&(n^=19*t[p&r])+s.charCodeAt(r++);return b(t)}function b(e){return String.fromCharCode.apply(0,e)}if(y(i.random(),a),e.exports){e.exports=d;try{o=n(42)}catch(e){}}else void 0===(s=function(){return d}.call(t,n,t,e))||(e.exports=s)}("undefined"!=typeof self?self:this,[],Math)},112:function(e,t,n){"use strict";var s=this&&this.__awaiter||function(e,t,n,s){return new(n||(n=Promise))((function(r,a){function i(e){try{l(s.next(e))}catch(e){a(e)}}function o(e){try{l(s.throw(e))}catch(e){a(e)}}function l(e){var t;e.done?r(e.value):(t=e.value,t instanceof n?t:new n((function(e){e(t)}))).then(i,o)}l((s=s.apply(e,t||[])).next())}))},r=this&&this.__generator||function(e,t){var n,s,r,a,i={label:0,sent:function(){if(1&r[0])throw r[1];return r[1]},trys:[],ops:[]};return a={next:o(0),throw:o(1),return:o(2)},"function"==typeof Symbol&&(a[Symbol.iterator]=function(){return this}),a;function o(o){return function(l){return function(o){if(n)throw new TypeError("Generator is already executing.");for(;a&&(a=0,o[0]&&(i=0)),i;)try{if(n=1,s&&(r=2&o[0]?s.return:o[0]?s.throw||((r=s.return)&&r.call(s),0):s.next)&&!(r=r.call(s,o[1])).done)return r;switch(s=0,r&&(o=[2&o[0],r.value]),o[0]){case 0:case 1:r=o;break;case 4:return i.label++,{value:o[1],done:!1};case 5:i.label++,s=o[1],o=[0];continue;case 7:o=i.ops.pop(),i.trys.pop();continue;default:if(!(r=i.trys,(r=r.length>0&&r[r.length-1])||6!==o[0]&&2!==o[0])){i=0;continue}if(3===o[0]&&(!r||o[1]>r[0]&&o[1]<r[3])){i.label=o[1];break}if(6===o[0]&&i.label<r[1]){i.label=r[1],r=o;break}if(r&&i.label<r[2]){i.label=r[2],i.ops.push(o);break}r[2]&&i.ops.pop(),i.trys.pop();continue}o=t.call(e,i)}catch(e){o=[6,e],s=0}finally{n=r=0}if(5&o[0])throw o[1];return{value:o[0]?o[1]:void 0,done:!0}}([o,l])}}},a=this&&this.__importDefault||function(e){return e&&e.__esModule?e:{default:e}};Object.defineProperty(t,"__esModule",{value:!0});var i=a(n(65)),o=function(){function e(e){this.container=e}return e.prototype.update=function(e,t){this.container.innerText="Status: ".concat(e," ").concat(t)},e}();!function(){s(this,void 0,void 0,(function(){function e(e){return s(this,void 0,void 0,(function(){var t,s,i;return r(this,(function(r){switch(r.label){case 0:return t=document.createElement("canvas"),s=document.createElement("video"),navigator.mediaDevices.getUserMedia?[4,navigator.mediaDevices.getUserMedia({video:!0})]:[3,2];case 1:i=r.sent(),s.srcObject=i,r.label=2;case 2:return s.addEventListener("loadedmetadata",(function(){s.play()})),s.addEventListener("play",(function(){t.width=128,t.height=128;var r=t.getContext("2d");r&&(r.drawImage(s,0,0,t.width,t.height),n.addData(e,r.getImageData(0,0,t.width,t.height)))})),a.appendChild(t),[2]}}))}))}function t(){return s(this,void 0,void 0,(function(){return r(this,(function(e){switch(e.label){case 0:return l()?[4,n.train()]:[3,2];case 1:e.sent(),e.label=2;case 2:return[2]}}))}))}var n,a,l,u,c,h,p;return r(this,(function(d){return(n=new i.default({epochs:30,batchSize:32})).onProgress=function(e){var t=document.getElementById("progress-bar");null!==t&&new o(t).update(e,"%")},n.onLoss=function(e){var t=document.getElementById("loss-bar");null!==t&&new o(t).update(e,"loss")},(a=document.createElement("div")).id="root",l=function(){return n.ready()?!n.running()||(window.alert("이미 진행 중입니다."),!1):(window.alert("준비된 데이터가 없습니다."),!1)},(u=document.createElement("button")).textContent="라벨1 이미지",u.addEventListener("click",(function(){return e("라벨1 이미지")})),a.appendChild(u),(c=document.createElement("button")).textContent="라벨2 이미지",c.addEventListener("click",(function(){return e("라벨2 이미지")})),a.appendChild(c),(h=document.createElement("button")).textContent="모델 Train",h.addEventListener("click",t),a.appendChild(h),document.body.appendChild(a),(p=document.createElement("button")).textContent="예측하기",p.addEventListener("click",(function(){return function(){return s(this,void 0,void 0,(function(){var e,t,s;return r(this,(function(r){switch(r.label){case 0:return l()?(e=document.createElement("canvas"),t=document.createElement("video"),navigator.mediaDevices.getUserMedia?[4,navigator.mediaDevices.getUserMedia({video:!0})]:[3,2]):[2];case 1:s=r.sent(),t.srcObject=s,r.label=2;case 2:return t.addEventListener("loadedmetadata",(function(){t.play()})),t.addEventListener("play",(function(){e.width=128,e.height=128;var s=e.getContext("2d");s&&(s.drawImage(t,0,0,e.width,e.height),n.infer(s.getImageData(0,0,e.width,e.height)))})),a.appendChild(e),[2]}}))}))}()})),a.appendChild(p),[2]}))}))}()},65:function(e,t,n){"use strict";var s=this&&this.__createBinding||(Object.create?function(e,t,n,s){void 0===s&&(s=n);var r=Object.getOwnPropertyDescriptor(t,n);r&&!("get"in r?!t.__esModule:r.writable||r.configurable)||(r={enumerable:!0,get:function(){return t[n]}}),Object.defineProperty(e,s,r)}:function(e,t,n,s){void 0===s&&(s=n),e[s]=t[n]}),r=this&&this.__setModuleDefault||(Object.create?function(e,t){Object.defineProperty(e,"default",{enumerable:!0,value:t})}:function(e,t){e.default=t}),a=this&&this.__importStar||function(e){if(e&&e.__esModule)return e;var t={};if(null!=e)for(var n in e)"default"!==n&&Object.prototype.hasOwnProperty.call(e,n)&&s(t,e,n);return r(t,e),t},i=this&&this.__awaiter||function(e,t,n,s){return new(n||(n=Promise))((function(r,a){function i(e){try{l(s.next(e))}catch(e){a(e)}}function o(e){try{l(s.throw(e))}catch(e){a(e)}}function l(e){var t;e.done?r(e.value):(t=e.value,t instanceof n?t:new n((function(e){e(t)}))).then(i,o)}l((s=s.apply(e,t||[])).next())}))},o=this&&this.__generator||function(e,t){var n,s,r,a,i={label:0,sent:function(){if(1&r[0])throw r[1];return r[1]},trys:[],ops:[]};return a={next:o(0),throw:o(1),return:o(2)},"function"==typeof Symbol&&(a[Symbol.iterator]=function(){return this}),a;function o(o){return function(l){return function(o){if(n)throw new TypeError("Generator is already executing.");for(;a&&(a=0,o[0]&&(i=0)),i;)try{if(n=1,s&&(r=2&o[0]?s.return:o[0]?s.throw||((r=s.return)&&r.call(s),0):s.next)&&!(r=r.call(s,o[1])).done)return r;switch(s=0,r&&(o=[2&o[0],r.value]),o[0]){case 0:case 1:r=o;break;case 4:return i.label++,{value:o[1],done:!1};case 5:i.label++,s=o[1],o=[0];continue;case 7:o=i.ops.pop(),i.trys.pop();continue;default:if(!(r=i.trys,(r=r.length>0&&r[r.length-1])||6!==o[0]&&2!==o[0])){i=0;continue}if(3===o[0]&&(!r||o[1]>r[0]&&o[1]<r[3])){i.label=o[1];break}if(6===o[0]&&i.label<r[1]){i.label=r[1],r=o;break}if(r&&i.label<r[2]){i.label=r[2],i.ops.push(o);break}r[2]&&i.ops.pop(),i.trys.pop();continue}o=t.call(e,i)}catch(e){o=[6,e],s=0}finally{n=r=0}if(5&o[0])throw o[1];return{value:o[0]?o[1]:void 0,done:!0}}([o,l])}}};Object.defineProperty(t,"__esModule",{value:!0});var l=a(n(401)),u=function(){function e(e){var t=void 0===e?{}:e,n=t.epochs,s=void 0===n?10:n,r=t.batchSize,a=void 0===r?16:r;this.trainImages=[],this.MOBILE_NET_INPUT_WIDTH=224,this.MOBILE_NET_INPUT_HEIGHT=224,this.MOBILE_NET_INPUT_CHANNEL=3,this.IMAGE_NORMALIZATION_FACTOR=255,this.onProgress=function(){},this.onLoss=function(){},this.model=null,this.epochs=s,this.batchSize=a,this.labels=[],this.isRunning=!1,this.isReady=!1,this.limitSize=2}return e.prototype.addData=function(e,t){try{var n=l.browser.fromPixels(t);return console.log("addData",n),this.trainImages.push(n),this.labels.push(e),void(this.labels.length>=this.limitSize&&(this.isReady=!0))}catch(e){throw console.error("Model training failed",e),e}},e.prototype.train=function(){return i(this,void 0,void 0,(function(){var e,t,n,s,r,a,i=this;return o(this,(function(o){switch(o.label){case 0:if(this.isRunning)return[2,Promise.reject(new Error("Training is already in progress."))];e={onTrainBegin:function(){console.log("Training has started.")},onTrainEnd:function(){console.log("Training has ended."),i.isRunning=!1},onBatchBegin:function(e,t){console.log("Batch ".concat(e," is starting."))},onBatchEnd:function(e,t){console.log("Batch ".concat(e," has ended."))},onEpochBegin:function(e,t){var n=Math.floor((e+1)/i.epochs*100);i.onProgress(n),console.log("Epoch ".concat(e+1," is starting."))},onEpochEnd:function(e,t){console.log("Epoch ".concat(e+1," has ended.")),i.onLoss(t.loss),console.log("Loss:",t.loss)}},o.label=1;case 1:return o.trys.push([1,4,,5]),this.isRunning=!0,this.labels.length<this.limitSize?[2,Promise.reject(new Error("Please train Data need over 2 data length"))]:(t=this,[4,this._createModel(this.labels.length)]);case 2:return t.model=o.sent(),n=this._preprocessedInputData(this.model),s=this._preprocessedTargetData(),[4,this.model.fit(n,s,{epochs:this.epochs,batchSize:this.batchSize,callbacks:e})];case 3:return r=o.sent(),console.log("Model training completed",r),[2,r];case 4:throw a=o.sent(),this.isRunning=!1,console.error("Model training failed",a),a;case 5:return[2]}}))}))},e.prototype.infer=function(e){return i(this,void 0,void 0,(function(){var t,n,s,r,a,i,u,c,h;return o(this,(function(o){switch(o.label){case 0:if(null===this.model)throw new Error("Model is null");o.label=1;case 1:return o.trys.push([1,3,,4]),t=l.browser.fromPixels(e),n=l.image.resizeBilinear(t,[this.MOBILE_NET_INPUT_WIDTH,this.MOBILE_NET_INPUT_HEIGHT]),s=n.expandDims(0),[4,this.model.predict(s).data()];case 2:for(r=o.sent(),a=new Map,i=0;i<r.length;i++)u=this.labels[i],c=r[i],void 0!==(h=a.get(u))?a.set(u,h+c):a.set(u,c);return console.log("Class Probabilities:",a),[2,a];case 3:throw o.sent();case 4:return[2]}}))}))},e.prototype.saveModel=function(){console.log("saved model")},e.prototype.running=function(){return this.isRunning},e.prototype.ready=function(){return this.isReady},e.prototype._preprocessedTargetData=function(){var e=this;console.log("uniqueLabels.length",this.labels,this.labels.length);var t=this.labels.map((function(t){return e.labels.indexOf(t)}));console.log("labelIndices",t);var n=l.oneHot(l.tensor1d(t,"int32"),this.labels.length);return console.log("oneHotEncode",n),n},e.prototype._preprocessedInputData=function(e){var t=this,n=e.inputs[0].shape;console.log("inputShape",n);var s=n.slice(1);return console.log("inputShapeArray",s),l.stack(this.trainImages.map((function(e){var n=t._preprocessData(e);return l.reshape(n,s)})))},e.prototype._preprocessData=function(e){try{return l.image.resizeBilinear(e,[this.MOBILE_NET_INPUT_WIDTH,this.MOBILE_NET_INPUT_HEIGHT]).div(this.IMAGE_NORMALIZATION_FACTOR).expandDims(0)}catch(e){throw console.error("Failed to _preprocessData data",e),e}},e.prototype._createModel=function(e){return i(this,void 0,void 0,(function(){var t,n;return o(this,(function(s){try{return t=[this.MOBILE_NET_INPUT_WIDTH,this.MOBILE_NET_INPUT_HEIGHT,this.MOBILE_NET_INPUT_CHANNEL],(n=l.sequential()).add(l.layers.conv2d({inputShape:t,filters:32,kernelSize:3,activation:"relu"})),n.add(l.layers.maxPooling2d({poolSize:2})),n.add(l.layers.conv2d({filters:64,kernelSize:3,activation:"relu"})),n.add(l.layers.maxPooling2d({poolSize:2})),n.add(l.layers.flatten()),n.add(l.layers.dense({units:e,activation:"softmax"})),n.compile({loss:2===e?"binaryCrossentropy":"categoricalCrossentropy",optimizer:l.train.adam(),metrics:["accuracy"]}),n.summary(),[2,n]}catch(e){throw console.error("Failed to load model",e),e}return[2]}))}))},e}();t.default=u},410:()=>{},628:()=>{},601:()=>{},792:()=>{},977:()=>{},42:()=>{}},t={};function n(s){var r=t[s];if(void 0!==r)return r.exports;var a=t[s]={id:s,loaded:!1,exports:{}};return e[s].call(a.exports,a,a.exports,n),a.loaded=!0,a.exports}n.amdD=function(){throw new Error("define cannot be used indirect")},n.amdO={},n.n=e=>{var t=e&&e.__esModule?()=>e.default:()=>e;return n.d(t,{a:t}),t},n.d=(e,t)=>{for(var s in t)n.o(t,s)&&!n.o(e,s)&&Object.defineProperty(e,s,{enumerable:!0,get:t[s]})},n.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(e){if("object"==typeof window)return window}}(),n.o=(e,t)=>Object.prototype.hasOwnProperty.call(e,t),n.r=e=>{"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},n.nmd=e=>(e.paths=[],e.children||(e.children=[]),e);n(112)})();