tempest-react-sdk 0.21.0 → 0.23.0

package/dist/vision/preprocess/image.js

@@ -0,0 +1,93 @@
+import * as v from "onnxruntime-web";
+import { createCanvas as y, get2DContext as h, rgbToImageData as I, imageDataToRGB as A } from "../core/canvas.js";
+import { RGBImage as $ } from "../types.js";
+function D(n, o, t) {
+  if (o <= 0 || t <= 0)
+    throw new Error(`Invalid resize target ${o}x${t}.`);
+  if (o === n.width && t === n.height)
+    return n;
+  const r = y(n.width, n.height);
+  h(r).putImageData(I(n), 0, 0);
+  const e = y(o, t), a = h(e);
+  a.imageSmoothingEnabled = !0, a.imageSmoothingQuality = "high", a.drawImage(r, 0, 0, o, t);
+  const l = a.getImageData(0, 0, o, t);
+  return A(l);
+}
+function B(n, o, t, r = 1 / 255) {
+  const s = new Float32Array(n.data.length), e = n.data, a = o[0], l = o[1], c = o[2], x = t[0], d = t[1], w = t[2];
+  for (let f = 0; f < e.length; f += 3)
+    s[f] = (e[f] * r - a) / x, s[f + 1] = (e[f + 1] * r - l) / d, s[f + 2] = (e[f + 2] * r - c) / w;
+  return s;
+}
+function T(n, o = 1 / 255) {
+  const t = new Float32Array(n.data.length), r = n.data;
+  for (let s = 0; s < r.length; s++)
+    t[s] = r[s] * o;
+  return t;
+}
+function F(n, o, t, r = 3) {
+  const s = o * t * r;
+  if (n.length !== s)
+    throw new Error(
+      `toCHW: expected length ${s} for ${o}x${t}x${r}, got ${n.length}.`
+    );
+  const e = new Float32Array(s), a = o * t;
+  for (let l = 0; l < t; l++)
+    for (let c = 0; c < o; c++) {
+      const x = (l * o + c) * r, d = l * o + c;
+      for (let w = 0; w < r; w++)
+        e[w * a + d] = n[x + w];
+    }
+  return e;
+}
+function E(n, o) {
+  return new v.Tensor("float32", n, o);
+}
+function R(n) {
+  const o = T(n);
+  return F(o, n.width, n.height, 3);
+}
+function U(n, o, t) {
+  if (n.length !== o * t * 3)
+    throw new Error(
+      `fromCv2: data length ${n.length} does not match width * height * 3 = ${o * t * 3}.`
+    );
+  const r = new Uint8Array(n.length);
+  for (let s = 0; s < n.length; s += 3)
+    r[s] = n[s + 2], r[s + 1] = n[s + 1], r[s + 2] = n[s];
+  return new $(r, o, t);
+}
+function G(n) {
+  const o = n.data, t = new Uint8Array(o.length);
+  for (let r = 0; r < o.length; r += 3)
+    t[r] = o[r + 2], t[r + 1] = o[r + 1], t[r + 2] = o[r];
+  return t;
+}
+function O(n, o, t, r = [114, 114, 114]) {
+  const s = Math.min(o / n.width, t / n.height), e = Math.round(n.width * s), a = Math.round(n.height * s), l = D(n, e, a), c = new Uint8Array(o * t * 3), x = r[0], d = r[1], w = r[2];
+  for (let u = 0; u < c.length; u += 3)
+    c[u] = x, c[u + 1] = d, c[u + 2] = w;
+  const f = Math.floor((o - e) / 2), m = Math.floor((t - a) / 2), p = e * 3;
+  for (let u = 0; u < a; u++) {
+    const C = u * p, i = ((m + u) * o + f) * 3;
+    c.set(l.data.subarray(C, C + p), i);
+  }
+  return {
+    image: new $(c, o, t),
+    scale: s,
+    padLeft: f,
+    padTop: m
+  };
+}
+export {
+  U as fromCv2,
+  O as letterbox,
+  B as normalize,
+  D as resize,
+  F as toCHW,
+  G as toCv2,
+  T as toFloat32,
+  E as toFloat32Tensor,
+  R as toTensor
+};
+//# sourceMappingURL=image.js.map

package/dist/vision/preprocess/image.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"image.js","sources":["../../../src/vision/preprocess/image.ts"],"sourcesContent":["/**\n * Composable image preprocessing primitives (resize, normalize, letterbox, layout).\n *\n * Mirrors the Python `preprocess.image` module. Operates on the canonical\n * {@link RGBImage} (HWC RGB uint8) and produces uint8 or float32 buffers\n * depending on the operation.\n */\n\nimport * as ortRuntime from \"onnxruntime-web\";\nimport type * as ort from \"onnxruntime-web\";\n\nimport { createCanvas, get2DContext, imageDataToRGB, rgbToImageData } from \"../core/canvas\";\nimport { RGBImage } from \"../types\";\n\n/** Resize an image to `(targetWidth, targetHeight)` using high-quality canvas resampling. */\nexport function resize(image: RGBImage, targetWidth: number, targetHeight: number): RGBImage {\n    if (targetWidth <= 0 || targetHeight <= 0) {\n        throw new Error(`Invalid resize target ${targetWidth}x${targetHeight}.`);\n    }\n    if (targetWidth === image.width && targetHeight === image.height) {\n        return image;\n    }\n\n    const srcCanvas = createCanvas(image.width, image.height);\n    const srcCtx = get2DContext(srcCanvas);\n    srcCtx.putImageData(rgbToImageData(image), 0, 0);\n\n    const dstCanvas = createCanvas(targetWidth, targetHeight);\n    const dstCtx = get2DContext(dstCanvas);\n    dstCtx.imageSmoothingEnabled = true;\n    dstCtx.imageSmoothingQuality = \"high\";\n    dstCtx.drawImage(srcCanvas as CanvasImageSource, 0, 0, targetWidth, targetHeight);\n\n    const imageData = dstCtx.getImageData(0, 0, targetWidth, targetHeight);\n    return imageDataToRGB(imageData);\n}\n\n/**\n * Convert a uint8 image to a normalized float32 array (HWC layout preserved).\n *\n * Applies `(pixel * scale - mean) / std` channel-wise.\n */\nexport function normalize(\n    image: RGBImage,\n    mean: readonly [number, number, number],\n    std: readonly [number, number, number],\n    scale: number = 1 / 255,\n): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    const m0 = mean[0];\n    const m1 = mean[1];\n    const m2 = mean[2];\n    const s0 = std[0];\n    const s1 = std[1];\n    const s2 = std[2];\n    for (let i = 0; i < data.length; i += 3) {\n        out[i] = ((data[i] as number) * scale - m0) / s0;\n        out[i + 1] = ((data[i + 1] as number) * scale - m1) / s1;\n        out[i + 2] = ((data[i + 2] as number) * scale - m2) / s2;\n    }\n    return out;\n}\n\n/** Convert a uint8 image to a `Float32Array` in `[0, 1]` (HWC layout preserved). */\nexport function toFloat32(image: RGBImage, scale: number = 1 / 255): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    for (let i = 0; i < data.length; i++) {\n        out[i] = (data[i] as number) * scale;\n    }\n    return out;\n}\n\n/**\n * Transpose interleaved HWC data to planar CHW layout.\n *\n * @param hwc Source array of length `width * height * channels`.\n */\nexport function toCHW(\n    hwc: Float32Array,\n    width: number,\n    height: number,\n    channels: number = 3,\n): Float32Array {\n    const expected = width * height * channels;\n    if (hwc.length !== expected) {\n        throw new Error(\n            `toCHW: expected length ${expected} for ${width}x${height}x${channels}, got ${hwc.length}.`,\n        );\n    }\n    const chw = new Float32Array(expected);\n    const plane = width * height;\n    for (let y = 0; y < height; y++) {\n        for (let x = 0; x < width; x++) {\n            const hwcBase = (y * width + x) * channels;\n            const planeIdx = y * width + x;\n            for (let c = 0; c < channels; c++) {\n                chw[c * plane + planeIdx] = hwc[hwcBase + c] as number;\n            }\n        }\n    }\n    return chw;\n}\n\n/** Wrap a Float32 buffer into an `ort.Tensor`. */\nexport function toFloat32Tensor(data: Float32Array, dims: readonly number[]): ort.Tensor {\n    return new ortRuntime.Tensor(\"float32\", data, dims as number[]);\n}\n\n/**\n * Convert an HWC uint8 image to a CHW `Float32Array` scaled to `[0, 1]`.\n *\n * Mirrors `torchvision.transforms.ToTensor()` semantics: HWC → CHW,\n * `uint8 → float32 / 255`. Useful as input to YOLO-style detectors that\n * don't require ImageNet normalization.\n *\n * @returns CHW `Float32Array` of length `width * height * 3`.\n */\nexport function toTensor(image: RGBImage): Float32Array {\n    const f32 = toFloat32(image);\n    return toCHW(f32, image.width, image.height, 3);\n}\n\n/**\n * Convert an HWC BGR uint8 buffer (OpenCV layout) to the SDK's HWC RGB.\n *\n * Use when you receive image bytes from `cv2.imencode` over the wire and\n * want to feed them to the SDK without going through a canvas decode.\n *\n * @param bgr Flat BGR Uint8Array of length `width * height * 3`.\n */\nexport function fromCv2(bgr: Uint8Array, width: number, height: number): RGBImage {\n    if (bgr.length !== width * height * 3) {\n        throw new Error(\n            `fromCv2: data length ${bgr.length} does not match width * height * 3 = ${width * height * 3}.`,\n        );\n    }\n    const rgb = new Uint8Array(bgr.length);\n    for (let i = 0; i < bgr.length; i += 3) {\n        rgb[i] = bgr[i + 2] as number;\n        rgb[i + 1] = bgr[i + 1] as number;\n        rgb[i + 2] = bgr[i] as number;\n    }\n    return new RGBImage(rgb, width, height);\n}\n\n/**\n * Convert the SDK's HWC RGB image to an HWC BGR `Uint8Array` (OpenCV layout).\n *\n * Useful for round-tripping data to a Python OpenCV consumer.\n */\nexport function toCv2(image: RGBImage): Uint8Array {\n    const rgb = image.data;\n    const bgr = new Uint8Array(rgb.length);\n    for (let i = 0; i < rgb.length; i += 3) {\n        bgr[i] = rgb[i + 2] as number;\n        bgr[i + 1] = rgb[i + 1] as number;\n        bgr[i + 2] = rgb[i] as number;\n    }\n    return bgr;\n}\n\nexport interface LetterboxResult {\n    /** The padded image at the target size. */\n    readonly image: RGBImage;\n    /** The factor applied to the original image (`< 1` if downscaled). */\n    readonly scale: number;\n    /** Horizontal padding in pixels (left side; right side has the same or +1). */\n    readonly padLeft: number;\n    /** Vertical padding in pixels (top side). */\n    readonly padTop: number;\n}\n\n/**\n * Resize preserving aspect ratio, padding to `(targetWidth, targetHeight)`\n * with a constant fill color.\n *\n * Standard YOLO preprocessing — returning `scale` and `padLeft`/`padTop`\n * lets callers map detections back to the original image coordinates.\n */\nexport function letterbox(\n    image: RGBImage,\n    targetWidth: number,\n    targetHeight: number,\n    fill: readonly [number, number, number] = [114, 114, 114],\n): LetterboxResult {\n    const scale = Math.min(targetWidth / image.width, targetHeight / image.height);\n    const newW = Math.round(image.width * scale);\n    const newH = Math.round(image.height * scale);\n    const resized = resize(image, newW, newH);\n\n    const out = new Uint8Array(targetWidth * targetHeight * 3);\n    const f0 = fill[0];\n    const f1 = fill[1];\n    const f2 = fill[2];\n    for (let i = 0; i < out.length; i += 3) {\n        out[i] = f0;\n        out[i + 1] = f1;\n        out[i + 2] = f2;\n    }\n\n    const padLeft = Math.floor((targetWidth - newW) / 2);\n    const padTop = Math.floor((targetHeight - newH) / 2);\n    const rowBytes = newW * 3;\n    for (let y = 0; y < newH; y++) {\n        const srcOffset = y * rowBytes;\n        const dstOffset = ((padTop + y) * targetWidth + padLeft) * 3;\n        out.set(resized.data.subarray(srcOffset, srcOffset + rowBytes), dstOffset);\n    }\n\n    return {\n        image: new RGBImage(out, targetWidth, targetHeight),\n        scale,\n        padLeft,\n        padTop,\n    };\n}\n"],"names":["resize","image","targetWidth","targetHeight","srcCanvas","createCanvas","get2DContext","rgbToImageData","dstCanvas","dstCtx","imageData","imageDataToRGB","normalize","mean","std","scale","out","data","m0","m1","m2","s0","s1","s2","i","toFloat32","toCHW","hwc","width","height","channels","expected","chw","plane","y","x","hwcBase","planeIdx","c","toFloat32Tensor","dims","ortRuntime","toTensor","f32","fromCv2","bgr","rgb","RGBImage","toCv2","letterbox","fill","newW","newH","resized","f0","f1","f2","padLeft","padTop","rowBytes","srcOffset","dstOffset"],"mappings":";;;AAeO,SAASA,EAAOC,GAAiBC,GAAqBC,GAAgC;AACzF,MAAID,KAAe,KAAKC,KAAgB;AACpC,UAAM,IAAI,MAAM,yBAAyBD,CAAW,IAAIC,CAAY,GAAG;AAE3E,MAAID,MAAgBD,EAAM,SAASE,MAAiBF,EAAM;AACtD,WAAOA;AAGX,QAAMG,IAAYC,EAAaJ,EAAM,OAAOA,EAAM,MAAM;AAExD,EADeK,EAAaF,CAAS,EAC9B,aAAaG,EAAeN,CAAK,GAAG,GAAG,CAAC;AAE/C,QAAMO,IAAYH,EAAaH,GAAaC,CAAY,GAClDM,IAASH,EAAaE,CAAS;AACrC,EAAAC,EAAO,wBAAwB,IAC/BA,EAAO,wBAAwB,QAC/BA,EAAO,UAAUL,GAAgC,GAAG,GAAGF,GAAaC,CAAY;AAEhF,QAAMO,IAAYD,EAAO,aAAa,GAAG,GAAGP,GAAaC,CAAY;AACrE,SAAOQ,EAAeD,CAAS;AACnC;AAOO,SAASE,EACZX,GACAY,GACAC,GACAC,IAAgB,IAAI,KACR;AACZ,QAAMC,IAAM,IAAI,aAAaf,EAAM,KAAK,MAAM,GACxCgB,IAAOhB,EAAM,MACbiB,IAAKL,EAAK,CAAC,GACXM,IAAKN,EAAK,CAAC,GACXO,IAAKP,EAAK,CAAC,GACXQ,IAAKP,EAAI,CAAC,GACVQ,IAAKR,EAAI,CAAC,GACVS,IAAKT,EAAI,CAAC;AAChB,WAASU,IAAI,GAAGA,IAAIP,EAAK,QAAQO,KAAK;AAClC,IAAAR,EAAIQ,CAAC,KAAMP,EAAKO,CAAC,IAAeT,IAAQG,KAAMG,GAC9CL,EAAIQ,IAAI,CAAC,KAAMP,EAAKO,IAAI,CAAC,IAAeT,IAAQI,KAAMG,GACtDN,EAAIQ,IAAI,CAAC,KAAMP,EAAKO,IAAI,CAAC,IAAeT,IAAQK,KAAMG;AAE1D,SAAOP;AACX;AAGO,SAASS,EAAUxB,GAAiBc,IAAgB,IAAI,KAAmB;AAC9E,QAAMC,IAAM,IAAI,aAAaf,EAAM,KAAK,MAAM,GACxCgB,IAAOhB,EAAM;AACnB,WAASuB,IAAI,GAAGA,IAAIP,EAAK,QAAQO;AAC7B,IAAAR,EAAIQ,CAAC,IAAKP,EAAKO,CAAC,IAAeT;AAEnC,SAAOC;AACX;AAOO,SAASU,EACZC,GACAC,GACAC,GACAC,IAAmB,GACP;AACZ,QAAMC,IAAWH,IAAQC,IAASC;AAClC,MAAIH,EAAI,WAAWI;AACf,UAAM,IAAI;AAAA,MACN,0BAA0BA,CAAQ,QAAQH,CAAK,IAAIC,CAAM,IAAIC,CAAQ,SAASH,EAAI,MAAM;AAAA,IAAA;AAGhG,QAAMK,IAAM,IAAI,aAAaD,CAAQ,GAC/BE,IAAQL,IAAQC;AACtB,WAASK,IAAI,GAAGA,IAAIL,GAAQK;AACxB,aAASC,IAAI,GAAGA,IAAIP,GAAOO,KAAK;AAC5B,YAAMC,KAAWF,IAAIN,IAAQO,KAAKL,GAC5BO,IAAWH,IAAIN,IAAQO;AAC7B,eAASG,IAAI,GAAGA,IAAIR,GAAUQ;AAC1B,QAAAN,EAAIM,IAAIL,IAAQI,CAAQ,IAAIV,EAAIS,IAAUE,CAAC;AAAA,IAEnD;AAEJ,SAAON;AACX;AAGO,SAASO,EAAgBtB,GAAoBuB,GAAqC;AACrF,SAAO,IAAIC,EAAW,OAAO,WAAWxB,GAAMuB,CAAgB;AAClE;AAWO,SAASE,EAASzC,GAA+B;AACpD,QAAM0C,IAAMlB,EAAUxB,CAAK;AAC3B,SAAOyB,EAAMiB,GAAK1C,EAAM,OAAOA,EAAM,QAAQ,CAAC;AAClD;AAUO,SAAS2C,EAAQC,GAAiBjB,GAAeC,GAA0B;AAC9E,MAAIgB,EAAI,WAAWjB,IAAQC,IAAS;AAChC,UAAM,IAAI;AAAA,MACN,wBAAwBgB,EAAI,MAAM,wCAAwCjB,IAAQC,IAAS,CAAC;AAAA,IAAA;AAGpG,QAAMiB,IAAM,IAAI,WAAWD,EAAI,MAAM;AACrC,WAASrB,IAAI,GAAGA,IAAIqB,EAAI,QAAQrB,KAAK;AACjC,IAAAsB,EAAItB,CAAC,IAAIqB,EAAIrB,IAAI,CAAC,GAClBsB,EAAItB,IAAI,CAAC,IAAIqB,EAAIrB,IAAI,CAAC,GACtBsB,EAAItB,IAAI,CAAC,IAAIqB,EAAIrB,CAAC;AAEtB,SAAO,IAAIuB,EAASD,GAAKlB,GAAOC,CAAM;AAC1C;AAOO,SAASmB,EAAM/C,GAA6B;AAC/C,QAAM6C,IAAM7C,EAAM,MACZ4C,IAAM,IAAI,WAAWC,EAAI,MAAM;AACrC,WAAStB,IAAI,GAAGA,IAAIsB,EAAI,QAAQtB,KAAK;AACjC,IAAAqB,EAAIrB,CAAC,IAAIsB,EAAItB,IAAI,CAAC,GAClBqB,EAAIrB,IAAI,CAAC,IAAIsB,EAAItB,IAAI,CAAC,GACtBqB,EAAIrB,IAAI,CAAC,IAAIsB,EAAItB,CAAC;AAEtB,SAAOqB;AACX;AAoBO,SAASI,EACZhD,GACAC,GACAC,GACA+C,IAA0C,CAAC,KAAK,KAAK,GAAG,GACzC;AACf,QAAMnC,IAAQ,KAAK,IAAIb,IAAcD,EAAM,OAAOE,IAAeF,EAAM,MAAM,GACvEkD,IAAO,KAAK,MAAMlD,EAAM,QAAQc,CAAK,GACrCqC,IAAO,KAAK,MAAMnD,EAAM,SAASc,CAAK,GACtCsC,IAAUrD,EAAOC,GAAOkD,GAAMC,CAAI,GAElCpC,IAAM,IAAI,WAAWd,IAAcC,IAAe,CAAC,GACnDmD,IAAKJ,EAAK,CAAC,GACXK,IAAKL,EAAK,CAAC,GACXM,IAAKN,EAAK,CAAC;AACjB,WAAS1B,IAAI,GAAGA,IAAIR,EAAI,QAAQQ,KAAK;AACjC,IAAAR,EAAIQ,CAAC,IAAI8B,GACTtC,EAAIQ,IAAI,CAAC,IAAI+B,GACbvC,EAAIQ,IAAI,CAAC,IAAIgC;AAGjB,QAAMC,IAAU,KAAK,OAAOvD,IAAciD,KAAQ,CAAC,GAC7CO,IAAS,KAAK,OAAOvD,IAAeiD,KAAQ,CAAC,GAC7CO,IAAWR,IAAO;AACxB,WAASjB,IAAI,GAAGA,IAAIkB,GAAMlB,KAAK;AAC3B,UAAM0B,IAAY1B,IAAIyB,GAChBE,MAAcH,IAASxB,KAAKhC,IAAcuD,KAAW;AAC3D,IAAAzC,EAAI,IAAIqC,EAAQ,KAAK,SAASO,GAAWA,IAAYD,CAAQ,GAAGE,CAAS;AAAA,EAC7E;AAEA,SAAO;AAAA,IACH,OAAO,IAAId,EAAS/B,GAAKd,GAAaC,CAAY;AAAA,IAClD,OAAAY;AAAA,IACA,SAAA0C;AAAA,IACA,QAAAC;AAAA,EAAA;AAER;"}

package/dist/vision/results.cjs

@@ -0,0 +1,2 @@
+"use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});class l{constructor(s,t,i,e){this.xyxy=s,this.cls=t,this.conf=i,this.origShape=e}xyxy;cls;conf;origShape;get length(){return this.cls.length}get shape(){return[this.length,4]}get xywh(){const s=new Float32Array(this.xyxy.length);for(let t=0;t<this.length;t++){const i=this.xyxy[t*4],e=this.xyxy[t*4+1],r=this.xyxy[t*4+2],h=this.xyxy[t*4+3];s[t*4]=(i+r)/2,s[t*4+1]=(e+h)/2,s[t*4+2]=r-i,s[t*4+3]=h-e}return s}get xyxyn(){const[s,t]=this.origShape,i=new Float32Array(this.xyxy.length);if(this.length===0||t<=0||s<=0)return i;for(let e=0;e<this.length;e++)i[e*4]=this.xyxy[e*4]/t,i[e*4+1]=this.xyxy[e*4+1]/s,i[e*4+2]=this.xyxy[e*4+2]/t,i[e*4+3]=this.xyxy[e*4+3]/s;return i}get xywhn(){const s=this.xywh,[t,i]=this.origShape;if(this.length===0||i<=0||t<=0)return s;for(let e=0;e<this.length;e++)s[e*4]=s[e*4]/i,s[e*4+1]=s[e*4+1]/t,s[e*4+2]=s[e*4+2]/i,s[e*4+3]=s[e*4+3]/t;return s}get data(){const s=new Float32Array(this.length*6);for(let t=0;t<this.length;t++)s[t*6]=this.xyxy[t*4],s[t*6+1]=this.xyxy[t*4+1],s[t*6+2]=this.xyxy[t*4+2],s[t*6+3]=this.xyxy[t*4+3],s[t*6+4]=this.conf[t],s[t*6+5]=this.cls[t];return s}}class g{constructor(s){this.data=s}data;get length(){return this.data.length}get shape(){return[this.length]}get top1(){if(this.data.length===0)return 0;let s=0,t=this.data[0];for(let i=1;i<this.data.length;i++){const e=this.data[i];e>t&&(s=i,t=e)}return s}get top1conf(){return this.data.length===0?0:this.data[this.top1]}get top5(){return this._topK(5).indices}get top5conf(){return this._topK(5).values}_topK(s){const t=Math.min(s,this.data.length),i=[];for(let h=0;h<this.data.length;h++)i.push(h);i.sort((h,n)=>this.data[n]-this.data[h]);const e=new Int32Array(t),r=new Float32Array(t);for(let h=0;h<t;h++)e[h]=i[h],r[h]=this.data[i[h]];return{indices:e,values:r}}}class c{constructor(s,t,i){this.data=s,this.xyxy=t,this.origShape=i}data;xyxy;origShape;get length(){return this.data.length}get shape(){return[this.length]}[Symbol.iterator](){return this.data[Symbol.iterator]()}}class u{constructor(s,t,i,e,r,h=null,n={}){this.boxes=s,this.detections=t,this.names=i,this.origImg=e,this.origShape=r,this.path=h,this.speed=n}boxes;detections;names;origImg;origShape;path;speed;get length(){return this.detections.length}get(s){return this.detections[s]}[Symbol.iterator](){return this.detections[Symbol.iterator]()}}class y{constructor(s,t,i,e,r,h=null,n={}){this.probs=s,this.result=t,this.names=i,this.origImg=e,this.origShape=r,this.path=h,this.speed=n}probs;result;names;origImg;origShape;path;speed;get cls(){return this.probs.top1}get conf(){return this.probs.top1conf}get name(){return this.names[this.cls]??`class_${this.cls}`}get probabilities(){return this.result.probabilities}}class x{constructor(s,t,i,e,r,h,n=null,a={}){this.boxes=s,this.masks=t,this.detections=i,this.names=e,this.origImg=r,this.origShape=h,this.path=n,this.speed=a}boxes;masks;detections;names;origImg;origShape;path;speed;get length(){return this.detections.length}get(s){return this.detections[s]}[Symbol.iterator](){return this.detections[Symbol.iterator]()}}exports.Boxes=l;exports.ClassificationResults=y;exports.DetectionResults=u;exports.Masks=c;exports.Probs=g;exports.SegmentationResults=x;
+//# sourceMappingURL=results.cjs.map

package/dist/vision/results.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"results.cjs","sources":["../../src/vision/results.ts"],"sourcesContent":["/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n */\n\nimport {\n    type ClassificationResult,\n    type DetectionResult,\n    type RGBImage,\n    type SegmentationResult,\n} from \"./types\";\n\n/**\n * Bulk numpy-style view of detected boxes for a single image.\n *\n * Mirrors Ultralytics' `Boxes` interface. Coordinates in {@link xyxy} and\n * {@link xywh} are absolute pixels in the original image; the `*n` variants\n * are normalized to `[0, 1]` using `origShape`.\n */\nexport class Boxes {\n    /**\n     * @param xyxy Flat array of length `4 * N` in `[x1, y1, x2, y2, ...]` order.\n     * @param cls One class index per box, length `N`.\n     * @param conf One confidence per box, length `N`.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly xyxy: Float32Array,\n        public readonly cls: Int32Array,\n        public readonly conf: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of detected boxes. */\n    get length(): number {\n        return this.cls.length;\n    }\n\n    /** `[N, 4]` shape of the `xyxy` view. */\n    get shape(): readonly [number, number] {\n        return [this.length, 4];\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` flat array in absolute pixels. */\n    get xywh(): Float32Array {\n        const out = new Float32Array(this.xyxy.length);\n        for (let i = 0; i < this.length; i++) {\n            const x1 = this.xyxy[i * 4] as number;\n            const y1 = this.xyxy[i * 4 + 1] as number;\n            const x2 = this.xyxy[i * 4 + 2] as number;\n            const y2 = this.xyxy[i * 4 + 3] as number;\n            out[i * 4] = (x1 + x2) / 2;\n            out[i * 4 + 1] = (y1 + y2) / 2;\n            out[i * 4 + 2] = x2 - x1;\n            out[i * 4 + 3] = y2 - y1;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[x1, y1, x2, y2]` normalized to `[0, 1]`. */\n    get xyxyn(): Float32Array {\n        const [h, w] = this.origShape;\n        const out = new Float32Array(this.xyxy.length);\n        if (this.length === 0 || w <= 0 || h <= 0) return out;\n        for (let i = 0; i < this.length; i++) {\n            out[i * 4] = (this.xyxy[i * 4] as number) / w;\n            out[i * 4 + 1] = (this.xyxy[i * 4 + 1] as number) / h;\n            out[i * 4 + 2] = (this.xyxy[i * 4 + 2] as number) / w;\n            out[i * 4 + 3] = (this.xyxy[i * 4 + 3] as number) / h;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` normalized to `[0, 1]`. */\n    get xywhn(): Float32Array {\n        const xywh = this.xywh;\n        const [h, w] = this.origShape;\n        if (this.length === 0 || w <= 0 || h <= 0) return xywh;\n        for (let i = 0; i < this.length; i++) {\n            xywh[i * 4] = (xywh[i * 4] as number) / w;\n            xywh[i * 4 + 1] = (xywh[i * 4 + 1] as number) / h;\n            xywh[i * 4 + 2] = (xywh[i * 4 + 2] as number) / w;\n            xywh[i * 4 + 3] = (xywh[i * 4 + 3] as number) / h;\n        }\n        return xywh;\n    }\n\n    /**\n     * Concatenated `[N, 6]` array of `[x1, y1, x2, y2, conf, cls]`.\n     *\n     * Matches Ultralytics' `boxes.data`.\n     */\n    get data(): Float32Array {\n        const out = new Float32Array(this.length * 6);\n        for (let i = 0; i < this.length; i++) {\n            out[i * 6] = this.xyxy[i * 4] as number;\n            out[i * 6 + 1] = this.xyxy[i * 4 + 1] as number;\n            out[i * 6 + 2] = this.xyxy[i * 4 + 2] as number;\n            out[i * 6 + 3] = this.xyxy[i * 4 + 3] as number;\n            out[i * 6 + 4] = this.conf[i] as number;\n            out[i * 6 + 5] = this.cls[i] as number;\n        }\n        return out;\n    }\n}\n\n/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._topK(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._topK(5).values;\n    }\n\n    private _topK(k: number): { indices: Int32Array; values: Float32Array } {\n        const n = Math.min(k, this.data.length);\n        const order: number[] = [];\n        for (let i = 0; i < this.data.length; i++) order.push(i);\n        order.sort((a, b) => (this.data[b] as number) - (this.data[a] as number));\n        const indices = new Int32Array(n);\n        const values = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            indices[i] = order[i] as number;\n            values[i] = this.data[order[i] as number] as number;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Record<string, number>> = {},\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image classification envelope (Ultralytics-style `Results`).\n */\nexport class ClassificationResults {\n    constructor(\n        public readonly probs: Probs,\n        public readonly result: ClassificationResult,\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Record<string, number>> = {},\n    ) {}\n\n    /** Top-1 class index (Ultralytics-style alias). */\n    get cls(): number {\n        return this.probs.top1;\n    }\n\n    /** Top-1 confidence (Ultralytics-style alias). */\n    get conf(): number {\n        return this.probs.top1conf;\n    }\n\n    /** Top-1 class name. */\n    get name(): string {\n        return this.names[this.cls] ?? `class_${this.cls}`;\n    }\n\n    /** Per-class probability list, sorted descending (legacy field). */\n    get probabilities(): readonly ClassificationResult[\"probabilities\"][number][] {\n        return this.result.probabilities;\n    }\n}\n\n/**\n * Per-image instance-segmentation envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link SegmentationResult} entries. `boxes`\n * and `masks` mirror Ultralytics' bulk-array views.\n */\nexport class SegmentationResults implements Iterable<SegmentationResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly masks: Masks,\n        public readonly detections: readonly SegmentationResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Record<string, number>> = {},\n    ) {}\n\n    /** Number of surviving instances. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance results. */\n    get(index: number): SegmentationResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<SegmentationResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n"],"names":["Boxes","xyxy","cls","conf","origShape","out","i","x1","y1","x2","y2","h","w","xywh","Probs","data","best","bestVal","v","k","n","order","a","b","indices","values","Masks","DetectionResults","boxes","detections","names","origImg","path","speed","index","ClassificationResults","probs","result","SegmentationResults","masks"],"mappings":"gFA6BO,MAAMA,CAAM,CAOf,YACoBC,EACAC,EACAC,EACAC,EAClB,CAJkB,KAAA,KAAAH,EACA,KAAA,IAAAC,EACA,KAAA,KAAAC,EACA,KAAA,UAAAC,CACjB,CAJiB,KACA,IACA,KACA,UAIpB,IAAI,QAAiB,CACjB,OAAO,KAAK,IAAI,MACpB,CAGA,IAAI,OAAmC,CACnC,MAAO,CAAC,KAAK,OAAQ,CAAC,CAC1B,CAGA,IAAI,MAAqB,CACrB,MAAMC,EAAM,IAAI,aAAa,KAAK,KAAK,MAAM,EAC7C,QAASC,EAAI,EAAGA,EAAI,KAAK,OAAQA,IAAK,CAClC,MAAMC,EAAK,KAAK,KAAKD,EAAI,CAAC,EACpBE,EAAK,KAAK,KAAKF,EAAI,EAAI,CAAC,EACxBG,EAAK,KAAK,KAAKH,EAAI,EAAI,CAAC,EACxBI,EAAK,KAAK,KAAKJ,EAAI,EAAI,CAAC,EAC9BD,EAAIC,EAAI,CAAC,GAAKC,EAAKE,GAAM,EACzBJ,EAAIC,EAAI,EAAI,CAAC,GAAKE,EAAKE,GAAM,EAC7BL,EAAIC,EAAI,EAAI,CAAC,EAAIG,EAAKF,EACtBF,EAAIC,EAAI,EAAI,CAAC,EAAII,EAAKF,CAC1B,CACA,OAAOH,CACX,CAGA,IAAI,OAAsB,CACtB,KAAM,CAACM,EAAGC,CAAC,EAAI,KAAK,UACdP,EAAM,IAAI,aAAa,KAAK,KAAK,MAAM,EAC7C,GAAI,KAAK,SAAW,GAAKO,GAAK,GAAKD,GAAK,EAAG,OAAON,EAClD,QAASC,EAAI,EAAGA,EAAI,KAAK,OAAQA,IAC7BD,EAAIC,EAAI,CAAC,EAAK,KAAK,KAAKA,EAAI,CAAC,EAAeM,EAC5CP,EAAIC,EAAI,EAAI,CAAC,EAAK,KAAK,KAAKA,EAAI,EAAI,CAAC,EAAeK,EACpDN,EAAIC,EAAI,EAAI,CAAC,EAAK,KAAK,KAAKA,EAAI,EAAI,CAAC,EAAeM,EACpDP,EAAIC,EAAI,EAAI,CAAC,EAAK,KAAK,KAAKA,EAAI,EAAI,CAAC,EAAeK,EAExD,OAAON,CACX,CAGA,IAAI,OAAsB,CACtB,MAAMQ,EAAO,KAAK,KACZ,CAACF,EAAGC,CAAC,EAAI,KAAK,UACpB,GAAI,KAAK,SAAW,GAAKA,GAAK,GAAKD,GAAK,EAAG,OAAOE,EAClD,QAASP,EAAI,EAAGA,EAAI,KAAK,OAAQA,IAC7BO,EAAKP,EAAI,CAAC,EAAKO,EAAKP,EAAI,CAAC,EAAeM,EACxCC,EAAKP,EAAI,EAAI,CAAC,EAAKO,EAAKP,EAAI,EAAI,CAAC,EAAeK,EAChDE,EAAKP,EAAI,EAAI,CAAC,EAAKO,EAAKP,EAAI,EAAI,CAAC,EAAeM,EAChDC,EAAKP,EAAI,EAAI,CAAC,EAAKO,EAAKP,EAAI,EAAI,CAAC,EAAeK,EAEpD,OAAOE,CACX,CAOA,IAAI,MAAqB,CACrB,MAAMR,EAAM,IAAI,aAAa,KAAK,OAAS,CAAC,EAC5C,QAASC,EAAI,EAAGA,EAAI,KAAK,OAAQA,IAC7BD,EAAIC,EAAI,CAAC,EAAI,KAAK,KAAKA,EAAI,CAAC,EAC5BD,EAAIC,EAAI,EAAI,CAAC,EAAI,KAAK,KAAKA,EAAI,EAAI,CAAC,EACpCD,EAAIC,EAAI,EAAI,CAAC,EAAI,KAAK,KAAKA,EAAI,EAAI,CAAC,EACpCD,EAAIC,EAAI,EAAI,CAAC,EAAI,KAAK,KAAKA,EAAI,EAAI,CAAC,EACpCD,EAAIC,EAAI,EAAI,CAAC,EAAI,KAAK,KAAKA,CAAC,EAC5BD,EAAIC,EAAI,EAAI,CAAC,EAAI,KAAK,IAAIA,CAAC,EAE/B,OAAOD,CACX,CACJ,CAOO,MAAMS,CAAM,CAEf,YAA4BC,EAAoB,CAApB,KAAA,KAAAA,CAAqB,CAArB,KAG5B,IAAI,QAAiB,CACjB,OAAO,KAAK,KAAK,MACrB,CAGA,IAAI,OAA2B,CAC3B,MAAO,CAAC,KAAK,MAAM,CACvB,CAGA,IAAI,MAAe,CACf,GAAI,KAAK,KAAK,SAAW,EAAG,MAAO,GACnC,IAAIC,EAAO,EACPC,EAAU,KAAK,KAAK,CAAC,EACzB,QAAS,EAAI,EAAG,EAAI,KAAK,KAAK,OAAQ,IAAK,CACvC,MAAMC,EAAI,KAAK,KAAK,CAAC,EACjBA,EAAID,IACJD,EAAO,EACPC,EAAUC,EAElB,CACA,OAAOF,CACX,CAGA,IAAI,UAAmB,CACnB,OAAI,KAAK,KAAK,SAAW,EAAU,EAC5B,KAAK,KAAK,KAAK,IAAI,CAC9B,CAGA,IAAI,MAAmB,CACnB,OAAO,KAAK,MAAM,CAAC,EAAE,OACzB,CAGA,IAAI,UAAyB,CACzB,OAAO,KAAK,MAAM,CAAC,EAAE,MACzB,CAEQ,MAAMG,EAA0D,CACpE,MAAMC,EAAI,KAAK,IAAID,EAAG,KAAK,KAAK,MAAM,EAChCE,EAAkB,CAAA,EACxB,QAASf,EAAI,EAAGA,EAAI,KAAK,KAAK,OAAQA,IAAKe,EAAM,KAAKf,CAAC,EACvDe,EAAM,KAAK,CAACC,EAAGC,IAAO,KAAK,KAAKA,CAAC,EAAgB,KAAK,KAAKD,CAAC,CAAY,EACxE,MAAME,EAAU,IAAI,WAAWJ,CAAC,EAC1BK,EAAS,IAAI,aAAaL,CAAC,EACjC,QAASd,EAAI,EAAGA,EAAIc,EAAGd,IACnBkB,EAAQlB,CAAC,EAAIe,EAAMf,CAAC,EACpBmB,EAAOnB,CAAC,EAAI,KAAK,KAAKe,EAAMf,CAAC,CAAW,EAE5C,MAAO,CAAE,QAAAkB,EAAS,OAAAC,CAAA,CACtB,CACJ,CAQO,MAAMC,CAAM,CAMf,YACoBX,EAKAd,EACAG,EAClB,CAPkB,KAAA,KAAAW,EAKA,KAAA,KAAAd,EACA,KAAA,UAAAG,CACjB,CAPiB,KAKA,KACA,UAIpB,IAAI,QAAiB,CACjB,OAAO,KAAK,KAAK,MACrB,CAGA,IAAI,OAA2B,CAC3B,MAAO,CAAC,KAAK,MAAM,CACvB,CAEA,CAAC,OAAO,QAAQ,GAIb,CACC,OAAO,KAAK,KAAK,OAAO,QAAQ,EAAA,CACpC,CACJ,CAiBO,MAAMuB,CAAsD,CAC/D,YACoBC,EACAC,EACAC,EACAC,EACA3B,EACA4B,EAAsB,KACtBC,EAA0C,GAC5D,CAPkB,KAAA,MAAAL,EACA,KAAA,WAAAC,EACA,KAAA,MAAAC,EACA,KAAA,QAAAC,EACA,KAAA,UAAA3B,EACA,KAAA,KAAA4B,EACA,KAAA,MAAAC,CACjB,CAPiB,MACA,WACA,MACA,QACA,UACA,KACA,MAIpB,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAIC,EAA4C,CAC5C,OAAO,KAAK,WAAWA,CAAK,CAChC,CAEA,CAAC,OAAO,QAAQ,GAA+B,CAC3C,OAAO,KAAK,WAAW,OAAO,QAAQ,EAAA,CAC1C,CACJ,CAKO,MAAMC,CAAsB,CAC/B,YACoBC,EACAC,EACAP,EACAC,EACA3B,EACA4B,EAAsB,KACtBC,EAA0C,GAC5D,CAPkB,KAAA,MAAAG,EACA,KAAA,OAAAC,EACA,KAAA,MAAAP,EACA,KAAA,QAAAC,EACA,KAAA,UAAA3B,EACA,KAAA,KAAA4B,EACA,KAAA,MAAAC,CACjB,CAPiB,MACA,OACA,MACA,QACA,UACA,KACA,MAIpB,IAAI,KAAc,CACd,OAAO,KAAK,MAAM,IACtB,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAM,QACtB,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAM,KAAK,GAAG,GAAK,SAAS,KAAK,GAAG,EACpD,CAGA,IAAI,eAA0E,CAC1E,OAAO,KAAK,OAAO,aACvB,CACJ,CAQO,MAAMK,CAA4D,CACrE,YACoBV,EACAW,EACAV,EACAC,EACAC,EACA3B,EACA4B,EAAsB,KACtBC,EAA0C,CAAA,EAC5D,CARkB,KAAA,MAAAL,EACA,KAAA,MAAAW,EACA,KAAA,WAAAV,EACA,KAAA,MAAAC,EACA,KAAA,QAAAC,EACA,KAAA,UAAA3B,EACA,KAAA,KAAA4B,EACA,KAAA,MAAAC,CACjB,CARiB,MACA,MACA,WACA,MACA,QACA,UACA,KACA,MAIpB,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAIC,EAA+C,CAC/C,OAAO,KAAK,WAAWA,CAAK,CAChC,CAEA,CAAC,OAAO,QAAQ,GAAkC,CAC9C,OAAO,KAAK,WAAW,OAAO,QAAQ,EAAA,CAC1C,CACJ"}

package/dist/vision/results.js

@@ -0,0 +1,213 @@
+class l {
+  /**
+   * @param xyxy Flat array of length `4 * N` in `[x1, y1, x2, y2, ...]` order.
+   * @param cls One class index per box, length `N`.
+   * @param conf One confidence per box, length `N`.
+   * @param origShape `[height, width]` of the original image.
+   */
+  constructor(s, t, i, e) {
+    this.xyxy = s, this.cls = t, this.conf = i, this.origShape = e;
+  }
+  xyxy;
+  cls;
+  conf;
+  origShape;
+  /** Number of detected boxes. */
+  get length() {
+    return this.cls.length;
+  }
+  /** `[N, 4]` shape of the `xyxy` view. */
+  get shape() {
+    return [this.length, 4];
+  }
+  /** Boxes as `[N, 4]` `[cx, cy, w, h]` flat array in absolute pixels. */
+  get xywh() {
+    const s = new Float32Array(this.xyxy.length);
+    for (let t = 0; t < this.length; t++) {
+      const i = this.xyxy[t * 4], e = this.xyxy[t * 4 + 1], r = this.xyxy[t * 4 + 2], h = this.xyxy[t * 4 + 3];
+      s[t * 4] = (i + r) / 2, s[t * 4 + 1] = (e + h) / 2, s[t * 4 + 2] = r - i, s[t * 4 + 3] = h - e;
+    }
+    return s;
+  }
+  /** Boxes as `[N, 4]` `[x1, y1, x2, y2]` normalized to `[0, 1]`. */
+  get xyxyn() {
+    const [s, t] = this.origShape, i = new Float32Array(this.xyxy.length);
+    if (this.length === 0 || t <= 0 || s <= 0) return i;
+    for (let e = 0; e < this.length; e++)
+      i[e * 4] = this.xyxy[e * 4] / t, i[e * 4 + 1] = this.xyxy[e * 4 + 1] / s, i[e * 4 + 2] = this.xyxy[e * 4 + 2] / t, i[e * 4 + 3] = this.xyxy[e * 4 + 3] / s;
+    return i;
+  }
+  /** Boxes as `[N, 4]` `[cx, cy, w, h]` normalized to `[0, 1]`. */
+  get xywhn() {
+    const s = this.xywh, [t, i] = this.origShape;
+    if (this.length === 0 || i <= 0 || t <= 0) return s;
+    for (let e = 0; e < this.length; e++)
+      s[e * 4] = s[e * 4] / i, s[e * 4 + 1] = s[e * 4 + 1] / t, s[e * 4 + 2] = s[e * 4 + 2] / i, s[e * 4 + 3] = s[e * 4 + 3] / t;
+    return s;
+  }
+  /**
+   * Concatenated `[N, 6]` array of `[x1, y1, x2, y2, conf, cls]`.
+   *
+   * Matches Ultralytics' `boxes.data`.
+   */
+  get data() {
+    const s = new Float32Array(this.length * 6);
+    for (let t = 0; t < this.length; t++)
+      s[t * 6] = this.xyxy[t * 4], s[t * 6 + 1] = this.xyxy[t * 4 + 1], s[t * 6 + 2] = this.xyxy[t * 4 + 2], s[t * 6 + 3] = this.xyxy[t * 4 + 3], s[t * 6 + 4] = this.conf[t], s[t * 6 + 5] = this.cls[t];
+    return s;
+  }
+}
+class g {
+  /** @param data `[numClasses]` per-class probabilities, indexed by class id. */
+  constructor(s) {
+    this.data = s;
+  }
+  data;
+  /** Number of classes. */
+  get length() {
+    return this.data.length;
+  }
+  /** `[numClasses]` shape of the underlying vector. */
+  get shape() {
+    return [this.length];
+  }
+  /** Index of the most probable class. */
+  get top1() {
+    if (this.data.length === 0) return 0;
+    let s = 0, t = this.data[0];
+    for (let i = 1; i < this.data.length; i++) {
+      const e = this.data[i];
+      e > t && (s = i, t = e);
+    }
+    return s;
+  }
+  /** Probability of the top-1 class. */
+  get top1conf() {
+    return this.data.length === 0 ? 0 : this.data[this.top1];
+  }
+  /** Indices of the top-5 most probable classes, descending. */
+  get top5() {
+    return this._topK(5).indices;
+  }
+  /** Probabilities of the top-5 classes, descending. */
+  get top5conf() {
+    return this._topK(5).values;
+  }
+  _topK(s) {
+    const t = Math.min(s, this.data.length), i = [];
+    for (let h = 0; h < this.data.length; h++) i.push(h);
+    i.sort((h, n) => this.data[n] - this.data[h]);
+    const e = new Int32Array(t), r = new Float32Array(t);
+    for (let h = 0; h < t; h++)
+      e[h] = i[h], r[h] = this.data[i[h]];
+    return { indices: e, values: r };
+  }
+}
+class c {
+  /**
+   * @param data Per-instance binary masks (`Mask` objects from `types.ts`).
+   * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.
+   * @param origShape `[height, width]` of the original image.
+   */
+  constructor(s, t, i) {
+    this.data = s, this.xyxy = t, this.origShape = i;
+  }
+  data;
+  xyxy;
+  origShape;
+  /** Number of instance masks. */
+  get length() {
+    return this.data.length;
+  }
+  /** `[N]` shape of the masks collection. */
+  get shape() {
+    return [this.length];
+  }
+  [Symbol.iterator]() {
+    return this.data[Symbol.iterator]();
+  }
+}
+class y {
+  constructor(s, t, i, e, r, h = null, n = {}) {
+    this.boxes = s, this.detections = t, this.names = i, this.origImg = e, this.origShape = r, this.path = h, this.speed = n;
+  }
+  boxes;
+  detections;
+  names;
+  origImg;
+  origShape;
+  path;
+  speed;
+  /** Number of surviving detections. */
+  get length() {
+    return this.detections.length;
+  }
+  /** Index into the per-instance detections. */
+  get(s) {
+    return this.detections[s];
+  }
+  [Symbol.iterator]() {
+    return this.detections[Symbol.iterator]();
+  }
+}
+class u {
+  constructor(s, t, i, e, r, h = null, n = {}) {
+    this.probs = s, this.result = t, this.names = i, this.origImg = e, this.origShape = r, this.path = h, this.speed = n;
+  }
+  probs;
+  result;
+  names;
+  origImg;
+  origShape;
+  path;
+  speed;
+  /** Top-1 class index (Ultralytics-style alias). */
+  get cls() {
+    return this.probs.top1;
+  }
+  /** Top-1 confidence (Ultralytics-style alias). */
+  get conf() {
+    return this.probs.top1conf;
+  }
+  /** Top-1 class name. */
+  get name() {
+    return this.names[this.cls] ?? `class_${this.cls}`;
+  }
+  /** Per-class probability list, sorted descending (legacy field). */
+  get probabilities() {
+    return this.result.probabilities;
+  }
+}
+class x {
+  constructor(s, t, i, e, r, h, n = null, a = {}) {
+    this.boxes = s, this.masks = t, this.detections = i, this.names = e, this.origImg = r, this.origShape = h, this.path = n, this.speed = a;
+  }
+  boxes;
+  masks;
+  detections;
+  names;
+  origImg;
+  origShape;
+  path;
+  speed;
+  /** Number of surviving instances. */
+  get length() {
+    return this.detections.length;
+  }
+  /** Index into the per-instance results. */
+  get(s) {
+    return this.detections[s];
+  }
+  [Symbol.iterator]() {
+    return this.detections[Symbol.iterator]();
+  }
+}
+export {
+  l as Boxes,
+  u as ClassificationResults,
+  y as DetectionResults,
+  c as Masks,
+  g as Probs,
+  x as SegmentationResults
+};
+//# sourceMappingURL=results.js.map

package/dist/vision/results.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"results.js","sources":["../../src/vision/results.ts"],"sourcesContent":["/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n */\n\nimport {\n    type ClassificationResult,\n    type DetectionResult,\n    type RGBImage,\n    type SegmentationResult,\n} from \"./types\";\n\n/**\n * Bulk numpy-style view of detected boxes for a single image.\n *\n * Mirrors Ultralytics' `Boxes` interface. Coordinates in {@link xyxy} and\n * {@link xywh} are absolute pixels in the original image; the `*n` variants\n * are normalized to `[0, 1]` using `origShape`.\n */\nexport class Boxes {\n    /**\n     * @param xyxy Flat array of length `4 * N` in `[x1, y1, x2, y2, ...]` order.\n     * @param cls One class index per box, length `N`.\n     * @param conf One confidence per box, length `N`.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly xyxy: Float32Array,\n        public readonly cls: Int32Array,\n        public readonly conf: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of detected boxes. */\n    get length(): number {\n        return this.cls.length;\n    }\n\n    /** `[N, 4]` shape of the `xyxy` view. */\n    get shape(): readonly [number, number] {\n        return [this.length, 4];\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` flat array in absolute pixels. */\n    get xywh(): Float32Array {\n        const out = new Float32Array(this.xyxy.length);\n        for (let i = 0; i < this.length; i++) {\n            const x1 = this.xyxy[i * 4] as number;\n            const y1 = this.xyxy[i * 4 + 1] as number;\n            const x2 = this.xyxy[i * 4 + 2] as number;\n            const y2 = this.xyxy[i * 4 + 3] as number;\n            out[i * 4] = (x1 + x2) / 2;\n            out[i * 4 + 1] = (y1 + y2) / 2;\n            out[i * 4 + 2] = x2 - x1;\n            out[i * 4 + 3] = y2 - y1;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[x1, y1, x2, y2]` normalized to `[0, 1]`. */\n    get xyxyn(): Float32Array {\n        const [h, w] = this.origShape;\n        const out = new Float32Array(this.xyxy.length);\n        if (this.length === 0 || w <= 0 || h <= 0) return out;\n        for (let i = 0; i < this.length; i++) {\n            out[i * 4] = (this.xyxy[i * 4] as number) / w;\n            out[i * 4 + 1] = (this.xyxy[i * 4 + 1] as number) / h;\n            out[i * 4 + 2] = (this.xyxy[i * 4 + 2] as number) / w;\n            out[i * 4 + 3] = (this.xyxy[i * 4 + 3] as number) / h;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` normalized to `[0, 1]`. */\n    get xywhn(): Float32Array {\n        const xywh = this.xywh;\n        const [h, w] = this.origShape;\n        if (this.length === 0 || w <= 0 || h <= 0) return xywh;\n        for (let i = 0; i < this.length; i++) {\n            xywh[i * 4] = (xywh[i * 4] as number) / w;\n            xywh[i * 4 + 1] = (xywh[i * 4 + 1] as number) / h;\n            xywh[i * 4 + 2] = (xywh[i * 4 + 2] as number) / w;\n            xywh[i * 4 + 3] = (xywh[i * 4 + 3] as number) / h;\n        }\n        return xywh;\n    }\n\n    /**\n     * Concatenated `[N, 6]` array of `[x1, y1, x2, y2, conf, cls]`.\n     *\n     * Matches Ultralytics' `boxes.data`.\n     */\n    get data(): Float32Array {\n        const out = new Float32Array(this.length * 6);\n        for (let i = 0; i < this.length; i++) {\n            out[i * 6] = this.xyxy[i * 4] as number;\n            out[i * 6 + 1] = this.xyxy[i * 4 + 1] as number;\n            out[i * 6 + 2] = this.xyxy[i * 4 + 2] as number;\n            out[i * 6 + 3] = this.xyxy[i * 4 + 3] as number;\n            out[i * 6 + 4] = this.conf[i] as number;\n            out[i * 6 + 5] = this.cls[i] as number;\n        }\n        return out;\n    }\n}\n\n/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._topK(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._topK(5).values;\n    }\n\n    private _topK(k: number): { indices: Int32Array; values: Float32Array } {\n        const n = Math.min(k, this.data.length);\n        const order: number[] = [];\n        for (let i = 0; i < this.data.length; i++) order.push(i);\n        order.sort((a, b) => (this.data[b] as number) - (this.data[a] as number));\n        const indices = new Int32Array(n);\n        const values = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            indices[i] = order[i] as number;\n            values[i] = this.data[order[i] as number] as number;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Record<string, number>> = {},\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image classification envelope (Ultralytics-style `Results`).\n */\nexport class ClassificationResults {\n    constructor(\n        public readonly probs: Probs,\n        public readonly result: ClassificationResult,\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Record<string, number>> = {},\n    ) {}\n\n    /** Top-1 class index (Ultralytics-style alias). */\n    get cls(): number {\n        return this.probs.top1;\n    }\n\n    /** Top-1 confidence (Ultralytics-style alias). */\n    get conf(): number {\n        return this.probs.top1conf;\n    }\n\n    /** Top-1 class name. */\n    get name(): string {\n        return this.names[this.cls] ?? `class_${this.cls}`;\n    }\n\n    /** Per-class probability list, sorted descending (legacy field). */\n    get probabilities(): readonly ClassificationResult[\"probabilities\"][number][] {\n        return this.result.probabilities;\n    }\n}\n\n/**\n * Per-image instance-segmentation envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link SegmentationResult} entries. `boxes`\n * and `masks` mirror Ultralytics' bulk-array views.\n */\nexport class SegmentationResults implements Iterable<SegmentationResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly masks: Masks,\n        public readonly detections: readonly SegmentationResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Record<string, number>> = {},\n    ) {}\n\n    /** Number of surviving instances. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance results. */\n    get(index: number): SegmentationResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<SegmentationResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n"],"names":["Boxes","xyxy","cls","conf","origShape","out","i","x1","y1","x2","y2","h","w","xywh","Probs","data","best","bestVal","v","k","n","order","a","b","indices","values","Masks","DetectionResults","boxes","detections","names","origImg","path","speed","index","ClassificationResults","probs","result","SegmentationResults","masks"],"mappings":"AA6BO,MAAMA,EAAM;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOf,YACoBC,GACAC,GACAC,GACAC,GAClB;AAJkB,SAAA,OAAAH,GACA,KAAA,MAAAC,GACA,KAAA,OAAAC,GACA,KAAA,YAAAC;AAAA,EACjB;AAAA,EAJiB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AAAA,EAIpB,IAAI,SAAiB;AACjB,WAAO,KAAK,IAAI;AAAA,EACpB;AAAA;AAAA,EAGA,IAAI,QAAmC;AACnC,WAAO,CAAC,KAAK,QAAQ,CAAC;AAAA,EAC1B;AAAA;AAAA,EAGA,IAAI,OAAqB;AACrB,UAAMC,IAAM,IAAI,aAAa,KAAK,KAAK,MAAM;AAC7C,aAASC,IAAI,GAAGA,IAAI,KAAK,QAAQA,KAAK;AAClC,YAAMC,IAAK,KAAK,KAAKD,IAAI,CAAC,GACpBE,IAAK,KAAK,KAAKF,IAAI,IAAI,CAAC,GACxBG,IAAK,KAAK,KAAKH,IAAI,IAAI,CAAC,GACxBI,IAAK,KAAK,KAAKJ,IAAI,IAAI,CAAC;AAC9B,MAAAD,EAAIC,IAAI,CAAC,KAAKC,IAAKE,KAAM,GACzBJ,EAAIC,IAAI,IAAI,CAAC,KAAKE,IAAKE,KAAM,GAC7BL,EAAIC,IAAI,IAAI,CAAC,IAAIG,IAAKF,GACtBF,EAAIC,IAAI,IAAI,CAAC,IAAII,IAAKF;AAAA,IAC1B;AACA,WAAOH;AAAA,EACX;AAAA;AAAA,EAGA,IAAI,QAAsB;AACtB,UAAM,CAACM,GAAGC,CAAC,IAAI,KAAK,WACdP,IAAM,IAAI,aAAa,KAAK,KAAK,MAAM;AAC7C,QAAI,KAAK,WAAW,KAAKO,KAAK,KAAKD,KAAK,EAAG,QAAON;AAClD,aAASC,IAAI,GAAGA,IAAI,KAAK,QAAQA;AAC7B,MAAAD,EAAIC,IAAI,CAAC,IAAK,KAAK,KAAKA,IAAI,CAAC,IAAeM,GAC5CP,EAAIC,IAAI,IAAI,CAAC,IAAK,KAAK,KAAKA,IAAI,IAAI,CAAC,IAAeK,GACpDN,EAAIC,IAAI,IAAI,CAAC,IAAK,KAAK,KAAKA,IAAI,IAAI,CAAC,IAAeM,GACpDP,EAAIC,IAAI,IAAI,CAAC,IAAK,KAAK,KAAKA,IAAI,IAAI,CAAC,IAAeK;AAExD,WAAON;AAAA,EACX;AAAA;AAAA,EAGA,IAAI,QAAsB;AACtB,UAAMQ,IAAO,KAAK,MACZ,CAACF,GAAGC,CAAC,IAAI,KAAK;AACpB,QAAI,KAAK,WAAW,KAAKA,KAAK,KAAKD,KAAK,EAAG,QAAOE;AAClD,aAASP,IAAI,GAAGA,IAAI,KAAK,QAAQA;AAC7B,MAAAO,EAAKP,IAAI,CAAC,IAAKO,EAAKP,IAAI,CAAC,IAAeM,GACxCC,EAAKP,IAAI,IAAI,CAAC,IAAKO,EAAKP,IAAI,IAAI,CAAC,IAAeK,GAChDE,EAAKP,IAAI,IAAI,CAAC,IAAKO,EAAKP,IAAI,IAAI,CAAC,IAAeM,GAChDC,EAAKP,IAAI,IAAI,CAAC,IAAKO,EAAKP,IAAI,IAAI,CAAC,IAAeK;AAEpD,WAAOE;AAAA,EACX;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,IAAI,OAAqB;AACrB,UAAMR,IAAM,IAAI,aAAa,KAAK,SAAS,CAAC;AAC5C,aAASC,IAAI,GAAGA,IAAI,KAAK,QAAQA;AAC7B,MAAAD,EAAIC,IAAI,CAAC,IAAI,KAAK,KAAKA,IAAI,CAAC,GAC5BD,EAAIC,IAAI,IAAI,CAAC,IAAI,KAAK,KAAKA,IAAI,IAAI,CAAC,GACpCD,EAAIC,IAAI,IAAI,CAAC,IAAI,KAAK,KAAKA,IAAI,IAAI,CAAC,GACpCD,EAAIC,IAAI,IAAI,CAAC,IAAI,KAAK,KAAKA,IAAI,IAAI,CAAC,GACpCD,EAAIC,IAAI,IAAI,CAAC,IAAI,KAAK,KAAKA,CAAC,GAC5BD,EAAIC,IAAI,IAAI,CAAC,IAAI,KAAK,IAAIA,CAAC;AAE/B,WAAOD;AAAA,EACX;AACJ;AAOO,MAAMS,EAAM;AAAA;AAAA,EAEf,YAA4BC,GAAoB;AAApB,SAAA,OAAAA;AAAA,EAAqB;AAAA,EAArB;AAAA;AAAA,EAG5B,IAAI,SAAiB;AACjB,WAAO,KAAK,KAAK;AAAA,EACrB;AAAA;AAAA,EAGA,IAAI,QAA2B;AAC3B,WAAO,CAAC,KAAK,MAAM;AAAA,EACvB;AAAA;AAAA,EAGA,IAAI,OAAe;AACf,QAAI,KAAK,KAAK,WAAW,EAAG,QAAO;AACnC,QAAIC,IAAO,GACPC,IAAU,KAAK,KAAK,CAAC;AACzB,aAAS,IAAI,GAAG,IAAI,KAAK,KAAK,QAAQ,KAAK;AACvC,YAAMC,IAAI,KAAK,KAAK,CAAC;AACrB,MAAIA,IAAID,MACJD,IAAO,GACPC,IAAUC;AAAA,IAElB;AACA,WAAOF;AAAA,EACX;AAAA;AAAA,EAGA,IAAI,WAAmB;AACnB,WAAI,KAAK,KAAK,WAAW,IAAU,IAC5B,KAAK,KAAK,KAAK,IAAI;AAAA,EAC9B;AAAA;AAAA,EAGA,IAAI,OAAmB;AACnB,WAAO,KAAK,MAAM,CAAC,EAAE;AAAA,EACzB;AAAA;AAAA,EAGA,IAAI,WAAyB;AACzB,WAAO,KAAK,MAAM,CAAC,EAAE;AAAA,EACzB;AAAA,EAEQ,MAAMG,GAA0D;AACpE,UAAMC,IAAI,KAAK,IAAID,GAAG,KAAK,KAAK,MAAM,GAChCE,IAAkB,CAAA;AACxB,aAASf,IAAI,GAAGA,IAAI,KAAK,KAAK,QAAQA,IAAK,CAAAe,EAAM,KAAKf,CAAC;AACvD,IAAAe,EAAM,KAAK,CAACC,GAAGC,MAAO,KAAK,KAAKA,CAAC,IAAgB,KAAK,KAAKD,CAAC,CAAY;AACxE,UAAME,IAAU,IAAI,WAAWJ,CAAC,GAC1BK,IAAS,IAAI,aAAaL,CAAC;AACjC,aAASd,IAAI,GAAGA,IAAIc,GAAGd;AACnB,MAAAkB,EAAQlB,CAAC,IAAIe,EAAMf,CAAC,GACpBmB,EAAOnB,CAAC,IAAI,KAAK,KAAKe,EAAMf,CAAC,CAAW;AAE5C,WAAO,EAAE,SAAAkB,GAAS,QAAAC,EAAA;AAAA,EACtB;AACJ;AAQO,MAAMC,EAAM;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAMf,YACoBX,GAKAd,GACAG,GAClB;AAPkB,SAAA,OAAAW,GAKA,KAAA,OAAAd,GACA,KAAA,YAAAG;AAAA,EACjB;AAAA,EAPiB;AAAA,EAKA;AAAA,EACA;AAAA;AAAA,EAIpB,IAAI,SAAiB;AACjB,WAAO,KAAK,KAAK;AAAA,EACrB;AAAA;AAAA,EAGA,IAAI,QAA2B;AAC3B,WAAO,CAAC,KAAK,MAAM;AAAA,EACvB;AAAA,EAEA,CAAC,OAAO,QAAQ,IAIb;AACC,WAAO,KAAK,KAAK,OAAO,QAAQ,EAAA;AAAA,EACpC;AACJ;AAiBO,MAAMuB,EAAsD;AAAA,EAC/D,YACoBC,GACAC,GACAC,GACAC,GACA3B,GACA4B,IAAsB,MACtBC,IAA0C,IAC5D;AAPkB,SAAA,QAAAL,GACA,KAAA,aAAAC,GACA,KAAA,QAAAC,GACA,KAAA,UAAAC,GACA,KAAA,YAAA3B,GACA,KAAA,OAAA4B,GACA,KAAA,QAAAC;AAAA,EACjB;AAAA,EAPiB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AAAA,EAIpB,IAAI,SAAiB;AACjB,WAAO,KAAK,WAAW;AAAA,EAC3B;AAAA;AAAA,EAGA,IAAIC,GAA4C;AAC5C,WAAO,KAAK,WAAWA,CAAK;AAAA,EAChC;AAAA,EAEA,CAAC,OAAO,QAAQ,IAA+B;AAC3C,WAAO,KAAK,WAAW,OAAO,QAAQ,EAAA;AAAA,EAC1C;AACJ;AAKO,MAAMC,EAAsB;AAAA,EAC/B,YACoBC,GACAC,GACAP,GACAC,GACA3B,GACA4B,IAAsB,MACtBC,IAA0C,IAC5D;AAPkB,SAAA,QAAAG,GACA,KAAA,SAAAC,GACA,KAAA,QAAAP,GACA,KAAA,UAAAC,GACA,KAAA,YAAA3B,GACA,KAAA,OAAA4B,GACA,KAAA,QAAAC;AAAA,EACjB;AAAA,EAPiB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AAAA,EAIpB,IAAI,MAAc;AACd,WAAO,KAAK,MAAM;AAAA,EACtB;AAAA;AAAA,EAGA,IAAI,OAAe;AACf,WAAO,KAAK,MAAM;AAAA,EACtB;AAAA;AAAA,EAGA,IAAI,OAAe;AACf,WAAO,KAAK,MAAM,KAAK,GAAG,KAAK,SAAS,KAAK,GAAG;AAAA,EACpD;AAAA;AAAA,EAGA,IAAI,gBAA0E;AAC1E,WAAO,KAAK,OAAO;AAAA,EACvB;AACJ;AAQO,MAAMK,EAA4D;AAAA,EACrE,YACoBV,GACAW,GACAV,GACAC,GACAC,GACA3B,GACA4B,IAAsB,MACtBC,IAA0C,CAAA,GAC5D;AARkB,SAAA,QAAAL,GACA,KAAA,QAAAW,GACA,KAAA,aAAAV,GACA,KAAA,QAAAC,GACA,KAAA,UAAAC,GACA,KAAA,YAAA3B,GACA,KAAA,OAAA4B,GACA,KAAA,QAAAC;AAAA,EACjB;AAAA,EARiB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AAAA,EAIpB,IAAI,SAAiB;AACjB,WAAO,KAAK,WAAW;AAAA,EAC3B;AAAA;AAAA,EAGA,IAAIC,GAA+C;AAC/C,WAAO,KAAK,WAAWA,CAAK;AAAA,EAChC;AAAA,EAEA,CAAC,OAAO,QAAQ,IAAkC;AAC9C,WAAO,KAAK,WAAW,OAAO,QAAQ,EAAA;AAAA,EAC1C;AACJ;"}

package/dist/vision/tasks/base.cjs

@@ -0,0 +1,2 @@
+"use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});class e{constructor(s){this._session=s}_session;get session(){return this._session}}exports.VisionTask=e;
+//# sourceMappingURL=base.cjs.map

package/dist/vision/tasks/base.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"base.cjs","sources":["../../../src/vision/tasks/base.ts"],"sourcesContent":["/**\n * Common foundation for task-oriented vision SDK objects.\n *\n * The base only owns the {@link OrtSession} — label resolution lives in each\n * subclass because how `numClasses` is read from the model differs per task.\n */\n\nimport type { OrtSession } from \"../core/session\";\n\nexport abstract class VisionTask {\n    protected constructor(protected readonly _session: OrtSession) {}\n\n    /** The underlying {@link OrtSession} used to run inference. */\n    get session(): OrtSession {\n        return this._session;\n    }\n}\n"],"names":["VisionTask","_session"],"mappings":"gFASO,MAAeA,CAAW,CACnB,YAA+BC,EAAsB,CAAtB,KAAA,SAAAA,CAAuB,CAAvB,SAGzC,IAAI,SAAsB,CACtB,OAAO,KAAK,QAChB,CACJ"}

package/dist/vision/tasks/base.js

@@ -0,0 +1,14 @@
+class o {
+  constructor(s) {
+    this._session = s;
+  }
+  _session;
+  /** The underlying {@link OrtSession} used to run inference. */
+  get session() {
+    return this._session;
+  }
+}
+export {
+  o as VisionTask
+};
+//# sourceMappingURL=base.js.map

package/dist/vision/tasks/base.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"base.js","sources":["../../../src/vision/tasks/base.ts"],"sourcesContent":["/**\n * Common foundation for task-oriented vision SDK objects.\n *\n * The base only owns the {@link OrtSession} — label resolution lives in each\n * subclass because how `numClasses` is read from the model differs per task.\n */\n\nimport type { OrtSession } from \"../core/session\";\n\nexport abstract class VisionTask {\n    protected constructor(protected readonly _session: OrtSession) {}\n\n    /** The underlying {@link OrtSession} used to run inference. */\n    get session(): OrtSession {\n        return this._session;\n    }\n}\n"],"names":["VisionTask","_session"],"mappings":"AASO,MAAeA,EAAW;AAAA,EACnB,YAA+BC,GAAsB;AAAtB,SAAA,WAAAA;AAAA,EAAuB;AAAA,EAAvB;AAAA;AAAA,EAGzC,IAAI,UAAsB;AACtB,WAAO,KAAK;AAAA,EAChB;AACJ;"}

package/dist/vision/tasks/classifier.cjs

@@ -0,0 +1,2 @@
+"use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});const N=require("../core/session.cjs"),C=require("../io/image.cjs"),z=require("../labels.cjs"),g=require("../postprocess/classification.cjs"),h=require("../preprocess/image.cjs"),w=require("../results.cjs"),E=require("./base.cjs"),q=[.485,.456,.406],I=[.229,.224,.225];class p extends E.VisionTask{constructor(e,t,a,s,n,i,o){super(e),this._labels=t,this._names=a,this._inputSize=s,this._mean=n,this._std=i,this._applySoftmax=o}_labels;_names;_inputSize;_mean;_std;_applySoftmax;static async create(e,t){const a=await N.OrtSession.create(e,t),s=z.resolveLabels(t.labels,{numClasses:t.numClasses}),n={};for(let i=0;i<s.length;i++)n[i]=s[i];return new p(a,s,n,t.inputSize??[224,224],t.mean??q,t.std??I,t.applySoftmax??!0)}get labels(){return this._labels}get names(){return this._names}get numClasses(){return this._labels.length}async call(e,t={}){return this.predict(e,t)}async predict(e,t={}){const a=typeof e=="string"?e:null,s=await C.loadImage(e),n=this._preprocess(s),i=await this._session.run({[this._session.inputName]:n}),o=this._session.outputNames[0];if(o===void 0)throw new Error("Classifier model has no outputs.");const m=i[o];if(m===void 0)throw new Error(`Classifier model output ${o} missing from run() result.`);const _=this._postprocess(m.data),{indices:d,values:b}=g.topK(_,t.topK??null),c=[];for(let l=0;l<d.length;l++){const u=d[l],f=this._labels[u]??`class_${u}`;c.push({classId:u,className:f,probability:b[l],cls:u,name:f,conf:b[l]})}if(c.length===0)throw new Error("Classifier produced no probabilities (empty output).");const r=c[0],y={classId:r.classId,className:r.className,confidence:r.probability,cls:r.classId,name:r.className,conf:r.probability,image:s,probabilities:c},S=[s.height,s.width];return[new w.ClassificationResults(new w.Probs(_),y,this._names,s,S,a)]}_preprocess(e){const[t,a]=this._inputSize,s=h.resize(e,t,a),n=h.normalize(s,this._mean,this._std),i=h.toCHW(n,s.width,s.height,3);return h.toFloat32Tensor(i,[1,3,s.height,s.width])}_postprocess(e){return this._applySoftmax?g.softmax(e):new Float32Array(e)}}exports.Classifier=p;
+//# sourceMappingURL=classifier.cjs.map

package/dist/vision/tasks/classifier.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"classifier.cjs","sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /** Class label spec — see {@link resolveLabels}. */\n    readonly labels: LabelSpec;\n    /**\n     * Number of classes the model can predict. Required when `labels` is `null`\n     * or when you want to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /** Model input `[width, height]` in pixels. Defaults to `[224, 224]`. */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const labels = resolveLabels(options.labels, { numClasses: options.numClasses });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            options.inputSize ?? [224, 224],\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        const tensor = this._preprocess(original);\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        return [\n            new ClassificationResults(\n                new Probs(fullProbs),\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"names":["IMAGENET_MEAN","IMAGENET_STD","Classifier","VisionTask","session","_labels","_names","_inputSize","_mean","_std","_applySoftmax","model","options","OrtSession","labels","resolveLabels","names","image","path","original","loadImage","tensor","outputs","firstOutputName","raw","fullProbs","indices","values","topK","probabilities","i","id","className","top","result","orig","ClassificationResults","Probs","tw","th","resized","resize","normalized","normalize","chw","toCHW","toFloat32Tensor","softmax"],"mappings":"uTAeMA,EAAmD,CAAC,KAAO,KAAO,IAAK,EACvEC,EAAkD,CAAC,KAAO,KAAO,IAAK,EAsDrE,MAAMC,UAAmBC,EAAAA,UAAW,CAC/B,YACJC,EACiBC,EACAC,EACAC,EACAC,EACAC,EACAC,EACnB,CACE,MAAMN,CAAO,EAPI,KAAA,QAAAC,EACA,KAAA,OAAAC,EACA,KAAA,WAAAC,EACA,KAAA,MAAAC,EACA,KAAA,KAAAC,EACA,KAAA,cAAAC,CAGrB,CARqB,QACA,OACA,WACA,MACA,KACA,cAMrB,aAAa,OAAOC,EAAoBC,EAAiD,CACrF,MAAMR,EAAU,MAAMS,EAAAA,WAAW,OAAOF,EAAOC,CAAO,EAChDE,EAASC,EAAAA,cAAcH,EAAQ,OAAQ,CAAE,WAAYA,EAAQ,WAAY,EACzEI,EAAgC,CAAA,EACtC,QAAS,EAAI,EAAG,EAAIF,EAAO,OAAQ,IAC/BE,EAAM,CAAC,EAAIF,EAAO,CAAC,EAEvB,OAAO,IAAIZ,EACPE,EACAU,EACAE,EACAJ,EAAQ,WAAa,CAAC,IAAK,GAAG,EAC9BA,EAAQ,MAAQZ,EAChBY,EAAQ,KAAOX,EACfW,EAAQ,cAAgB,EAAA,CAEhC,CAGA,IAAI,QAA4B,CAC5B,OAAO,KAAK,OAChB,CAGA,IAAI,OAA0C,CAC1C,OAAO,KAAK,MAChB,CAGA,IAAI,YAAqB,CACrB,OAAO,KAAK,QAAQ,MACxB,CAGA,MAAM,KACFK,EACAL,EAAoC,GACJ,CAChC,OAAO,KAAK,QAAQK,EAAOL,CAAO,CACtC,CAGA,MAAM,QACFK,EACAL,EAAoC,GACJ,CAChC,MAAMM,EAAO,OAAOD,GAAU,SAAWA,EAAQ,KAC3CE,EAAW,MAAMC,EAAAA,UAAUH,CAAK,EAChCI,EAAS,KAAK,YAAYF,CAAQ,EAClCG,EAAU,MAAM,KAAK,SAAS,IAAI,CAAE,CAAC,KAAK,SAAS,SAAS,EAAGD,EAAQ,EACvEE,EAAkB,KAAK,SAAS,YAAY,CAAC,EACnD,GAAIA,IAAoB,OACpB,MAAM,IAAI,MAAM,kCAAkC,EAEtD,MAAMC,EAAMF,EAAQC,CAAe,EACnC,GAAIC,IAAQ,OACR,MAAM,IAAI,MACN,2BAA2BD,CAAe,6BAAA,EAGlD,MAAME,EAAY,KAAK,aAAaD,EAAI,IAAoB,EAEtD,CAAE,QAAAE,EAAS,OAAAC,GAAWC,EAAAA,KAAKH,EAAWb,EAAQ,MAAQ,IAAI,EAC1DiB,EAAoC,CAAA,EAC1C,QAASC,EAAI,EAAGA,EAAIJ,EAAQ,OAAQI,IAAK,CACrC,MAAMC,EAAKL,EAAQI,CAAC,EACdE,EAAY,KAAK,QAAQD,CAAE,GAAK,SAASA,CAAE,GACjDF,EAAc,KAAK,CACf,QAASE,EACT,UAAAC,EACA,YAAaL,EAAOG,CAAC,EACrB,IAAKC,EACL,KAAMC,EACN,KAAML,EAAOG,CAAC,CAAA,CACjB,CACL,CACA,GAAID,EAAc,SAAW,EACzB,MAAM,IAAI,MAAM,sDAAsD,EAG1E,MAAMI,EAAMJ,EAAc,CAAC,EACrBK,EAA+B,CACjC,QAASD,EAAI,QACb,UAAWA,EAAI,UACf,WAAYA,EAAI,YAChB,IAAKA,EAAI,QACT,KAAMA,EAAI,UACV,KAAMA,EAAI,YACV,MAAOd,EACP,cAAAU,CAAA,EAGEM,EAAkC,CAAChB,EAAS,OAAQA,EAAS,KAAK,EACxE,MAAO,CACH,IAAIiB,EAAAA,sBACA,IAAIC,EAAAA,MAAMZ,CAAS,EACnBS,EACA,KAAK,OACLf,EACAgB,EACAjB,CAAA,CACJ,CAER,CAEQ,YAAYD,EAA6B,CAC7C,KAAM,CAACqB,EAAIC,CAAE,EAAI,KAAK,WAChBC,EAAUC,EAAAA,OAAOxB,EAAOqB,EAAIC,CAAE,EAC9BG,EAAaC,EAAAA,UAAUH,EAAS,KAAK,MAAO,KAAK,IAAI,EACrDI,EAAMC,EAAAA,MAAMH,EAAYF,EAAQ,MAAOA,EAAQ,OAAQ,CAAC,EAC9D,OAAOM,EAAAA,gBAAgBF,EAAK,CAAC,EAAG,EAAGJ,EAAQ,OAAQA,EAAQ,KAAK,CAAC,CACrE,CAEQ,aAAahB,EAAiC,CAClD,OAAO,KAAK,cAAgBuB,EAAAA,QAAQvB,CAAG,EAAI,IAAI,aAAaA,CAAG,CACnE,CACJ"}

package/dist/vision/tasks/classifier.js

@@ -0,0 +1,106 @@
+import { OrtSession as g } from "../core/session.js";
+import { loadImage as y } from "../io/image.js";
+import { resolveLabels as N } from "../labels.js";
+import { topK as S, softmax as z } from "../postprocess/classification.js";
+import { resize as C, normalize as E, toCHW as x, toFloat32Tensor as I } from "../preprocess/image.js";
+import { ClassificationResults as T, Probs as v } from "../results.js";
+import { VisionTask as A } from "./base.js";
+const M = [0.485, 0.456, 0.406], F = [0.229, 0.224, 0.225];
+class d extends A {
+  constructor(e, t, r, s, i, o, n) {
+    super(e), this._labels = t, this._names = r, this._inputSize = s, this._mean = i, this._std = o, this._applySoftmax = n;
+  }
+  _labels;
+  _names;
+  _inputSize;
+  _mean;
+  _std;
+  _applySoftmax;
+  /** Load the model and resolve labels. */
+  static async create(e, t) {
+    const r = await g.create(e, t), s = N(t.labels, { numClasses: t.numClasses }), i = {};
+    for (let o = 0; o < s.length; o++)
+      i[o] = s[o];
+    return new d(
+      r,
+      s,
+      i,
+      t.inputSize ?? [224, 224],
+      t.mean ?? M,
+      t.std ?? F,
+      t.applySoftmax ?? !0
+    );
+  }
+  /** Class labels indexed by class id. */
+  get labels() {
+    return this._labels;
+  }
+  /** Class id → class name dict (matches Ultralytics' `model.names`). */
+  get names() {
+    return this._names;
+  }
+  /** Number of classes the model can predict. */
+  get numClasses() {
+    return this._labels.length;
+  }
+  /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */
+  async call(e, t = {}) {
+    return this.predict(e, t);
+  }
+  /** Run classification on a single image. */
+  async predict(e, t = {}) {
+    const r = typeof e == "string" ? e : null, s = await y(e), i = this._preprocess(s), o = await this._session.run({ [this._session.inputName]: i }), n = this._session.outputNames[0];
+    if (n === void 0)
+      throw new Error("Classifier model has no outputs.");
+    const p = o[n];
+    if (p === void 0)
+      throw new Error(
+        `Classifier model output ${n} missing from run() result.`
+      );
+    const h = this._postprocess(p.data), { indices: u, values: _ } = S(h, t.topK ?? null), c = [];
+    for (let l = 0; l < u.length; l++) {
+      const m = u[l], f = this._labels[m] ?? `class_${m}`;
+      c.push({
+        classId: m,
+        className: f,
+        probability: _[l],
+        cls: m,
+        name: f,
+        conf: _[l]
+      });
+    }
+    if (c.length === 0)
+      throw new Error("Classifier produced no probabilities (empty output).");
+    const a = c[0], b = {
+      classId: a.classId,
+      className: a.className,
+      confidence: a.probability,
+      cls: a.classId,
+      name: a.className,
+      conf: a.probability,
+      image: s,
+      probabilities: c
+    }, w = [s.height, s.width];
+    return [
+      new T(
+        new v(h),
+        b,
+        this._names,
+        s,
+        w,
+        r
+      )
+    ];
+  }
+  _preprocess(e) {
+    const [t, r] = this._inputSize, s = C(e, t, r), i = E(s, this._mean, this._std), o = x(i, s.width, s.height, 3);
+    return I(o, [1, 3, s.height, s.width]);
+  }
+  _postprocess(e) {
+    return this._applySoftmax ? z(e) : new Float32Array(e);
+  }
+}
+export {
+  d as Classifier
+};
+//# sourceMappingURL=classifier.js.map

package/dist/vision/tasks/classifier.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"classifier.js","sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /** Class label spec — see {@link resolveLabels}. */\n    readonly labels: LabelSpec;\n    /**\n     * Number of classes the model can predict. Required when `labels` is `null`\n     * or when you want to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /** Model input `[width, height]` in pixels. Defaults to `[224, 224]`. */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const labels = resolveLabels(options.labels, { numClasses: options.numClasses });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            options.inputSize ?? [224, 224],\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        const tensor = this._preprocess(original);\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        return [\n            new ClassificationResults(\n                new Probs(fullProbs),\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"names":["IMAGENET_MEAN","IMAGENET_STD","Classifier","VisionTask","session","_labels","_names","_inputSize","_mean","_std","_applySoftmax","model","options","OrtSession","labels","resolveLabels","names","i","image","path","original","loadImage","tensor","outputs","firstOutputName","raw","fullProbs","indices","values","topK","probabilities","id","className","top","result","orig","ClassificationResults","Probs","tw","th","resized","resize","normalized","normalize","chw","toCHW","toFloat32Tensor","softmax"],"mappings":";;;;;;;AAeA,MAAMA,IAAmD,CAAC,OAAO,OAAO,KAAK,GACvEC,IAAkD,CAAC,OAAO,OAAO,KAAK;AAsDrE,MAAMC,UAAmBC,EAAW;AAAA,EAC/B,YACJC,GACiBC,GACAC,GACAC,GACAC,GACAC,GACAC,GACnB;AACE,UAAMN,CAAO,GAPI,KAAA,UAAAC,GACA,KAAA,SAAAC,GACA,KAAA,aAAAC,GACA,KAAA,QAAAC,GACA,KAAA,OAAAC,GACA,KAAA,gBAAAC;AAAA,EAGrB;AAAA,EARqB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AAAA,EAMrB,aAAa,OAAOC,GAAoBC,GAAiD;AACrF,UAAMR,IAAU,MAAMS,EAAW,OAAOF,GAAOC,CAAO,GAChDE,IAASC,EAAcH,EAAQ,QAAQ,EAAE,YAAYA,EAAQ,YAAY,GACzEI,IAAgC,CAAA;AACtC,aAASC,IAAI,GAAGA,IAAIH,EAAO,QAAQG;AAC/B,MAAAD,EAAMC,CAAC,IAAIH,EAAOG,CAAC;AAEvB,WAAO,IAAIf;AAAA,MACPE;AAAA,MACAU;AAAA,MACAE;AAAA,MACAJ,EAAQ,aAAa,CAAC,KAAK,GAAG;AAAA,MAC9BA,EAAQ,QAAQZ;AAAA,MAChBY,EAAQ,OAAOX;AAAA,MACfW,EAAQ,gBAAgB;AAAA,IAAA;AAAA,EAEhC;AAAA;AAAA,EAGA,IAAI,SAA4B;AAC5B,WAAO,KAAK;AAAA,EAChB;AAAA;AAAA,EAGA,IAAI,QAA0C;AAC1C,WAAO,KAAK;AAAA,EAChB;AAAA;AAAA,EAGA,IAAI,aAAqB;AACrB,WAAO,KAAK,QAAQ;AAAA,EACxB;AAAA;AAAA,EAGA,MAAM,KACFM,GACAN,IAAoC,IACJ;AAChC,WAAO,KAAK,QAAQM,GAAON,CAAO;AAAA,EACtC;AAAA;AAAA,EAGA,MAAM,QACFM,GACAN,IAAoC,IACJ;AAChC,UAAMO,IAAO,OAAOD,KAAU,WAAWA,IAAQ,MAC3CE,IAAW,MAAMC,EAAUH,CAAK,GAChCI,IAAS,KAAK,YAAYF,CAAQ,GAClCG,IAAU,MAAM,KAAK,SAAS,IAAI,EAAE,CAAC,KAAK,SAAS,SAAS,GAAGD,GAAQ,GACvEE,IAAkB,KAAK,SAAS,YAAY,CAAC;AACnD,QAAIA,MAAoB;AACpB,YAAM,IAAI,MAAM,kCAAkC;AAEtD,UAAMC,IAAMF,EAAQC,CAAe;AACnC,QAAIC,MAAQ;AACR,YAAM,IAAI;AAAA,QACN,2BAA2BD,CAAe;AAAA,MAAA;AAGlD,UAAME,IAAY,KAAK,aAAaD,EAAI,IAAoB,GAEtD,EAAE,SAAAE,GAAS,QAAAC,MAAWC,EAAKH,GAAWd,EAAQ,QAAQ,IAAI,GAC1DkB,IAAoC,CAAA;AAC1C,aAASb,IAAI,GAAGA,IAAIU,EAAQ,QAAQV,KAAK;AACrC,YAAMc,IAAKJ,EAAQV,CAAC,GACde,IAAY,KAAK,QAAQD,CAAE,KAAK,SAASA,CAAE;AACjD,MAAAD,EAAc,KAAK;AAAA,QACf,SAASC;AAAA,QACT,WAAAC;AAAA,QACA,aAAaJ,EAAOX,CAAC;AAAA,QACrB,KAAKc;AAAA,QACL,MAAMC;AAAA,QACN,MAAMJ,EAAOX,CAAC;AAAA,MAAA,CACjB;AAAA,IACL;AACA,QAAIa,EAAc,WAAW;AACzB,YAAM,IAAI,MAAM,sDAAsD;AAG1E,UAAMG,IAAMH,EAAc,CAAC,GACrBI,IAA+B;AAAA,MACjC,SAASD,EAAI;AAAA,MACb,WAAWA,EAAI;AAAA,MACf,YAAYA,EAAI;AAAA,MAChB,KAAKA,EAAI;AAAA,MACT,MAAMA,EAAI;AAAA,MACV,MAAMA,EAAI;AAAA,MACV,OAAOb;AAAA,MACP,eAAAU;AAAA,IAAA,GAGEK,IAAkC,CAACf,EAAS,QAAQA,EAAS,KAAK;AACxE,WAAO;AAAA,MACH,IAAIgB;AAAA,QACA,IAAIC,EAAMX,CAAS;AAAA,QACnBQ;AAAA,QACA,KAAK;AAAA,QACLd;AAAA,QACAe;AAAA,QACAhB;AAAA,MAAA;AAAA,IACJ;AAAA,EAER;AAAA,EAEQ,YAAYD,GAA6B;AAC7C,UAAM,CAACoB,GAAIC,CAAE,IAAI,KAAK,YAChBC,IAAUC,EAAOvB,GAAOoB,GAAIC,CAAE,GAC9BG,IAAaC,EAAUH,GAAS,KAAK,OAAO,KAAK,IAAI,GACrDI,IAAMC,EAAMH,GAAYF,EAAQ,OAAOA,EAAQ,QAAQ,CAAC;AAC9D,WAAOM,EAAgBF,GAAK,CAAC,GAAG,GAAGJ,EAAQ,QAAQA,EAAQ,KAAK,CAAC;AAAA,EACrE;AAAA,EAEQ,aAAaf,GAAiC;AAClD,WAAO,KAAK,gBAAgBsB,EAAQtB,CAAG,IAAI,IAAI,aAAaA,CAAG;AAAA,EACnE;AACJ;"}

package/dist/vision/tasks/detector.cjs

@@ -0,0 +1,2 @@
+"use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});const D=require("../core/session.cjs"),S=require("../io/image.cjs"),q=require("../labels.cjs"),A=require("../postprocess/detection.cjs"),g=require("../preprocess/image.cjs"),x=require("../results.cjs"),I=require("./base.cjs"),T=require("../types.cjs");class b extends I.VisionTask{constructor(o,t,n,e,r,a,s,c){super(o),this._head=t,this._labels=n,this._names=e,this._inputSize=r,this._confThreshold=a,this._iouThreshold=s,this._maxDetections=c}_head;_labels;_names;_inputSize;_confThreshold;_iouThreshold;_maxDetections;static async create(o,t={}){const n=t.head??"yolo";if(n!=="yolo")throw new Error(`Unsupported detector head '${n}'. Supported: 'yolo'.`);const e=await D.OrtSession.create(o,t),r=q.resolveLabels(t.labels??"coco",{numClasses:t.numClasses}),a={};for(let s=0;s<r.length;s++)a[s]=r[s];return new b(e,n,r,a,t.inputSize??[640,640],t.confThreshold??.25,t.iouThreshold??.45,t.maxDetections??300)}get head(){return this._head}get labels(){return this._labels}get names(){return this._names}get numClasses(){return this._labels.length}async call(o,t={}){return this.predict(o,t)}async predict(o,t={}){const n=typeof o=="string"?o:null,e=await S.loadImage(o),{tensor:r,scale:a,padLeft:s,padTop:c}=this._preprocess(e),u=await this._session.run({[this._session.inputName]:r}),h=this._session.outputNames[0];if(h===void 0)throw new Error("Detector model has no outputs.");const d=u[h];if(d===void 0)throw new Error(`Detector model output ${h} missing from run() result.`);const m=A.decodeYolo(d.data,d.dims,{originalWidth:e.width,originalHeight:e.height,padLeft:s,padTop:c,scale:a,confThreshold:t.confThreshold??this._confThreshold,iouThreshold:t.iouThreshold??this._iouThreshold,maxDetections:this._maxDetections}),_=(t.classes!==void 0?(()=>{const i=new Set(t.classes);return m.filter(p=>i.has(p.classId))})():m).map(i=>this._buildResult(e,i.bbox,i.classId,i.confidence)),l=[e.height,e.width];return[new x.DetectionResults(this._buildBoxes(_,l),_,this._names,e,l,n)]}_preprocess(o){const[t,n]=this._inputSize,e=g.letterbox(o,t,n),r=g.toFloat32(e.image),a=g.toCHW(r,e.image.width,e.image.height,3);return{tensor:g.toFloat32Tensor(a,[1,3,e.image.height,e.image.width]),scale:e.scale,padLeft:e.padLeft,padTop:e.padTop}}_buildResult(o,t,n,e){const[r,a,s,c]=t.asIntXyxy(),u=Math.max(0,r),h=Math.max(0,a),d=Math.min(o.width,s),m=Math.min(o.height,c);let w;if(d>u&&m>h){const l=d-u,i=m-h,p=new Uint8Array(l*i*3);for(let f=0;f<i;f++){const y=((h+f)*o.width+u)*3;p.set(o.data.subarray(y,y+l*3),f*l*3)}w=new T.RGBImage(p,l,i)}else w=new T.RGBImage(new Uint8Array(0),0,0);const _=this._names[n]??`class_${n}`;return{classId:n,className:_,confidence:e,bbox:t,cls:n,name:_,conf:e,box:t,croppedImage:w}}_buildBoxes(o,t){const n=o.length,e=new Float32Array(n*4),r=new Int32Array(n),a=new Float32Array(n);for(let s=0;s<n;s++){const c=o[s];e[s*4]=c.bbox.x1,e[s*4+1]=c.bbox.y1,e[s*4+2]=c.bbox.x2,e[s*4+3]=c.bbox.y2,r[s]=c.classId,a[s]=c.confidence}return new x.Boxes(e,r,a,t)}}exports.Detector=b;
+//# sourceMappingURL=detector.cjs.map