tempest-react-sdk 0.38.3 → 0.39.0

package/dist/vision/fusion.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"fusion.js","names":[],"sources":["../../src/vision/fusion.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * The contract a fused pipeline carries inside its own `.onnx` file.\n *\n * A pipeline built by the Python SDK's `ort_vision_sdk.compose` is a single\n * graph that already contains the detector, the crop-and-resize bridge and the\n * classifier. Everything the runtime needs to drive it — the letterbox\n * resolution, the crop resolution, where the crops come from, how many\n * detections the graph emits, the class names of both stages — was decided at\n * fusion time and written into the model's metadata.\n *\n * This module reads it back. It is the browser half of a contract whose other\n * half lives in `ort_vision_sdk/fusion.py`: the same keys, the same encodings,\n * the same fallbacks. A pipeline fused once therefore runs identically in\n * Python and in a browser tab, off the same file.\n *\n * Building a pipeline stays a Python-side build step — there is no ONNX\n * protobuf writer here, and there is no reason for one: fusing is something you\n * do once next to your export pipeline, not in a page load.\n */\n\nimport { parseNames } from \"./core/metadata\";\n\n/**\n * Which tensor the bridge crops the detected boxes out of.\n *\n * - `\"detector_input\"`: the letterboxed tensor already fed to the detector.\n *   The fused graph then has a **single** image input, but a small object is\n *   cropped out of its downscaled copy.\n * - `\"original\"`: a second, full-resolution image input. The bridge undoes the\n *   letterbox transform in-graph and crops at native resolution. Two tensors to\n *   feed, still one session and one model load.\n */\nexport type CropSource = \"detector_input\" | \"original\";\n\n/** Value of the `ovs.kind` metadata key for a detector→classifier pipeline. */\nexport const FUSION_KIND_DETECT_CLASSIFY = \"detect_classify\";\n\n/**\n * Namespace for every metadata key the fusion writes.\n *\n * Namespaced on purpose: the detector's own Ultralytics metadata (`names`,\n * `task`, `imgsz`) is carried over into the fused model, and an un-prefixed key\n * would either collide with it or be mistaken for it.\n */\nexport const METADATA_PREFIX = \"ovs.\";\n\n/** Name of the fused graph's letterboxed detector input, `[1, 3, H, W]` float32 in `[0, 1]`. */\nexport const INPUT_IMAGE = \"images\";\n\n/** Name of the full-resolution input. Present only when `cropSource === \"original\"`. */\nexport const INPUT_SOURCE = \"source_image\";\n\n/** Name of the `[1]` float32 letterbox scale factor. Only with `cropSource === \"original\"`. */\nexport const INPUT_SCALE = \"letterbox_scale\";\n\n/** Name of the `[2]` float32 `[padLeft, padTop]`. Only with `cropSource === \"original\"`. */\nexport const INPUT_PAD = \"letterbox_pad\";\n\n/** Name of the `[K, 4]` float32 xyxy output, in **letterboxed** input pixels. */\nexport const OUTPUT_BOXES = \"boxes\";\n\n/** Name of the `[K]` float32 detection-confidence output. */\nexport const OUTPUT_SCORES = \"scores\";\n\n/** Name of the `[K]` int64 detector-class output. */\nexport const OUTPUT_CLASSES = \"classes\";\n\n/** Name of the `[1]` int64 output holding how many of the `K` rows are real. */\nexport const OUTPUT_NUM_DETECTIONS = \"num_detections\";\n\n/** Name of the `[K, numClassifierClasses]` float32 classifier output, one row per box. */\nexport const OUTPUT_PROBS = \"probs\";\n\n/** Everything a fused pipeline declares about how it must be driven. */\nexport interface FusionSpec {\n    /** Pipeline family. Only `\"detect_classify\"` exists today. */\n    readonly kind: string;\n    /** `[width, height]` the detector stage expects — the resolution to letterbox to. */\n    readonly inputSize: readonly [number, number];\n    /** `[width, height]` every crop is resampled to inside the graph. */\n    readonly cropSize: readonly [number, number];\n    /** Which tensor the crops are taken from. */\n    readonly cropSource: CropSource;\n    /**\n     * Fixed number of rows `K` every output carries, surplus zero-padded and\n     * counted by {@link OUTPUT_NUM_DETECTIONS}. `null` means the graph emits\n     * exactly as many rows as survived NMS.\n     */\n    readonly maxDetections: number | null;\n    /** Score threshold baked into the graph's NMS node. */\n    readonly confThreshold: number;\n    /** IoU threshold baked into the graph's NMS node. */\n    readonly iouThreshold: number;\n    /** Whether the classifier stage emits logits that still need a softmax. */\n    readonly applySoftmax: boolean;\n    /** Detector class names in class-id order, or `null` when the fusion recorded none. */\n    readonly detectorNames: readonly string[] | null;\n    /** Classifier class names in class-id order, or `null`. */\n    readonly classifierNames: readonly string[] | null;\n    /** Version of `ort-vision-sdk` that produced the file. */\n    readonly sdkVersion: string;\n    /** Whether driving this pipeline requires feeding the full-resolution input. */\n    readonly needsSourceImage: boolean;\n}\n\nconst KEY_KIND = \"kind\";\nconst KEY_SDK_VERSION = \"sdk_version\";\nconst KEY_INPUT_SIZE = \"input_size\";\nconst KEY_CROP_SIZE = \"crop_size\";\nconst KEY_CROP_SOURCE = \"crop_source\";\nconst KEY_MAX_DETECTIONS = \"max_detections\";\nconst KEY_CONF_THRESHOLD = \"conf_threshold\";\nconst KEY_IOU_THRESHOLD = \"iou_threshold\";\nconst KEY_APPLY_SOFTMAX = \"apply_softmax\";\nconst KEY_DETECTOR_NAMES = \"detector_names\";\nconst KEY_CLASSIFIER_NAMES = \"classifier_names\";\n\nconst DYNAMIC = \"dynamic\";\n\n/**\n * Decode a `\"640,640\"` pair.\n *\n * @param raw The encoded pair.\n * @returns `[width, height]`, or `null` when the value is missing or malformed.\n */\nfunction decodeSize(raw: string | undefined): readonly [number, number] | null {\n    if (!raw) return null;\n    const parts = raw.split(\",\");\n    if (parts.length !== 2) return null;\n    const width = Number(parts[0]);\n    const height = Number(parts[1]);\n    if (!Number.isInteger(width) || !Number.isInteger(height)) return null;\n    if (width < 1 || height < 1) return null;\n    return [width, height];\n}\n\n/**\n * Decode a float, falling back when the value is missing or malformed.\n *\n * @param raw The encoded value.\n * @param fallback Value to use when `raw` cannot be read.\n * @returns The parsed number, or `fallback`.\n */\nfunction decodeFloat(raw: string | undefined, fallback: number): number {\n    if (!raw) return fallback;\n    const value = Number(raw);\n    return Number.isFinite(value) ? value : fallback;\n}\n\n/**\n * Read a pipeline spec out of a model's custom metadata.\n *\n * Individual malformed entries fall back to the value a fusion would have used\n * by default — a single bad float is not a reason to reject an otherwise\n * loadable pipeline. A malformed resolution is fatal, because there is no safe\n * default for one.\n *\n * @param metadata A model's custom metadata map, as read by\n *   {@link readModelMetadata}.\n * @returns The decoded spec, or `null` when the model is not a fused pipeline —\n *   it carries no `ovs.kind` entry, or one naming a pipeline kind this version\n *   does not know how to drive.\n */\nexport function readFusionSpec(\n    metadata: Readonly<Record<string, string>> | undefined,\n): FusionSpec | null {\n    if (!metadata) return null;\n\n    const read: Record<string, string> = {};\n    for (const [key, value] of Object.entries(metadata)) {\n        if (key.startsWith(METADATA_PREFIX)) read[key.slice(METADATA_PREFIX.length)] = value;\n    }\n    if (read[KEY_KIND] !== FUSION_KIND_DETECT_CLASSIFY) return null;\n\n    const inputSize = decodeSize(read[KEY_INPUT_SIZE]);\n    const cropSize = decodeSize(read[KEY_CROP_SIZE]);\n    if (inputSize === null || cropSize === null) return null;\n\n    const rawMax = read[KEY_MAX_DETECTIONS] ?? DYNAMIC;\n    const parsedMax = Number(rawMax);\n    const maxDetections =\n        rawMax === DYNAMIC || !Number.isInteger(parsedMax) || parsedMax < 1 ? null : parsedMax;\n\n    const cropSource: CropSource =\n        read[KEY_CROP_SOURCE] === \"original\" ? \"original\" : \"detector_input\";\n\n    return {\n        kind: FUSION_KIND_DETECT_CLASSIFY,\n        inputSize,\n        cropSize,\n        cropSource,\n        maxDetections,\n        confThreshold: decodeFloat(read[KEY_CONF_THRESHOLD], 0.25),\n        iouThreshold: decodeFloat(read[KEY_IOU_THRESHOLD], 0.45),\n        applySoftmax: (read[KEY_APPLY_SOFTMAX] ?? \"1\") !== \"0\",\n        detectorNames: parseNames(read[KEY_DETECTOR_NAMES]),\n        classifierNames: parseNames(read[KEY_CLASSIFIER_NAMES]),\n        sdkVersion: read[KEY_SDK_VERSION] ?? \"\",\n        needsSourceImage: cropSource === \"original\",\n    };\n}\n"],"mappings":";;AAoCA,IAAa,IAA8B,mBAS9B,IAAkB,QAGlB,IAAc,UAGd,IAAe,gBAGf,IAAc,mBAGd,IAAY,iBAGZ,IAAe,SAGf,IAAgB,UAGhB,IAAiB,WAGjB,IAAwB,kBAGxB,IAAe,SAkCtB,IAAW,QACX,IAAkB,eAClB,IAAiB,cACjB,IAAgB,aAChB,IAAkB,eAClB,IAAqB,kBACrB,IAAqB,kBACrB,IAAoB,iBACpB,IAAoB,iBACpB,IAAqB,kBACrB,IAAuB,oBAEvB,IAAU;AAQhB,SAAS,EAAW,GAA2D;CAC3E,IAAI,CAAC,GAAK,OAAO;CACjB,IAAM,IAAQ,EAAI,MAAM,GAAG;CAC3B,IAAI,EAAM,WAAW,GAAG,OAAO;CAC/B,IAAM,IAAQ,OAAO,EAAM,EAAE,GACvB,IAAS,OAAO,EAAM,EAAE;CAG9B,OAFI,CAAC,OAAO,UAAU,CAAK,KAAK,CAAC,OAAO,UAAU,CAAM,KACpD,IAAQ,KAAK,IAAS,IAAU,OAC7B,CAAC,GAAO,CAAM;AACzB;AASA,SAAS,EAAY,GAAyB,GAA0B;CACpE,IAAI,CAAC,GAAK,OAAO;CACjB,IAAM,IAAQ,OAAO,CAAG;CACxB,OAAO,OAAO,SAAS,CAAK,IAAI,IAAQ;AAC5C;AAgBA,SAAgB,EACZ,GACiB;CACjB,IAAI,CAAC,GAAU,OAAO;CAEtB,IAAM,IAA+B,CAAC;CACtC,KAAK,IAAM,CAAC,GAAK,MAAU,OAAO,QAAQ,CAAQ,GAC9C,AAAI,EAAI,WAAA,MAA0B,MAAG,EAAK,EAAI,MAAM,CAAsB,KAAK;CAEnF,IAAI,EAAK,OAAA,mBAA2C,OAAO;CAE3D,IAAM,IAAY,EAAW,EAAK,EAAe,GAC3C,IAAW,EAAW,EAAK,EAAc;CAC/C,IAAI,MAAc,QAAQ,MAAa,MAAM,OAAO;CAEpD,IAAM,IAAS,EAAK,MAAuB,GACrC,IAAY,OAAO,CAAM,GACzB,IACF,MAAW,KAAW,CAAC,OAAO,UAAU,CAAS,KAAK,IAAY,IAAI,OAAO,GAE3E,IACF,EAAK,OAAqB,aAAa,aAAa;CAExD,OAAO;EACH,MAAM;EACN;EACA;EACA;EACA;EACA,eAAe,EAAY,EAAK,IAAqB,GAAI;EACzD,cAAc,EAAY,EAAK,IAAoB,GAAI;EACvD,eAAe,EAAK,MAAsB,SAAS;EACnD,eAAe,EAAW,EAAK,EAAmB;EAClD,iBAAiB,EAAW,EAAK,EAAqB;EACtD,YAAY,EAAK,MAAoB;EACrC,kBAAkB,MAAe;CACrC;AACJ"}

package/dist/vision/index.cjs

@@ -1,2 +1,2 @@
-const e=require("./core/exceptions.cjs"),t=require("./types.cjs"),n=require("./core/timing.cjs"),r=require("./results.cjs"),i=require("./labels.cjs"),a=require("./core/graph.cjs"),o=require("./core/metadata.cjs"),s=require("./core/providers.cjs"),c=require("./core/session.cjs"),l=require("./io/image.cjs"),u=require("./preprocess/image.cjs"),d=require("./postprocess/classification.cjs"),f=require("./postprocess/detection.cjs"),p=require("./postprocess/segmentation.cjs"),m=require("./tasks/base.cjs"),h=require("./tasks/classifier.cjs"),g=require("./tasks/detector.cjs"),_=require("./tasks/segmenter.cjs");var v=`0.5.1`;exports.BoundingBox=t.BoundingBox,exports.Boxes=r.Boxes,exports.COCO_CLASSES=i.COCO_CLASSES,exports.ClassificationResults=r.ClassificationResults,exports.Classifier=h.Classifier,exports.DEFAULT_PROVIDERS=s.DEFAULT_PROVIDERS,exports.DetectionResults=r.DetectionResults,exports.Detector=g.Detector,exports.ImageLoadError=e.ImageLoadError,exports.InferenceError=e.InferenceError,exports.LabelMapError=e.LabelMapError,exports.Mask=t.Mask,exports.Masks=r.Masks,exports.ModelLoadError=e.ModelLoadError,exports.OrtSession=c.OrtSession,exports.OrtVisionError=e.OrtVisionError,exports.Probs=r.Probs,exports.ProviderNotAvailableError=e.ProviderNotAvailableError,exports.RGBImage=t.RGBImage,exports.SegmentationResults=r.SegmentationResults,exports.Segmenter=_.Segmenter,exports.SpeedTimer=n.SpeedTimer,exports.VERSION=v,exports.VisionTask=m.VisionTask,exports.batchedNms=f.batchedNms,exports.classificationNumClasses=a.classificationNumClasses,exports.declaredShapesFrom=a.declaredShapesFrom,exports.decodeYolo=f.decodeYolo,exports.decodeYoloAnchors=f.decodeYoloAnchors,exports.decodeYoloSeg=p.decodeYoloSeg,exports.decodeYoloV8=f.decodeYoloV8,exports.decodeYoloV8Anchors=f.decodeYoloV8Anchors,exports.decodeYoloV8Seg=p.decodeYoloV8Seg,exports.detectionNumClasses=a.detectionNumClasses,exports.fromCv2=u.fromCv2,exports.letterbox=u.letterbox,exports.loadImage=l.loadImage,exports.modelNames=o.modelNames,exports.nms=f.nms,exports.normalize=u.normalize,exports.readModelMetadata=o.readModelMetadata,exports.resize=u.resize,exports.resolveInputSize=a.resolveInputSize,exports.resolveLabels=i.resolveLabels,exports.resolveProviders=s.resolveProviders,exports.softmax=d.softmax,exports.spatialInputSize=a.spatialInputSize,exports.toCHW=u.toCHW,exports.toCv2=u.toCv2,exports.toFloat32=u.toFloat32,exports.toFloat32Tensor=u.toFloat32Tensor,exports.toTensor=u.toTensor,exports.topK=d.topK;
+const e=require("./core/exceptions.cjs"),t=require("./types.cjs"),n=require("./core/timing.cjs"),r=require("./results.cjs"),i=require("./labels.cjs"),a=require("./core/graph.cjs"),o=require("./core/metadata.cjs"),s=require("./core/providers.cjs"),c=require("./core/session.cjs"),l=require("./io/image.cjs"),u=require("./fusion.cjs"),d=require("./preprocess/image.cjs"),f=require("./preprocess/pipeline.cjs"),p=require("./postprocess/classification.cjs"),m=require("./postprocess/detection.cjs"),h=require("./postprocess/segmentation.cjs"),g=require("./tasks/base.cjs"),_=require("./tasks/classifier.cjs"),v=require("./tasks/detectClassify.cjs"),y=require("./tasks/detector.cjs"),b=require("./tasks/segmenter.cjs");var x=`0.6.1`;exports.BoundingBox=t.BoundingBox,exports.Boxes=r.Boxes,exports.COCO_CLASSES=i.COCO_CLASSES,exports.ClassificationResults=r.ClassificationResults,exports.Classifier=_.Classifier,exports.DEFAULT_PROVIDERS=s.DEFAULT_PROVIDERS,exports.DetectClassify=v.DetectClassify,exports.DetectClassifyResults=r.DetectClassifyResults,exports.DetectionResults=r.DetectionResults,exports.Detector=y.Detector,exports.FUSION_KIND_DETECT_CLASSIFY=u.FUSION_KIND_DETECT_CLASSIFY,exports.FusionError=e.FusionError,exports.INPUT_IMAGE=u.INPUT_IMAGE,exports.INPUT_PAD=u.INPUT_PAD,exports.INPUT_SCALE=u.INPUT_SCALE,exports.INPUT_SOURCE=u.INPUT_SOURCE,exports.ImageLoadError=e.ImageLoadError,exports.InferenceError=e.InferenceError,exports.LabelMapError=e.LabelMapError,exports.LetterboxPipeline=f.LetterboxPipeline,exports.METADATA_PREFIX=u.METADATA_PREFIX,exports.Mask=t.Mask,exports.Masks=r.Masks,exports.ModelLoadError=e.ModelLoadError,exports.NoDetectionsError=e.NoDetectionsError,exports.OUTPUT_BOXES=u.OUTPUT_BOXES,exports.OUTPUT_CLASSES=u.OUTPUT_CLASSES,exports.OUTPUT_NUM_DETECTIONS=u.OUTPUT_NUM_DETECTIONS,exports.OUTPUT_PROBS=u.OUTPUT_PROBS,exports.OUTPUT_SCORES=u.OUTPUT_SCORES,exports.OrtSession=c.OrtSession,exports.OrtVisionError=e.OrtVisionError,exports.Probs=r.Probs,exports.ProviderNotAvailableError=e.ProviderNotAvailableError,exports.RGBImage=t.RGBImage,exports.SegmentationResults=r.SegmentationResults,exports.Segmenter=b.Segmenter,exports.SpeedTimer=n.SpeedTimer,exports.VERSION=x,exports.VisionTask=g.VisionTask,exports.batchedNms=m.batchedNms,exports.classificationNumClasses=a.classificationNumClasses,exports.declaredShapesFrom=a.declaredShapesFrom,exports.decodeYolo=m.decodeYolo,exports.decodeYoloAnchors=m.decodeYoloAnchors,exports.decodeYoloSeg=h.decodeYoloSeg,exports.defaultLabels=i.defaultLabels,exports.detectionNumClasses=a.detectionNumClasses,exports.fromCv2=d.fromCv2,exports.letterbox=d.letterbox,exports.letterboxToTensorData=f.letterboxToTensorData,exports.loadImage=l.loadImage,exports.modelNames=o.modelNames,exports.nms=m.nms,exports.normalize=d.normalize,exports.parseNames=o.parseNames,exports.readFusionSpec=u.readFusionSpec,exports.readModelMetadata=o.readModelMetadata,exports.requireDetections=g.requireDetections,exports.resize=d.resize,exports.resolveInputSize=a.resolveInputSize,exports.resolveLabels=i.resolveLabels,exports.resolveProviders=s.resolveProviders,exports.softmax=p.softmax,exports.spatialInputSize=a.spatialInputSize,exports.toCHW=d.toCHW,exports.toCv2=d.toCv2,exports.toFloat32=d.toFloat32,exports.toFloat32Tensor=d.toFloat32Tensor,exports.toTensor=d.toTensor,exports.topK=p.topK,exports.zeroTensorData=f.zeroTensorData;
 //# sourceMappingURL=index.cjs.map

package/dist/vision/index.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"index.cjs","names":[],"sources":["../../src/vision/index.ts"],"sourcesContent":["/**\n * `tempest-react-sdk/vision` — browser computer-vision inference with ONNX\n * Runtime Web (classification, detection, segmentation).\n *\n * Vendored from `@mauriciobenjamin700/ort-vision-sdk-web@0.5.1` (MIT, same\n * author) so it ships inside this SDK without an extra package install.\n * `onnxruntime-web` stays an optional peer dependency — install it (and ship\n * the matching `.wasm` files) only when you use this subpath.\n *\n * Do not hand-edit — regenerate with `npm run vendor:vision`.\n */\n\nexport {\n    BoundingBox,\n    Mask,\n    RGBImage,\n    type ClassProbability,\n    type ClassificationResult,\n    type DetectionResult,\n    type SegmentationResult,\n} from \"./types\";\n\nexport {\n    Boxes,\n    ClassificationResults,\n    DetectionResults,\n    Masks,\n    Probs,\n    SegmentationResults,\n} from \"./results\";\n\nexport { COCO_CLASSES, type LabelSpec, type ResolveLabelsOptions, resolveLabels } from \"./labels\";\n\nexport {\n    ImageLoadError,\n    InferenceError,\n    LabelMapError,\n    ModelLoadError,\n    OrtVisionError,\n    ProviderNotAvailableError,\n} from \"./core/exceptions\";\n\nexport { type ModelSource, type OrtSessionOptions, OrtSession } from \"./core/session\";\nexport {\n    type DeclaredDim,\n    type DeclaredShape,\n    type ResolveInputSizeOptions,\n    classificationNumClasses,\n    declaredShapesFrom,\n    detectionNumClasses,\n    resolveInputSize,\n    spatialInputSize,\n} from \"./core/graph\";\nexport { modelNames, readModelMetadata } from \"./core/metadata\";\nexport { DEFAULT_PROVIDERS, resolveProviders } from \"./core/providers\";\nexport { type Speed, SpeedTimer } from \"./core/timing\";\n\nexport { type ImageInput, loadImage } from \"./io/image\";\n\nexport {\n    type LetterboxResult,\n    fromCv2,\n    letterbox,\n    normalize,\n    resize,\n    toCHW,\n    toCv2,\n    toFloat32,\n    toFloat32Tensor,\n    toTensor,\n} from \"./preprocess/image\";\n\nexport { type TopKResult, softmax, topK } from \"./postprocess/classification\";\n\nexport {\n    type DecodeYoloAnchorsOptions,\n    type DecodeYoloOptions,\n    type DecodeYoloV8AnchorsOptions,\n    type DecodeYoloV8Options,\n    type DecodedAnchors,\n    type DecodedDetection,\n    batchedNms,\n    decodeYolo,\n    decodeYoloAnchors,\n    decodeYoloV8,\n    decodeYoloV8Anchors,\n    nms,\n} from \"./postprocess/detection\";\n\nexport {\n    type DecodeYoloSegOptions,\n    type DecodeYoloV8SegOptions,\n    type DecodedSegmentation,\n    decodeYoloSeg,\n    decodeYoloV8Seg,\n} from \"./postprocess/segmentation\";\n\nexport { VisionTask } from \"./tasks/base\";\nexport {\n    type ClassifierOptions,\n    type ClassifierPredictOptions,\n    Classifier,\n} from \"./tasks/classifier\";\nexport {\n    type DetectorHead,\n    type DetectorOptions,\n    type DetectorPredictOptions,\n    Detector,\n} from \"./tasks/detector\";\nexport {\n    type SegmenterHead,\n    type SegmenterOptions,\n    type SegmenterPredictOptions,\n    Segmenter,\n} from \"./tasks/segmenter\";\n\nexport const VERSION: string = \"0.5.1\";\n"],"mappings":"imBAoHA,IAAa,EAAkB"}
+{"version":3,"file":"index.cjs","names":[],"sources":["../../src/vision/index.ts"],"sourcesContent":["/**\n * `tempest-react-sdk/vision` — browser computer-vision inference with ONNX\n * Runtime Web (classification, detection, segmentation).\n *\n * Vendored from `@mauriciobenjamin700/ort-vision-sdk-web@0.6.1` (MIT, same\n * author) so it ships inside this SDK without an extra package install.\n * `onnxruntime-web` stays an optional peer dependency — install it (and ship\n * the matching `.wasm` files) only when you use this subpath.\n *\n * Do not hand-edit — regenerate with `npm run vendor:vision`.\n */\n\nexport {\n    BoundingBox,\n    Mask,\n    RGBImage,\n    type ClassProbability,\n    type ClassificationResult,\n    type DetectionResult,\n    type SegmentationResult,\n} from \"./types\";\n\nexport {\n    Boxes,\n    ClassificationResults,\n    DetectClassifyResults,\n    DetectionResults,\n    Masks,\n    Probs,\n    SegmentationResults,\n} from \"./results\";\n\nexport {\n    COCO_CLASSES,\n    type LabelSpec,\n    type ResolveLabelsOptions,\n    defaultLabels,\n    resolveLabels,\n} from \"./labels\";\n\nexport {\n    FusionError,\n    ImageLoadError,\n    InferenceError,\n    LabelMapError,\n    ModelLoadError,\n    NoDetectionsError,\n    OrtVisionError,\n    ProviderNotAvailableError,\n} from \"./core/exceptions\";\n\nexport { type ModelSource, type OrtSessionOptions, OrtSession } from \"./core/session\";\nexport {\n    type DeclaredDim,\n    type DeclaredShape,\n    type ResolveInputSizeOptions,\n    classificationNumClasses,\n    declaredShapesFrom,\n    detectionNumClasses,\n    resolveInputSize,\n    spatialInputSize,\n} from \"./core/graph\";\nexport { modelNames, parseNames, readModelMetadata } from \"./core/metadata\";\nexport { DEFAULT_PROVIDERS, resolveProviders } from \"./core/providers\";\nexport { type Speed, SpeedTimer } from \"./core/timing\";\n\nexport { type ImageInput, loadImage } from \"./io/image\";\n\nexport {\n    FUSION_KIND_DETECT_CLASSIFY,\n    INPUT_IMAGE,\n    INPUT_PAD,\n    INPUT_SCALE,\n    INPUT_SOURCE,\n    METADATA_PREFIX,\n    OUTPUT_BOXES,\n    OUTPUT_CLASSES,\n    OUTPUT_NUM_DETECTIONS,\n    OUTPUT_PROBS,\n    OUTPUT_SCORES,\n    type CropSource,\n    type FusionSpec,\n    readFusionSpec,\n} from \"./fusion\";\n\nexport {\n    type LetterboxResult,\n    fromCv2,\n    letterbox,\n    normalize,\n    resize,\n    toCHW,\n    toCv2,\n    toFloat32,\n    toFloat32Tensor,\n    toTensor,\n} from \"./preprocess/image\";\n\nexport {\n    type FusedLetterboxResult,\n    LetterboxPipeline,\n    letterboxToTensorData,\n    zeroTensorData,\n} from \"./preprocess/pipeline\";\n\nexport { type TopKResult, softmax, topK } from \"./postprocess/classification\";\n\nexport {\n    type DecodeYoloAnchorsOptions,\n    type DecodeYoloOptions,\n    type DecodedAnchors,\n    type DecodedDetection,\n    batchedNms,\n    decodeYolo,\n    decodeYoloAnchors,\n    nms,\n} from \"./postprocess/detection\";\n\nexport {\n    type DecodeYoloSegOptions,\n    type DecodedSegmentation,\n    decodeYoloSeg,\n} from \"./postprocess/segmentation\";\n\nexport { VisionTask, requireDetections } from \"./tasks/base\";\nexport {\n    type ClassifierOptions,\n    type ClassifierPredictOptions,\n    Classifier,\n} from \"./tasks/classifier\";\nexport {\n    type DetectClassifyOptions,\n    type DetectClassifyPredictOptions,\n    DetectClassify,\n} from \"./tasks/detectClassify\";\nexport {\n    type DetectorHead,\n    type DetectorOptions,\n    type DetectorPredictOptions,\n    Detector,\n} from \"./tasks/detector\";\nexport {\n    type SegmenterHead,\n    type SegmenterOptions,\n    type SegmenterPredictOptions,\n    Segmenter,\n} from \"./tasks/segmenter\";\n\nexport const VERSION: string = \"0.6.1\";\n"],"mappings":"0sBAoJA,IAAa,EAAkB"}

package/dist/vision/index.js

@@ -1,24 +1,27 @@
-import { ImageLoadError as e, InferenceError as t, LabelMapError as n, ModelLoadError as r, OrtVisionError as i, ProviderNotAvailableError as a } from "./core/exceptions.js";
-import { BoundingBox as o, Mask as s, RGBImage as c } from "./types.js";
-import { SpeedTimer as l } from "./core/timing.js";
-import { Boxes as u, ClassificationResults as d, DetectionResults as f, Masks as p, Probs as m, SegmentationResults as h } from "./results.js";
-import { COCO_CLASSES as g, resolveLabels as _ } from "./labels.js";
-import { classificationNumClasses as v, declaredShapesFrom as y, detectionNumClasses as b, resolveInputSize as x, spatialInputSize as S } from "./core/graph.js";
-import { modelNames as C, readModelMetadata as w } from "./core/metadata.js";
-import { DEFAULT_PROVIDERS as T, resolveProviders as E } from "./core/providers.js";
-import { OrtSession as D } from "./core/session.js";
-import { loadImage as O } from "./io/image.js";
-import { fromCv2 as k, letterbox as A, normalize as j, resize as M, toCHW as N, toCv2 as P, toFloat32 as F, toFloat32Tensor as I, toTensor as L } from "./preprocess/image.js";
-import { softmax as R, topK as z } from "./postprocess/classification.js";
-import { batchedNms as B, decodeYolo as V, decodeYoloAnchors as H, decodeYoloV8 as U, decodeYoloV8Anchors as W, nms as G } from "./postprocess/detection.js";
-import { decodeYoloSeg as K, decodeYoloV8Seg as q } from "./postprocess/segmentation.js";
-import { VisionTask as J } from "./tasks/base.js";
-import { Classifier as Y } from "./tasks/classifier.js";
-import { Detector as X } from "./tasks/detector.js";
-import { Segmenter as Z } from "./tasks/segmenter.js";
+import { FusionError as e, ImageLoadError as t, InferenceError as n, LabelMapError as r, ModelLoadError as i, NoDetectionsError as a, OrtVisionError as o, ProviderNotAvailableError as s } from "./core/exceptions.js";
+import { BoundingBox as c, Mask as l, RGBImage as u } from "./types.js";
+import { SpeedTimer as d } from "./core/timing.js";
+import { Boxes as f, ClassificationResults as p, DetectClassifyResults as m, DetectionResults as h, Masks as g, Probs as _, SegmentationResults as v } from "./results.js";
+import { COCO_CLASSES as y, defaultLabels as b, resolveLabels as x } from "./labels.js";
+import { classificationNumClasses as S, declaredShapesFrom as C, detectionNumClasses as w, resolveInputSize as T, spatialInputSize as E } from "./core/graph.js";
+import { modelNames as D, parseNames as O, readModelMetadata as k } from "./core/metadata.js";
+import { DEFAULT_PROVIDERS as A, resolveProviders as j } from "./core/providers.js";
+import { OrtSession as M } from "./core/session.js";
+import { loadImage as N } from "./io/image.js";
+import { FUSION_KIND_DETECT_CLASSIFY as P, INPUT_IMAGE as F, INPUT_PAD as I, INPUT_SCALE as L, INPUT_SOURCE as R, METADATA_PREFIX as z, OUTPUT_BOXES as B, OUTPUT_CLASSES as V, OUTPUT_NUM_DETECTIONS as H, OUTPUT_PROBS as U, OUTPUT_SCORES as W, readFusionSpec as G } from "./fusion.js";
+import { fromCv2 as K, letterbox as q, normalize as J, resize as Y, toCHW as X, toCv2 as Z, toFloat32 as Q, toFloat32Tensor as $, toTensor as ee } from "./preprocess/image.js";
+import { LetterboxPipeline as te, letterboxToTensorData as ne, zeroTensorData as re } from "./preprocess/pipeline.js";
+import { softmax as ie, topK as ae } from "./postprocess/classification.js";
+import { batchedNms as oe, decodeYolo as se, decodeYoloAnchors as ce, nms as le } from "./postprocess/detection.js";
+import { decodeYoloSeg as ue } from "./postprocess/segmentation.js";
+import { VisionTask as de, requireDetections as fe } from "./tasks/base.js";
+import { Classifier as pe } from "./tasks/classifier.js";
+import { DetectClassify as me } from "./tasks/detectClassify.js";
+import { Detector as he } from "./tasks/detector.js";
+import { Segmenter as ge } from "./tasks/segmenter.js";
 //#region src/vision/index.ts
-var Q = "0.5.1";
+var _e = "0.6.1";
 //#endregion
-export { o as BoundingBox, u as Boxes, g as COCO_CLASSES, d as ClassificationResults, Y as Classifier, T as DEFAULT_PROVIDERS, f as DetectionResults, X as Detector, e as ImageLoadError, t as InferenceError, n as LabelMapError, s as Mask, p as Masks, r as ModelLoadError, D as OrtSession, i as OrtVisionError, m as Probs, a as ProviderNotAvailableError, c as RGBImage, h as SegmentationResults, Z as Segmenter, l as SpeedTimer, Q as VERSION, J as VisionTask, B as batchedNms, v as classificationNumClasses, y as declaredShapesFrom, V as decodeYolo, H as decodeYoloAnchors, K as decodeYoloSeg, U as decodeYoloV8, W as decodeYoloV8Anchors, q as decodeYoloV8Seg, b as detectionNumClasses, k as fromCv2, A as letterbox, O as loadImage, C as modelNames, G as nms, j as normalize, w as readModelMetadata, M as resize, x as resolveInputSize, _ as resolveLabels, E as resolveProviders, R as softmax, S as spatialInputSize, N as toCHW, P as toCv2, F as toFloat32, I as toFloat32Tensor, L as toTensor, z as topK };
+export { c as BoundingBox, f as Boxes, y as COCO_CLASSES, p as ClassificationResults, pe as Classifier, A as DEFAULT_PROVIDERS, me as DetectClassify, m as DetectClassifyResults, h as DetectionResults, he as Detector, P as FUSION_KIND_DETECT_CLASSIFY, e as FusionError, F as INPUT_IMAGE, I as INPUT_PAD, L as INPUT_SCALE, R as INPUT_SOURCE, t as ImageLoadError, n as InferenceError, r as LabelMapError, te as LetterboxPipeline, z as METADATA_PREFIX, l as Mask, g as Masks, i as ModelLoadError, a as NoDetectionsError, B as OUTPUT_BOXES, V as OUTPUT_CLASSES, H as OUTPUT_NUM_DETECTIONS, U as OUTPUT_PROBS, W as OUTPUT_SCORES, M as OrtSession, o as OrtVisionError, _ as Probs, s as ProviderNotAvailableError, u as RGBImage, v as SegmentationResults, ge as Segmenter, d as SpeedTimer, _e as VERSION, de as VisionTask, oe as batchedNms, S as classificationNumClasses, C as declaredShapesFrom, se as decodeYolo, ce as decodeYoloAnchors, ue as decodeYoloSeg, b as defaultLabels, w as detectionNumClasses, K as fromCv2, q as letterbox, ne as letterboxToTensorData, N as loadImage, D as modelNames, le as nms, J as normalize, O as parseNames, G as readFusionSpec, k as readModelMetadata, fe as requireDetections, Y as resize, T as resolveInputSize, x as resolveLabels, j as resolveProviders, ie as softmax, E as spatialInputSize, X as toCHW, Z as toCv2, Q as toFloat32, $ as toFloat32Tensor, ee as toTensor, ae as topK, re as zeroTensorData };
 
 //# sourceMappingURL=index.js.map

package/dist/vision/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","names":[],"sources":["../../src/vision/index.ts"],"sourcesContent":["/**\n * `tempest-react-sdk/vision` — browser computer-vision inference with ONNX\n * Runtime Web (classification, detection, segmentation).\n *\n * Vendored from `@mauriciobenjamin700/ort-vision-sdk-web@0.5.1` (MIT, same\n * author) so it ships inside this SDK without an extra package install.\n * `onnxruntime-web` stays an optional peer dependency — install it (and ship\n * the matching `.wasm` files) only when you use this subpath.\n *\n * Do not hand-edit — regenerate with `npm run vendor:vision`.\n */\n\nexport {\n    BoundingBox,\n    Mask,\n    RGBImage,\n    type ClassProbability,\n    type ClassificationResult,\n    type DetectionResult,\n    type SegmentationResult,\n} from \"./types\";\n\nexport {\n    Boxes,\n    ClassificationResults,\n    DetectionResults,\n    Masks,\n    Probs,\n    SegmentationResults,\n} from \"./results\";\n\nexport { COCO_CLASSES, type LabelSpec, type ResolveLabelsOptions, resolveLabels } from \"./labels\";\n\nexport {\n    ImageLoadError,\n    InferenceError,\n    LabelMapError,\n    ModelLoadError,\n    OrtVisionError,\n    ProviderNotAvailableError,\n} from \"./core/exceptions\";\n\nexport { type ModelSource, type OrtSessionOptions, OrtSession } from \"./core/session\";\nexport {\n    type DeclaredDim,\n    type DeclaredShape,\n    type ResolveInputSizeOptions,\n    classificationNumClasses,\n    declaredShapesFrom,\n    detectionNumClasses,\n    resolveInputSize,\n    spatialInputSize,\n} from \"./core/graph\";\nexport { modelNames, readModelMetadata } from \"./core/metadata\";\nexport { DEFAULT_PROVIDERS, resolveProviders } from \"./core/providers\";\nexport { type Speed, SpeedTimer } from \"./core/timing\";\n\nexport { type ImageInput, loadImage } from \"./io/image\";\n\nexport {\n    type LetterboxResult,\n    fromCv2,\n    letterbox,\n    normalize,\n    resize,\n    toCHW,\n    toCv2,\n    toFloat32,\n    toFloat32Tensor,\n    toTensor,\n} from \"./preprocess/image\";\n\nexport { type TopKResult, softmax, topK } from \"./postprocess/classification\";\n\nexport {\n    type DecodeYoloAnchorsOptions,\n    type DecodeYoloOptions,\n    type DecodeYoloV8AnchorsOptions,\n    type DecodeYoloV8Options,\n    type DecodedAnchors,\n    type DecodedDetection,\n    batchedNms,\n    decodeYolo,\n    decodeYoloAnchors,\n    decodeYoloV8,\n    decodeYoloV8Anchors,\n    nms,\n} from \"./postprocess/detection\";\n\nexport {\n    type DecodeYoloSegOptions,\n    type DecodeYoloV8SegOptions,\n    type DecodedSegmentation,\n    decodeYoloSeg,\n    decodeYoloV8Seg,\n} from \"./postprocess/segmentation\";\n\nexport { VisionTask } from \"./tasks/base\";\nexport {\n    type ClassifierOptions,\n    type ClassifierPredictOptions,\n    Classifier,\n} from \"./tasks/classifier\";\nexport {\n    type DetectorHead,\n    type DetectorOptions,\n    type DetectorPredictOptions,\n    Detector,\n} from \"./tasks/detector\";\nexport {\n    type SegmenterHead,\n    type SegmenterOptions,\n    type SegmenterPredictOptions,\n    Segmenter,\n} from \"./tasks/segmenter\";\n\nexport const VERSION: string = \"0.5.1\";\n"],"mappings":";;;;;;;;;;;;;;;;;;;AAoHA,IAAa,IAAkB"}
+{"version":3,"file":"index.js","names":[],"sources":["../../src/vision/index.ts"],"sourcesContent":["/**\n * `tempest-react-sdk/vision` — browser computer-vision inference with ONNX\n * Runtime Web (classification, detection, segmentation).\n *\n * Vendored from `@mauriciobenjamin700/ort-vision-sdk-web@0.6.1` (MIT, same\n * author) so it ships inside this SDK without an extra package install.\n * `onnxruntime-web` stays an optional peer dependency — install it (and ship\n * the matching `.wasm` files) only when you use this subpath.\n *\n * Do not hand-edit — regenerate with `npm run vendor:vision`.\n */\n\nexport {\n    BoundingBox,\n    Mask,\n    RGBImage,\n    type ClassProbability,\n    type ClassificationResult,\n    type DetectionResult,\n    type SegmentationResult,\n} from \"./types\";\n\nexport {\n    Boxes,\n    ClassificationResults,\n    DetectClassifyResults,\n    DetectionResults,\n    Masks,\n    Probs,\n    SegmentationResults,\n} from \"./results\";\n\nexport {\n    COCO_CLASSES,\n    type LabelSpec,\n    type ResolveLabelsOptions,\n    defaultLabels,\n    resolveLabels,\n} from \"./labels\";\n\nexport {\n    FusionError,\n    ImageLoadError,\n    InferenceError,\n    LabelMapError,\n    ModelLoadError,\n    NoDetectionsError,\n    OrtVisionError,\n    ProviderNotAvailableError,\n} from \"./core/exceptions\";\n\nexport { type ModelSource, type OrtSessionOptions, OrtSession } from \"./core/session\";\nexport {\n    type DeclaredDim,\n    type DeclaredShape,\n    type ResolveInputSizeOptions,\n    classificationNumClasses,\n    declaredShapesFrom,\n    detectionNumClasses,\n    resolveInputSize,\n    spatialInputSize,\n} from \"./core/graph\";\nexport { modelNames, parseNames, readModelMetadata } from \"./core/metadata\";\nexport { DEFAULT_PROVIDERS, resolveProviders } from \"./core/providers\";\nexport { type Speed, SpeedTimer } from \"./core/timing\";\n\nexport { type ImageInput, loadImage } from \"./io/image\";\n\nexport {\n    FUSION_KIND_DETECT_CLASSIFY,\n    INPUT_IMAGE,\n    INPUT_PAD,\n    INPUT_SCALE,\n    INPUT_SOURCE,\n    METADATA_PREFIX,\n    OUTPUT_BOXES,\n    OUTPUT_CLASSES,\n    OUTPUT_NUM_DETECTIONS,\n    OUTPUT_PROBS,\n    OUTPUT_SCORES,\n    type CropSource,\n    type FusionSpec,\n    readFusionSpec,\n} from \"./fusion\";\n\nexport {\n    type LetterboxResult,\n    fromCv2,\n    letterbox,\n    normalize,\n    resize,\n    toCHW,\n    toCv2,\n    toFloat32,\n    toFloat32Tensor,\n    toTensor,\n} from \"./preprocess/image\";\n\nexport {\n    type FusedLetterboxResult,\n    LetterboxPipeline,\n    letterboxToTensorData,\n    zeroTensorData,\n} from \"./preprocess/pipeline\";\n\nexport { type TopKResult, softmax, topK } from \"./postprocess/classification\";\n\nexport {\n    type DecodeYoloAnchorsOptions,\n    type DecodeYoloOptions,\n    type DecodedAnchors,\n    type DecodedDetection,\n    batchedNms,\n    decodeYolo,\n    decodeYoloAnchors,\n    nms,\n} from \"./postprocess/detection\";\n\nexport {\n    type DecodeYoloSegOptions,\n    type DecodedSegmentation,\n    decodeYoloSeg,\n} from \"./postprocess/segmentation\";\n\nexport { VisionTask, requireDetections } from \"./tasks/base\";\nexport {\n    type ClassifierOptions,\n    type ClassifierPredictOptions,\n    Classifier,\n} from \"./tasks/classifier\";\nexport {\n    type DetectClassifyOptions,\n    type DetectClassifyPredictOptions,\n    DetectClassify,\n} from \"./tasks/detectClassify\";\nexport {\n    type DetectorHead,\n    type DetectorOptions,\n    type DetectorPredictOptions,\n    Detector,\n} from \"./tasks/detector\";\nexport {\n    type SegmenterHead,\n    type SegmenterOptions,\n    type SegmenterPredictOptions,\n    Segmenter,\n} from \"./tasks/segmenter\";\n\nexport const VERSION: string = \"0.6.1\";\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;AAoJA,IAAa,KAAkB"}

package/dist/vision/labels.cjs

@@ -1,2 +1,2 @@
-const e=require("./core/exceptions.cjs");var t=Object.freeze(`person.bicycle.car.motorcycle.airplane.bus.train.truck.boat.traffic light.fire hydrant.stop sign.parking meter.bench.bird.cat.dog.horse.sheep.cow.elephant.bear.zebra.giraffe.backpack.umbrella.handbag.tie.suitcase.frisbee.skis.snowboard.sports ball.kite.baseball bat.baseball glove.skateboard.surfboard.tennis racket.bottle.wine glass.cup.fork.knife.spoon.bowl.banana.apple.sandwich.orange.broccoli.carrot.hot dog.pizza.donut.cake.chair.couch.potted plant.bed.dining table.toilet.tv.laptop.mouse.remote.keyboard.cell phone.microwave.oven.toaster.sink.refrigerator.book.clock.vase.scissors.teddy bear.hair drier.toothbrush`.split(`.`)),n={coco:t};function r(t,n={}){let r=i(t,n.numClasses);if(n.numClasses!==void 0&&r.length!==n.numClasses)throw new e.LabelMapError(`Resolved ${r.length} labels but the model has ${n.numClasses} classes.`);return r}function i(t,r){if(t==null){if(r===void 0)throw new e.LabelMapError(`Cannot auto-generate labels without numClasses. Pass an explicit labels spec or numClasses.`);return Array.from({length:r},(e,t)=>`class_${t}`)}if(Array.isArray(t))return[...t];if(typeof t==`string`){let r=n[t];if(r!==void 0)return r;throw new e.LabelMapError(`Unknown labels preset: ${JSON.stringify(t)}. Known presets: ${Object.keys(n).join(`, `)}.`)}if(typeof t==`object`){let e=t,n=Object.keys(e).map(e=>Number(e));if(n.length===0)return[];let r=Math.max(...n);return Array.from({length:r+1},(t,n)=>e[n]??`class_${n}`)}throw new e.LabelMapError(`Unsupported labels spec type: ${typeof t}.`)}exports.COCO_CLASSES=t,exports.resolveLabels=r;
+const e=require("./core/exceptions.cjs");var t=Object.freeze(`person.bicycle.car.motorcycle.airplane.bus.train.truck.boat.traffic light.fire hydrant.stop sign.parking meter.bench.bird.cat.dog.horse.sheep.cow.elephant.bear.zebra.giraffe.backpack.umbrella.handbag.tie.suitcase.frisbee.skis.snowboard.sports ball.kite.baseball bat.baseball glove.skateboard.surfboard.tennis racket.bottle.wine glass.cup.fork.knife.spoon.bowl.banana.apple.sandwich.orange.broccoli.carrot.hot dog.pizza.donut.cake.chair.couch.potted plant.bed.dining table.toilet.tv.laptop.mouse.remote.keyboard.cell phone.microwave.oven.toaster.sink.refrigerator.book.clock.vase.scissors.teddy bear.hair drier.toothbrush`.split(`.`)),n={coco:t};function r(e){return e===void 0||e===t.length?`coco`:null}function i(t,n={}){let r=a(t,n.numClasses);if(n.numClasses!==void 0&&r.length!==n.numClasses)throw new e.LabelMapError(`Resolved ${r.length} labels but the model has ${n.numClasses} classes.`);return r}function a(t,r){if(t==null){if(r===void 0)throw new e.LabelMapError(`Cannot auto-generate labels without numClasses. Pass an explicit labels spec or numClasses.`);return Array.from({length:r},(e,t)=>`class_${t}`)}if(Array.isArray(t))return[...t];if(typeof t==`string`){let r=n[t];if(r!==void 0)return r;throw new e.LabelMapError(`Unknown labels preset: ${JSON.stringify(t)}. Known presets: ${Object.keys(n).join(`, `)}.`)}if(typeof t==`object`){let e=t,n=Object.keys(e).map(e=>Number(e));if(n.length===0)return[];let r=Math.max(...n);return Array.from({length:r+1},(t,n)=>e[n]??`class_${n}`)}throw new e.LabelMapError(`Unsupported labels spec type: ${typeof t}.`)}exports.COCO_CLASSES=t,exports.defaultLabels=r,exports.resolveLabels=i;
 //# sourceMappingURL=labels.cjs.map

package/dist/vision/labels.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"labels.cjs","names":[],"sources":["../../src/vision/labels.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Class label resolution: presets, lists, dicts, or auto-generated.\n *\n * Tasks call {@link resolveLabels} once at construction time to turn whatever\n * the caller passed (preset name, array, dict, or `null`) into an ordered\n * array of class names indexed by class id.\n *\n * In the browser there is no filesystem, so this module does not load labels\n * from a path — fetch the file yourself and pass an array.\n */\n\nimport { LabelMapError } from \"./core/exceptions\";\n\n/**\n * Anything accepted by {@link resolveLabels}.\n *\n * - `string[]` / `readonly string[]`: explicit names indexed by class id.\n * - `Record<number, string>`: sparse mapping (gaps filled with `class_<id>`).\n * - `string`: a preset name (e.g. `\"coco\"`).\n * - `null` / `undefined`: auto-generate `class_0` ... `class_{numClasses-1}`.\n */\nexport type LabelSpec = readonly string[] | Record<number, string> | string | null | undefined;\n\n/** COCO 2017 80-class labels in canonical class-id order. */\nexport const COCO_CLASSES: readonly string[] = Object.freeze([\n    \"person\",\n    \"bicycle\",\n    \"car\",\n    \"motorcycle\",\n    \"airplane\",\n    \"bus\",\n    \"train\",\n    \"truck\",\n    \"boat\",\n    \"traffic light\",\n    \"fire hydrant\",\n    \"stop sign\",\n    \"parking meter\",\n    \"bench\",\n    \"bird\",\n    \"cat\",\n    \"dog\",\n    \"horse\",\n    \"sheep\",\n    \"cow\",\n    \"elephant\",\n    \"bear\",\n    \"zebra\",\n    \"giraffe\",\n    \"backpack\",\n    \"umbrella\",\n    \"handbag\",\n    \"tie\",\n    \"suitcase\",\n    \"frisbee\",\n    \"skis\",\n    \"snowboard\",\n    \"sports ball\",\n    \"kite\",\n    \"baseball bat\",\n    \"baseball glove\",\n    \"skateboard\",\n    \"surfboard\",\n    \"tennis racket\",\n    \"bottle\",\n    \"wine glass\",\n    \"cup\",\n    \"fork\",\n    \"knife\",\n    \"spoon\",\n    \"bowl\",\n    \"banana\",\n    \"apple\",\n    \"sandwich\",\n    \"orange\",\n    \"broccoli\",\n    \"carrot\",\n    \"hot dog\",\n    \"pizza\",\n    \"donut\",\n    \"cake\",\n    \"chair\",\n    \"couch\",\n    \"potted plant\",\n    \"bed\",\n    \"dining table\",\n    \"toilet\",\n    \"tv\",\n    \"laptop\",\n    \"mouse\",\n    \"remote\",\n    \"keyboard\",\n    \"cell phone\",\n    \"microwave\",\n    \"oven\",\n    \"toaster\",\n    \"sink\",\n    \"refrigerator\",\n    \"book\",\n    \"clock\",\n    \"vase\",\n    \"scissors\",\n    \"teddy bear\",\n    \"hair drier\",\n    \"toothbrush\",\n]);\n\nconst PRESETS: Readonly<Record<string, readonly string[]>> = {\n    coco: COCO_CLASSES,\n};\n\nexport interface ResolveLabelsOptions {\n    /**\n     * Expected number of classes.\n     *\n     * - When `spec` is `null`/`undefined`, this is required to auto-generate names.\n     * - When `spec` is provided, it validates that the resolved length matches.\n     */\n    readonly numClasses?: number;\n}\n\n/**\n * Resolve a labels specification into an ordered array of class names.\n *\n * @throws {@link LabelMapError} if the spec is invalid, the preset is unknown,\n *   or the resolved length disagrees with `numClasses`.\n */\nexport function resolveLabels(\n    spec: LabelSpec,\n    options: ResolveLabelsOptions = {},\n): readonly string[] {\n    const labels = resolve(spec, options.numClasses);\n    if (options.numClasses !== undefined && labels.length !== options.numClasses) {\n        throw new LabelMapError(\n            `Resolved ${labels.length} labels but the model has ${options.numClasses} classes.`,\n        );\n    }\n    return labels;\n}\n\nfunction resolve(spec: LabelSpec, numClasses: number | undefined): readonly string[] {\n    if (spec === null || spec === undefined) {\n        if (numClasses === undefined) {\n            throw new LabelMapError(\n                \"Cannot auto-generate labels without numClasses. Pass an explicit labels spec or numClasses.\",\n            );\n        }\n        return Array.from({ length: numClasses }, (_, i) => `class_${i}`);\n    }\n\n    if (Array.isArray(spec)) {\n        return [...spec];\n    }\n\n    if (typeof spec === \"string\") {\n        const preset = PRESETS[spec];\n        if (preset !== undefined) {\n            return preset;\n        }\n        throw new LabelMapError(\n            `Unknown labels preset: ${JSON.stringify(spec)}. Known presets: ${Object.keys(PRESETS).join(\", \")}.`,\n        );\n    }\n\n    if (typeof spec === \"object\") {\n        const map = spec as Record<number, string>;\n        const ids = Object.keys(map).map((k) => Number(k));\n        if (ids.length === 0) {\n            return [];\n        }\n        const maxId = Math.max(...ids);\n        return Array.from({ length: maxId + 1 }, (_, i) => map[i] ?? `class_${i}`);\n    }\n\n    throw new LabelMapError(`Unsupported labels spec type: ${typeof spec}.`);\n}\n"],"mappings":"yCAyBA,IAAa,EAAkC,OAAO,OAAO,wnBAiF7D,CAAC,EAEK,EAAuD,CACzD,KAAM,CACV,EAkBA,SAAgB,EACZ,EACA,EAAgC,CAAC,EAChB,CACjB,IAAM,EAAS,EAAQ,EAAM,EAAQ,UAAU,EAC/C,GAAI,EAAQ,aAAe,IAAA,IAAa,EAAO,SAAW,EAAQ,WAC9D,MAAM,IAAI,EAAA,cACN,YAAY,EAAO,OAAO,4BAA4B,EAAQ,WAAW,UAC7E,EAEJ,OAAO,CACX,CAEA,SAAS,EAAQ,EAAiB,EAAmD,CACjF,GAAI,GAAS,KAA4B,CACrC,GAAI,IAAe,IAAA,GACf,MAAM,IAAI,EAAA,cACN,6FACJ,EAEJ,OAAO,MAAM,KAAK,CAAE,OAAQ,CAAW,GAAI,EAAG,IAAM,SAAS,GAAG,CACpE,CAEA,GAAI,MAAM,QAAQ,CAAI,EAClB,MAAO,CAAC,GAAG,CAAI,EAGnB,GAAI,OAAO,GAAS,SAAU,CAC1B,IAAM,EAAS,EAAQ,GACvB,GAAI,IAAW,IAAA,GACX,OAAO,EAEX,MAAM,IAAI,EAAA,cACN,0BAA0B,KAAK,UAAU,CAAI,EAAE,mBAAmB,OAAO,KAAK,CAAO,CAAC,CAAC,KAAK,IAAI,EAAE,EACtG,CACJ,CAEA,GAAI,OAAO,GAAS,SAAU,CAC1B,IAAM,EAAM,EACN,EAAM,OAAO,KAAK,CAAG,CAAC,CAAC,IAAK,GAAM,OAAO,CAAC,CAAC,EACjD,GAAI,EAAI,SAAW,EACf,MAAO,CAAC,EAEZ,IAAM,EAAQ,KAAK,IAAI,GAAG,CAAG,EAC7B,OAAO,MAAM,KAAK,CAAE,OAAQ,EAAQ,CAAE,GAAI,EAAG,IAAM,EAAI,IAAM,SAAS,GAAG,CAC7E,CAEA,MAAM,IAAI,EAAA,cAAc,iCAAiC,OAAO,EAAK,EAAE,CAC3E"}
+{"version":3,"file":"labels.cjs","names":[],"sources":["../../src/vision/labels.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Class label resolution: presets, lists, dicts, or auto-generated.\n *\n * Tasks call {@link resolveLabels} once at construction time to turn whatever\n * the caller passed (preset name, array, dict, or `null`) into an ordered\n * array of class names indexed by class id.\n *\n * In the browser there is no filesystem, so this module does not load labels\n * from a path — fetch the file yourself and pass an array.\n */\n\nimport { LabelMapError } from \"./core/exceptions\";\n\n/**\n * Anything accepted by {@link resolveLabels}.\n *\n * - `string[]` / `readonly string[]`: explicit names indexed by class id.\n * - `Record<number, string>`: sparse mapping (gaps filled with `class_<id>`).\n * - `string`: a preset name (e.g. `\"coco\"`).\n * - `null` / `undefined`: auto-generate `class_0` ... `class_{numClasses-1}`.\n */\nexport type LabelSpec = readonly string[] | Record<number, string> | string | null | undefined;\n\n/** COCO 2017 80-class labels in canonical class-id order. */\nexport const COCO_CLASSES: readonly string[] = Object.freeze([\n    \"person\",\n    \"bicycle\",\n    \"car\",\n    \"motorcycle\",\n    \"airplane\",\n    \"bus\",\n    \"train\",\n    \"truck\",\n    \"boat\",\n    \"traffic light\",\n    \"fire hydrant\",\n    \"stop sign\",\n    \"parking meter\",\n    \"bench\",\n    \"bird\",\n    \"cat\",\n    \"dog\",\n    \"horse\",\n    \"sheep\",\n    \"cow\",\n    \"elephant\",\n    \"bear\",\n    \"zebra\",\n    \"giraffe\",\n    \"backpack\",\n    \"umbrella\",\n    \"handbag\",\n    \"tie\",\n    \"suitcase\",\n    \"frisbee\",\n    \"skis\",\n    \"snowboard\",\n    \"sports ball\",\n    \"kite\",\n    \"baseball bat\",\n    \"baseball glove\",\n    \"skateboard\",\n    \"surfboard\",\n    \"tennis racket\",\n    \"bottle\",\n    \"wine glass\",\n    \"cup\",\n    \"fork\",\n    \"knife\",\n    \"spoon\",\n    \"bowl\",\n    \"banana\",\n    \"apple\",\n    \"sandwich\",\n    \"orange\",\n    \"broccoli\",\n    \"carrot\",\n    \"hot dog\",\n    \"pizza\",\n    \"donut\",\n    \"cake\",\n    \"chair\",\n    \"couch\",\n    \"potted plant\",\n    \"bed\",\n    \"dining table\",\n    \"toilet\",\n    \"tv\",\n    \"laptop\",\n    \"mouse\",\n    \"remote\",\n    \"keyboard\",\n    \"cell phone\",\n    \"microwave\",\n    \"oven\",\n    \"toaster\",\n    \"sink\",\n    \"refrigerator\",\n    \"book\",\n    \"clock\",\n    \"vase\",\n    \"scissors\",\n    \"teddy bear\",\n    \"hair drier\",\n    \"toothbrush\",\n]);\n\nconst PRESETS: Readonly<Record<string, readonly string[]>> = {\n    coco: COCO_CLASSES,\n};\n\nexport interface ResolveLabelsOptions {\n    /**\n     * Expected number of classes.\n     *\n     * - When `spec` is `null`/`undefined`, this is required to auto-generate names.\n     * - When `spec` is provided, it validates that the resolved length matches.\n     */\n    readonly numClasses?: number;\n}\n\n/**\n * Resolve a labels specification into an ordered array of class names.\n *\n * @throws {@link LabelMapError} if the spec is invalid, the preset is unknown,\n *   or the resolved length disagrees with `numClasses`.\n */\n/**\n * Pick the fallback label spec for a model that declares no class names.\n *\n * The COCO preset is the right default for a stock YOLO export and an\n * impossible one for anything else: it names exactly 80 classes, so handing it\n * to a 3-class head makes {@link resolveLabels} throw `Resolved 80 labels but\n * the model has 3 classes` and the task cannot be created at all. A custom\n * model without baked-in `names` is an ordinary thing to have — it should come\n * up as `class_0`, `class_1`, ..., not as a failure.\n *\n * @param numClasses Classes the model predicts, or `undefined` when the output\n *   shape does not say.\n * @returns `\"coco\"` when the preset can describe the model, otherwise `null`,\n *   which makes {@link resolveLabels} generate `class_N` names.\n */\nexport function defaultLabels(numClasses: number | undefined): LabelSpec {\n    if (numClasses === undefined || numClasses === COCO_CLASSES.length) {\n        return \"coco\";\n    }\n    return null;\n}\n\nexport function resolveLabels(\n    spec: LabelSpec,\n    options: ResolveLabelsOptions = {},\n): readonly string[] {\n    const labels = resolve(spec, options.numClasses);\n    if (options.numClasses !== undefined && labels.length !== options.numClasses) {\n        throw new LabelMapError(\n            `Resolved ${labels.length} labels but the model has ${options.numClasses} classes.`,\n        );\n    }\n    return labels;\n}\n\nfunction resolve(spec: LabelSpec, numClasses: number | undefined): readonly string[] {\n    if (spec === null || spec === undefined) {\n        if (numClasses === undefined) {\n            throw new LabelMapError(\n                \"Cannot auto-generate labels without numClasses. Pass an explicit labels spec or numClasses.\",\n            );\n        }\n        return Array.from({ length: numClasses }, (_, i) => `class_${i}`);\n    }\n\n    if (Array.isArray(spec)) {\n        return [...spec];\n    }\n\n    if (typeof spec === \"string\") {\n        const preset = PRESETS[spec];\n        if (preset !== undefined) {\n            return preset;\n        }\n        throw new LabelMapError(\n            `Unknown labels preset: ${JSON.stringify(spec)}. Known presets: ${Object.keys(PRESETS).join(\", \")}.`,\n        );\n    }\n\n    if (typeof spec === \"object\") {\n        const map = spec as Record<number, string>;\n        const ids = Object.keys(map).map((k) => Number(k));\n        if (ids.length === 0) {\n            return [];\n        }\n        const maxId = Math.max(...ids);\n        return Array.from({ length: maxId + 1 }, (_, i) => map[i] ?? `class_${i}`);\n    }\n\n    throw new LabelMapError(`Unsupported labels spec type: ${typeof spec}.`);\n}\n"],"mappings":"yCAyBA,IAAa,EAAkC,OAAO,OAAO,wnBAiF7D,CAAC,EAEK,EAAuD,CACzD,KAAM,CACV,EAiCA,SAAgB,EAAc,EAA2C,CAIrE,OAHI,IAAe,IAAA,IAAa,IAAe,EAAa,OACjD,OAEJ,IACX,CAEA,SAAgB,EACZ,EACA,EAAgC,CAAC,EAChB,CACjB,IAAM,EAAS,EAAQ,EAAM,EAAQ,UAAU,EAC/C,GAAI,EAAQ,aAAe,IAAA,IAAa,EAAO,SAAW,EAAQ,WAC9D,MAAM,IAAI,EAAA,cACN,YAAY,EAAO,OAAO,4BAA4B,EAAQ,WAAW,UAC7E,EAEJ,OAAO,CACX,CAEA,SAAS,EAAQ,EAAiB,EAAmD,CACjF,GAAI,GAAS,KAA4B,CACrC,GAAI,IAAe,IAAA,GACf,MAAM,IAAI,EAAA,cACN,6FACJ,EAEJ,OAAO,MAAM,KAAK,CAAE,OAAQ,CAAW,GAAI,EAAG,IAAM,SAAS,GAAG,CACpE,CAEA,GAAI,MAAM,QAAQ,CAAI,EAClB,MAAO,CAAC,GAAG,CAAI,EAGnB,GAAI,OAAO,GAAS,SAAU,CAC1B,IAAM,EAAS,EAAQ,GACvB,GAAI,IAAW,IAAA,GACX,OAAO,EAEX,MAAM,IAAI,EAAA,cACN,0BAA0B,KAAK,UAAU,CAAI,EAAE,mBAAmB,OAAO,KAAK,CAAO,CAAC,CAAC,KAAK,IAAI,EAAE,EACtG,CACJ,CAEA,GAAI,OAAO,GAAS,SAAU,CAC1B,IAAM,EAAM,EACN,EAAM,OAAO,KAAK,CAAG,CAAC,CAAC,IAAK,GAAM,OAAO,CAAC,CAAC,EACjD,GAAI,EAAI,SAAW,EACf,MAAO,CAAC,EAEZ,IAAM,EAAQ,KAAK,IAAI,GAAG,CAAG,EAC7B,OAAO,MAAM,KAAK,CAAE,OAAQ,EAAQ,CAAE,GAAI,EAAG,IAAM,EAAI,IAAM,SAAS,GAAG,CAC7E,CAEA,MAAM,IAAI,EAAA,cAAc,iCAAiC,OAAO,EAAK,EAAE,CAC3E"}

package/dist/vision/labels.js

@@ -1,12 +1,15 @@
 import { LabelMapError as e } from "./core/exceptions.js";
 //#region src/vision/labels.ts
 var t = Object.freeze(/* @__PURE__ */ "person.bicycle.car.motorcycle.airplane.bus.train.truck.boat.traffic light.fire hydrant.stop sign.parking meter.bench.bird.cat.dog.horse.sheep.cow.elephant.bear.zebra.giraffe.backpack.umbrella.handbag.tie.suitcase.frisbee.skis.snowboard.sports ball.kite.baseball bat.baseball glove.skateboard.surfboard.tennis racket.bottle.wine glass.cup.fork.knife.spoon.bowl.banana.apple.sandwich.orange.broccoli.carrot.hot dog.pizza.donut.cake.chair.couch.potted plant.bed.dining table.toilet.tv.laptop.mouse.remote.keyboard.cell phone.microwave.oven.toaster.sink.refrigerator.book.clock.vase.scissors.teddy bear.hair drier.toothbrush".split(".")), n = { coco: t };
-function r(t, n = {}) {
-	let r = i(t, n.numClasses);
+function r(e) {
+	return e === void 0 || e === t.length ? "coco" : null;
+}
+function i(t, n = {}) {
+	let r = a(t, n.numClasses);
 	if (n.numClasses !== void 0 && r.length !== n.numClasses) throw new e(`Resolved ${r.length} labels but the model has ${n.numClasses} classes.`);
 	return r;
 }
-function i(t, r) {
+function a(t, r) {
 	if (t == null) {
 		if (r === void 0) throw new e("Cannot auto-generate labels without numClasses. Pass an explicit labels spec or numClasses.");
 		return Array.from({ length: r }, (e, t) => `class_${t}`);
@@ -26,6 +29,6 @@ function i(t, r) {
 	throw new e(`Unsupported labels spec type: ${typeof t}.`);
 }
 //#endregion
-export { t as COCO_CLASSES, r as resolveLabels };
+export { t as COCO_CLASSES, r as defaultLabels, i as resolveLabels };
 
 //# sourceMappingURL=labels.js.map

package/dist/vision/labels.js.map

@@ -1 +1 @@
-{"version":3,"file":"labels.js","names":[],"sources":["../../src/vision/labels.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Class label resolution: presets, lists, dicts, or auto-generated.\n *\n * Tasks call {@link resolveLabels} once at construction time to turn whatever\n * the caller passed (preset name, array, dict, or `null`) into an ordered\n * array of class names indexed by class id.\n *\n * In the browser there is no filesystem, so this module does not load labels\n * from a path — fetch the file yourself and pass an array.\n */\n\nimport { LabelMapError } from \"./core/exceptions\";\n\n/**\n * Anything accepted by {@link resolveLabels}.\n *\n * - `string[]` / `readonly string[]`: explicit names indexed by class id.\n * - `Record<number, string>`: sparse mapping (gaps filled with `class_<id>`).\n * - `string`: a preset name (e.g. `\"coco\"`).\n * - `null` / `undefined`: auto-generate `class_0` ... `class_{numClasses-1}`.\n */\nexport type LabelSpec = readonly string[] | Record<number, string> | string | null | undefined;\n\n/** COCO 2017 80-class labels in canonical class-id order. */\nexport const COCO_CLASSES: readonly string[] = Object.freeze([\n    \"person\",\n    \"bicycle\",\n    \"car\",\n    \"motorcycle\",\n    \"airplane\",\n    \"bus\",\n    \"train\",\n    \"truck\",\n    \"boat\",\n    \"traffic light\",\n    \"fire hydrant\",\n    \"stop sign\",\n    \"parking meter\",\n    \"bench\",\n    \"bird\",\n    \"cat\",\n    \"dog\",\n    \"horse\",\n    \"sheep\",\n    \"cow\",\n    \"elephant\",\n    \"bear\",\n    \"zebra\",\n    \"giraffe\",\n    \"backpack\",\n    \"umbrella\",\n    \"handbag\",\n    \"tie\",\n    \"suitcase\",\n    \"frisbee\",\n    \"skis\",\n    \"snowboard\",\n    \"sports ball\",\n    \"kite\",\n    \"baseball bat\",\n    \"baseball glove\",\n    \"skateboard\",\n    \"surfboard\",\n    \"tennis racket\",\n    \"bottle\",\n    \"wine glass\",\n    \"cup\",\n    \"fork\",\n    \"knife\",\n    \"spoon\",\n    \"bowl\",\n    \"banana\",\n    \"apple\",\n    \"sandwich\",\n    \"orange\",\n    \"broccoli\",\n    \"carrot\",\n    \"hot dog\",\n    \"pizza\",\n    \"donut\",\n    \"cake\",\n    \"chair\",\n    \"couch\",\n    \"potted plant\",\n    \"bed\",\n    \"dining table\",\n    \"toilet\",\n    \"tv\",\n    \"laptop\",\n    \"mouse\",\n    \"remote\",\n    \"keyboard\",\n    \"cell phone\",\n    \"microwave\",\n    \"oven\",\n    \"toaster\",\n    \"sink\",\n    \"refrigerator\",\n    \"book\",\n    \"clock\",\n    \"vase\",\n    \"scissors\",\n    \"teddy bear\",\n    \"hair drier\",\n    \"toothbrush\",\n]);\n\nconst PRESETS: Readonly<Record<string, readonly string[]>> = {\n    coco: COCO_CLASSES,\n};\n\nexport interface ResolveLabelsOptions {\n    /**\n     * Expected number of classes.\n     *\n     * - When `spec` is `null`/`undefined`, this is required to auto-generate names.\n     * - When `spec` is provided, it validates that the resolved length matches.\n     */\n    readonly numClasses?: number;\n}\n\n/**\n * Resolve a labels specification into an ordered array of class names.\n *\n * @throws {@link LabelMapError} if the spec is invalid, the preset is unknown,\n *   or the resolved length disagrees with `numClasses`.\n */\nexport function resolveLabels(\n    spec: LabelSpec,\n    options: ResolveLabelsOptions = {},\n): readonly string[] {\n    const labels = resolve(spec, options.numClasses);\n    if (options.numClasses !== undefined && labels.length !== options.numClasses) {\n        throw new LabelMapError(\n            `Resolved ${labels.length} labels but the model has ${options.numClasses} classes.`,\n        );\n    }\n    return labels;\n}\n\nfunction resolve(spec: LabelSpec, numClasses: number | undefined): readonly string[] {\n    if (spec === null || spec === undefined) {\n        if (numClasses === undefined) {\n            throw new LabelMapError(\n                \"Cannot auto-generate labels without numClasses. Pass an explicit labels spec or numClasses.\",\n            );\n        }\n        return Array.from({ length: numClasses }, (_, i) => `class_${i}`);\n    }\n\n    if (Array.isArray(spec)) {\n        return [...spec];\n    }\n\n    if (typeof spec === \"string\") {\n        const preset = PRESETS[spec];\n        if (preset !== undefined) {\n            return preset;\n        }\n        throw new LabelMapError(\n            `Unknown labels preset: ${JSON.stringify(spec)}. Known presets: ${Object.keys(PRESETS).join(\", \")}.`,\n        );\n    }\n\n    if (typeof spec === \"object\") {\n        const map = spec as Record<number, string>;\n        const ids = Object.keys(map).map((k) => Number(k));\n        if (ids.length === 0) {\n            return [];\n        }\n        const maxId = Math.max(...ids);\n        return Array.from({ length: maxId + 1 }, (_, i) => map[i] ?? `class_${i}`);\n    }\n\n    throw new LabelMapError(`Unsupported labels spec type: ${typeof spec}.`);\n}\n"],"mappings":";;AAyBA,IAAa,IAAkC,OAAO,OAAO,woBAiF7D,CAAC,GAEK,IAAuD,EACzD,MAAM,EACV;AAkBA,SAAgB,EACZ,GACA,IAAgC,CAAC,GAChB;CACjB,IAAM,IAAS,EAAQ,GAAM,EAAQ,UAAU;CAC/C,IAAI,EAAQ,eAAe,KAAA,KAAa,EAAO,WAAW,EAAQ,YAC9D,MAAM,IAAI,EACN,YAAY,EAAO,OAAO,4BAA4B,EAAQ,WAAW,UAC7E;CAEJ,OAAO;AACX;AAEA,SAAS,EAAQ,GAAiB,GAAmD;CACjF,IAAI,KAAS,MAA4B;EACrC,IAAI,MAAe,KAAA,GACf,MAAM,IAAI,EACN,6FACJ;EAEJ,OAAO,MAAM,KAAK,EAAE,QAAQ,EAAW,IAAI,GAAG,MAAM,SAAS,GAAG;CACpE;CAEA,IAAI,MAAM,QAAQ,CAAI,GAClB,OAAO,CAAC,GAAG,CAAI;CAGnB,IAAI,OAAO,KAAS,UAAU;EAC1B,IAAM,IAAS,EAAQ;EACvB,IAAI,MAAW,KAAA,GACX,OAAO;EAEX,MAAM,IAAI,EACN,0BAA0B,KAAK,UAAU,CAAI,EAAE,mBAAmB,OAAO,KAAK,CAAO,CAAC,CAAC,KAAK,IAAI,EAAE,EACtG;CACJ;CAEA,IAAI,OAAO,KAAS,UAAU;EAC1B,IAAM,IAAM,GACN,IAAM,OAAO,KAAK,CAAG,CAAC,CAAC,KAAK,MAAM,OAAO,CAAC,CAAC;EACjD,IAAI,EAAI,WAAW,GACf,OAAO,CAAC;EAEZ,IAAM,IAAQ,KAAK,IAAI,GAAG,CAAG;EAC7B,OAAO,MAAM,KAAK,EAAE,QAAQ,IAAQ,EAAE,IAAI,GAAG,MAAM,EAAI,MAAM,SAAS,GAAG;CAC7E;CAEA,MAAM,IAAI,EAAc,iCAAiC,OAAO,EAAK,EAAE;AAC3E"}
+{"version":3,"file":"labels.js","names":[],"sources":["../../src/vision/labels.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Class label resolution: presets, lists, dicts, or auto-generated.\n *\n * Tasks call {@link resolveLabels} once at construction time to turn whatever\n * the caller passed (preset name, array, dict, or `null`) into an ordered\n * array of class names indexed by class id.\n *\n * In the browser there is no filesystem, so this module does not load labels\n * from a path — fetch the file yourself and pass an array.\n */\n\nimport { LabelMapError } from \"./core/exceptions\";\n\n/**\n * Anything accepted by {@link resolveLabels}.\n *\n * - `string[]` / `readonly string[]`: explicit names indexed by class id.\n * - `Record<number, string>`: sparse mapping (gaps filled with `class_<id>`).\n * - `string`: a preset name (e.g. `\"coco\"`).\n * - `null` / `undefined`: auto-generate `class_0` ... `class_{numClasses-1}`.\n */\nexport type LabelSpec = readonly string[] | Record<number, string> | string | null | undefined;\n\n/** COCO 2017 80-class labels in canonical class-id order. */\nexport const COCO_CLASSES: readonly string[] = Object.freeze([\n    \"person\",\n    \"bicycle\",\n    \"car\",\n    \"motorcycle\",\n    \"airplane\",\n    \"bus\",\n    \"train\",\n    \"truck\",\n    \"boat\",\n    \"traffic light\",\n    \"fire hydrant\",\n    \"stop sign\",\n    \"parking meter\",\n    \"bench\",\n    \"bird\",\n    \"cat\",\n    \"dog\",\n    \"horse\",\n    \"sheep\",\n    \"cow\",\n    \"elephant\",\n    \"bear\",\n    \"zebra\",\n    \"giraffe\",\n    \"backpack\",\n    \"umbrella\",\n    \"handbag\",\n    \"tie\",\n    \"suitcase\",\n    \"frisbee\",\n    \"skis\",\n    \"snowboard\",\n    \"sports ball\",\n    \"kite\",\n    \"baseball bat\",\n    \"baseball glove\",\n    \"skateboard\",\n    \"surfboard\",\n    \"tennis racket\",\n    \"bottle\",\n    \"wine glass\",\n    \"cup\",\n    \"fork\",\n    \"knife\",\n    \"spoon\",\n    \"bowl\",\n    \"banana\",\n    \"apple\",\n    \"sandwich\",\n    \"orange\",\n    \"broccoli\",\n    \"carrot\",\n    \"hot dog\",\n    \"pizza\",\n    \"donut\",\n    \"cake\",\n    \"chair\",\n    \"couch\",\n    \"potted plant\",\n    \"bed\",\n    \"dining table\",\n    \"toilet\",\n    \"tv\",\n    \"laptop\",\n    \"mouse\",\n    \"remote\",\n    \"keyboard\",\n    \"cell phone\",\n    \"microwave\",\n    \"oven\",\n    \"toaster\",\n    \"sink\",\n    \"refrigerator\",\n    \"book\",\n    \"clock\",\n    \"vase\",\n    \"scissors\",\n    \"teddy bear\",\n    \"hair drier\",\n    \"toothbrush\",\n]);\n\nconst PRESETS: Readonly<Record<string, readonly string[]>> = {\n    coco: COCO_CLASSES,\n};\n\nexport interface ResolveLabelsOptions {\n    /**\n     * Expected number of classes.\n     *\n     * - When `spec` is `null`/`undefined`, this is required to auto-generate names.\n     * - When `spec` is provided, it validates that the resolved length matches.\n     */\n    readonly numClasses?: number;\n}\n\n/**\n * Resolve a labels specification into an ordered array of class names.\n *\n * @throws {@link LabelMapError} if the spec is invalid, the preset is unknown,\n *   or the resolved length disagrees with `numClasses`.\n */\n/**\n * Pick the fallback label spec for a model that declares no class names.\n *\n * The COCO preset is the right default for a stock YOLO export and an\n * impossible one for anything else: it names exactly 80 classes, so handing it\n * to a 3-class head makes {@link resolveLabels} throw `Resolved 80 labels but\n * the model has 3 classes` and the task cannot be created at all. A custom\n * model without baked-in `names` is an ordinary thing to have — it should come\n * up as `class_0`, `class_1`, ..., not as a failure.\n *\n * @param numClasses Classes the model predicts, or `undefined` when the output\n *   shape does not say.\n * @returns `\"coco\"` when the preset can describe the model, otherwise `null`,\n *   which makes {@link resolveLabels} generate `class_N` names.\n */\nexport function defaultLabels(numClasses: number | undefined): LabelSpec {\n    if (numClasses === undefined || numClasses === COCO_CLASSES.length) {\n        return \"coco\";\n    }\n    return null;\n}\n\nexport function resolveLabels(\n    spec: LabelSpec,\n    options: ResolveLabelsOptions = {},\n): readonly string[] {\n    const labels = resolve(spec, options.numClasses);\n    if (options.numClasses !== undefined && labels.length !== options.numClasses) {\n        throw new LabelMapError(\n            `Resolved ${labels.length} labels but the model has ${options.numClasses} classes.`,\n        );\n    }\n    return labels;\n}\n\nfunction resolve(spec: LabelSpec, numClasses: number | undefined): readonly string[] {\n    if (spec === null || spec === undefined) {\n        if (numClasses === undefined) {\n            throw new LabelMapError(\n                \"Cannot auto-generate labels without numClasses. Pass an explicit labels spec or numClasses.\",\n            );\n        }\n        return Array.from({ length: numClasses }, (_, i) => `class_${i}`);\n    }\n\n    if (Array.isArray(spec)) {\n        return [...spec];\n    }\n\n    if (typeof spec === \"string\") {\n        const preset = PRESETS[spec];\n        if (preset !== undefined) {\n            return preset;\n        }\n        throw new LabelMapError(\n            `Unknown labels preset: ${JSON.stringify(spec)}. Known presets: ${Object.keys(PRESETS).join(\", \")}.`,\n        );\n    }\n\n    if (typeof spec === \"object\") {\n        const map = spec as Record<number, string>;\n        const ids = Object.keys(map).map((k) => Number(k));\n        if (ids.length === 0) {\n            return [];\n        }\n        const maxId = Math.max(...ids);\n        return Array.from({ length: maxId + 1 }, (_, i) => map[i] ?? `class_${i}`);\n    }\n\n    throw new LabelMapError(`Unsupported labels spec type: ${typeof spec}.`);\n}\n"],"mappings":";;AAyBA,IAAa,IAAkC,OAAO,OAAO,woBAiF7D,CAAC,GAEK,IAAuD,EACzD,MAAM,EACV;AAiCA,SAAgB,EAAc,GAA2C;CAIrE,OAHI,MAAe,KAAA,KAAa,MAAe,EAAa,SACjD,SAEJ;AACX;AAEA,SAAgB,EACZ,GACA,IAAgC,CAAC,GAChB;CACjB,IAAM,IAAS,EAAQ,GAAM,EAAQ,UAAU;CAC/C,IAAI,EAAQ,eAAe,KAAA,KAAa,EAAO,WAAW,EAAQ,YAC9D,MAAM,IAAI,EACN,YAAY,EAAO,OAAO,4BAA4B,EAAQ,WAAW,UAC7E;CAEJ,OAAO;AACX;AAEA,SAAS,EAAQ,GAAiB,GAAmD;CACjF,IAAI,KAAS,MAA4B;EACrC,IAAI,MAAe,KAAA,GACf,MAAM,IAAI,EACN,6FACJ;EAEJ,OAAO,MAAM,KAAK,EAAE,QAAQ,EAAW,IAAI,GAAG,MAAM,SAAS,GAAG;CACpE;CAEA,IAAI,MAAM,QAAQ,CAAI,GAClB,OAAO,CAAC,GAAG,CAAI;CAGnB,IAAI,OAAO,KAAS,UAAU;EAC1B,IAAM,IAAS,EAAQ;EACvB,IAAI,MAAW,KAAA,GACX,OAAO;EAEX,MAAM,IAAI,EACN,0BAA0B,KAAK,UAAU,CAAI,EAAE,mBAAmB,OAAO,KAAK,CAAO,CAAC,CAAC,KAAK,IAAI,EAAE,EACtG;CACJ;CAEA,IAAI,OAAO,KAAS,UAAU;EAC1B,IAAM,IAAM,GACN,IAAM,OAAO,KAAK,CAAG,CAAC,CAAC,KAAK,MAAM,OAAO,CAAC,CAAC;EACjD,IAAI,EAAI,WAAW,GACf,OAAO,CAAC;EAEZ,IAAM,IAAQ,KAAK,IAAI,GAAG,CAAG;EAC7B,OAAO,MAAM,KAAK,EAAE,QAAQ,IAAQ,EAAE,IAAI,GAAG,MAAM,EAAI,MAAM,SAAS,GAAG;CAC7E;CAEA,MAAM,IAAI,EAAc,iCAAiC,OAAO,EAAK,EAAE;AAC3E"}

package/dist/vision/postprocess/detection.cjs

@@ -1,2 +1,2 @@
-const e=require("../types.cjs");function t(e,t,n){let r=t.length;if(r===0)return new Int32Array;let i=new Float32Array(r);for(let t=0;t<r;t++){let n=e[t*4],r=e[t*4+1],a=e[t*4+2],o=e[t*4+3];i[t]=Math.max(0,a-n)*Math.max(0,o-r)}let a=Array(r);for(let e=0;e<r;e++)a[e]=e;a.sort((e,n)=>t[n]-t[e]);let o=new Uint8Array(r),s=[];for(let t=0;t<a.length;t++){let r=a[t];if(o[r])continue;s.push(r);let c=e[r*4],l=e[r*4+1],u=e[r*4+2],d=e[r*4+3],f=i[r];for(let r=t+1;r<a.length;r++){let t=a[r];if(o[t])continue;let s=e[t*4],p=e[t*4+1],m=e[t*4+2],h=e[t*4+3],g=Math.max(c,s),_=Math.max(l,p),v=Math.min(u,m),y=Math.min(d,h),b=Math.max(0,v-g)*Math.max(0,y-_),x=f+i[t]-b;(x>0?b/x:0)>n&&(o[t]=1)}}return Int32Array.from(s)}function n(e,n,r,i){if(n.length===0)return new Int32Array;let a=new Map;for(let e=0;e<r.length;e++){let t=r[e],n=a.get(t);n===void 0?a.set(t,[e]):n.push(e)}let o=[];for(let r of a.values()){let a=r.length,s=new Float32Array(a*4),c=new Float32Array(a);for(let t=0;t<a;t++){let i=r[t];s[t*4]=e[i*4],s[t*4+1]=e[i*4+1],s[t*4+2]=e[i*4+2],s[t*4+3]=e[i*4+3],c[t]=n[i]}let l=t(s,c,i);for(let e=0;e<l.length;e++)o.push(r[l[e]])}return o.sort((e,t)=>n[t]-n[e]),Int32Array.from(o)}function r(e,t,r){let a=t;if(a.length===3){if(a[0]!==1)throw Error(`decodeYoloAnchors: expected batch size 1, got ${a[0]}.`);a=[a[1],a[2]]}if(a.length!==2)throw Error(`decodeYoloAnchors: expected 2-D output after batch removal, got dims=${JSON.stringify(t)}.`);let o=a[0],s=a[1],{numClasses:c,originalWidth:l,originalHeight:u,padLeft:d,padTop:f,scale:p,confThreshold:m,iouThreshold:h,maxDetections:g}=r;if(c<1||c+4>o)throw Error(`decodeYoloAnchors: invalid numClasses=${c} for channels=${o}.`);if(e.length!==o*s)throw Error(`decodeYoloAnchors: data length ${e.length} does not match channels*numAnchors=${o*s}.`);let _=[];for(let t=0;t<s;t++){let n=0,r=-1/0;for(let i=0;i<c;i++){let a=e[(4+i)*s+t];a!==void 0&&a>r&&(r=a,n=i)}if(r<m)continue;let i=e[t],a=e[s+t],o=e[2*s+t],h=e[3*s+t],g=i-o/2,v=a-h/2,y=i+o/2,b=a+h/2;g=(g-d)/p,v=(v-f)/p,y=(y-d)/p,b=(b-f)/p,g=Math.max(0,Math.min(l,g)),v=Math.max(0,Math.min(u,v)),y=Math.max(0,Math.min(l,y)),b=Math.max(0,Math.min(u,b)),_.push({anchorIdx:t,x1:g,y1:v,x2:y,y2:b,classId:n,confidence:r})}if(_.length===0)return i();let v=new Float32Array(_.length*4),y=new Float32Array(_.length),b=new Int32Array(_.length);for(let e=0;e<_.length;e++){let t=_[e];v[e*4]=t.x1,v[e*4+1]=t.y1,v[e*4+2]=t.x2,v[e*4+3]=t.y2,y[e]=t.confidence,b[e]=t.classId}let x=n(v,y,b,h);if(x.length===0)return i();let S=Array.from(x).slice(0,g),C=S.length,w=new Int32Array(C),T=new Float32Array(C*4),E=new Int32Array(C),D=new Float32Array(C);for(let e=0;e<C;e++){let t=_[S[e]];w[e]=t.anchorIdx,T[e*4]=t.x1,T[e*4+1]=t.y1,T[e*4+2]=t.x2,T[e*4+3]=t.y2,E[e]=t.classId,D[e]=t.confidence}return{anchorIndices:w,boxesXyxy:T,classIds:E,confidences:D}}function i(){return{anchorIndices:new Int32Array,boxesXyxy:new Float32Array,classIds:new Int32Array,confidences:new Float32Array}}function a(t,n,i){let a=n.length===3?n[1]:n[0];if(a===void 0||a<5)throw Error(`decodeYolo: invalid output channel count ${a} (expected >= 5).`);let o=r(t,n,{numClasses:a-4,...i}),s=[];for(let t=0;t<o.classIds.length;t++)s.push({bbox:new e.BoundingBox(o.boxesXyxy[t*4],o.boxesXyxy[t*4+1],o.boxesXyxy[t*4+2],o.boxesXyxy[t*4+3]),classId:o.classIds[t],confidence:o.confidences[t]});return s}var o=!1,s=!1;function c(e,t,n){return o||(o=!0,console.warn(`[@ort-vision-sdk/web] decodeYoloV8 is deprecated since 0.2.0; use decodeYolo. The alias will be removed in 0.4.0.`)),a(e,t,n)}function l(e,t,n){return s||(s=!0,console.warn(`[@ort-vision-sdk/web] decodeYoloV8Anchors is deprecated since 0.2.0; use decodeYoloAnchors. The alias will be removed in 0.4.0.`)),r(e,t,n)}exports.batchedNms=n,exports.decodeYolo=a,exports.decodeYoloAnchors=r,exports.decodeYoloV8=c,exports.decodeYoloV8Anchors=l,exports.nms=t;
+const e=require("../types.cjs");function t(e,t,n){let r=t.length;if(r===0)return new Int32Array;let i=new Float32Array(r);for(let t=0;t<r;t++){let n=e[t*4],r=e[t*4+1],a=e[t*4+2],o=e[t*4+3];i[t]=Math.max(0,a-n)*Math.max(0,o-r)}let a=Array(r);for(let e=0;e<r;e++)a[e]=e;a.sort((e,n)=>t[n]-t[e]||e-n);let o=new Uint8Array(r),s=[];for(let t=0;t<a.length;t++){let r=a[t];if(o[r])continue;s.push(r);let c=e[r*4],l=e[r*4+1],u=e[r*4+2],d=e[r*4+3],f=i[r];for(let r=t+1;r<a.length;r++){let t=a[r];if(o[t])continue;let s=e[t*4],p=e[t*4+1],m=e[t*4+2],h=e[t*4+3],g=Math.max(c,s),_=Math.max(l,p),v=Math.min(u,m),y=Math.min(d,h),b=Math.max(0,v-g)*Math.max(0,y-_),x=f+i[t]-b;(x>0?b/x:0)>n&&(o[t]=1)}}return Int32Array.from(s)}function n(e,n,r,i){if(n.length===0)return new Int32Array;let a=new Map;for(let e=0;e<r.length;e++){let t=r[e],n=a.get(t);n===void 0?a.set(t,[e]):n.push(e)}let o=[];for(let r of a.values()){let a=r.length,s=new Float32Array(a*4),c=new Float32Array(a);for(let t=0;t<a;t++){let i=r[t];s[t*4]=e[i*4],s[t*4+1]=e[i*4+1],s[t*4+2]=e[i*4+2],s[t*4+3]=e[i*4+3],c[t]=n[i]}let l=t(s,c,i);for(let e=0;e<l.length;e++)o.push(r[l[e]])}return o.sort((e,t)=>n[t]-n[e]||e-t),Int32Array.from(o)}function r(e,t,r){let a=t;if(a.length===3){if(a[0]!==1)throw Error(`decodeYoloAnchors: expected batch size 1, got ${a[0]}.`);a=[a[1],a[2]]}if(a.length!==2)throw Error(`decodeYoloAnchors: expected 2-D output after batch removal, got dims=${JSON.stringify(t)}.`);let o=a[0],s=a[1],{numClasses:c,originalWidth:l,originalHeight:u,padLeft:d,padTop:f,scale:p,confThreshold:m,iouThreshold:h,maxDetections:g}=r;if(c<1||c+4>o)throw Error(`decodeYoloAnchors: invalid numClasses=${c} for channels=${o}.`);if(e.length!==o*s)throw Error(`decodeYoloAnchors: data length ${e.length} does not match channels*numAnchors=${o*s}.`);let _=[];for(let t=0;t<s;t++){let n=0,r=-1/0;for(let i=0;i<c;i++){let a=e[(4+i)*s+t];a!==void 0&&a>r&&(r=a,n=i)}if(r<m)continue;let i=e[t],a=e[s+t],o=e[2*s+t],h=e[3*s+t],g=i-o/2,v=a-h/2,y=i+o/2,b=a+h/2;g=(g-d)/p,v=(v-f)/p,y=(y-d)/p,b=(b-f)/p,g=Math.max(0,Math.min(l,g)),v=Math.max(0,Math.min(u,v)),y=Math.max(0,Math.min(l,y)),b=Math.max(0,Math.min(u,b)),_.push({anchorIdx:t,x1:g,y1:v,x2:y,y2:b,classId:n,confidence:r})}if(_.length===0)return i();let v=new Float32Array(_.length*4),y=new Float32Array(_.length),b=new Int32Array(_.length);for(let e=0;e<_.length;e++){let t=_[e];v[e*4]=t.x1,v[e*4+1]=t.y1,v[e*4+2]=t.x2,v[e*4+3]=t.y2,y[e]=t.confidence,b[e]=t.classId}let x=n(v,y,b,h);if(x.length===0)return i();let S=Array.from(x).slice(0,g),C=S.length,w=new Int32Array(C),T=new Float32Array(C*4),E=new Int32Array(C),D=new Float32Array(C);for(let e=0;e<C;e++){let t=_[S[e]];w[e]=t.anchorIdx,T[e*4]=t.x1,T[e*4+1]=t.y1,T[e*4+2]=t.x2,T[e*4+3]=t.y2,E[e]=t.classId,D[e]=t.confidence}return{anchorIndices:w,boxesXyxy:T,classIds:E,confidences:D}}function i(){return{anchorIndices:new Int32Array,boxesXyxy:new Float32Array,classIds:new Int32Array,confidences:new Float32Array}}function a(t,n,i){let a=n.length===3?n[1]:n[0];if(a===void 0||a<5)throw Error(`decodeYolo: invalid output channel count ${a} (expected >= 5).`);let o=r(t,n,{numClasses:a-4,...i}),s=[];for(let t=0;t<o.classIds.length;t++)s.push({bbox:new e.BoundingBox(o.boxesXyxy[t*4],o.boxesXyxy[t*4+1],o.boxesXyxy[t*4+2],o.boxesXyxy[t*4+3]),classId:o.classIds[t],confidence:o.confidences[t]});return s}exports.batchedNms=n,exports.decodeYolo=a,exports.decodeYoloAnchors=r,exports.nms=t;
 //# sourceMappingURL=detection.cjs.map

package/dist/vision/postprocess/detection.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"detection.cjs","names":[],"sources":["../../../src/vision/postprocess/detection.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Detection head postprocessing: anchor-free YOLO decoding + non-maximum suppression.\n *\n * The shared {@link decodeYoloAnchors} helper does the per-anchor work that\n * is identical for plain detection and segmentation (transpose, xywh→xyxy,\n * letterbox unmap, per-class NMS, sort & cap). {@link decodeYolo} is a thin\n * wrapper around it; the segmentation module ({@link ./segmentation.js})\n * calls the helper directly so it can also recover the per-anchor mask\n * coefficients.\n *\n * Works for any YOLO export with the post-v8 anchor-free head:\n * **YOLOv8 / v9 / v10 / v11 / v12** detect heads, all of which share the\n * `[1, 4 + nc, N]` output layout.\n */\n\nimport { BoundingBox } from \"../types\";\n\n/**\n * Greedy non-maximum suppression on axis-aligned bounding boxes.\n *\n * Mirrors `torchvision.ops.nms` (keeps boxes with the highest score, drops\n * any subsequent box whose IoU exceeds the threshold).\n *\n * @param boxes Flat array of length `4 * N` in xyxy order: `[x1,y1,x2,y2, ...]`.\n * @param scores Detection score per box, length `N`.\n * @param iouThreshold Boxes with IoU above this threshold relative to a kept box are suppressed.\n * @returns Indices of kept boxes, in descending score order.\n */\nexport function nms(boxes: Float32Array, scores: Float32Array, iouThreshold: number): Int32Array {\n    const n = scores.length;\n    if (n === 0) return new Int32Array(0);\n\n    const areas = new Float32Array(n);\n    for (let i = 0; i < n; i++) {\n        const x1 = boxes[i * 4] as number;\n        const y1 = boxes[i * 4 + 1] as number;\n        const x2 = boxes[i * 4 + 2] as number;\n        const y2 = boxes[i * 4 + 3] as number;\n        areas[i] = Math.max(0, x2 - x1) * Math.max(0, y2 - y1);\n    }\n\n    const order = new Array<number>(n);\n    for (let i = 0; i < n; i++) order[i] = i;\n    order.sort((a, b) => (scores[b] as number) - (scores[a] as number));\n\n    const suppressed = new Uint8Array(n);\n    const keep: number[] = [];\n\n    for (let oi = 0; oi < order.length; oi++) {\n        const i = order[oi] as number;\n        if (suppressed[i]) continue;\n        keep.push(i);\n\n        const ax1 = boxes[i * 4] as number;\n        const ay1 = boxes[i * 4 + 1] as number;\n        const ax2 = boxes[i * 4 + 2] as number;\n        const ay2 = boxes[i * 4 + 3] as number;\n        const ai = areas[i] as number;\n\n        for (let oj = oi + 1; oj < order.length; oj++) {\n            const j = order[oj] as number;\n            if (suppressed[j]) continue;\n\n            const bx1 = boxes[j * 4] as number;\n            const by1 = boxes[j * 4 + 1] as number;\n            const bx2 = boxes[j * 4 + 2] as number;\n            const by2 = boxes[j * 4 + 3] as number;\n\n            const ix1 = Math.max(ax1, bx1);\n            const iy1 = Math.max(ay1, by1);\n            const ix2 = Math.min(ax2, bx2);\n            const iy2 = Math.min(ay2, by2);\n            const iw = Math.max(0, ix2 - ix1);\n            const ih = Math.max(0, iy2 - iy1);\n            const inter = iw * ih;\n            const union = ai + (areas[j] as number) - inter;\n            const iou = union > 0 ? inter / union : 0;\n            if (iou > iouThreshold) suppressed[j] = 1;\n        }\n    }\n\n    return Int32Array.from(keep);\n}\n\n/**\n * Per-class NMS — boxes are suppressed only by other boxes of the same class.\n *\n * Mirrors `torchvision.ops.batched_nms`.\n *\n * @param boxes Flat array of length `4 * N` in xyxy order.\n * @param scores Detection score per box, length `N`.\n * @param idxs Class index per box, length `N`. Boxes with different `idxs`\n *   never suppress each other.\n * @param iouThreshold IoU threshold for suppression within a class.\n */\nexport function batchedNms(\n    boxes: Float32Array,\n    scores: Float32Array,\n    idxs: Int32Array,\n    iouThreshold: number,\n): Int32Array {\n    if (scores.length === 0) return new Int32Array(0);\n\n    const byClass = new Map<number, number[]>();\n    for (let i = 0; i < idxs.length; i++) {\n        const c = idxs[i] as number;\n        const list = byClass.get(c);\n        if (list === undefined) byClass.set(c, [i]);\n        else list.push(i);\n    }\n\n    const keep: number[] = [];\n    for (const indices of byClass.values()) {\n        const m = indices.length;\n        const subBoxes = new Float32Array(m * 4);\n        const subScores = new Float32Array(m);\n        for (let k = 0; k < m; k++) {\n            const i = indices[k] as number;\n            subBoxes[k * 4] = boxes[i * 4] as number;\n            subBoxes[k * 4 + 1] = boxes[i * 4 + 1] as number;\n            subBoxes[k * 4 + 2] = boxes[i * 4 + 2] as number;\n            subBoxes[k * 4 + 3] = boxes[i * 4 + 3] as number;\n            subScores[k] = scores[i] as number;\n        }\n        const subKeep = nms(subBoxes, subScores, iouThreshold);\n        for (let k = 0; k < subKeep.length; k++) {\n            keep.push(indices[subKeep[k] as number] as number);\n        }\n    }\n\n    keep.sort((a, b) => (scores[b] as number) - (scores[a] as number));\n    return Int32Array.from(keep);\n}\n\nexport interface DecodeYoloAnchorsOptions {\n    /** Number of class-score channels following the 4 box channels. */\n    readonly numClasses: number;\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedAnchors {\n    /** Indices into the original `numAnchors` axis, in descending confidence order. */\n    readonly anchorIndices: Int32Array;\n    /** `[k, 4]` boxes in original-image pixel coords, flat row-major xyxy. */\n    readonly boxesXyxy: Float32Array;\n    /** Predicted class id per survivor. */\n    readonly classIds: Int32Array;\n    /** Confidence per survivor. */\n    readonly confidences: Float32Array;\n}\n\n/**\n * Shared YOLO per-anchor decode used by both detection and segmentation\n * (v8 / v9 / v10 / v11 / v12).\n *\n * Only the first `4 + numClasses` channels are read; later channels (e.g.\n * mask coefficients) are ignored — callers can fetch them via the returned\n * {@link DecodedAnchors.anchorIndices}.\n *\n * @param data Flat per-anchor output, length `channels * numAnchors`.\n * @param dims Dims as reported by ORT, e.g. `[1, 84, 8400]` (det) or\n *   `[1, 116, 8400]` (seg). The leading batch dim must be 1.\n */\nexport function decodeYoloAnchors(\n    data: Float32Array,\n    dims: readonly number[],\n    options: DecodeYoloAnchorsOptions,\n): DecodedAnchors {\n    let normalized = dims;\n    if (normalized.length === 3) {\n        if (normalized[0] !== 1) {\n            throw new Error(`decodeYoloAnchors: expected batch size 1, got ${normalized[0]}.`);\n        }\n        normalized = [normalized[1] as number, normalized[2] as number];\n    }\n    if (normalized.length !== 2) {\n        throw new Error(\n            `decodeYoloAnchors: expected 2-D output after batch removal, got dims=${JSON.stringify(dims)}.`,\n        );\n    }\n    const channels = normalized[0] as number;\n    const numAnchors = normalized[1] as number;\n\n    const {\n        numClasses,\n        originalWidth,\n        originalHeight,\n        padLeft,\n        padTop,\n        scale,\n        confThreshold,\n        iouThreshold,\n        maxDetections,\n    } = options;\n\n    if (numClasses < 1 || numClasses + 4 > channels) {\n        throw new Error(\n            `decodeYoloAnchors: invalid numClasses=${numClasses} for channels=${channels}.`,\n        );\n    }\n    if (data.length !== channels * numAnchors) {\n        throw new Error(\n            `decodeYoloAnchors: data length ${data.length} does not match channels*numAnchors=${channels * numAnchors}.`,\n        );\n    }\n\n    type Candidate = {\n        anchorIdx: number;\n        x1: number;\n        y1: number;\n        x2: number;\n        y2: number;\n        classId: number;\n        confidence: number;\n    };\n    const candidates: Candidate[] = [];\n\n    for (let a = 0; a < numAnchors; a++) {\n        let bestCls = 0;\n        let bestScore = -Infinity;\n        for (let c = 0; c < numClasses; c++) {\n            const s = data[(4 + c) * numAnchors + a];\n            if (s !== undefined && s > bestScore) {\n                bestScore = s;\n                bestCls = c;\n            }\n        }\n        if (bestScore < confThreshold) continue;\n\n        const cx = data[a] as number;\n        const cy = data[numAnchors + a] as number;\n        const w = data[2 * numAnchors + a] as number;\n        const h = data[3 * numAnchors + a] as number;\n\n        let x1 = cx - w / 2;\n        let y1 = cy - h / 2;\n        let x2 = cx + w / 2;\n        let y2 = cy + h / 2;\n\n        x1 = (x1 - padLeft) / scale;\n        y1 = (y1 - padTop) / scale;\n        x2 = (x2 - padLeft) / scale;\n        y2 = (y2 - padTop) / scale;\n\n        x1 = Math.max(0, Math.min(originalWidth, x1));\n        y1 = Math.max(0, Math.min(originalHeight, y1));\n        x2 = Math.max(0, Math.min(originalWidth, x2));\n        y2 = Math.max(0, Math.min(originalHeight, y2));\n\n        candidates.push({ anchorIdx: a, x1, y1, x2, y2, classId: bestCls, confidence: bestScore });\n    }\n\n    if (candidates.length === 0) return emptyDecoded();\n\n    // Build flat arrays then delegate to batchedNms — same algorithm as before\n    // but funnelled through the public per-class NMS helper.\n    const flatBoxes = new Float32Array(candidates.length * 4);\n    const scoresArr = new Float32Array(candidates.length);\n    const idxsArr = new Int32Array(candidates.length);\n    for (let i = 0; i < candidates.length; i++) {\n        const c = candidates[i] as Candidate;\n        flatBoxes[i * 4] = c.x1;\n        flatBoxes[i * 4 + 1] = c.y1;\n        flatBoxes[i * 4 + 2] = c.x2;\n        flatBoxes[i * 4 + 3] = c.y2;\n        scoresArr[i] = c.confidence;\n        idxsArr[i] = c.classId;\n    }\n    const kept = batchedNms(flatBoxes, scoresArr, idxsArr, iouThreshold);\n    if (kept.length === 0) return emptyDecoded();\n\n    const limited = Array.from(kept).slice(0, maxDetections);\n    const k = limited.length;\n    const anchorIndices = new Int32Array(k);\n    const boxesXyxy = new Float32Array(k * 4);\n    const classIds = new Int32Array(k);\n    const confidences = new Float32Array(k);\n    for (let i = 0; i < k; i++) {\n        const c = candidates[limited[i] as number] as Candidate;\n        anchorIndices[i] = c.anchorIdx;\n        boxesXyxy[i * 4] = c.x1;\n        boxesXyxy[i * 4 + 1] = c.y1;\n        boxesXyxy[i * 4 + 2] = c.x2;\n        boxesXyxy[i * 4 + 3] = c.y2;\n        classIds[i] = c.classId;\n        confidences[i] = c.confidence;\n    }\n    return { anchorIndices, boxesXyxy, classIds, confidences };\n}\n\nfunction emptyDecoded(): DecodedAnchors {\n    return {\n        anchorIndices: new Int32Array(0),\n        boxesXyxy: new Float32Array(0),\n        classIds: new Int32Array(0),\n        confidences: new Float32Array(0),\n    };\n}\n\nexport interface DecodeYoloOptions {\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedDetection {\n    readonly bbox: BoundingBox;\n    readonly classId: number;\n    readonly confidence: number;\n}\n\n/**\n * Decode an anchor-free YOLO detection output into a list of detections.\n *\n * Works for **YOLOv8 / v9 / v10 / v11 / v12** detect heads.\n *\n * Expected raw shape: `[1, 4 + numClasses, N]`. `numClasses` is inferred\n * from the channel count.\n */\nexport function decodeYolo(\n    output: Float32Array,\n    outputDims: readonly number[],\n    options: DecodeYoloOptions,\n): DecodedDetection[] {\n    const channels = outputDims.length === 3 ? outputDims[1] : outputDims[0];\n    if (channels === undefined || channels < 5) {\n        throw new Error(`decodeYolo: invalid output channel count ${channels} (expected >= 5).`);\n    }\n    const numClasses = channels - 4;\n\n    const decoded = decodeYoloAnchors(output, outputDims, {\n        numClasses,\n        ...options,\n    });\n\n    const results: DecodedDetection[] = [];\n    for (let i = 0; i < decoded.classIds.length; i++) {\n        results.push({\n            bbox: new BoundingBox(\n                decoded.boxesXyxy[i * 4] as number,\n                decoded.boxesXyxy[i * 4 + 1] as number,\n                decoded.boxesXyxy[i * 4 + 2] as number,\n                decoded.boxesXyxy[i * 4 + 3] as number,\n            ),\n            classId: decoded.classIds[i] as number,\n            confidence: decoded.confidences[i] as number,\n        });\n    }\n    return results;\n}\n\nlet _warnedDecodeYoloV8 = false;\nlet _warnedDecodeYoloV8Anchors = false;\n\n/**\n * @deprecated since 0.2.0 — use {@link decodeYolo}. Same behavior; the\n * decoder covers v8/v9/v10/v11/v12 detect heads. Will be removed in 0.4.0.\n */\nexport function decodeYoloV8(\n    output: Float32Array,\n    outputDims: readonly number[],\n    options: DecodeYoloOptions,\n): DecodedDetection[] {\n    if (!_warnedDecodeYoloV8) {\n        _warnedDecodeYoloV8 = true;\n        console.warn(\n            \"[@ort-vision-sdk/web] decodeYoloV8 is deprecated since 0.2.0; use decodeYolo. \" +\n                \"The alias will be removed in 0.4.0.\",\n        );\n    }\n    return decodeYolo(output, outputDims, options);\n}\n\n/**\n * @deprecated since 0.2.0 — use {@link decodeYoloAnchors}. Will be removed in 0.4.0.\n */\nexport function decodeYoloV8Anchors(\n    data: Float32Array,\n    dims: readonly number[],\n    options: DecodeYoloAnchorsOptions,\n): DecodedAnchors {\n    if (!_warnedDecodeYoloV8Anchors) {\n        _warnedDecodeYoloV8Anchors = true;\n        console.warn(\n            \"[@ort-vision-sdk/web] decodeYoloV8Anchors is deprecated since 0.2.0; use decodeYoloAnchors. \" +\n                \"The alias will be removed in 0.4.0.\",\n        );\n    }\n    return decodeYoloAnchors(data, dims, options);\n}\n\n/** @deprecated since 0.2.0 — use {@link DecodeYoloAnchorsOptions}. */\nexport type DecodeYoloV8AnchorsOptions = DecodeYoloAnchorsOptions;\n\n/** @deprecated since 0.2.0 — use {@link DecodeYoloOptions}. */\nexport type DecodeYoloV8Options = DecodeYoloOptions;\n"],"mappings":"gCA6BA,SAAgB,EAAI,EAAqB,EAAsB,EAAkC,CAC7F,IAAM,EAAI,EAAO,OACjB,GAAI,IAAM,EAAG,OAAO,IAAI,WAExB,IAAM,EAAQ,IAAI,aAAa,CAAC,EAChC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,CACxB,IAAM,EAAK,EAAM,EAAI,GACf,EAAK,EAAM,EAAI,EAAI,GACnB,EAAK,EAAM,EAAI,EAAI,GACnB,EAAK,EAAM,EAAI,EAAI,GACzB,EAAM,GAAK,KAAK,IAAI,EAAG,EAAK,CAAE,EAAI,KAAK,IAAI,EAAG,EAAK,CAAE,CACzD,CAEA,IAAM,EAAY,MAAc,CAAC,EACjC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,EAAM,GAAK,EACvC,EAAM,MAAM,EAAG,IAAO,EAAO,GAAiB,EAAO,EAAa,EAElE,IAAM,EAAa,IAAI,WAAW,CAAC,EAC7B,EAAiB,CAAC,EAExB,IAAK,IAAI,EAAK,EAAG,EAAK,EAAM,OAAQ,IAAM,CACtC,IAAM,EAAI,EAAM,GAChB,GAAI,EAAW,GAAI,SACnB,EAAK,KAAK,CAAC,EAEX,IAAM,EAAM,EAAM,EAAI,GAChB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAK,EAAM,GAEjB,IAAK,IAAI,EAAK,EAAK,EAAG,EAAK,EAAM,OAAQ,IAAM,CAC3C,IAAM,EAAI,EAAM,GAChB,GAAI,EAAW,GAAI,SAEnB,IAAM,EAAM,EAAM,EAAI,GAChB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GAEpB,EAAM,KAAK,IAAI,EAAK,CAAG,EACvB,EAAM,KAAK,IAAI,EAAK,CAAG,EACvB,EAAM,KAAK,IAAI,EAAK,CAAG,EACvB,EAAM,KAAK,IAAI,EAAK,CAAG,EAGvB,EAFK,KAAK,IAAI,EAAG,EAAM,CAEf,EADH,KAAK,IAAI,EAAG,EAAM,CACV,EACb,EAAQ,EAAM,EAAM,GAAgB,GAC9B,EAAQ,EAAI,EAAQ,EAAQ,GAC9B,IAAc,EAAW,GAAK,EAC5C,CACJ,CAEA,OAAO,WAAW,KAAK,CAAI,CAC/B,CAaA,SAAgB,EACZ,EACA,EACA,EACA,EACU,CACV,GAAI,EAAO,SAAW,EAAG,OAAO,IAAI,WAEpC,IAAM,EAAU,IAAI,IACpB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAK,OAAQ,IAAK,CAClC,IAAM,EAAI,EAAK,GACT,EAAO,EAAQ,IAAI,CAAC,EACtB,IAAS,IAAA,GAAW,EAAQ,IAAI,EAAG,CAAC,CAAC,CAAC,EACrC,EAAK,KAAK,CAAC,CACpB,CAEA,IAAM,EAAiB,CAAC,EACxB,IAAK,IAAM,KAAW,EAAQ,OAAO,EAAG,CACpC,IAAM,EAAI,EAAQ,OACZ,EAAW,IAAI,aAAa,EAAI,CAAC,EACjC,EAAY,IAAI,aAAa,CAAC,EACpC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,CACxB,IAAM,EAAI,EAAQ,GAClB,EAAS,EAAI,GAAK,EAAM,EAAI,GAC5B,EAAS,EAAI,EAAI,GAAK,EAAM,EAAI,EAAI,GACpC,EAAS,EAAI,EAAI,GAAK,EAAM,EAAI,EAAI,GACpC,EAAS,EAAI,EAAI,GAAK,EAAM,EAAI,EAAI,GACpC,EAAU,GAAK,EAAO,EAC1B,CACA,IAAM,EAAU,EAAI,EAAU,EAAW,CAAY,EACrD,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,OAAQ,IAChC,EAAK,KAAK,EAAQ,EAAQ,GAAuB,CAEzD,CAGA,OADA,EAAK,MAAM,EAAG,IAAO,EAAO,GAAiB,EAAO,EAAa,EAC1D,WAAW,KAAK,CAAI,CAC/B,CAsCA,SAAgB,EACZ,EACA,EACA,EACc,CACd,IAAI,EAAa,EACjB,GAAI,EAAW,SAAW,EAAG,CACzB,GAAI,EAAW,KAAO,EAClB,MAAU,MAAM,iDAAiD,EAAW,GAAG,EAAE,EAErF,EAAa,CAAC,EAAW,GAAc,EAAW,EAAY,CAClE,CACA,GAAI,EAAW,SAAW,EACtB,MAAU,MACN,wEAAwE,KAAK,UAAU,CAAI,EAAE,EACjG,EAEJ,IAAM,EAAW,EAAW,GACtB,EAAa,EAAW,GAExB,CACF,aACA,gBACA,iBACA,UACA,SACA,QACA,gBACA,eACA,iBACA,EAEJ,GAAI,EAAa,GAAK,EAAa,EAAI,EACnC,MAAU,MACN,yCAAyC,EAAW,gBAAgB,EAAS,EACjF,EAEJ,GAAI,EAAK,SAAW,EAAW,EAC3B,MAAU,MACN,kCAAkC,EAAK,OAAO,sCAAsC,EAAW,EAAW,EAC9G,EAYJ,IAAM,EAA0B,CAAC,EAEjC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAY,IAAK,CACjC,IAAI,EAAU,EACV,EAAY,KAChB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAY,IAAK,CACjC,IAAM,EAAI,GAAM,EAAI,GAAK,EAAa,GAClC,IAAM,IAAA,IAAa,EAAI,IACvB,EAAY,EACZ,EAAU,EAElB,CACA,GAAI,EAAY,EAAe,SAE/B,IAAM,EAAK,EAAK,GACV,EAAK,EAAK,EAAa,GACvB,EAAI,EAAK,EAAI,EAAa,GAC1B,EAAI,EAAK,EAAI,EAAa,GAE5B,EAAK,EAAK,EAAI,EACd,EAAK,EAAK,EAAI,EACd,EAAK,EAAK,EAAI,EACd,EAAK,EAAK,EAAI,EAElB,GAAM,EAAK,GAAW,EACtB,GAAM,EAAK,GAAU,EACrB,GAAM,EAAK,GAAW,EACtB,GAAM,EAAK,GAAU,EAErB,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAe,CAAE,CAAC,EAC5C,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAgB,CAAE,CAAC,EAC7C,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAe,CAAE,CAAC,EAC5C,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAgB,CAAE,CAAC,EAE7C,EAAW,KAAK,CAAE,UAAW,EAAG,KAAI,KAAI,KAAI,KAAI,QAAS,EAAS,WAAY,CAAU,CAAC,CAC7F,CAEA,GAAI,EAAW,SAAW,EAAG,OAAO,EAAa,EAIjD,IAAM,EAAY,IAAI,aAAa,EAAW,OAAS,CAAC,EAClD,EAAY,IAAI,aAAa,EAAW,MAAM,EAC9C,EAAU,IAAI,WAAW,EAAW,MAAM,EAChD,IAAK,IAAI,EAAI,EAAG,EAAI,EAAW,OAAQ,IAAK,CACxC,IAAM,EAAI,EAAW,GACrB,EAAU,EAAI,GAAK,EAAE,GACrB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,GAAK,EAAE,WACjB,EAAQ,GAAK,EAAE,OACnB,CACA,IAAM,EAAO,EAAW,EAAW,EAAW,EAAS,CAAY,EACnE,GAAI,EAAK,SAAW,EAAG,OAAO,EAAa,EAE3C,IAAM,EAAU,MAAM,KAAK,CAAI,CAAC,CAAC,MAAM,EAAG,CAAa,EACjD,EAAI,EAAQ,OACZ,EAAgB,IAAI,WAAW,CAAC,EAChC,EAAY,IAAI,aAAa,EAAI,CAAC,EAClC,EAAW,IAAI,WAAW,CAAC,EAC3B,EAAc,IAAI,aAAa,CAAC,EACtC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,CACxB,IAAM,EAAI,EAAW,EAAQ,IAC7B,EAAc,GAAK,EAAE,UACrB,EAAU,EAAI,GAAK,EAAE,GACrB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAS,GAAK,EAAE,QAChB,EAAY,GAAK,EAAE,UACvB,CACA,MAAO,CAAE,gBAAe,YAAW,WAAU,aAAY,CAC7D,CAEA,SAAS,GAA+B,CACpC,MAAO,CACH,cAAe,IAAI,WACnB,UAAW,IAAI,aACf,SAAU,IAAI,WACd,YAAa,IAAI,YACrB,CACJ,CA2BA,SAAgB,EACZ,EACA,EACA,EACkB,CAClB,IAAM,EAAW,EAAW,SAAW,EAAI,EAAW,GAAK,EAAW,GACtE,GAAI,IAAa,IAAA,IAAa,EAAW,EACrC,MAAU,MAAM,4CAA4C,EAAS,kBAAkB,EAI3F,IAAM,EAAU,EAAkB,EAAQ,EAAY,CAClD,WAHe,EAAW,EAI1B,GAAG,CACP,CAAC,EAEK,EAA8B,CAAC,EACrC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,SAAS,OAAQ,IACzC,EAAQ,KAAK,CACT,KAAM,IAAI,EAAA,YACN,EAAQ,UAAU,EAAI,GACtB,EAAQ,UAAU,EAAI,EAAI,GAC1B,EAAQ,UAAU,EAAI,EAAI,GAC1B,EAAQ,UAAU,EAAI,EAAI,EAC9B,EACA,QAAS,EAAQ,SAAS,GAC1B,WAAY,EAAQ,YAAY,EACpC,CAAC,EAEL,OAAO,CACX,CAEA,IAAI,EAAsB,GACtB,EAA6B,GAMjC,SAAgB,EACZ,EACA,EACA,EACkB,CAQlB,OAPK,IACD,EAAsB,GACtB,QAAQ,KACJ,mHAEJ,GAEG,EAAW,EAAQ,EAAY,CAAO,CACjD,CAKA,SAAgB,EACZ,EACA,EACA,EACc,CAQd,OAPK,IACD,EAA6B,GAC7B,QAAQ,KACJ,iIAEJ,GAEG,EAAkB,EAAM,EAAM,CAAO,CAChD"}
+{"version":3,"file":"detection.cjs","names":[],"sources":["../../../src/vision/postprocess/detection.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Detection head postprocessing: anchor-free YOLO decoding + non-maximum suppression.\n *\n * The shared {@link decodeYoloAnchors} helper does the per-anchor work that\n * is identical for plain detection and segmentation (transpose, xywh→xyxy,\n * letterbox unmap, per-class NMS, sort & cap). {@link decodeYolo} is a thin\n * wrapper around it; the segmentation module ({@link ./segmentation.js})\n * calls the helper directly so it can also recover the per-anchor mask\n * coefficients.\n *\n * Works for any YOLO export with the post-v8 anchor-free head:\n * **YOLOv8 / v9 / v10 / v11 / v12** detect heads, all of which share the\n * `[1, 4 + nc, N]` output layout.\n */\n\nimport { BoundingBox } from \"../types\";\n\n/**\n * Greedy non-maximum suppression on axis-aligned bounding boxes.\n *\n * Mirrors `torchvision.ops.nms` (keeps boxes with the highest score, drops\n * any subsequent box whose IoU exceeds the threshold).\n *\n * @param boxes Flat array of length `4 * N` in xyxy order: `[x1,y1,x2,y2, ...]`.\n * @param scores Detection score per box, length `N`.\n * @param iouThreshold Boxes with IoU above this threshold relative to a kept box are suppressed.\n * @returns Indices of kept boxes, in descending score order. Boxes tied on\n *   score are visited lowest-index first, so the survivor of a tie is\n *   deterministic and matches both `torchvision` and the Python SDK.\n */\nexport function nms(boxes: Float32Array, scores: Float32Array, iouThreshold: number): Int32Array {\n    const n = scores.length;\n    if (n === 0) return new Int32Array(0);\n\n    const areas = new Float32Array(n);\n    for (let i = 0; i < n; i++) {\n        const x1 = boxes[i * 4] as number;\n        const y1 = boxes[i * 4 + 1] as number;\n        const x2 = boxes[i * 4 + 2] as number;\n        const y2 = boxes[i * 4 + 3] as number;\n        areas[i] = Math.max(0, x2 - x1) * Math.max(0, y2 - y1);\n    }\n\n    const order = new Array<number>(n);\n    for (let i = 0; i < n; i++) order[i] = i;\n    order.sort((a, b) => (scores[b] as number) - (scores[a] as number) || a - b);\n\n    const suppressed = new Uint8Array(n);\n    const keep: number[] = [];\n\n    for (let oi = 0; oi < order.length; oi++) {\n        const i = order[oi] as number;\n        if (suppressed[i]) continue;\n        keep.push(i);\n\n        const ax1 = boxes[i * 4] as number;\n        const ay1 = boxes[i * 4 + 1] as number;\n        const ax2 = boxes[i * 4 + 2] as number;\n        const ay2 = boxes[i * 4 + 3] as number;\n        const ai = areas[i] as number;\n\n        for (let oj = oi + 1; oj < order.length; oj++) {\n            const j = order[oj] as number;\n            if (suppressed[j]) continue;\n\n            const bx1 = boxes[j * 4] as number;\n            const by1 = boxes[j * 4 + 1] as number;\n            const bx2 = boxes[j * 4 + 2] as number;\n            const by2 = boxes[j * 4 + 3] as number;\n\n            const ix1 = Math.max(ax1, bx1);\n            const iy1 = Math.max(ay1, by1);\n            const ix2 = Math.min(ax2, bx2);\n            const iy2 = Math.min(ay2, by2);\n            const iw = Math.max(0, ix2 - ix1);\n            const ih = Math.max(0, iy2 - iy1);\n            const inter = iw * ih;\n            const union = ai + (areas[j] as number) - inter;\n            const iou = union > 0 ? inter / union : 0;\n            if (iou > iouThreshold) suppressed[j] = 1;\n        }\n    }\n\n    return Int32Array.from(keep);\n}\n\n/**\n * Per-class NMS — boxes are suppressed only by other boxes of the same class.\n *\n * Mirrors `torchvision.ops.batched_nms`.\n *\n * @param boxes Flat array of length `4 * N` in xyxy order.\n * @param scores Detection score per box, length `N`.\n * @param idxs Class index per box, length `N`. Boxes with different `idxs`\n *   never suppress each other.\n * @param iouThreshold IoU threshold for suppression within a class.\n * @returns Indices of kept boxes, sorted by descending score across all\n *   classes. Survivors from different classes that are tied on score are\n *   ordered lowest-index first — an explicit tie-break, because the order the\n *   per-class loop emits them in is an implementation detail (here, `Map`\n *   insertion order; in Python, sorted class order).\n */\nexport function batchedNms(\n    boxes: Float32Array,\n    scores: Float32Array,\n    idxs: Int32Array,\n    iouThreshold: number,\n): Int32Array {\n    if (scores.length === 0) return new Int32Array(0);\n\n    const byClass = new Map<number, number[]>();\n    for (let i = 0; i < idxs.length; i++) {\n        const c = idxs[i] as number;\n        const list = byClass.get(c);\n        if (list === undefined) byClass.set(c, [i]);\n        else list.push(i);\n    }\n\n    const keep: number[] = [];\n    for (const indices of byClass.values()) {\n        const m = indices.length;\n        const subBoxes = new Float32Array(m * 4);\n        const subScores = new Float32Array(m);\n        for (let k = 0; k < m; k++) {\n            const i = indices[k] as number;\n            subBoxes[k * 4] = boxes[i * 4] as number;\n            subBoxes[k * 4 + 1] = boxes[i * 4 + 1] as number;\n            subBoxes[k * 4 + 2] = boxes[i * 4 + 2] as number;\n            subBoxes[k * 4 + 3] = boxes[i * 4 + 3] as number;\n            subScores[k] = scores[i] as number;\n        }\n        const subKeep = nms(subBoxes, subScores, iouThreshold);\n        for (let k = 0; k < subKeep.length; k++) {\n            keep.push(indices[subKeep[k] as number] as number);\n        }\n    }\n\n    keep.sort((a, b) => (scores[b] as number) - (scores[a] as number) || a - b);\n    return Int32Array.from(keep);\n}\n\nexport interface DecodeYoloAnchorsOptions {\n    /** Number of class-score channels following the 4 box channels. */\n    readonly numClasses: number;\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedAnchors {\n    /** Indices into the original `numAnchors` axis, in descending confidence order. */\n    readonly anchorIndices: Int32Array;\n    /** `[k, 4]` boxes in original-image pixel coords, flat row-major xyxy. */\n    readonly boxesXyxy: Float32Array;\n    /** Predicted class id per survivor. */\n    readonly classIds: Int32Array;\n    /** Confidence per survivor. */\n    readonly confidences: Float32Array;\n}\n\n/**\n * Shared YOLO per-anchor decode used by both detection and segmentation\n * (v8 / v9 / v10 / v11 / v12).\n *\n * Only the first `4 + numClasses` channels are read; later channels (e.g.\n * mask coefficients) are ignored — callers can fetch them via the returned\n * {@link DecodedAnchors.anchorIndices}.\n *\n * @param data Flat per-anchor output, length `channels * numAnchors`.\n * @param dims Dims as reported by ORT, e.g. `[1, 84, 8400]` (det) or\n *   `[1, 116, 8400]` (seg). The leading batch dim must be 1.\n */\nexport function decodeYoloAnchors(\n    data: Float32Array,\n    dims: readonly number[],\n    options: DecodeYoloAnchorsOptions,\n): DecodedAnchors {\n    let normalized = dims;\n    if (normalized.length === 3) {\n        if (normalized[0] !== 1) {\n            throw new Error(`decodeYoloAnchors: expected batch size 1, got ${normalized[0]}.`);\n        }\n        normalized = [normalized[1] as number, normalized[2] as number];\n    }\n    if (normalized.length !== 2) {\n        throw new Error(\n            `decodeYoloAnchors: expected 2-D output after batch removal, got dims=${JSON.stringify(dims)}.`,\n        );\n    }\n    const channels = normalized[0] as number;\n    const numAnchors = normalized[1] as number;\n\n    const {\n        numClasses,\n        originalWidth,\n        originalHeight,\n        padLeft,\n        padTop,\n        scale,\n        confThreshold,\n        iouThreshold,\n        maxDetections,\n    } = options;\n\n    if (numClasses < 1 || numClasses + 4 > channels) {\n        throw new Error(\n            `decodeYoloAnchors: invalid numClasses=${numClasses} for channels=${channels}.`,\n        );\n    }\n    if (data.length !== channels * numAnchors) {\n        throw new Error(\n            `decodeYoloAnchors: data length ${data.length} does not match channels*numAnchors=${channels * numAnchors}.`,\n        );\n    }\n\n    type Candidate = {\n        anchorIdx: number;\n        x1: number;\n        y1: number;\n        x2: number;\n        y2: number;\n        classId: number;\n        confidence: number;\n    };\n    const candidates: Candidate[] = [];\n\n    for (let a = 0; a < numAnchors; a++) {\n        let bestCls = 0;\n        let bestScore = -Infinity;\n        for (let c = 0; c < numClasses; c++) {\n            const s = data[(4 + c) * numAnchors + a];\n            if (s !== undefined && s > bestScore) {\n                bestScore = s;\n                bestCls = c;\n            }\n        }\n        if (bestScore < confThreshold) continue;\n\n        const cx = data[a] as number;\n        const cy = data[numAnchors + a] as number;\n        const w = data[2 * numAnchors + a] as number;\n        const h = data[3 * numAnchors + a] as number;\n\n        let x1 = cx - w / 2;\n        let y1 = cy - h / 2;\n        let x2 = cx + w / 2;\n        let y2 = cy + h / 2;\n\n        x1 = (x1 - padLeft) / scale;\n        y1 = (y1 - padTop) / scale;\n        x2 = (x2 - padLeft) / scale;\n        y2 = (y2 - padTop) / scale;\n\n        x1 = Math.max(0, Math.min(originalWidth, x1));\n        y1 = Math.max(0, Math.min(originalHeight, y1));\n        x2 = Math.max(0, Math.min(originalWidth, x2));\n        y2 = Math.max(0, Math.min(originalHeight, y2));\n\n        candidates.push({ anchorIdx: a, x1, y1, x2, y2, classId: bestCls, confidence: bestScore });\n    }\n\n    if (candidates.length === 0) return emptyDecoded();\n\n    // Build flat arrays then delegate to batchedNms — same algorithm as before\n    // but funnelled through the public per-class NMS helper.\n    const flatBoxes = new Float32Array(candidates.length * 4);\n    const scoresArr = new Float32Array(candidates.length);\n    const idxsArr = new Int32Array(candidates.length);\n    for (let i = 0; i < candidates.length; i++) {\n        const c = candidates[i] as Candidate;\n        flatBoxes[i * 4] = c.x1;\n        flatBoxes[i * 4 + 1] = c.y1;\n        flatBoxes[i * 4 + 2] = c.x2;\n        flatBoxes[i * 4 + 3] = c.y2;\n        scoresArr[i] = c.confidence;\n        idxsArr[i] = c.classId;\n    }\n    const kept = batchedNms(flatBoxes, scoresArr, idxsArr, iouThreshold);\n    if (kept.length === 0) return emptyDecoded();\n\n    const limited = Array.from(kept).slice(0, maxDetections);\n    const k = limited.length;\n    const anchorIndices = new Int32Array(k);\n    const boxesXyxy = new Float32Array(k * 4);\n    const classIds = new Int32Array(k);\n    const confidences = new Float32Array(k);\n    for (let i = 0; i < k; i++) {\n        const c = candidates[limited[i] as number] as Candidate;\n        anchorIndices[i] = c.anchorIdx;\n        boxesXyxy[i * 4] = c.x1;\n        boxesXyxy[i * 4 + 1] = c.y1;\n        boxesXyxy[i * 4 + 2] = c.x2;\n        boxesXyxy[i * 4 + 3] = c.y2;\n        classIds[i] = c.classId;\n        confidences[i] = c.confidence;\n    }\n    return { anchorIndices, boxesXyxy, classIds, confidences };\n}\n\nfunction emptyDecoded(): DecodedAnchors {\n    return {\n        anchorIndices: new Int32Array(0),\n        boxesXyxy: new Float32Array(0),\n        classIds: new Int32Array(0),\n        confidences: new Float32Array(0),\n    };\n}\n\nexport interface DecodeYoloOptions {\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedDetection {\n    readonly bbox: BoundingBox;\n    readonly classId: number;\n    readonly confidence: number;\n}\n\n/**\n * Decode an anchor-free YOLO detection output into a list of detections.\n *\n * Works for **YOLOv8 / v9 / v10 / v11 / v12** detect heads.\n *\n * Expected raw shape: `[1, 4 + numClasses, N]`. `numClasses` is inferred\n * from the channel count.\n */\nexport function decodeYolo(\n    output: Float32Array,\n    outputDims: readonly number[],\n    options: DecodeYoloOptions,\n): DecodedDetection[] {\n    const channels = outputDims.length === 3 ? outputDims[1] : outputDims[0];\n    if (channels === undefined || channels < 5) {\n        throw new Error(`decodeYolo: invalid output channel count ${channels} (expected >= 5).`);\n    }\n    const numClasses = channels - 4;\n\n    const decoded = decodeYoloAnchors(output, outputDims, {\n        numClasses,\n        ...options,\n    });\n\n    const results: DecodedDetection[] = [];\n    for (let i = 0; i < decoded.classIds.length; i++) {\n        results.push({\n            bbox: new BoundingBox(\n                decoded.boxesXyxy[i * 4] as number,\n                decoded.boxesXyxy[i * 4 + 1] as number,\n                decoded.boxesXyxy[i * 4 + 2] as number,\n                decoded.boxesXyxy[i * 4 + 3] as number,\n            ),\n            classId: decoded.classIds[i] as number,\n            confidence: decoded.confidences[i] as number,\n        });\n    }\n    return results;\n}\n"],"mappings":"gCA+BA,SAAgB,EAAI,EAAqB,EAAsB,EAAkC,CAC7F,IAAM,EAAI,EAAO,OACjB,GAAI,IAAM,EAAG,OAAO,IAAI,WAExB,IAAM,EAAQ,IAAI,aAAa,CAAC,EAChC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,CACxB,IAAM,EAAK,EAAM,EAAI,GACf,EAAK,EAAM,EAAI,EAAI,GACnB,EAAK,EAAM,EAAI,EAAI,GACnB,EAAK,EAAM,EAAI,EAAI,GACzB,EAAM,GAAK,KAAK,IAAI,EAAG,EAAK,CAAE,EAAI,KAAK,IAAI,EAAG,EAAK,CAAE,CACzD,CAEA,IAAM,EAAY,MAAc,CAAC,EACjC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,EAAM,GAAK,EACvC,EAAM,MAAM,EAAG,IAAO,EAAO,GAAiB,EAAO,IAAiB,EAAI,CAAC,EAE3E,IAAM,EAAa,IAAI,WAAW,CAAC,EAC7B,EAAiB,CAAC,EAExB,IAAK,IAAI,EAAK,EAAG,EAAK,EAAM,OAAQ,IAAM,CACtC,IAAM,EAAI,EAAM,GAChB,GAAI,EAAW,GAAI,SACnB,EAAK,KAAK,CAAC,EAEX,IAAM,EAAM,EAAM,EAAI,GAChB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAK,EAAM,GAEjB,IAAK,IAAI,EAAK,EAAK,EAAG,EAAK,EAAM,OAAQ,IAAM,CAC3C,IAAM,EAAI,EAAM,GAChB,GAAI,EAAW,GAAI,SAEnB,IAAM,EAAM,EAAM,EAAI,GAChB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GACpB,EAAM,EAAM,EAAI,EAAI,GAEpB,EAAM,KAAK,IAAI,EAAK,CAAG,EACvB,EAAM,KAAK,IAAI,EAAK,CAAG,EACvB,EAAM,KAAK,IAAI,EAAK,CAAG,EACvB,EAAM,KAAK,IAAI,EAAK,CAAG,EAGvB,EAFK,KAAK,IAAI,EAAG,EAAM,CAEf,EADH,KAAK,IAAI,EAAG,EAAM,CACV,EACb,EAAQ,EAAM,EAAM,GAAgB,GAC9B,EAAQ,EAAI,EAAQ,EAAQ,GAC9B,IAAc,EAAW,GAAK,EAC5C,CACJ,CAEA,OAAO,WAAW,KAAK,CAAI,CAC/B,CAkBA,SAAgB,EACZ,EACA,EACA,EACA,EACU,CACV,GAAI,EAAO,SAAW,EAAG,OAAO,IAAI,WAEpC,IAAM,EAAU,IAAI,IACpB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAK,OAAQ,IAAK,CAClC,IAAM,EAAI,EAAK,GACT,EAAO,EAAQ,IAAI,CAAC,EACtB,IAAS,IAAA,GAAW,EAAQ,IAAI,EAAG,CAAC,CAAC,CAAC,EACrC,EAAK,KAAK,CAAC,CACpB,CAEA,IAAM,EAAiB,CAAC,EACxB,IAAK,IAAM,KAAW,EAAQ,OAAO,EAAG,CACpC,IAAM,EAAI,EAAQ,OACZ,EAAW,IAAI,aAAa,EAAI,CAAC,EACjC,EAAY,IAAI,aAAa,CAAC,EACpC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,CACxB,IAAM,EAAI,EAAQ,GAClB,EAAS,EAAI,GAAK,EAAM,EAAI,GAC5B,EAAS,EAAI,EAAI,GAAK,EAAM,EAAI,EAAI,GACpC,EAAS,EAAI,EAAI,GAAK,EAAM,EAAI,EAAI,GACpC,EAAS,EAAI,EAAI,GAAK,EAAM,EAAI,EAAI,GACpC,EAAU,GAAK,EAAO,EAC1B,CACA,IAAM,EAAU,EAAI,EAAU,EAAW,CAAY,EACrD,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,OAAQ,IAChC,EAAK,KAAK,EAAQ,EAAQ,GAAuB,CAEzD,CAGA,OADA,EAAK,MAAM,EAAG,IAAO,EAAO,GAAiB,EAAO,IAAiB,EAAI,CAAC,EACnE,WAAW,KAAK,CAAI,CAC/B,CAsCA,SAAgB,EACZ,EACA,EACA,EACc,CACd,IAAI,EAAa,EACjB,GAAI,EAAW,SAAW,EAAG,CACzB,GAAI,EAAW,KAAO,EAClB,MAAU,MAAM,iDAAiD,EAAW,GAAG,EAAE,EAErF,EAAa,CAAC,EAAW,GAAc,EAAW,EAAY,CAClE,CACA,GAAI,EAAW,SAAW,EACtB,MAAU,MACN,wEAAwE,KAAK,UAAU,CAAI,EAAE,EACjG,EAEJ,IAAM,EAAW,EAAW,GACtB,EAAa,EAAW,GAExB,CACF,aACA,gBACA,iBACA,UACA,SACA,QACA,gBACA,eACA,iBACA,EAEJ,GAAI,EAAa,GAAK,EAAa,EAAI,EACnC,MAAU,MACN,yCAAyC,EAAW,gBAAgB,EAAS,EACjF,EAEJ,GAAI,EAAK,SAAW,EAAW,EAC3B,MAAU,MACN,kCAAkC,EAAK,OAAO,sCAAsC,EAAW,EAAW,EAC9G,EAYJ,IAAM,EAA0B,CAAC,EAEjC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAY,IAAK,CACjC,IAAI,EAAU,EACV,EAAY,KAChB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAY,IAAK,CACjC,IAAM,EAAI,GAAM,EAAI,GAAK,EAAa,GAClC,IAAM,IAAA,IAAa,EAAI,IACvB,EAAY,EACZ,EAAU,EAElB,CACA,GAAI,EAAY,EAAe,SAE/B,IAAM,EAAK,EAAK,GACV,EAAK,EAAK,EAAa,GACvB,EAAI,EAAK,EAAI,EAAa,GAC1B,EAAI,EAAK,EAAI,EAAa,GAE5B,EAAK,EAAK,EAAI,EACd,EAAK,EAAK,EAAI,EACd,EAAK,EAAK,EAAI,EACd,EAAK,EAAK,EAAI,EAElB,GAAM,EAAK,GAAW,EACtB,GAAM,EAAK,GAAU,EACrB,GAAM,EAAK,GAAW,EACtB,GAAM,EAAK,GAAU,EAErB,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAe,CAAE,CAAC,EAC5C,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAgB,CAAE,CAAC,EAC7C,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAe,CAAE,CAAC,EAC5C,EAAK,KAAK,IAAI,EAAG,KAAK,IAAI,EAAgB,CAAE,CAAC,EAE7C,EAAW,KAAK,CAAE,UAAW,EAAG,KAAI,KAAI,KAAI,KAAI,QAAS,EAAS,WAAY,CAAU,CAAC,CAC7F,CAEA,GAAI,EAAW,SAAW,EAAG,OAAO,EAAa,EAIjD,IAAM,EAAY,IAAI,aAAa,EAAW,OAAS,CAAC,EAClD,EAAY,IAAI,aAAa,EAAW,MAAM,EAC9C,EAAU,IAAI,WAAW,EAAW,MAAM,EAChD,IAAK,IAAI,EAAI,EAAG,EAAI,EAAW,OAAQ,IAAK,CACxC,IAAM,EAAI,EAAW,GACrB,EAAU,EAAI,GAAK,EAAE,GACrB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,GAAK,EAAE,WACjB,EAAQ,GAAK,EAAE,OACnB,CACA,IAAM,EAAO,EAAW,EAAW,EAAW,EAAS,CAAY,EACnE,GAAI,EAAK,SAAW,EAAG,OAAO,EAAa,EAE3C,IAAM,EAAU,MAAM,KAAK,CAAI,CAAC,CAAC,MAAM,EAAG,CAAa,EACjD,EAAI,EAAQ,OACZ,EAAgB,IAAI,WAAW,CAAC,EAChC,EAAY,IAAI,aAAa,EAAI,CAAC,EAClC,EAAW,IAAI,WAAW,CAAC,EAC3B,EAAc,IAAI,aAAa,CAAC,EACtC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,CACxB,IAAM,EAAI,EAAW,EAAQ,IAC7B,EAAc,GAAK,EAAE,UACrB,EAAU,EAAI,GAAK,EAAE,GACrB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAU,EAAI,EAAI,GAAK,EAAE,GACzB,EAAS,GAAK,EAAE,QAChB,EAAY,GAAK,EAAE,UACvB,CACA,MAAO,CAAE,gBAAe,YAAW,WAAU,aAAY,CAC7D,CAEA,SAAS,GAA+B,CACpC,MAAO,CACH,cAAe,IAAI,WACnB,UAAW,IAAI,aACf,SAAU,IAAI,WACd,YAAa,IAAI,YACrB,CACJ,CA2BA,SAAgB,EACZ,EACA,EACA,EACkB,CAClB,IAAM,EAAW,EAAW,SAAW,EAAI,EAAW,GAAK,EAAW,GACtE,GAAI,IAAa,IAAA,IAAa,EAAW,EACrC,MAAU,MAAM,4CAA4C,EAAS,kBAAkB,EAI3F,IAAM,EAAU,EAAkB,EAAQ,EAAY,CAClD,WAHe,EAAW,EAI1B,GAAG,CACP,CAAC,EAEK,EAA8B,CAAC,EACrC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,SAAS,OAAQ,IACzC,EAAQ,KAAK,CACT,KAAM,IAAI,EAAA,YACN,EAAQ,UAAU,EAAI,GACtB,EAAQ,UAAU,EAAI,EAAI,GAC1B,EAAQ,UAAU,EAAI,EAAI,GAC1B,EAAQ,UAAU,EAAI,EAAI,EAC9B,EACA,QAAS,EAAQ,SAAS,GAC1B,WAAY,EAAQ,YAAY,EACpC,CAAC,EAEL,OAAO,CACX"}

package/dist/vision/postprocess/detection.js

@@ -10,7 +10,7 @@ function t(e, t, n) {
 	}
 	let a = Array(r);
 	for (let e = 0; e < r; e++) a[e] = e;
-	a.sort((e, n) => t[n] - t[e]);
+	a.sort((e, n) => t[n] - t[e] || e - n);
 	let o = new Uint8Array(r), s = [];
 	for (let t = 0; t < a.length; t++) {
 		let r = a[t];
@@ -43,7 +43,7 @@ function n(e, n, r, i) {
 		let l = t(s, c, i);
 		for (let e = 0; e < l.length; e++) o.push(r[l[e]]);
 	}
-	return o.sort((e, t) => n[t] - n[e]), Int32Array.from(o);
+	return o.sort((e, t) => n[t] - n[e] || e - t), Int32Array.from(o);
 }
 function r(e, t, r) {
 	let a = t;
@@ -116,14 +116,7 @@ function a(t, n, i) {
 	});
 	return s;
 }
-var o = !1, s = !1;
-function c(e, t, n) {
-	return o || (o = !0, console.warn("[@ort-vision-sdk/web] decodeYoloV8 is deprecated since 0.2.0; use decodeYolo. The alias will be removed in 0.4.0.")), a(e, t, n);
-}
-function l(e, t, n) {
-	return s || (s = !0, console.warn("[@ort-vision-sdk/web] decodeYoloV8Anchors is deprecated since 0.2.0; use decodeYoloAnchors. The alias will be removed in 0.4.0.")), r(e, t, n);
-}
 //#endregion
-export { n as batchedNms, a as decodeYolo, r as decodeYoloAnchors, c as decodeYoloV8, l as decodeYoloV8Anchors, t as nms };
+export { n as batchedNms, a as decodeYolo, r as decodeYoloAnchors, t as nms };
 
 //# sourceMappingURL=detection.js.map

package/dist/vision/postprocess/detection.js.map

@@ -1 +1 @@
-{"version":3,"file":"detection.js","names":[],"sources":["../../../src/vision/postprocess/detection.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Detection head postprocessing: anchor-free YOLO decoding + non-maximum suppression.\n *\n * The shared {@link decodeYoloAnchors} helper does the per-anchor work that\n * is identical for plain detection and segmentation (transpose, xywh→xyxy,\n * letterbox unmap, per-class NMS, sort & cap). {@link decodeYolo} is a thin\n * wrapper around it; the segmentation module ({@link ./segmentation.js})\n * calls the helper directly so it can also recover the per-anchor mask\n * coefficients.\n *\n * Works for any YOLO export with the post-v8 anchor-free head:\n * **YOLOv8 / v9 / v10 / v11 / v12** detect heads, all of which share the\n * `[1, 4 + nc, N]` output layout.\n */\n\nimport { BoundingBox } from \"../types\";\n\n/**\n * Greedy non-maximum suppression on axis-aligned bounding boxes.\n *\n * Mirrors `torchvision.ops.nms` (keeps boxes with the highest score, drops\n * any subsequent box whose IoU exceeds the threshold).\n *\n * @param boxes Flat array of length `4 * N` in xyxy order: `[x1,y1,x2,y2, ...]`.\n * @param scores Detection score per box, length `N`.\n * @param iouThreshold Boxes with IoU above this threshold relative to a kept box are suppressed.\n * @returns Indices of kept boxes, in descending score order.\n */\nexport function nms(boxes: Float32Array, scores: Float32Array, iouThreshold: number): Int32Array {\n    const n = scores.length;\n    if (n === 0) return new Int32Array(0);\n\n    const areas = new Float32Array(n);\n    for (let i = 0; i < n; i++) {\n        const x1 = boxes[i * 4] as number;\n        const y1 = boxes[i * 4 + 1] as number;\n        const x2 = boxes[i * 4 + 2] as number;\n        const y2 = boxes[i * 4 + 3] as number;\n        areas[i] = Math.max(0, x2 - x1) * Math.max(0, y2 - y1);\n    }\n\n    const order = new Array<number>(n);\n    for (let i = 0; i < n; i++) order[i] = i;\n    order.sort((a, b) => (scores[b] as number) - (scores[a] as number));\n\n    const suppressed = new Uint8Array(n);\n    const keep: number[] = [];\n\n    for (let oi = 0; oi < order.length; oi++) {\n        const i = order[oi] as number;\n        if (suppressed[i]) continue;\n        keep.push(i);\n\n        const ax1 = boxes[i * 4] as number;\n        const ay1 = boxes[i * 4 + 1] as number;\n        const ax2 = boxes[i * 4 + 2] as number;\n        const ay2 = boxes[i * 4 + 3] as number;\n        const ai = areas[i] as number;\n\n        for (let oj = oi + 1; oj < order.length; oj++) {\n            const j = order[oj] as number;\n            if (suppressed[j]) continue;\n\n            const bx1 = boxes[j * 4] as number;\n            const by1 = boxes[j * 4 + 1] as number;\n            const bx2 = boxes[j * 4 + 2] as number;\n            const by2 = boxes[j * 4 + 3] as number;\n\n            const ix1 = Math.max(ax1, bx1);\n            const iy1 = Math.max(ay1, by1);\n            const ix2 = Math.min(ax2, bx2);\n            const iy2 = Math.min(ay2, by2);\n            const iw = Math.max(0, ix2 - ix1);\n            const ih = Math.max(0, iy2 - iy1);\n            const inter = iw * ih;\n            const union = ai + (areas[j] as number) - inter;\n            const iou = union > 0 ? inter / union : 0;\n            if (iou > iouThreshold) suppressed[j] = 1;\n        }\n    }\n\n    return Int32Array.from(keep);\n}\n\n/**\n * Per-class NMS — boxes are suppressed only by other boxes of the same class.\n *\n * Mirrors `torchvision.ops.batched_nms`.\n *\n * @param boxes Flat array of length `4 * N` in xyxy order.\n * @param scores Detection score per box, length `N`.\n * @param idxs Class index per box, length `N`. Boxes with different `idxs`\n *   never suppress each other.\n * @param iouThreshold IoU threshold for suppression within a class.\n */\nexport function batchedNms(\n    boxes: Float32Array,\n    scores: Float32Array,\n    idxs: Int32Array,\n    iouThreshold: number,\n): Int32Array {\n    if (scores.length === 0) return new Int32Array(0);\n\n    const byClass = new Map<number, number[]>();\n    for (let i = 0; i < idxs.length; i++) {\n        const c = idxs[i] as number;\n        const list = byClass.get(c);\n        if (list === undefined) byClass.set(c, [i]);\n        else list.push(i);\n    }\n\n    const keep: number[] = [];\n    for (const indices of byClass.values()) {\n        const m = indices.length;\n        const subBoxes = new Float32Array(m * 4);\n        const subScores = new Float32Array(m);\n        for (let k = 0; k < m; k++) {\n            const i = indices[k] as number;\n            subBoxes[k * 4] = boxes[i * 4] as number;\n            subBoxes[k * 4 + 1] = boxes[i * 4 + 1] as number;\n            subBoxes[k * 4 + 2] = boxes[i * 4 + 2] as number;\n            subBoxes[k * 4 + 3] = boxes[i * 4 + 3] as number;\n            subScores[k] = scores[i] as number;\n        }\n        const subKeep = nms(subBoxes, subScores, iouThreshold);\n        for (let k = 0; k < subKeep.length; k++) {\n            keep.push(indices[subKeep[k] as number] as number);\n        }\n    }\n\n    keep.sort((a, b) => (scores[b] as number) - (scores[a] as number));\n    return Int32Array.from(keep);\n}\n\nexport interface DecodeYoloAnchorsOptions {\n    /** Number of class-score channels following the 4 box channels. */\n    readonly numClasses: number;\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedAnchors {\n    /** Indices into the original `numAnchors` axis, in descending confidence order. */\n    readonly anchorIndices: Int32Array;\n    /** `[k, 4]` boxes in original-image pixel coords, flat row-major xyxy. */\n    readonly boxesXyxy: Float32Array;\n    /** Predicted class id per survivor. */\n    readonly classIds: Int32Array;\n    /** Confidence per survivor. */\n    readonly confidences: Float32Array;\n}\n\n/**\n * Shared YOLO per-anchor decode used by both detection and segmentation\n * (v8 / v9 / v10 / v11 / v12).\n *\n * Only the first `4 + numClasses` channels are read; later channels (e.g.\n * mask coefficients) are ignored — callers can fetch them via the returned\n * {@link DecodedAnchors.anchorIndices}.\n *\n * @param data Flat per-anchor output, length `channels * numAnchors`.\n * @param dims Dims as reported by ORT, e.g. `[1, 84, 8400]` (det) or\n *   `[1, 116, 8400]` (seg). The leading batch dim must be 1.\n */\nexport function decodeYoloAnchors(\n    data: Float32Array,\n    dims: readonly number[],\n    options: DecodeYoloAnchorsOptions,\n): DecodedAnchors {\n    let normalized = dims;\n    if (normalized.length === 3) {\n        if (normalized[0] !== 1) {\n            throw new Error(`decodeYoloAnchors: expected batch size 1, got ${normalized[0]}.`);\n        }\n        normalized = [normalized[1] as number, normalized[2] as number];\n    }\n    if (normalized.length !== 2) {\n        throw new Error(\n            `decodeYoloAnchors: expected 2-D output after batch removal, got dims=${JSON.stringify(dims)}.`,\n        );\n    }\n    const channels = normalized[0] as number;\n    const numAnchors = normalized[1] as number;\n\n    const {\n        numClasses,\n        originalWidth,\n        originalHeight,\n        padLeft,\n        padTop,\n        scale,\n        confThreshold,\n        iouThreshold,\n        maxDetections,\n    } = options;\n\n    if (numClasses < 1 || numClasses + 4 > channels) {\n        throw new Error(\n            `decodeYoloAnchors: invalid numClasses=${numClasses} for channels=${channels}.`,\n        );\n    }\n    if (data.length !== channels * numAnchors) {\n        throw new Error(\n            `decodeYoloAnchors: data length ${data.length} does not match channels*numAnchors=${channels * numAnchors}.`,\n        );\n    }\n\n    type Candidate = {\n        anchorIdx: number;\n        x1: number;\n        y1: number;\n        x2: number;\n        y2: number;\n        classId: number;\n        confidence: number;\n    };\n    const candidates: Candidate[] = [];\n\n    for (let a = 0; a < numAnchors; a++) {\n        let bestCls = 0;\n        let bestScore = -Infinity;\n        for (let c = 0; c < numClasses; c++) {\n            const s = data[(4 + c) * numAnchors + a];\n            if (s !== undefined && s > bestScore) {\n                bestScore = s;\n                bestCls = c;\n            }\n        }\n        if (bestScore < confThreshold) continue;\n\n        const cx = data[a] as number;\n        const cy = data[numAnchors + a] as number;\n        const w = data[2 * numAnchors + a] as number;\n        const h = data[3 * numAnchors + a] as number;\n\n        let x1 = cx - w / 2;\n        let y1 = cy - h / 2;\n        let x2 = cx + w / 2;\n        let y2 = cy + h / 2;\n\n        x1 = (x1 - padLeft) / scale;\n        y1 = (y1 - padTop) / scale;\n        x2 = (x2 - padLeft) / scale;\n        y2 = (y2 - padTop) / scale;\n\n        x1 = Math.max(0, Math.min(originalWidth, x1));\n        y1 = Math.max(0, Math.min(originalHeight, y1));\n        x2 = Math.max(0, Math.min(originalWidth, x2));\n        y2 = Math.max(0, Math.min(originalHeight, y2));\n\n        candidates.push({ anchorIdx: a, x1, y1, x2, y2, classId: bestCls, confidence: bestScore });\n    }\n\n    if (candidates.length === 0) return emptyDecoded();\n\n    // Build flat arrays then delegate to batchedNms — same algorithm as before\n    // but funnelled through the public per-class NMS helper.\n    const flatBoxes = new Float32Array(candidates.length * 4);\n    const scoresArr = new Float32Array(candidates.length);\n    const idxsArr = new Int32Array(candidates.length);\n    for (let i = 0; i < candidates.length; i++) {\n        const c = candidates[i] as Candidate;\n        flatBoxes[i * 4] = c.x1;\n        flatBoxes[i * 4 + 1] = c.y1;\n        flatBoxes[i * 4 + 2] = c.x2;\n        flatBoxes[i * 4 + 3] = c.y2;\n        scoresArr[i] = c.confidence;\n        idxsArr[i] = c.classId;\n    }\n    const kept = batchedNms(flatBoxes, scoresArr, idxsArr, iouThreshold);\n    if (kept.length === 0) return emptyDecoded();\n\n    const limited = Array.from(kept).slice(0, maxDetections);\n    const k = limited.length;\n    const anchorIndices = new Int32Array(k);\n    const boxesXyxy = new Float32Array(k * 4);\n    const classIds = new Int32Array(k);\n    const confidences = new Float32Array(k);\n    for (let i = 0; i < k; i++) {\n        const c = candidates[limited[i] as number] as Candidate;\n        anchorIndices[i] = c.anchorIdx;\n        boxesXyxy[i * 4] = c.x1;\n        boxesXyxy[i * 4 + 1] = c.y1;\n        boxesXyxy[i * 4 + 2] = c.x2;\n        boxesXyxy[i * 4 + 3] = c.y2;\n        classIds[i] = c.classId;\n        confidences[i] = c.confidence;\n    }\n    return { anchorIndices, boxesXyxy, classIds, confidences };\n}\n\nfunction emptyDecoded(): DecodedAnchors {\n    return {\n        anchorIndices: new Int32Array(0),\n        boxesXyxy: new Float32Array(0),\n        classIds: new Int32Array(0),\n        confidences: new Float32Array(0),\n    };\n}\n\nexport interface DecodeYoloOptions {\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedDetection {\n    readonly bbox: BoundingBox;\n    readonly classId: number;\n    readonly confidence: number;\n}\n\n/**\n * Decode an anchor-free YOLO detection output into a list of detections.\n *\n * Works for **YOLOv8 / v9 / v10 / v11 / v12** detect heads.\n *\n * Expected raw shape: `[1, 4 + numClasses, N]`. `numClasses` is inferred\n * from the channel count.\n */\nexport function decodeYolo(\n    output: Float32Array,\n    outputDims: readonly number[],\n    options: DecodeYoloOptions,\n): DecodedDetection[] {\n    const channels = outputDims.length === 3 ? outputDims[1] : outputDims[0];\n    if (channels === undefined || channels < 5) {\n        throw new Error(`decodeYolo: invalid output channel count ${channels} (expected >= 5).`);\n    }\n    const numClasses = channels - 4;\n\n    const decoded = decodeYoloAnchors(output, outputDims, {\n        numClasses,\n        ...options,\n    });\n\n    const results: DecodedDetection[] = [];\n    for (let i = 0; i < decoded.classIds.length; i++) {\n        results.push({\n            bbox: new BoundingBox(\n                decoded.boxesXyxy[i * 4] as number,\n                decoded.boxesXyxy[i * 4 + 1] as number,\n                decoded.boxesXyxy[i * 4 + 2] as number,\n                decoded.boxesXyxy[i * 4 + 3] as number,\n            ),\n            classId: decoded.classIds[i] as number,\n            confidence: decoded.confidences[i] as number,\n        });\n    }\n    return results;\n}\n\nlet _warnedDecodeYoloV8 = false;\nlet _warnedDecodeYoloV8Anchors = false;\n\n/**\n * @deprecated since 0.2.0 — use {@link decodeYolo}. Same behavior; the\n * decoder covers v8/v9/v10/v11/v12 detect heads. Will be removed in 0.4.0.\n */\nexport function decodeYoloV8(\n    output: Float32Array,\n    outputDims: readonly number[],\n    options: DecodeYoloOptions,\n): DecodedDetection[] {\n    if (!_warnedDecodeYoloV8) {\n        _warnedDecodeYoloV8 = true;\n        console.warn(\n            \"[@ort-vision-sdk/web] decodeYoloV8 is deprecated since 0.2.0; use decodeYolo. \" +\n                \"The alias will be removed in 0.4.0.\",\n        );\n    }\n    return decodeYolo(output, outputDims, options);\n}\n\n/**\n * @deprecated since 0.2.0 — use {@link decodeYoloAnchors}. Will be removed in 0.4.0.\n */\nexport function decodeYoloV8Anchors(\n    data: Float32Array,\n    dims: readonly number[],\n    options: DecodeYoloAnchorsOptions,\n): DecodedAnchors {\n    if (!_warnedDecodeYoloV8Anchors) {\n        _warnedDecodeYoloV8Anchors = true;\n        console.warn(\n            \"[@ort-vision-sdk/web] decodeYoloV8Anchors is deprecated since 0.2.0; use decodeYoloAnchors. \" +\n                \"The alias will be removed in 0.4.0.\",\n        );\n    }\n    return decodeYoloAnchors(data, dims, options);\n}\n\n/** @deprecated since 0.2.0 — use {@link DecodeYoloAnchorsOptions}. */\nexport type DecodeYoloV8AnchorsOptions = DecodeYoloAnchorsOptions;\n\n/** @deprecated since 0.2.0 — use {@link DecodeYoloOptions}. */\nexport type DecodeYoloV8Options = DecodeYoloOptions;\n"],"mappings":";;AA6BA,SAAgB,EAAI,GAAqB,GAAsB,GAAkC;CAC7F,IAAM,IAAI,EAAO;CACjB,IAAI,MAAM,GAAG,uBAAO,IAAI,WAAY;CAEpC,IAAM,IAAQ,IAAI,aAAa,CAAC;CAChC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EACxB,IAAM,IAAK,EAAM,IAAI,IACf,IAAK,EAAM,IAAI,IAAI,IACnB,IAAK,EAAM,IAAI,IAAI,IACnB,IAAK,EAAM,IAAI,IAAI;EACzB,EAAM,KAAK,KAAK,IAAI,GAAG,IAAK,CAAE,IAAI,KAAK,IAAI,GAAG,IAAK,CAAE;CACzD;CAEA,IAAM,IAAY,MAAc,CAAC;CACjC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,EAAM,KAAK;CACvC,EAAM,MAAM,GAAG,MAAO,EAAO,KAAiB,EAAO,EAAa;CAElE,IAAM,IAAa,IAAI,WAAW,CAAC,GAC7B,IAAiB,CAAC;CAExB,KAAK,IAAI,IAAK,GAAG,IAAK,EAAM,QAAQ,KAAM;EACtC,IAAM,IAAI,EAAM;EAChB,IAAI,EAAW,IAAI;EACnB,EAAK,KAAK,CAAC;EAEX,IAAM,IAAM,EAAM,IAAI,IAChB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAK,EAAM;EAEjB,KAAK,IAAI,IAAK,IAAK,GAAG,IAAK,EAAM,QAAQ,KAAM;GAC3C,IAAM,IAAI,EAAM;GAChB,IAAI,EAAW,IAAI;GAEnB,IAAM,IAAM,EAAM,IAAI,IAChB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IAEpB,IAAM,KAAK,IAAI,GAAK,CAAG,GACvB,IAAM,KAAK,IAAI,GAAK,CAAG,GACvB,IAAM,KAAK,IAAI,GAAK,CAAG,GACvB,IAAM,KAAK,IAAI,GAAK,CAAG,GAGvB,IAFK,KAAK,IAAI,GAAG,IAAM,CAEf,IADH,KAAK,IAAI,GAAG,IAAM,CACV,GACb,IAAQ,IAAM,EAAM,KAAgB;GAE1C,CADY,IAAQ,IAAI,IAAQ,IAAQ,KAC9B,MAAc,EAAW,KAAK;EAC5C;CACJ;CAEA,OAAO,WAAW,KAAK,CAAI;AAC/B;AAaA,SAAgB,EACZ,GACA,GACA,GACA,GACU;CACV,IAAI,EAAO,WAAW,GAAG,uBAAO,IAAI,WAAY;CAEhD,IAAM,oBAAU,IAAI,IAAsB;CAC1C,KAAK,IAAI,IAAI,GAAG,IAAI,EAAK,QAAQ,KAAK;EAClC,IAAM,IAAI,EAAK,IACT,IAAO,EAAQ,IAAI,CAAC;EAC1B,AAAI,MAAS,KAAA,IAAW,EAAQ,IAAI,GAAG,CAAC,CAAC,CAAC,IACrC,EAAK,KAAK,CAAC;CACpB;CAEA,IAAM,IAAiB,CAAC;CACxB,KAAK,IAAM,KAAW,EAAQ,OAAO,GAAG;EACpC,IAAM,IAAI,EAAQ,QACZ,IAAW,IAAI,aAAa,IAAI,CAAC,GACjC,IAAY,IAAI,aAAa,CAAC;EACpC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;GACxB,IAAM,IAAI,EAAQ;GAKlB,AAJA,EAAS,IAAI,KAAK,EAAM,IAAI,IAC5B,EAAS,IAAI,IAAI,KAAK,EAAM,IAAI,IAAI,IACpC,EAAS,IAAI,IAAI,KAAK,EAAM,IAAI,IAAI,IACpC,EAAS,IAAI,IAAI,KAAK,EAAM,IAAI,IAAI,IACpC,EAAU,KAAK,EAAO;EAC1B;EACA,IAAM,IAAU,EAAI,GAAU,GAAW,CAAY;EACrD,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,QAAQ,KAChC,EAAK,KAAK,EAAQ,EAAQ,GAAuB;CAEzD;CAGA,OADA,EAAK,MAAM,GAAG,MAAO,EAAO,KAAiB,EAAO,EAAa,GAC1D,WAAW,KAAK,CAAI;AAC/B;AAsCA,SAAgB,EACZ,GACA,GACA,GACc;CACd,IAAI,IAAa;CACjB,IAAI,EAAW,WAAW,GAAG;EACzB,IAAI,EAAW,OAAO,GAClB,MAAU,MAAM,iDAAiD,EAAW,GAAG,EAAE;EAErF,IAAa,CAAC,EAAW,IAAc,EAAW,EAAY;CAClE;CACA,IAAI,EAAW,WAAW,GACtB,MAAU,MACN,wEAAwE,KAAK,UAAU,CAAI,EAAE,EACjG;CAEJ,IAAM,IAAW,EAAW,IACtB,IAAa,EAAW,IAExB,EACF,eACA,kBACA,mBACA,YACA,WACA,UACA,kBACA,iBACA,qBACA;CAEJ,IAAI,IAAa,KAAK,IAAa,IAAI,GACnC,MAAU,MACN,yCAAyC,EAAW,gBAAgB,EAAS,EACjF;CAEJ,IAAI,EAAK,WAAW,IAAW,GAC3B,MAAU,MACN,kCAAkC,EAAK,OAAO,sCAAsC,IAAW,EAAW,EAC9G;CAYJ,IAAM,IAA0B,CAAC;CAEjC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAY,KAAK;EACjC,IAAI,IAAU,GACV,IAAY;EAChB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAY,KAAK;GACjC,IAAM,IAAI,GAAM,IAAI,KAAK,IAAa;GACtC,AAAI,MAAM,KAAA,KAAa,IAAI,MACvB,IAAY,GACZ,IAAU;EAElB;EACA,IAAI,IAAY,GAAe;EAE/B,IAAM,IAAK,EAAK,IACV,IAAK,EAAK,IAAa,IACvB,IAAI,EAAK,IAAI,IAAa,IAC1B,IAAI,EAAK,IAAI,IAAa,IAE5B,IAAK,IAAK,IAAI,GACd,IAAK,IAAK,IAAI,GACd,IAAK,IAAK,IAAI,GACd,IAAK,IAAK,IAAI;EAYlB,AAVA,KAAM,IAAK,KAAW,GACtB,KAAM,IAAK,KAAU,GACrB,KAAM,IAAK,KAAW,GACtB,KAAM,IAAK,KAAU,GAErB,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAe,CAAE,CAAC,GAC5C,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAgB,CAAE,CAAC,GAC7C,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAe,CAAE,CAAC,GAC5C,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAgB,CAAE,CAAC,GAE7C,EAAW,KAAK;GAAE,WAAW;GAAG;GAAI;GAAI;GAAI;GAAI,SAAS;GAAS,YAAY;EAAU,CAAC;CAC7F;CAEA,IAAI,EAAW,WAAW,GAAG,OAAO,EAAa;CAIjD,IAAM,IAAY,IAAI,aAAa,EAAW,SAAS,CAAC,GAClD,IAAY,IAAI,aAAa,EAAW,MAAM,GAC9C,IAAU,IAAI,WAAW,EAAW,MAAM;CAChD,KAAK,IAAI,IAAI,GAAG,IAAI,EAAW,QAAQ,KAAK;EACxC,IAAM,IAAI,EAAW;EAMrB,AALA,EAAU,IAAI,KAAK,EAAE,IACrB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,KAAK,EAAE,YACjB,EAAQ,KAAK,EAAE;CACnB;CACA,IAAM,IAAO,EAAW,GAAW,GAAW,GAAS,CAAY;CACnE,IAAI,EAAK,WAAW,GAAG,OAAO,EAAa;CAE3C,IAAM,IAAU,MAAM,KAAK,CAAI,CAAC,CAAC,MAAM,GAAG,CAAa,GACjD,IAAI,EAAQ,QACZ,IAAgB,IAAI,WAAW,CAAC,GAChC,IAAY,IAAI,aAAa,IAAI,CAAC,GAClC,IAAW,IAAI,WAAW,CAAC,GAC3B,IAAc,IAAI,aAAa,CAAC;CACtC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EACxB,IAAM,IAAI,EAAW,EAAQ;EAO7B,AANA,EAAc,KAAK,EAAE,WACrB,EAAU,IAAI,KAAK,EAAE,IACrB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAS,KAAK,EAAE,SAChB,EAAY,KAAK,EAAE;CACvB;CACA,OAAO;EAAE;EAAe;EAAW;EAAU;CAAY;AAC7D;AAEA,SAAS,IAA+B;CACpC,OAAO;EACH,+BAAe,IAAI,WAAY;EAC/B,2BAAW,IAAI,aAAc;EAC7B,0BAAU,IAAI,WAAY;EAC1B,6BAAa,IAAI,aAAc;CACnC;AACJ;AA2BA,SAAgB,EACZ,GACA,GACA,GACkB;CAClB,IAAM,IAAW,EAAW,WAAW,IAAI,EAAW,KAAK,EAAW;CACtE,IAAI,MAAa,KAAA,KAAa,IAAW,GACrC,MAAU,MAAM,4CAA4C,EAAS,kBAAkB;CAI3F,IAAM,IAAU,EAAkB,GAAQ,GAAY;EAClD,YAHe,IAAW;EAI1B,GAAG;CACP,CAAC,GAEK,IAA8B,CAAC;CACrC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,SAAS,QAAQ,KACzC,EAAQ,KAAK;EACT,MAAM,IAAI,EACN,EAAQ,UAAU,IAAI,IACtB,EAAQ,UAAU,IAAI,IAAI,IAC1B,EAAQ,UAAU,IAAI,IAAI,IAC1B,EAAQ,UAAU,IAAI,IAAI,EAC9B;EACA,SAAS,EAAQ,SAAS;EAC1B,YAAY,EAAQ,YAAY;CACpC,CAAC;CAEL,OAAO;AACX;AAEA,IAAI,IAAsB,IACtB,IAA6B;AAMjC,SAAgB,EACZ,GACA,GACA,GACkB;CAQlB,OAPK,MACD,IAAsB,IACtB,QAAQ,KACJ,mHAEJ,IAEG,EAAW,GAAQ,GAAY,CAAO;AACjD;AAKA,SAAgB,EACZ,GACA,GACA,GACc;CAQd,OAPK,MACD,IAA6B,IAC7B,QAAQ,KACJ,iIAEJ,IAEG,EAAkB,GAAM,GAAM,CAAO;AAChD"}
+{"version":3,"file":"detection.js","names":[],"sources":["../../../src/vision/postprocess/detection.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Detection head postprocessing: anchor-free YOLO decoding + non-maximum suppression.\n *\n * The shared {@link decodeYoloAnchors} helper does the per-anchor work that\n * is identical for plain detection and segmentation (transpose, xywh→xyxy,\n * letterbox unmap, per-class NMS, sort & cap). {@link decodeYolo} is a thin\n * wrapper around it; the segmentation module ({@link ./segmentation.js})\n * calls the helper directly so it can also recover the per-anchor mask\n * coefficients.\n *\n * Works for any YOLO export with the post-v8 anchor-free head:\n * **YOLOv8 / v9 / v10 / v11 / v12** detect heads, all of which share the\n * `[1, 4 + nc, N]` output layout.\n */\n\nimport { BoundingBox } from \"../types\";\n\n/**\n * Greedy non-maximum suppression on axis-aligned bounding boxes.\n *\n * Mirrors `torchvision.ops.nms` (keeps boxes with the highest score, drops\n * any subsequent box whose IoU exceeds the threshold).\n *\n * @param boxes Flat array of length `4 * N` in xyxy order: `[x1,y1,x2,y2, ...]`.\n * @param scores Detection score per box, length `N`.\n * @param iouThreshold Boxes with IoU above this threshold relative to a kept box are suppressed.\n * @returns Indices of kept boxes, in descending score order. Boxes tied on\n *   score are visited lowest-index first, so the survivor of a tie is\n *   deterministic and matches both `torchvision` and the Python SDK.\n */\nexport function nms(boxes: Float32Array, scores: Float32Array, iouThreshold: number): Int32Array {\n    const n = scores.length;\n    if (n === 0) return new Int32Array(0);\n\n    const areas = new Float32Array(n);\n    for (let i = 0; i < n; i++) {\n        const x1 = boxes[i * 4] as number;\n        const y1 = boxes[i * 4 + 1] as number;\n        const x2 = boxes[i * 4 + 2] as number;\n        const y2 = boxes[i * 4 + 3] as number;\n        areas[i] = Math.max(0, x2 - x1) * Math.max(0, y2 - y1);\n    }\n\n    const order = new Array<number>(n);\n    for (let i = 0; i < n; i++) order[i] = i;\n    order.sort((a, b) => (scores[b] as number) - (scores[a] as number) || a - b);\n\n    const suppressed = new Uint8Array(n);\n    const keep: number[] = [];\n\n    for (let oi = 0; oi < order.length; oi++) {\n        const i = order[oi] as number;\n        if (suppressed[i]) continue;\n        keep.push(i);\n\n        const ax1 = boxes[i * 4] as number;\n        const ay1 = boxes[i * 4 + 1] as number;\n        const ax2 = boxes[i * 4 + 2] as number;\n        const ay2 = boxes[i * 4 + 3] as number;\n        const ai = areas[i] as number;\n\n        for (let oj = oi + 1; oj < order.length; oj++) {\n            const j = order[oj] as number;\n            if (suppressed[j]) continue;\n\n            const bx1 = boxes[j * 4] as number;\n            const by1 = boxes[j * 4 + 1] as number;\n            const bx2 = boxes[j * 4 + 2] as number;\n            const by2 = boxes[j * 4 + 3] as number;\n\n            const ix1 = Math.max(ax1, bx1);\n            const iy1 = Math.max(ay1, by1);\n            const ix2 = Math.min(ax2, bx2);\n            const iy2 = Math.min(ay2, by2);\n            const iw = Math.max(0, ix2 - ix1);\n            const ih = Math.max(0, iy2 - iy1);\n            const inter = iw * ih;\n            const union = ai + (areas[j] as number) - inter;\n            const iou = union > 0 ? inter / union : 0;\n            if (iou > iouThreshold) suppressed[j] = 1;\n        }\n    }\n\n    return Int32Array.from(keep);\n}\n\n/**\n * Per-class NMS — boxes are suppressed only by other boxes of the same class.\n *\n * Mirrors `torchvision.ops.batched_nms`.\n *\n * @param boxes Flat array of length `4 * N` in xyxy order.\n * @param scores Detection score per box, length `N`.\n * @param idxs Class index per box, length `N`. Boxes with different `idxs`\n *   never suppress each other.\n * @param iouThreshold IoU threshold for suppression within a class.\n * @returns Indices of kept boxes, sorted by descending score across all\n *   classes. Survivors from different classes that are tied on score are\n *   ordered lowest-index first — an explicit tie-break, because the order the\n *   per-class loop emits them in is an implementation detail (here, `Map`\n *   insertion order; in Python, sorted class order).\n */\nexport function batchedNms(\n    boxes: Float32Array,\n    scores: Float32Array,\n    idxs: Int32Array,\n    iouThreshold: number,\n): Int32Array {\n    if (scores.length === 0) return new Int32Array(0);\n\n    const byClass = new Map<number, number[]>();\n    for (let i = 0; i < idxs.length; i++) {\n        const c = idxs[i] as number;\n        const list = byClass.get(c);\n        if (list === undefined) byClass.set(c, [i]);\n        else list.push(i);\n    }\n\n    const keep: number[] = [];\n    for (const indices of byClass.values()) {\n        const m = indices.length;\n        const subBoxes = new Float32Array(m * 4);\n        const subScores = new Float32Array(m);\n        for (let k = 0; k < m; k++) {\n            const i = indices[k] as number;\n            subBoxes[k * 4] = boxes[i * 4] as number;\n            subBoxes[k * 4 + 1] = boxes[i * 4 + 1] as number;\n            subBoxes[k * 4 + 2] = boxes[i * 4 + 2] as number;\n            subBoxes[k * 4 + 3] = boxes[i * 4 + 3] as number;\n            subScores[k] = scores[i] as number;\n        }\n        const subKeep = nms(subBoxes, subScores, iouThreshold);\n        for (let k = 0; k < subKeep.length; k++) {\n            keep.push(indices[subKeep[k] as number] as number);\n        }\n    }\n\n    keep.sort((a, b) => (scores[b] as number) - (scores[a] as number) || a - b);\n    return Int32Array.from(keep);\n}\n\nexport interface DecodeYoloAnchorsOptions {\n    /** Number of class-score channels following the 4 box channels. */\n    readonly numClasses: number;\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedAnchors {\n    /** Indices into the original `numAnchors` axis, in descending confidence order. */\n    readonly anchorIndices: Int32Array;\n    /** `[k, 4]` boxes in original-image pixel coords, flat row-major xyxy. */\n    readonly boxesXyxy: Float32Array;\n    /** Predicted class id per survivor. */\n    readonly classIds: Int32Array;\n    /** Confidence per survivor. */\n    readonly confidences: Float32Array;\n}\n\n/**\n * Shared YOLO per-anchor decode used by both detection and segmentation\n * (v8 / v9 / v10 / v11 / v12).\n *\n * Only the first `4 + numClasses` channels are read; later channels (e.g.\n * mask coefficients) are ignored — callers can fetch them via the returned\n * {@link DecodedAnchors.anchorIndices}.\n *\n * @param data Flat per-anchor output, length `channels * numAnchors`.\n * @param dims Dims as reported by ORT, e.g. `[1, 84, 8400]` (det) or\n *   `[1, 116, 8400]` (seg). The leading batch dim must be 1.\n */\nexport function decodeYoloAnchors(\n    data: Float32Array,\n    dims: readonly number[],\n    options: DecodeYoloAnchorsOptions,\n): DecodedAnchors {\n    let normalized = dims;\n    if (normalized.length === 3) {\n        if (normalized[0] !== 1) {\n            throw new Error(`decodeYoloAnchors: expected batch size 1, got ${normalized[0]}.`);\n        }\n        normalized = [normalized[1] as number, normalized[2] as number];\n    }\n    if (normalized.length !== 2) {\n        throw new Error(\n            `decodeYoloAnchors: expected 2-D output after batch removal, got dims=${JSON.stringify(dims)}.`,\n        );\n    }\n    const channels = normalized[0] as number;\n    const numAnchors = normalized[1] as number;\n\n    const {\n        numClasses,\n        originalWidth,\n        originalHeight,\n        padLeft,\n        padTop,\n        scale,\n        confThreshold,\n        iouThreshold,\n        maxDetections,\n    } = options;\n\n    if (numClasses < 1 || numClasses + 4 > channels) {\n        throw new Error(\n            `decodeYoloAnchors: invalid numClasses=${numClasses} for channels=${channels}.`,\n        );\n    }\n    if (data.length !== channels * numAnchors) {\n        throw new Error(\n            `decodeYoloAnchors: data length ${data.length} does not match channels*numAnchors=${channels * numAnchors}.`,\n        );\n    }\n\n    type Candidate = {\n        anchorIdx: number;\n        x1: number;\n        y1: number;\n        x2: number;\n        y2: number;\n        classId: number;\n        confidence: number;\n    };\n    const candidates: Candidate[] = [];\n\n    for (let a = 0; a < numAnchors; a++) {\n        let bestCls = 0;\n        let bestScore = -Infinity;\n        for (let c = 0; c < numClasses; c++) {\n            const s = data[(4 + c) * numAnchors + a];\n            if (s !== undefined && s > bestScore) {\n                bestScore = s;\n                bestCls = c;\n            }\n        }\n        if (bestScore < confThreshold) continue;\n\n        const cx = data[a] as number;\n        const cy = data[numAnchors + a] as number;\n        const w = data[2 * numAnchors + a] as number;\n        const h = data[3 * numAnchors + a] as number;\n\n        let x1 = cx - w / 2;\n        let y1 = cy - h / 2;\n        let x2 = cx + w / 2;\n        let y2 = cy + h / 2;\n\n        x1 = (x1 - padLeft) / scale;\n        y1 = (y1 - padTop) / scale;\n        x2 = (x2 - padLeft) / scale;\n        y2 = (y2 - padTop) / scale;\n\n        x1 = Math.max(0, Math.min(originalWidth, x1));\n        y1 = Math.max(0, Math.min(originalHeight, y1));\n        x2 = Math.max(0, Math.min(originalWidth, x2));\n        y2 = Math.max(0, Math.min(originalHeight, y2));\n\n        candidates.push({ anchorIdx: a, x1, y1, x2, y2, classId: bestCls, confidence: bestScore });\n    }\n\n    if (candidates.length === 0) return emptyDecoded();\n\n    // Build flat arrays then delegate to batchedNms — same algorithm as before\n    // but funnelled through the public per-class NMS helper.\n    const flatBoxes = new Float32Array(candidates.length * 4);\n    const scoresArr = new Float32Array(candidates.length);\n    const idxsArr = new Int32Array(candidates.length);\n    for (let i = 0; i < candidates.length; i++) {\n        const c = candidates[i] as Candidate;\n        flatBoxes[i * 4] = c.x1;\n        flatBoxes[i * 4 + 1] = c.y1;\n        flatBoxes[i * 4 + 2] = c.x2;\n        flatBoxes[i * 4 + 3] = c.y2;\n        scoresArr[i] = c.confidence;\n        idxsArr[i] = c.classId;\n    }\n    const kept = batchedNms(flatBoxes, scoresArr, idxsArr, iouThreshold);\n    if (kept.length === 0) return emptyDecoded();\n\n    const limited = Array.from(kept).slice(0, maxDetections);\n    const k = limited.length;\n    const anchorIndices = new Int32Array(k);\n    const boxesXyxy = new Float32Array(k * 4);\n    const classIds = new Int32Array(k);\n    const confidences = new Float32Array(k);\n    for (let i = 0; i < k; i++) {\n        const c = candidates[limited[i] as number] as Candidate;\n        anchorIndices[i] = c.anchorIdx;\n        boxesXyxy[i * 4] = c.x1;\n        boxesXyxy[i * 4 + 1] = c.y1;\n        boxesXyxy[i * 4 + 2] = c.x2;\n        boxesXyxy[i * 4 + 3] = c.y2;\n        classIds[i] = c.classId;\n        confidences[i] = c.confidence;\n    }\n    return { anchorIndices, boxesXyxy, classIds, confidences };\n}\n\nfunction emptyDecoded(): DecodedAnchors {\n    return {\n        anchorIndices: new Int32Array(0),\n        boxesXyxy: new Float32Array(0),\n        classIds: new Int32Array(0),\n        confidences: new Float32Array(0),\n    };\n}\n\nexport interface DecodeYoloOptions {\n    readonly originalWidth: number;\n    readonly originalHeight: number;\n    readonly padLeft: number;\n    readonly padTop: number;\n    readonly scale: number;\n    readonly confThreshold: number;\n    readonly iouThreshold: number;\n    readonly maxDetections: number;\n}\n\nexport interface DecodedDetection {\n    readonly bbox: BoundingBox;\n    readonly classId: number;\n    readonly confidence: number;\n}\n\n/**\n * Decode an anchor-free YOLO detection output into a list of detections.\n *\n * Works for **YOLOv8 / v9 / v10 / v11 / v12** detect heads.\n *\n * Expected raw shape: `[1, 4 + numClasses, N]`. `numClasses` is inferred\n * from the channel count.\n */\nexport function decodeYolo(\n    output: Float32Array,\n    outputDims: readonly number[],\n    options: DecodeYoloOptions,\n): DecodedDetection[] {\n    const channels = outputDims.length === 3 ? outputDims[1] : outputDims[0];\n    if (channels === undefined || channels < 5) {\n        throw new Error(`decodeYolo: invalid output channel count ${channels} (expected >= 5).`);\n    }\n    const numClasses = channels - 4;\n\n    const decoded = decodeYoloAnchors(output, outputDims, {\n        numClasses,\n        ...options,\n    });\n\n    const results: DecodedDetection[] = [];\n    for (let i = 0; i < decoded.classIds.length; i++) {\n        results.push({\n            bbox: new BoundingBox(\n                decoded.boxesXyxy[i * 4] as number,\n                decoded.boxesXyxy[i * 4 + 1] as number,\n                decoded.boxesXyxy[i * 4 + 2] as number,\n                decoded.boxesXyxy[i * 4 + 3] as number,\n            ),\n            classId: decoded.classIds[i] as number,\n            confidence: decoded.confidences[i] as number,\n        });\n    }\n    return results;\n}\n"],"mappings":";;AA+BA,SAAgB,EAAI,GAAqB,GAAsB,GAAkC;CAC7F,IAAM,IAAI,EAAO;CACjB,IAAI,MAAM,GAAG,uBAAO,IAAI,WAAY;CAEpC,IAAM,IAAQ,IAAI,aAAa,CAAC;CAChC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EACxB,IAAM,IAAK,EAAM,IAAI,IACf,IAAK,EAAM,IAAI,IAAI,IACnB,IAAK,EAAM,IAAI,IAAI,IACnB,IAAK,EAAM,IAAI,IAAI;EACzB,EAAM,KAAK,KAAK,IAAI,GAAG,IAAK,CAAE,IAAI,KAAK,IAAI,GAAG,IAAK,CAAE;CACzD;CAEA,IAAM,IAAY,MAAc,CAAC;CACjC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK,EAAM,KAAK;CACvC,EAAM,MAAM,GAAG,MAAO,EAAO,KAAiB,EAAO,MAAiB,IAAI,CAAC;CAE3E,IAAM,IAAa,IAAI,WAAW,CAAC,GAC7B,IAAiB,CAAC;CAExB,KAAK,IAAI,IAAK,GAAG,IAAK,EAAM,QAAQ,KAAM;EACtC,IAAM,IAAI,EAAM;EAChB,IAAI,EAAW,IAAI;EACnB,EAAK,KAAK,CAAC;EAEX,IAAM,IAAM,EAAM,IAAI,IAChB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAK,EAAM;EAEjB,KAAK,IAAI,IAAK,IAAK,GAAG,IAAK,EAAM,QAAQ,KAAM;GAC3C,IAAM,IAAI,EAAM;GAChB,IAAI,EAAW,IAAI;GAEnB,IAAM,IAAM,EAAM,IAAI,IAChB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IACpB,IAAM,EAAM,IAAI,IAAI,IAEpB,IAAM,KAAK,IAAI,GAAK,CAAG,GACvB,IAAM,KAAK,IAAI,GAAK,CAAG,GACvB,IAAM,KAAK,IAAI,GAAK,CAAG,GACvB,IAAM,KAAK,IAAI,GAAK,CAAG,GAGvB,IAFK,KAAK,IAAI,GAAG,IAAM,CAEf,IADH,KAAK,IAAI,GAAG,IAAM,CACV,GACb,IAAQ,IAAM,EAAM,KAAgB;GAE1C,CADY,IAAQ,IAAI,IAAQ,IAAQ,KAC9B,MAAc,EAAW,KAAK;EAC5C;CACJ;CAEA,OAAO,WAAW,KAAK,CAAI;AAC/B;AAkBA,SAAgB,EACZ,GACA,GACA,GACA,GACU;CACV,IAAI,EAAO,WAAW,GAAG,uBAAO,IAAI,WAAY;CAEhD,IAAM,oBAAU,IAAI,IAAsB;CAC1C,KAAK,IAAI,IAAI,GAAG,IAAI,EAAK,QAAQ,KAAK;EAClC,IAAM,IAAI,EAAK,IACT,IAAO,EAAQ,IAAI,CAAC;EAC1B,AAAI,MAAS,KAAA,IAAW,EAAQ,IAAI,GAAG,CAAC,CAAC,CAAC,IACrC,EAAK,KAAK,CAAC;CACpB;CAEA,IAAM,IAAiB,CAAC;CACxB,KAAK,IAAM,KAAW,EAAQ,OAAO,GAAG;EACpC,IAAM,IAAI,EAAQ,QACZ,IAAW,IAAI,aAAa,IAAI,CAAC,GACjC,IAAY,IAAI,aAAa,CAAC;EACpC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;GACxB,IAAM,IAAI,EAAQ;GAKlB,AAJA,EAAS,IAAI,KAAK,EAAM,IAAI,IAC5B,EAAS,IAAI,IAAI,KAAK,EAAM,IAAI,IAAI,IACpC,EAAS,IAAI,IAAI,KAAK,EAAM,IAAI,IAAI,IACpC,EAAS,IAAI,IAAI,KAAK,EAAM,IAAI,IAAI,IACpC,EAAU,KAAK,EAAO;EAC1B;EACA,IAAM,IAAU,EAAI,GAAU,GAAW,CAAY;EACrD,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,QAAQ,KAChC,EAAK,KAAK,EAAQ,EAAQ,GAAuB;CAEzD;CAGA,OADA,EAAK,MAAM,GAAG,MAAO,EAAO,KAAiB,EAAO,MAAiB,IAAI,CAAC,GACnE,WAAW,KAAK,CAAI;AAC/B;AAsCA,SAAgB,EACZ,GACA,GACA,GACc;CACd,IAAI,IAAa;CACjB,IAAI,EAAW,WAAW,GAAG;EACzB,IAAI,EAAW,OAAO,GAClB,MAAU,MAAM,iDAAiD,EAAW,GAAG,EAAE;EAErF,IAAa,CAAC,EAAW,IAAc,EAAW,EAAY;CAClE;CACA,IAAI,EAAW,WAAW,GACtB,MAAU,MACN,wEAAwE,KAAK,UAAU,CAAI,EAAE,EACjG;CAEJ,IAAM,IAAW,EAAW,IACtB,IAAa,EAAW,IAExB,EACF,eACA,kBACA,mBACA,YACA,WACA,UACA,kBACA,iBACA,qBACA;CAEJ,IAAI,IAAa,KAAK,IAAa,IAAI,GACnC,MAAU,MACN,yCAAyC,EAAW,gBAAgB,EAAS,EACjF;CAEJ,IAAI,EAAK,WAAW,IAAW,GAC3B,MAAU,MACN,kCAAkC,EAAK,OAAO,sCAAsC,IAAW,EAAW,EAC9G;CAYJ,IAAM,IAA0B,CAAC;CAEjC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAY,KAAK;EACjC,IAAI,IAAU,GACV,IAAY;EAChB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAY,KAAK;GACjC,IAAM,IAAI,GAAM,IAAI,KAAK,IAAa;GACtC,AAAI,MAAM,KAAA,KAAa,IAAI,MACvB,IAAY,GACZ,IAAU;EAElB;EACA,IAAI,IAAY,GAAe;EAE/B,IAAM,IAAK,EAAK,IACV,IAAK,EAAK,IAAa,IACvB,IAAI,EAAK,IAAI,IAAa,IAC1B,IAAI,EAAK,IAAI,IAAa,IAE5B,IAAK,IAAK,IAAI,GACd,IAAK,IAAK,IAAI,GACd,IAAK,IAAK,IAAI,GACd,IAAK,IAAK,IAAI;EAYlB,AAVA,KAAM,IAAK,KAAW,GACtB,KAAM,IAAK,KAAU,GACrB,KAAM,IAAK,KAAW,GACtB,KAAM,IAAK,KAAU,GAErB,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAe,CAAE,CAAC,GAC5C,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAgB,CAAE,CAAC,GAC7C,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAe,CAAE,CAAC,GAC5C,IAAK,KAAK,IAAI,GAAG,KAAK,IAAI,GAAgB,CAAE,CAAC,GAE7C,EAAW,KAAK;GAAE,WAAW;GAAG;GAAI;GAAI;GAAI;GAAI,SAAS;GAAS,YAAY;EAAU,CAAC;CAC7F;CAEA,IAAI,EAAW,WAAW,GAAG,OAAO,EAAa;CAIjD,IAAM,IAAY,IAAI,aAAa,EAAW,SAAS,CAAC,GAClD,IAAY,IAAI,aAAa,EAAW,MAAM,GAC9C,IAAU,IAAI,WAAW,EAAW,MAAM;CAChD,KAAK,IAAI,IAAI,GAAG,IAAI,EAAW,QAAQ,KAAK;EACxC,IAAM,IAAI,EAAW;EAMrB,AALA,EAAU,IAAI,KAAK,EAAE,IACrB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,KAAK,EAAE,YACjB,EAAQ,KAAK,EAAE;CACnB;CACA,IAAM,IAAO,EAAW,GAAW,GAAW,GAAS,CAAY;CACnE,IAAI,EAAK,WAAW,GAAG,OAAO,EAAa;CAE3C,IAAM,IAAU,MAAM,KAAK,CAAI,CAAC,CAAC,MAAM,GAAG,CAAa,GACjD,IAAI,EAAQ,QACZ,IAAgB,IAAI,WAAW,CAAC,GAChC,IAAY,IAAI,aAAa,IAAI,CAAC,GAClC,IAAW,IAAI,WAAW,CAAC,GAC3B,IAAc,IAAI,aAAa,CAAC;CACtC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;EACxB,IAAM,IAAI,EAAW,EAAQ;EAO7B,AANA,EAAc,KAAK,EAAE,WACrB,EAAU,IAAI,KAAK,EAAE,IACrB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAU,IAAI,IAAI,KAAK,EAAE,IACzB,EAAS,KAAK,EAAE,SAChB,EAAY,KAAK,EAAE;CACvB;CACA,OAAO;EAAE;EAAe;EAAW;EAAU;CAAY;AAC7D;AAEA,SAAS,IAA+B;CACpC,OAAO;EACH,+BAAe,IAAI,WAAY;EAC/B,2BAAW,IAAI,aAAc;EAC7B,0BAAU,IAAI,WAAY;EAC1B,6BAAa,IAAI,aAAc;CACnC;AACJ;AA2BA,SAAgB,EACZ,GACA,GACA,GACkB;CAClB,IAAM,IAAW,EAAW,WAAW,IAAI,EAAW,KAAK,EAAW;CACtE,IAAI,MAAa,KAAA,KAAa,IAAW,GACrC,MAAU,MAAM,4CAA4C,EAAS,kBAAkB;CAI3F,IAAM,IAAU,EAAkB,GAAQ,GAAY;EAClD,YAHe,IAAW;EAI1B,GAAG;CACP,CAAC,GAEK,IAA8B,CAAC;CACrC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,SAAS,QAAQ,KACzC,EAAQ,KAAK;EACT,MAAM,IAAI,EACN,EAAQ,UAAU,IAAI,IACtB,EAAQ,UAAU,IAAI,IAAI,IAC1B,EAAQ,UAAU,IAAI,IAAI,IAC1B,EAAQ,UAAU,IAAI,IAAI,EAC9B;EACA,SAAS,EAAQ,SAAS;EAC1B,YAAY,EAAQ,YAAY;CACpC,CAAC;CAEL,OAAO;AACX"}

package/dist/vision/postprocess/segmentation.cjs

@@ -1,2 +1,2 @@
-const e=require("../types.cjs"),t=require("./detection.cjs");function n(n,i,a,s,c){let l=s;if(l.length===4){if(l[0]!==1)throw Error(`decodeYoloSeg: expected batch size 1 in prototypes, got ${l[0]}.`);l=[l[1],l[2],l[3]]}if(l.length!==3)throw Error(`decodeYoloSeg: expected 3-D prototypes after batch removal, got dims=${JSON.stringify(s)}.`);let u=l[0],d=l[1],f=l[2],p=i.length===3?i[1]:i[0],m=i.length===3?i[2]:i[1];if(p===void 0||m===void 0)throw Error(`decodeYoloSeg: cannot read channels/numAnchors from dims=${JSON.stringify(i)}.`);let h=4+c.numClasses+u;if(p!==h)throw Error(`decodeYoloSeg: channels=${p} does not match 4 + numClasses(${c.numClasses}) + numMaskCoefs(${u}) = ${h}.`);if(a.length!==u*d*f)throw Error(`decodeYoloSeg: prototype length ${a.length} does not match dims=${JSON.stringify(s)}.`);let g=t.decodeYoloAnchors(n,i,{numClasses:c.numClasses,originalWidth:c.originalWidth,originalHeight:c.originalHeight,padLeft:c.padLeft,padTop:c.padTop,scale:c.scale,confThreshold:c.confThreshold,iouThreshold:c.iouThreshold,maxDetections:c.maxDetections});if(g.anchorIndices.length===0)return[];let _=c.maskThreshold??.5,v=f/c.inputWidth,y=d/c.inputHeight,b=d*f,x=(4+c.numClasses)*m,S=[];for(let t=0;t<g.anchorIndices.length;t++){let i=g.anchorIndices[t],s=g.boxesXyxy[t*4],l=g.boxesXyxy[t*4+1],p=g.boxesXyxy[t*4+2],h=g.boxesXyxy[t*4+3],C=new e.BoundingBox(s,l,p,h),w=g.classIds[t],T=g.confidences[t],E=Math.max(0,Math.trunc(p)-Math.trunc(s)),D=Math.max(0,Math.trunc(h)-Math.trunc(l));if(E===0||D===0){S.push({bbox:C,classId:w,confidence:T,mask:new e.Mask(new Uint8Array,0,0)});continue}let O=s*c.scale+c.padLeft,k=l*c.scale+c.padTop,A=p*c.scale+c.padLeft,j=h*c.scale+c.padTop,M=Math.max(0,Math.floor(O*v)),N=Math.max(0,Math.floor(k*y)),P=Math.min(f,Math.ceil(A*v)),F=Math.min(d,Math.ceil(j*y));if(P<=M||F<=N){S.push({bbox:C,classId:w,confidence:T,mask:new e.Mask(new Uint8Array(E*D),E,D)});continue}let I=P-M,L=F-N,R=new Float32Array(I*L);for(let e=0;e<L;e++){let t=N+e;for(let o=0;o<I;o++){let s=M+o,c=0;for(let e=0;e<u;e++){let r=n[x+e*m+i],o=a[e*b+t*f+s];c+=r*o}R[e*I+o]=r(c)}}let z=o(R,I,L,E,D),B=new Uint8Array(E*D);for(let e=0;e<B.length;e++)B[e]=z[e]>=_?255:0;S.push({bbox:C,classId:w,confidence:T,mask:new e.Mask(B,E,D)})}return S}function r(e){if(e>=0)return 1/(1+Math.exp(-e));let t=Math.exp(e);return t/(1+t)}var i=!1;function a(e,t,r,a,o){return i||(i=!0,console.warn(`[@ort-vision-sdk/web] decodeYoloV8Seg is deprecated since 0.2.0; use decodeYoloSeg. The alias will be removed in 0.4.0.`)),n(e,t,r,a,o)}function o(e,t,n,r,i){let a=new Float32Array(r*i);if(r===0||i===0||t===0||n===0)return a;if(r===t&&i===n)return a.set(e),a;let o=t/r,s=n/i;for(let c=0;c<i;c++){let i=(c+.5)*s-.5,l=Math.max(0,Math.floor(i)),u=Math.min(n-1,l+1),d=Math.max(0,Math.min(1,i-l));for(let n=0;n<r;n++){let i=(n+.5)*o-.5,s=Math.max(0,Math.floor(i)),f=Math.min(t-1,s+1),p=Math.max(0,Math.min(1,i-s)),m=e[l*t+s],h=e[l*t+f],g=e[u*t+s],_=e[u*t+f],v=m*(1-p)+h*p,y=g*(1-p)+_*p;a[c*r+n]=v*(1-d)+y*d}}return a}exports.decodeYoloSeg=n,exports.decodeYoloV8Seg=a;
+const e=require("../types.cjs"),t=require("./detection.cjs");function n(n,a,o,s,c){let l=s;if(l.length===4){if(l[0]!==1)throw Error(`decodeYoloSeg: expected batch size 1 in prototypes, got ${l[0]}.`);l=[l[1],l[2],l[3]]}if(l.length!==3)throw Error(`decodeYoloSeg: expected 3-D prototypes after batch removal, got dims=${JSON.stringify(s)}.`);let u=l[0],d=l[1],f=l[2],p=a.length===3?a[1]:a[0],m=a.length===3?a[2]:a[1];if(p===void 0||m===void 0)throw Error(`decodeYoloSeg: cannot read channels/numAnchors from dims=${JSON.stringify(a)}.`);let h=4+c.numClasses+u;if(p!==h)throw Error(`decodeYoloSeg: channels=${p} does not match 4 + numClasses(${c.numClasses}) + numMaskCoefs(${u}) = ${h}.`);if(o.length!==u*d*f)throw Error(`decodeYoloSeg: prototype length ${o.length} does not match dims=${JSON.stringify(s)}.`);let g=t.decodeYoloAnchors(n,a,{numClasses:c.numClasses,originalWidth:c.originalWidth,originalHeight:c.originalHeight,padLeft:c.padLeft,padTop:c.padTop,scale:c.scale,confThreshold:c.confThreshold,iouThreshold:c.iouThreshold,maxDetections:c.maxDetections});if(g.anchorIndices.length===0)return[];let _=c.maskThreshold??.5,v=f/c.inputWidth,y=d/c.inputHeight,b=d*f,x=(4+c.numClasses)*m,S=[];for(let t=0;t<g.anchorIndices.length;t++){let a=g.anchorIndices[t],s=g.boxesXyxy[t*4],l=g.boxesXyxy[t*4+1],p=g.boxesXyxy[t*4+2],h=g.boxesXyxy[t*4+3],C=new e.BoundingBox(s,l,p,h),w=g.classIds[t],T=g.confidences[t],E=Math.max(0,Math.trunc(p)-Math.trunc(s)),D=Math.max(0,Math.trunc(h)-Math.trunc(l));if(E===0||D===0){S.push({bbox:C,classId:w,confidence:T,mask:new e.Mask(new Uint8Array,0,0)});continue}let O=s*c.scale+c.padLeft,k=l*c.scale+c.padTop,A=p*c.scale+c.padLeft,j=h*c.scale+c.padTop,M=Math.max(0,Math.floor(O*v)),N=Math.max(0,Math.floor(k*y)),P=Math.min(f,Math.ceil(A*v)),F=Math.min(d,Math.ceil(j*y));if(P<=M||F<=N){S.push({bbox:C,classId:w,confidence:T,mask:new e.Mask(new Uint8Array(E*D),E,D)});continue}let I=P-M,L=F-N,R=new Float32Array(I*L);for(let e=0;e<L;e++){let t=N+e;for(let i=0;i<I;i++){let s=M+i,c=0;for(let e=0;e<u;e++){let r=n[x+e*m+a],i=o[e*b+t*f+s];c+=r*i}R[e*I+i]=r(c)}}let z=i(R,I,L,E,D),B=new Uint8Array(E*D);for(let e=0;e<B.length;e++)B[e]=z[e]>=_?255:0;S.push({bbox:C,classId:w,confidence:T,mask:new e.Mask(B,E,D)})}return S}function r(e){if(e>=0)return 1/(1+Math.exp(-e));let t=Math.exp(e);return t/(1+t)}function i(e,t,n,r,i){let a=new Float32Array(r*i);if(r===0||i===0||t===0||n===0)return a;if(r===t&&i===n)return a.set(e),a;let o=t/r,s=n/i;for(let c=0;c<i;c++){let i=(c+.5)*s-.5,l=Math.max(0,Math.floor(i)),u=Math.min(n-1,l+1),d=Math.max(0,Math.min(1,i-l));for(let n=0;n<r;n++){let i=(n+.5)*o-.5,s=Math.max(0,Math.floor(i)),f=Math.min(t-1,s+1),p=Math.max(0,Math.min(1,i-s)),m=e[l*t+s],h=e[l*t+f],g=e[u*t+s],_=e[u*t+f],v=m*(1-p)+h*p,y=g*(1-p)+_*p;a[c*r+n]=v*(1-d)+y*d}}return a}exports.decodeYoloSeg=n;
 //# sourceMappingURL=segmentation.cjs.map