tempest-react-sdk 0.57.0 → 0.59.0

package/dist/vision/results.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"results.cjs","names":[],"sources":["../../src/vision/results.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n * - `speed`: per-stage timings of the `predict()` call that produced it.\n */\n\nimport { type Speed } from \"./core/timing\";\nimport {\n    type ClassificationResult,\n    type DetectionResult,\n    type RGBImage,\n    type SegmentationResult,\n} from \"./types\";\n\n/**\n * Zero timings for an envelope built outside a `predict()` call.\n *\n * Hand-constructed envelopes (tests, adapters) have nothing to measure, and\n * zeros keep `speed.inference` a plain `number` at every call site instead of\n * forcing an optional check that only ever fires for synthetic data.\n */\nconst NO_SPEED: Speed = { load: 0, preprocess: 0, inference: 0, postprocess: 0 };\n\n/**\n * Bulk numpy-style view of detected boxes for a single image.\n *\n * Mirrors Ultralytics' `Boxes` interface. Coordinates in {@link xyxy} and\n * {@link xywh} are absolute pixels in the original image; the `*n` variants\n * are normalized to `[0, 1]` using `origShape`.\n */\nexport class Boxes {\n    /**\n     * @param xyxy Flat array of length `4 * N` in `[x1, y1, x2, y2, ...]` order.\n     * @param cls One class index per box, length `N`.\n     * @param conf One confidence per box, length `N`.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly xyxy: Float32Array,\n        public readonly cls: Int32Array,\n        public readonly conf: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of detected boxes. */\n    get length(): number {\n        return this.cls.length;\n    }\n\n    /** `[N, 4]` shape of the `xyxy` view. */\n    get shape(): readonly [number, number] {\n        return [this.length, 4];\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` flat array in absolute pixels. */\n    get xywh(): Float32Array {\n        const out = new Float32Array(this.xyxy.length);\n        for (let i = 0; i < this.length; i++) {\n            const x1 = this.xyxy[i * 4] as number;\n            const y1 = this.xyxy[i * 4 + 1] as number;\n            const x2 = this.xyxy[i * 4 + 2] as number;\n            const y2 = this.xyxy[i * 4 + 3] as number;\n            out[i * 4] = (x1 + x2) / 2;\n            out[i * 4 + 1] = (y1 + y2) / 2;\n            out[i * 4 + 2] = x2 - x1;\n            out[i * 4 + 3] = y2 - y1;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[x1, y1, x2, y2]` normalized to `[0, 1]`. */\n    get xyxyn(): Float32Array {\n        const [h, w] = this.origShape;\n        const out = new Float32Array(this.xyxy.length);\n        if (this.length === 0 || w <= 0 || h <= 0) return out;\n        for (let i = 0; i < this.length; i++) {\n            out[i * 4] = (this.xyxy[i * 4] as number) / w;\n            out[i * 4 + 1] = (this.xyxy[i * 4 + 1] as number) / h;\n            out[i * 4 + 2] = (this.xyxy[i * 4 + 2] as number) / w;\n            out[i * 4 + 3] = (this.xyxy[i * 4 + 3] as number) / h;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` normalized to `[0, 1]`. */\n    get xywhn(): Float32Array {\n        const xywh = this.xywh;\n        const [h, w] = this.origShape;\n        if (this.length === 0 || w <= 0 || h <= 0) return xywh;\n        for (let i = 0; i < this.length; i++) {\n            xywh[i * 4] = (xywh[i * 4] as number) / w;\n            xywh[i * 4 + 1] = (xywh[i * 4 + 1] as number) / h;\n            xywh[i * 4 + 2] = (xywh[i * 4 + 2] as number) / w;\n            xywh[i * 4 + 3] = (xywh[i * 4 + 3] as number) / h;\n        }\n        return xywh;\n    }\n\n    /**\n     * Concatenated `[N, 6]` array of `[x1, y1, x2, y2, conf, cls]`.\n     *\n     * Matches Ultralytics' `boxes.data`.\n     */\n    get data(): Float32Array {\n        const out = new Float32Array(this.length * 6);\n        for (let i = 0; i < this.length; i++) {\n            out[i * 6] = this.xyxy[i * 4] as number;\n            out[i * 6 + 1] = this.xyxy[i * 4 + 1] as number;\n            out[i * 6 + 2] = this.xyxy[i * 4 + 2] as number;\n            out[i * 6 + 3] = this.xyxy[i * 4 + 3] as number;\n            out[i * 6 + 4] = this.conf[i] as number;\n            out[i * 6 + 5] = this.cls[i] as number;\n        }\n        return out;\n    }\n}\n\n/** One selection of the highest-probability classes, descending. */\ninterface TopK {\n    indices: Int32Array;\n    values: Float32Array;\n}\n\n/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        return this._top(1).indices[0] ?? 0;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        return this._top(1).values[0] ?? 0;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._top(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._top(5).values;\n    }\n\n    private _cache = new Map<number, TopK>();\n\n    /**\n     * Memoised {@link Probs._topK}.\n     *\n     * `top5` and `top5conf` are separate getters over the same selection, so a\n     * caller reading both would otherwise pay for it twice — once per frame, in\n     * a camera loop. The probabilities a `Probs` was built from do not change,\n     * so the result is computed once per `k` and kept.\n     *\n     * @param k - How many classes to select.\n     * @returns The cached selection for that `k`.\n     */\n    private _top(k: number): TopK {\n        const hit = this._cache.get(k);\n        if (hit) return hit;\n        const computed = this._topK(k);\n        this._cache.set(k, computed);\n        return computed;\n    }\n\n    /**\n     * Select the `k` highest probabilities without ordering the rest.\n     *\n     * A full sort to read five entries out of a thousand-class vector costs\n     * O(n log n) plus an index array the size of the vector; keeping `k` slots\n     * ordered by insertion and scanning once costs O(n·k) with no allocation\n     * beyond the result. Measured on 1000 classes, that is 123.7 µs against\n     * 1.9 µs for the same output.\n     *\n     * Ties keep the lower class index first, matching the stable sort this\n     * replaced: a candidate only displaces an entry it is strictly greater\n     * than.\n     *\n     * @param k - How many classes to select.\n     * @returns Indices and probabilities, descending by probability.\n     */\n    private _topK(k: number): TopK {\n        const size = Math.min(k, this.data.length);\n        const indices = new Int32Array(size);\n        const values = new Float32Array(size);\n        if (size === 0) return { indices, values };\n\n        values.fill(Number.NEGATIVE_INFINITY);\n        for (let i = 0; i < this.data.length; i++) {\n            const value = this.data[i] as number;\n            if (value <= (values[size - 1] as number)) continue;\n            let slot = size - 1;\n            while (slot > 0 && (values[slot - 1] as number) < value) {\n                values[slot] = values[slot - 1] as number;\n                indices[slot] = indices[slot - 1] as number;\n                slot -= 1;\n            }\n            values[slot] = value;\n            indices[slot] = i;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image envelope for a fused detect→classify pipeline.\n *\n * Structurally a {@link DetectionResults} with a second class map: every\n * detection it yields carries a populated `classification`, and the two stages\n * have their own, unrelated label spaces — a detector that finds `sheep`\n * feeding a classifier that answers `famacha_3` shares no class ids with it.\n * Merging them into one `names` record would make `cls` and\n * `classification.cls` look comparable when they are not.\n *\n * ```typescript\n * const result = (await pipeline.predict(\"flock.jpg\"))[0];\n * for (const detection of result) {\n *   console.log(detection.name, detection.conf, detection.classification?.name);\n * }\n * ```\n */\nexport class DetectClassifyResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly classifierNames: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image classification envelope (Ultralytics-style `Results`).\n */\nexport class ClassificationResults {\n    constructor(\n        public readonly probs: Probs,\n        public readonly result: ClassificationResult,\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Top-1 class index (Ultralytics-style alias). */\n    get cls(): number {\n        return this.probs.top1;\n    }\n\n    /** Top-1 confidence (Ultralytics-style alias). */\n    get conf(): number {\n        return this.probs.top1conf;\n    }\n\n    /** Top-1 class name. */\n    get name(): string {\n        return this.names[this.cls] ?? `class_${this.cls}`;\n    }\n\n    /** Per-class probability list, sorted descending (legacy field). */\n    get probabilities(): readonly ClassificationResult[\"probabilities\"][number][] {\n        return this.result.probabilities;\n    }\n}\n\n/**\n * Per-image instance-segmentation envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link SegmentationResult} entries. `boxes`\n * and `masks` mirror Ultralytics' bulk-array views.\n */\nexport class SegmentationResults implements Iterable<SegmentationResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly masks: Masks,\n        public readonly detections: readonly SegmentationResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving instances. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance results. */\n    get(index: number): SegmentationResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<SegmentationResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n"],"mappings":"AAgCA,IAAM,EAAkB,CAAE,KAAM,EAAG,WAAY,EAAG,UAAW,EAAG,YAAa,CAAE,EASlE,EAAb,KAAmB,CAQK,KACA,IACA,KACA,UAJpB,YACI,EACA,EACA,EACA,EACF,CAJkB,KAAA,KAAA,EACA,KAAA,IAAA,EACA,KAAA,KAAA,EACA,KAAA,UAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,IAAI,MACpB,CAGA,IAAI,OAAmC,CACnC,MAAO,CAAC,KAAK,OAAQ,CAAC,CAC1B,CAGA,IAAI,MAAqB,CACrB,IAAM,EAAM,IAAI,aAAa,KAAK,KAAK,MAAM,EAC7C,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAAK,CAClC,IAAM,EAAK,KAAK,KAAK,EAAI,GACnB,EAAK,KAAK,KAAK,EAAI,EAAI,GACvB,EAAK,KAAK,KAAK,EAAI,EAAI,GACvB,EAAK,KAAK,KAAK,EAAI,EAAI,GAC7B,EAAI,EAAI,IAAM,EAAK,GAAM,EACzB,EAAI,EAAI,EAAI,IAAM,EAAK,GAAM,EAC7B,EAAI,EAAI,EAAI,GAAK,EAAK,EACtB,EAAI,EAAI,EAAI,GAAK,EAAK,CAC1B,CACA,OAAO,CACX,CAGA,IAAI,OAAsB,CACtB,GAAM,CAAC,EAAG,GAAK,KAAK,UACd,EAAM,IAAI,aAAa,KAAK,KAAK,MAAM,EAC7C,GAAI,KAAK,SAAW,GAAK,GAAK,GAAK,GAAK,EAAG,OAAO,EAClD,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAC7B,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,GAAgB,EAC5C,EAAI,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,EAAI,GAAgB,EACpD,EAAI,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,EAAI,GAAgB,EACpD,EAAI,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,EAAI,GAAgB,EAExD,OAAO,CACX,CAGA,IAAI,OAAsB,CACtB,IAAM,EAAO,KAAK,KACZ,CAAC,EAAG,GAAK,KAAK,UACpB,GAAI,KAAK,SAAW,GAAK,GAAK,GAAK,GAAK,EAAG,OAAO,EAClD,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAC7B,EAAK,EAAI,GAAM,EAAK,EAAI,GAAgB,EACxC,EAAK,EAAI,EAAI,GAAM,EAAK,EAAI,EAAI,GAAgB,EAChD,EAAK,EAAI,EAAI,GAAM,EAAK,EAAI,EAAI,GAAgB,EAChD,EAAK,EAAI,EAAI,GAAM,EAAK,EAAI,EAAI,GAAgB,EAEpD,OAAO,CACX,CAOA,IAAI,MAAqB,CACrB,IAAM,EAAM,IAAI,aAAa,KAAK,OAAS,CAAC,EAC5C,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAC7B,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,GAC3B,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,EAAI,GACnC,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,EAAI,GACnC,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,EAAI,GACnC,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,GAC3B,EAAI,EAAI,EAAI,GAAK,KAAK,IAAI,GAE9B,OAAO,CACX,CACJ,EAaa,EAAb,KAAmB,CAEa,KAA5B,YAAY,EAAoC,CAApB,KAAA,KAAA,CAAqB,CAGjD,IAAI,QAAiB,CACjB,OAAO,KAAK,KAAK,MACrB,CAGA,IAAI,OAA2B,CAC3B,MAAO,CAAC,KAAK,MAAM,CACvB,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,QAAQ,IAAM,CACtC,CAGA,IAAI,UAAmB,CACnB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,OAAO,IAAM,CACrC,CAGA,IAAI,MAAmB,CACnB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,OACxB,CAGA,IAAI,UAAyB,CACzB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,MACxB,CAEA,OAAiB,IAAI,IAarB,KAAa,EAAiB,CAC1B,IAAM,EAAM,KAAK,OAAO,IAAI,CAAC,EAC7B,GAAI,EAAK,OAAO,EAChB,IAAM,EAAW,KAAK,MAAM,CAAC,EAE7B,OADA,KAAK,OAAO,IAAI,EAAG,CAAQ,EACpB,CACX,CAkBA,MAAc,EAAiB,CAC3B,IAAM,EAAO,KAAK,IAAI,EAAG,KAAK,KAAK,MAAM,EACnC,EAAU,IAAI,WAAW,CAAI,EAC7B,EAAS,IAAI,aAAa,CAAI,EACpC,GAAI,IAAS,EAAG,MAAO,CAAE,UAAS,QAAO,EAEzC,EAAO,KAAK,IAAwB,EACpC,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,KAAK,OAAQ,IAAK,CACvC,IAAM,EAAQ,KAAK,KAAK,GACxB,GAAI,GAAU,EAAO,EAAO,GAAe,SAC3C,IAAI,EAAO,EAAO,EAClB,KAAO,EAAO,GAAM,EAAO,EAAO,GAAgB,GAC9C,EAAO,GAAQ,EAAO,EAAO,GAC7B,EAAQ,GAAQ,EAAQ,EAAO,GAC/B,IAEJ,EAAO,GAAQ,EACf,EAAQ,GAAQ,CACpB,CACA,MAAO,CAAE,UAAS,QAAO,CAC7B,CACJ,EAQa,EAAb,KAAmB,CAOK,KAKA,KACA,UAPpB,YACI,EAKA,EACA,EACF,CAPkB,KAAA,KAAA,EAKA,KAAA,KAAA,EACA,KAAA,UAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,KAAK,MACrB,CAGA,IAAI,OAA2B,CAC3B,MAAO,CAAC,KAAK,MAAM,CACvB,CAEA,CAAC,OAAO,WAIL,CACC,OAAO,KAAK,KAAK,OAAO,SAAS,CAAC,CACtC,CACJ,EAiBa,EAAb,KAAmE,CAE3C,MACA,WACA,MACA,QACA,UACA,KACA,MAPpB,YACI,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CAPkB,KAAA,MAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAI,EAA4C,CAC5C,OAAO,KAAK,WAAW,EAC3B,CAEA,CAAC,OAAO,WAAuC,CAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC,CAC5C,CACJ,EAmBa,EAAb,KAAwE,CAEhD,MACA,WACA,MACA,gBACA,QACA,UACA,KACA,MARpB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CARkB,KAAA,MAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,gBAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAI,EAA4C,CAC5C,OAAO,KAAK,WAAW,EAC3B,CAEA,CAAC,OAAO,WAAuC,CAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC,CAC5C,CACJ,EAKa,EAAb,KAAmC,CAEX,MACA,OACA,MACA,QACA,UACA,KACA,MAPpB,YACI,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CAPkB,KAAA,MAAA,EACA,KAAA,OAAA,EACA,KAAA,MAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,KAAc,CACd,OAAO,KAAK,MAAM,IACtB,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAM,QACtB,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAM,KAAK,MAAQ,SAAS,KAAK,KACjD,CAGA,IAAI,eAA0E,CAC1E,OAAO,KAAK,OAAO,aACvB,CACJ,EAQa,EAAb,KAAyE,CAEjD,MACA,MACA,WACA,MACA,QACA,UACA,KACA,MARpB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CARkB,KAAA,MAAA,EACA,KAAA,MAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAI,EAA+C,CAC/C,OAAO,KAAK,WAAW,EAC3B,CAEA,CAAC,OAAO,WAA0C,CAC9C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC,CAC5C,CACJ"}
+{"version":3,"file":"results.cjs","names":[],"sources":["../../src/vision/results.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n * - `speed`: per-stage timings of the `predict()` call that produced it.\n */\n\nimport { type Speed } from \"./core/timing\";\nimport {\n    type ClassificationResult,\n    type DetectionResult,\n    type RGBImage,\n    type SegmentationResult,\n} from \"./types\";\n\n/**\n * Zero timings for an envelope built outside a `predict()` call.\n *\n * Hand-constructed envelopes (tests, adapters) have nothing to measure, and\n * zeros keep `speed.inference` a plain `number` at every call site instead of\n * forcing an optional check that only ever fires for synthetic data.\n */\nconst NO_SPEED: Speed = { load: 0, preprocess: 0, inference: 0, postprocess: 0 };\n\n/**\n * Bulk numpy-style view of detected boxes for a single image.\n *\n * Mirrors Ultralytics' `Boxes` interface. Coordinates in {@link xyxy} and\n * {@link xywh} are absolute pixels in the original image; the `*n` variants\n * are normalized to `[0, 1]` using `origShape`.\n */\nexport class Boxes {\n    /**\n     * @param xyxy Flat array of length `4 * N` in `[x1, y1, x2, y2, ...]` order.\n     * @param cls One class index per box, length `N`.\n     * @param conf One confidence per box, length `N`.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly xyxy: Float32Array,\n        public readonly cls: Int32Array,\n        public readonly conf: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of detected boxes. */\n    get length(): number {\n        return this.cls.length;\n    }\n\n    /** `[N, 4]` shape of the `xyxy` view. */\n    get shape(): readonly [number, number] {\n        return [this.length, 4];\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` flat array in absolute pixels. */\n    get xywh(): Float32Array {\n        const out = new Float32Array(this.xyxy.length);\n        for (let i = 0; i < this.length; i++) {\n            const x1 = this.xyxy[i * 4] as number;\n            const y1 = this.xyxy[i * 4 + 1] as number;\n            const x2 = this.xyxy[i * 4 + 2] as number;\n            const y2 = this.xyxy[i * 4 + 3] as number;\n            out[i * 4] = (x1 + x2) / 2;\n            out[i * 4 + 1] = (y1 + y2) / 2;\n            out[i * 4 + 2] = x2 - x1;\n            out[i * 4 + 3] = y2 - y1;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[x1, y1, x2, y2]` normalized to `[0, 1]`. */\n    get xyxyn(): Float32Array {\n        const [h, w] = this.origShape;\n        const out = new Float32Array(this.xyxy.length);\n        if (this.length === 0 || w <= 0 || h <= 0) return out;\n        for (let i = 0; i < this.length; i++) {\n            out[i * 4] = (this.xyxy[i * 4] as number) / w;\n            out[i * 4 + 1] = (this.xyxy[i * 4 + 1] as number) / h;\n            out[i * 4 + 2] = (this.xyxy[i * 4 + 2] as number) / w;\n            out[i * 4 + 3] = (this.xyxy[i * 4 + 3] as number) / h;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` normalized to `[0, 1]`. */\n    get xywhn(): Float32Array {\n        const xywh = this.xywh;\n        const [h, w] = this.origShape;\n        if (this.length === 0 || w <= 0 || h <= 0) return xywh;\n        for (let i = 0; i < this.length; i++) {\n            xywh[i * 4] = (xywh[i * 4] as number) / w;\n            xywh[i * 4 + 1] = (xywh[i * 4 + 1] as number) / h;\n            xywh[i * 4 + 2] = (xywh[i * 4 + 2] as number) / w;\n            xywh[i * 4 + 3] = (xywh[i * 4 + 3] as number) / h;\n        }\n        return xywh;\n    }\n\n    /**\n     * Concatenated `[N, 6]` array of `[x1, y1, x2, y2, conf, cls]`.\n     *\n     * Matches Ultralytics' `boxes.data`.\n     */\n    get data(): Float32Array {\n        const out = new Float32Array(this.length * 6);\n        for (let i = 0; i < this.length; i++) {\n            out[i * 6] = this.xyxy[i * 4] as number;\n            out[i * 6 + 1] = this.xyxy[i * 4 + 1] as number;\n            out[i * 6 + 2] = this.xyxy[i * 4 + 2] as number;\n            out[i * 6 + 3] = this.xyxy[i * 4 + 3] as number;\n            out[i * 6 + 4] = this.conf[i] as number;\n            out[i * 6 + 5] = this.cls[i] as number;\n        }\n        return out;\n    }\n}\n\n/** One selection of the highest-probability classes, descending. */\ninterface TopK {\n    indices: Int32Array;\n    values: Float32Array;\n}\n\n/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /**\n     * Indices of the top-5 most probable classes, descending.\n     *\n     * The array is the memoised selection itself, not a copy — reading it twice\n     * hands back the same object. Treat it as read-only: writing into it edits\n     * what every later read of this `Probs` returns.\n     */\n    get top5(): Int32Array {\n        return this._top(5).indices;\n    }\n\n    /**\n     * Probabilities of the top-5 classes, descending.\n     *\n     * Shares the memoised selection with {@link Probs.top5}, under the same\n     * read-only caveat.\n     */\n    get top5conf(): Float32Array {\n        return this._top(5).values;\n    }\n\n    private _cache = new Map<number, TopK>();\n\n    /**\n     * Memoised {@link Probs._topK}.\n     *\n     * `top5` and `top5conf` are separate getters over the same selection, so a\n     * caller reading both would otherwise pay for it twice — once per frame, in\n     * a camera loop. The probabilities a `Probs` was built from do not change,\n     * so the result is computed once per `k` and kept.\n     *\n     * @param k - How many classes to select.\n     * @returns The cached selection for that `k`.\n     */\n    private _top(k: number): TopK {\n        const hit = this._cache.get(k);\n        if (hit) return hit;\n        const computed = this._topK(k);\n        this._cache.set(k, computed);\n        return computed;\n    }\n\n    /**\n     * Select the `k` highest probabilities without ordering the rest.\n     *\n     * A full sort to read five entries out of a thousand-class vector costs\n     * O(n log n) plus an index array the size of the vector; keeping `k` slots\n     * ordered by insertion and scanning once costs O(n·k) with no allocation\n     * beyond the result. Measured on 1000 classes over 2000 iterations, 134.5 µs\n     * against 1.5 µs for the same output.\n     *\n     * Ties keep the lower class index first, matching the stable sort this\n     * replaced: a candidate only displaces an entry it is strictly greater\n     * than. That is also what keeps this selection in step with the Python\n     * SDK's `np.argsort(-data, kind=\"stable\")`, where the sort is C and the\n     * cost this avoids does not arise.\n     *\n     * @param k - How many classes to select.\n     * @returns Indices and probabilities, descending by probability.\n     */\n    private _topK(k: number): TopK {\n        const size = Math.min(k, this.data.length);\n        const indices = new Int32Array(size);\n        const values = new Float32Array(size);\n        if (size === 0) return { indices, values };\n\n        values.fill(Number.NEGATIVE_INFINITY);\n        for (let i = 0; i < this.data.length; i++) {\n            const value = this.data[i] as number;\n            if (value <= (values[size - 1] as number)) continue;\n            let slot = size - 1;\n            while (slot > 0 && (values[slot - 1] as number) < value) {\n                values[slot] = values[slot - 1] as number;\n                indices[slot] = indices[slot - 1] as number;\n                slot -= 1;\n            }\n            values[slot] = value;\n            indices[slot] = i;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image envelope for a fused detect→classify pipeline.\n *\n * Structurally a {@link DetectionResults} with a second class map: every\n * detection it yields carries a populated `classification`, and the two stages\n * have their own, unrelated label spaces — a detector that finds `sheep`\n * feeding a classifier that answers `famacha_3` shares no class ids with it.\n * Merging them into one `names` record would make `cls` and\n * `classification.cls` look comparable when they are not.\n *\n * ```typescript\n * const result = (await pipeline.predict(\"flock.jpg\"))[0];\n * for (const detection of result) {\n *   console.log(detection.name, detection.conf, detection.classification?.name);\n * }\n * ```\n */\nexport class DetectClassifyResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly classifierNames: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image classification envelope (Ultralytics-style `Results`).\n */\nexport class ClassificationResults {\n    constructor(\n        public readonly probs: Probs,\n        public readonly result: ClassificationResult,\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Top-1 class index (Ultralytics-style alias). */\n    get cls(): number {\n        return this.probs.top1;\n    }\n\n    /** Top-1 confidence (Ultralytics-style alias). */\n    get conf(): number {\n        return this.probs.top1conf;\n    }\n\n    /** Top-1 class name. */\n    get name(): string {\n        return this.names[this.cls] ?? `class_${this.cls}`;\n    }\n\n    /** Per-class probability list, sorted descending (legacy field). */\n    get probabilities(): readonly ClassificationResult[\"probabilities\"][number][] {\n        return this.result.probabilities;\n    }\n}\n\n/**\n * Per-image instance-segmentation envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link SegmentationResult} entries. `boxes`\n * and `masks` mirror Ultralytics' bulk-array views.\n */\nexport class SegmentationResults implements Iterable<SegmentationResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly masks: Masks,\n        public readonly detections: readonly SegmentationResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving instances. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance results. */\n    get(index: number): SegmentationResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<SegmentationResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n"],"mappings":"AAgCA,IAAM,EAAkB,CAAE,KAAM,EAAG,WAAY,EAAG,UAAW,EAAG,YAAa,CAAE,EASlE,EAAb,KAAmB,CAQK,KACA,IACA,KACA,UAJpB,YACI,EACA,EACA,EACA,EACF,CAJkB,KAAA,KAAA,EACA,KAAA,IAAA,EACA,KAAA,KAAA,EACA,KAAA,UAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,IAAI,MACpB,CAGA,IAAI,OAAmC,CACnC,MAAO,CAAC,KAAK,OAAQ,CAAC,CAC1B,CAGA,IAAI,MAAqB,CACrB,IAAM,EAAM,IAAI,aAAa,KAAK,KAAK,MAAM,EAC7C,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAAK,CAClC,IAAM,EAAK,KAAK,KAAK,EAAI,GACnB,EAAK,KAAK,KAAK,EAAI,EAAI,GACvB,EAAK,KAAK,KAAK,EAAI,EAAI,GACvB,EAAK,KAAK,KAAK,EAAI,EAAI,GAC7B,EAAI,EAAI,IAAM,EAAK,GAAM,EACzB,EAAI,EAAI,EAAI,IAAM,EAAK,GAAM,EAC7B,EAAI,EAAI,EAAI,GAAK,EAAK,EACtB,EAAI,EAAI,EAAI,GAAK,EAAK,CAC1B,CACA,OAAO,CACX,CAGA,IAAI,OAAsB,CACtB,GAAM,CAAC,EAAG,GAAK,KAAK,UACd,EAAM,IAAI,aAAa,KAAK,KAAK,MAAM,EAC7C,GAAI,KAAK,SAAW,GAAK,GAAK,GAAK,GAAK,EAAG,OAAO,EAClD,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAC7B,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,GAAgB,EAC5C,EAAI,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,EAAI,GAAgB,EACpD,EAAI,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,EAAI,GAAgB,EACpD,EAAI,EAAI,EAAI,GAAM,KAAK,KAAK,EAAI,EAAI,GAAgB,EAExD,OAAO,CACX,CAGA,IAAI,OAAsB,CACtB,IAAM,EAAO,KAAK,KACZ,CAAC,EAAG,GAAK,KAAK,UACpB,GAAI,KAAK,SAAW,GAAK,GAAK,GAAK,GAAK,EAAG,OAAO,EAClD,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAC7B,EAAK,EAAI,GAAM,EAAK,EAAI,GAAgB,EACxC,EAAK,EAAI,EAAI,GAAM,EAAK,EAAI,EAAI,GAAgB,EAChD,EAAK,EAAI,EAAI,GAAM,EAAK,EAAI,EAAI,GAAgB,EAChD,EAAK,EAAI,EAAI,GAAM,EAAK,EAAI,EAAI,GAAgB,EAEpD,OAAO,CACX,CAOA,IAAI,MAAqB,CACrB,IAAM,EAAM,IAAI,aAAa,KAAK,OAAS,CAAC,EAC5C,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,OAAQ,IAC7B,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,GAC3B,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,EAAI,GACnC,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,EAAI,GACnC,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,EAAI,EAAI,GACnC,EAAI,EAAI,EAAI,GAAK,KAAK,KAAK,GAC3B,EAAI,EAAI,EAAI,GAAK,KAAK,IAAI,GAE9B,OAAO,CACX,CACJ,EAaa,EAAb,KAAmB,CAEa,KAA5B,YAAY,EAAoC,CAApB,KAAA,KAAA,CAAqB,CAGjD,IAAI,QAAiB,CACjB,OAAO,KAAK,KAAK,MACrB,CAGA,IAAI,OAA2B,CAC3B,MAAO,CAAC,KAAK,MAAM,CACvB,CAGA,IAAI,MAAe,CACf,GAAI,KAAK,KAAK,SAAW,EAAG,MAAO,GACnC,IAAI,EAAO,EACP,EAAU,KAAK,KAAK,GACxB,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,KAAK,OAAQ,IAAK,CACvC,IAAM,EAAI,KAAK,KAAK,GAChB,EAAI,IACJ,EAAO,EACP,EAAU,EAElB,CACA,OAAO,CACX,CAGA,IAAI,UAAmB,CAEnB,OADI,KAAK,KAAK,SAAW,EAAU,EAC5B,KAAK,KAAK,KAAK,KAC1B,CASA,IAAI,MAAmB,CACnB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,OACxB,CAQA,IAAI,UAAyB,CACzB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,MACxB,CAEA,OAAiB,IAAI,IAarB,KAAa,EAAiB,CAC1B,IAAM,EAAM,KAAK,OAAO,IAAI,CAAC,EAC7B,GAAI,EAAK,OAAO,EAChB,IAAM,EAAW,KAAK,MAAM,CAAC,EAE7B,OADA,KAAK,OAAO,IAAI,EAAG,CAAQ,EACpB,CACX,CAoBA,MAAc,EAAiB,CAC3B,IAAM,EAAO,KAAK,IAAI,EAAG,KAAK,KAAK,MAAM,EACnC,EAAU,IAAI,WAAW,CAAI,EAC7B,EAAS,IAAI,aAAa,CAAI,EACpC,GAAI,IAAS,EAAG,MAAO,CAAE,UAAS,QAAO,EAEzC,EAAO,KAAK,IAAwB,EACpC,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,KAAK,OAAQ,IAAK,CACvC,IAAM,EAAQ,KAAK,KAAK,GACxB,GAAI,GAAU,EAAO,EAAO,GAAe,SAC3C,IAAI,EAAO,EAAO,EAClB,KAAO,EAAO,GAAM,EAAO,EAAO,GAAgB,GAC9C,EAAO,GAAQ,EAAO,EAAO,GAC7B,EAAQ,GAAQ,EAAQ,EAAO,GAC/B,IAEJ,EAAO,GAAQ,EACf,EAAQ,GAAQ,CACpB,CACA,MAAO,CAAE,UAAS,QAAO,CAC7B,CACJ,EAQa,EAAb,KAAmB,CAOK,KAKA,KACA,UAPpB,YACI,EAKA,EACA,EACF,CAPkB,KAAA,KAAA,EAKA,KAAA,KAAA,EACA,KAAA,UAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,KAAK,MACrB,CAGA,IAAI,OAA2B,CAC3B,MAAO,CAAC,KAAK,MAAM,CACvB,CAEA,CAAC,OAAO,WAIL,CACC,OAAO,KAAK,KAAK,OAAO,SAAS,CAAC,CACtC,CACJ,EAiBa,EAAb,KAAmE,CAE3C,MACA,WACA,MACA,QACA,UACA,KACA,MAPpB,YACI,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CAPkB,KAAA,MAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAI,EAA4C,CAC5C,OAAO,KAAK,WAAW,EAC3B,CAEA,CAAC,OAAO,WAAuC,CAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC,CAC5C,CACJ,EAmBa,EAAb,KAAwE,CAEhD,MACA,WACA,MACA,gBACA,QACA,UACA,KACA,MARpB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CARkB,KAAA,MAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,gBAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAI,EAA4C,CAC5C,OAAO,KAAK,WAAW,EAC3B,CAEA,CAAC,OAAO,WAAuC,CAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC,CAC5C,CACJ,EAKa,EAAb,KAAmC,CAEX,MACA,OACA,MACA,QACA,UACA,KACA,MAPpB,YACI,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CAPkB,KAAA,MAAA,EACA,KAAA,OAAA,EACA,KAAA,MAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,KAAc,CACd,OAAO,KAAK,MAAM,IACtB,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAM,QACtB,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAM,KAAK,MAAQ,SAAS,KAAK,KACjD,CAGA,IAAI,eAA0E,CAC1E,OAAO,KAAK,OAAO,aACvB,CACJ,EAQa,EAAb,KAAyE,CAEjD,MACA,MACA,WACA,MACA,QACA,UACA,KACA,MARpB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EAAsC,KACtC,EAAyC,EAC3C,CARkB,KAAA,MAAA,EACA,KAAA,MAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,QAAA,EACA,KAAA,UAAA,EACA,KAAA,KAAA,EACA,KAAA,MAAA,CACjB,CAGH,IAAI,QAAiB,CACjB,OAAO,KAAK,WAAW,MAC3B,CAGA,IAAI,EAA+C,CAC/C,OAAO,KAAK,WAAW,EAC3B,CAEA,CAAC,OAAO,WAA0C,CAC9C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC,CAC5C,CACJ"}

package/dist/vision/results.js

@@ -55,10 +55,16 @@ var e = {
 		return [this.length];
 	}
 	get top1() {
-		return this._top(1).indices[0] ?? 0;
+		if (this.data.length === 0) return 0;
+		let e = 0, t = this.data[0];
+		for (let n = 1; n < this.data.length; n++) {
+			let r = this.data[n];
+			r > t && (e = n, t = r);
+		}
+		return e;
 	}
 	get top1conf() {
-		return this._top(1).values[0] ?? 0;
+		return this.data.length === 0 ? 0 : this.data[this.top1];
 	}
 	get top5() {
 		return this._top(5).indices;

package/dist/vision/results.js.map

@@ -1 +1 @@
-{"version":3,"file":"results.js","names":[],"sources":["../../src/vision/results.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n * - `speed`: per-stage timings of the `predict()` call that produced it.\n */\n\nimport { type Speed } from \"./core/timing\";\nimport {\n    type ClassificationResult,\n    type DetectionResult,\n    type RGBImage,\n    type SegmentationResult,\n} from \"./types\";\n\n/**\n * Zero timings for an envelope built outside a `predict()` call.\n *\n * Hand-constructed envelopes (tests, adapters) have nothing to measure, and\n * zeros keep `speed.inference` a plain `number` at every call site instead of\n * forcing an optional check that only ever fires for synthetic data.\n */\nconst NO_SPEED: Speed = { load: 0, preprocess: 0, inference: 0, postprocess: 0 };\n\n/**\n * Bulk numpy-style view of detected boxes for a single image.\n *\n * Mirrors Ultralytics' `Boxes` interface. Coordinates in {@link xyxy} and\n * {@link xywh} are absolute pixels in the original image; the `*n` variants\n * are normalized to `[0, 1]` using `origShape`.\n */\nexport class Boxes {\n    /**\n     * @param xyxy Flat array of length `4 * N` in `[x1, y1, x2, y2, ...]` order.\n     * @param cls One class index per box, length `N`.\n     * @param conf One confidence per box, length `N`.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly xyxy: Float32Array,\n        public readonly cls: Int32Array,\n        public readonly conf: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of detected boxes. */\n    get length(): number {\n        return this.cls.length;\n    }\n\n    /** `[N, 4]` shape of the `xyxy` view. */\n    get shape(): readonly [number, number] {\n        return [this.length, 4];\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` flat array in absolute pixels. */\n    get xywh(): Float32Array {\n        const out = new Float32Array(this.xyxy.length);\n        for (let i = 0; i < this.length; i++) {\n            const x1 = this.xyxy[i * 4] as number;\n            const y1 = this.xyxy[i * 4 + 1] as number;\n            const x2 = this.xyxy[i * 4 + 2] as number;\n            const y2 = this.xyxy[i * 4 + 3] as number;\n            out[i * 4] = (x1 + x2) / 2;\n            out[i * 4 + 1] = (y1 + y2) / 2;\n            out[i * 4 + 2] = x2 - x1;\n            out[i * 4 + 3] = y2 - y1;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[x1, y1, x2, y2]` normalized to `[0, 1]`. */\n    get xyxyn(): Float32Array {\n        const [h, w] = this.origShape;\n        const out = new Float32Array(this.xyxy.length);\n        if (this.length === 0 || w <= 0 || h <= 0) return out;\n        for (let i = 0; i < this.length; i++) {\n            out[i * 4] = (this.xyxy[i * 4] as number) / w;\n            out[i * 4 + 1] = (this.xyxy[i * 4 + 1] as number) / h;\n            out[i * 4 + 2] = (this.xyxy[i * 4 + 2] as number) / w;\n            out[i * 4 + 3] = (this.xyxy[i * 4 + 3] as number) / h;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` normalized to `[0, 1]`. */\n    get xywhn(): Float32Array {\n        const xywh = this.xywh;\n        const [h, w] = this.origShape;\n        if (this.length === 0 || w <= 0 || h <= 0) return xywh;\n        for (let i = 0; i < this.length; i++) {\n            xywh[i * 4] = (xywh[i * 4] as number) / w;\n            xywh[i * 4 + 1] = (xywh[i * 4 + 1] as number) / h;\n            xywh[i * 4 + 2] = (xywh[i * 4 + 2] as number) / w;\n            xywh[i * 4 + 3] = (xywh[i * 4 + 3] as number) / h;\n        }\n        return xywh;\n    }\n\n    /**\n     * Concatenated `[N, 6]` array of `[x1, y1, x2, y2, conf, cls]`.\n     *\n     * Matches Ultralytics' `boxes.data`.\n     */\n    get data(): Float32Array {\n        const out = new Float32Array(this.length * 6);\n        for (let i = 0; i < this.length; i++) {\n            out[i * 6] = this.xyxy[i * 4] as number;\n            out[i * 6 + 1] = this.xyxy[i * 4 + 1] as number;\n            out[i * 6 + 2] = this.xyxy[i * 4 + 2] as number;\n            out[i * 6 + 3] = this.xyxy[i * 4 + 3] as number;\n            out[i * 6 + 4] = this.conf[i] as number;\n            out[i * 6 + 5] = this.cls[i] as number;\n        }\n        return out;\n    }\n}\n\n/** One selection of the highest-probability classes, descending. */\ninterface TopK {\n    indices: Int32Array;\n    values: Float32Array;\n}\n\n/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        return this._top(1).indices[0] ?? 0;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        return this._top(1).values[0] ?? 0;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._top(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._top(5).values;\n    }\n\n    private _cache = new Map<number, TopK>();\n\n    /**\n     * Memoised {@link Probs._topK}.\n     *\n     * `top5` and `top5conf` are separate getters over the same selection, so a\n     * caller reading both would otherwise pay for it twice — once per frame, in\n     * a camera loop. The probabilities a `Probs` was built from do not change,\n     * so the result is computed once per `k` and kept.\n     *\n     * @param k - How many classes to select.\n     * @returns The cached selection for that `k`.\n     */\n    private _top(k: number): TopK {\n        const hit = this._cache.get(k);\n        if (hit) return hit;\n        const computed = this._topK(k);\n        this._cache.set(k, computed);\n        return computed;\n    }\n\n    /**\n     * Select the `k` highest probabilities without ordering the rest.\n     *\n     * A full sort to read five entries out of a thousand-class vector costs\n     * O(n log n) plus an index array the size of the vector; keeping `k` slots\n     * ordered by insertion and scanning once costs O(n·k) with no allocation\n     * beyond the result. Measured on 1000 classes, that is 123.7 µs against\n     * 1.9 µs for the same output.\n     *\n     * Ties keep the lower class index first, matching the stable sort this\n     * replaced: a candidate only displaces an entry it is strictly greater\n     * than.\n     *\n     * @param k - How many classes to select.\n     * @returns Indices and probabilities, descending by probability.\n     */\n    private _topK(k: number): TopK {\n        const size = Math.min(k, this.data.length);\n        const indices = new Int32Array(size);\n        const values = new Float32Array(size);\n        if (size === 0) return { indices, values };\n\n        values.fill(Number.NEGATIVE_INFINITY);\n        for (let i = 0; i < this.data.length; i++) {\n            const value = this.data[i] as number;\n            if (value <= (values[size - 1] as number)) continue;\n            let slot = size - 1;\n            while (slot > 0 && (values[slot - 1] as number) < value) {\n                values[slot] = values[slot - 1] as number;\n                indices[slot] = indices[slot - 1] as number;\n                slot -= 1;\n            }\n            values[slot] = value;\n            indices[slot] = i;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image envelope for a fused detect→classify pipeline.\n *\n * Structurally a {@link DetectionResults} with a second class map: every\n * detection it yields carries a populated `classification`, and the two stages\n * have their own, unrelated label spaces — a detector that finds `sheep`\n * feeding a classifier that answers `famacha_3` shares no class ids with it.\n * Merging them into one `names` record would make `cls` and\n * `classification.cls` look comparable when they are not.\n *\n * ```typescript\n * const result = (await pipeline.predict(\"flock.jpg\"))[0];\n * for (const detection of result) {\n *   console.log(detection.name, detection.conf, detection.classification?.name);\n * }\n * ```\n */\nexport class DetectClassifyResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly classifierNames: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image classification envelope (Ultralytics-style `Results`).\n */\nexport class ClassificationResults {\n    constructor(\n        public readonly probs: Probs,\n        public readonly result: ClassificationResult,\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Top-1 class index (Ultralytics-style alias). */\n    get cls(): number {\n        return this.probs.top1;\n    }\n\n    /** Top-1 confidence (Ultralytics-style alias). */\n    get conf(): number {\n        return this.probs.top1conf;\n    }\n\n    /** Top-1 class name. */\n    get name(): string {\n        return this.names[this.cls] ?? `class_${this.cls}`;\n    }\n\n    /** Per-class probability list, sorted descending (legacy field). */\n    get probabilities(): readonly ClassificationResult[\"probabilities\"][number][] {\n        return this.result.probabilities;\n    }\n}\n\n/**\n * Per-image instance-segmentation envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link SegmentationResult} entries. `boxes`\n * and `masks` mirror Ultralytics' bulk-array views.\n */\nexport class SegmentationResults implements Iterable<SegmentationResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly masks: Masks,\n        public readonly detections: readonly SegmentationResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving instances. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance results. */\n    get(index: number): SegmentationResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<SegmentationResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n"],"mappings":";AAgCA,IAAM,IAAkB;CAAE,MAAM;CAAG,YAAY;CAAG,WAAW;CAAG,aAAa;AAAE,GASlE,IAAb,MAAmB;CAQK;CACA;CACA;CACA;CAJpB,YACI,GACA,GACA,GACA,GACF;EADkB,AAHA,KAAA,OAAA,GACA,KAAA,MAAA,GACA,KAAA,OAAA,GACA,KAAA,YAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,IAAI;CACpB;CAGA,IAAI,QAAmC;EACnC,OAAO,CAAC,KAAK,QAAQ,CAAC;CAC1B;CAGA,IAAI,OAAqB;EACrB,IAAM,IAAM,IAAI,aAAa,KAAK,KAAK,MAAM;EAC7C,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAAK;GAClC,IAAM,IAAK,KAAK,KAAK,IAAI,IACnB,IAAK,KAAK,KAAK,IAAI,IAAI,IACvB,IAAK,KAAK,KAAK,IAAI,IAAI,IACvB,IAAK,KAAK,KAAK,IAAI,IAAI;GAI7B,AAHA,EAAI,IAAI,MAAM,IAAK,KAAM,GACzB,EAAI,IAAI,IAAI,MAAM,IAAK,KAAM,GAC7B,EAAI,IAAI,IAAI,KAAK,IAAK,GACtB,EAAI,IAAI,IAAI,KAAK,IAAK;EAC1B;EACA,OAAO;CACX;CAGA,IAAI,QAAsB;EACtB,IAAM,CAAC,GAAG,KAAK,KAAK,WACd,IAAM,IAAI,aAAa,KAAK,KAAK,MAAM;EAC7C,IAAI,KAAK,WAAW,KAAK,KAAK,KAAK,KAAK,GAAG,OAAO;EAClD,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAI7B,AAHA,EAAI,IAAI,KAAM,KAAK,KAAK,IAAI,KAAgB,GAC5C,EAAI,IAAI,IAAI,KAAM,KAAK,KAAK,IAAI,IAAI,KAAgB,GACpD,EAAI,IAAI,IAAI,KAAM,KAAK,KAAK,IAAI,IAAI,KAAgB,GACpD,EAAI,IAAI,IAAI,KAAM,KAAK,KAAK,IAAI,IAAI,KAAgB;EAExD,OAAO;CACX;CAGA,IAAI,QAAsB;EACtB,IAAM,IAAO,KAAK,MACZ,CAAC,GAAG,KAAK,KAAK;EACpB,IAAI,KAAK,WAAW,KAAK,KAAK,KAAK,KAAK,GAAG,OAAO;EAClD,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAI7B,AAHA,EAAK,IAAI,KAAM,EAAK,IAAI,KAAgB,GACxC,EAAK,IAAI,IAAI,KAAM,EAAK,IAAI,IAAI,KAAgB,GAChD,EAAK,IAAI,IAAI,KAAM,EAAK,IAAI,IAAI,KAAgB,GAChD,EAAK,IAAI,IAAI,KAAM,EAAK,IAAI,IAAI,KAAgB;EAEpD,OAAO;CACX;CAOA,IAAI,OAAqB;EACrB,IAAM,IAAM,IAAI,aAAa,KAAK,SAAS,CAAC;EAC5C,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAM7B,AALA,EAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAC3B,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAAI,IACnC,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAAI,IACnC,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAAI,IACnC,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAC3B,EAAI,IAAI,IAAI,KAAK,KAAK,IAAI;EAE9B,OAAO;CACX;AACJ,GAaa,IAAb,MAAmB;CAEa;CAA5B,YAAY,GAAoC;EAApB,KAAA,OAAA;CAAqB;CAGjD,IAAI,SAAiB;EACjB,OAAO,KAAK,KAAK;CACrB;CAGA,IAAI,QAA2B;EAC3B,OAAO,CAAC,KAAK,MAAM;CACvB;CAGA,IAAI,OAAe;EACf,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,QAAQ,MAAM;CACtC;CAGA,IAAI,WAAmB;EACnB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,OAAO,MAAM;CACrC;CAGA,IAAI,OAAmB;EACnB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC;CACxB;CAGA,IAAI,WAAyB;EACzB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC;CACxB;CAEA,yBAAiB,IAAI,IAAkB;CAavC,KAAa,GAAiB;EAC1B,IAAM,IAAM,KAAK,OAAO,IAAI,CAAC;EAC7B,IAAI,GAAK,OAAO;EAChB,IAAM,IAAW,KAAK,MAAM,CAAC;EAE7B,OADA,KAAK,OAAO,IAAI,GAAG,CAAQ,GACpB;CACX;CAkBA,MAAc,GAAiB;EAC3B,IAAM,IAAO,KAAK,IAAI,GAAG,KAAK,KAAK,MAAM,GACnC,IAAU,IAAI,WAAW,CAAI,GAC7B,IAAS,IAAI,aAAa,CAAI;EACpC,IAAI,MAAS,GAAG,OAAO;GAAE;GAAS;EAAO;EAEzC,EAAO,KAAK,SAAwB;EACpC,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,KAAK,QAAQ,KAAK;GACvC,IAAM,IAAQ,KAAK,KAAK;GACxB,IAAI,KAAU,EAAO,IAAO,IAAe;GAC3C,IAAI,IAAO,IAAO;GAClB,OAAO,IAAO,KAAM,EAAO,IAAO,KAAgB,IAG9C,AAFA,EAAO,KAAQ,EAAO,IAAO,IAC7B,EAAQ,KAAQ,EAAQ,IAAO,IAC/B;GAGJ,AADA,EAAO,KAAQ,GACf,EAAQ,KAAQ;EACpB;EACA,OAAO;GAAE;GAAS;EAAO;CAC7B;AACJ,GAQa,IAAb,MAAmB;CAOK;CAKA;CACA;CAPpB,YACI,GAKA,GACA,GACF;EADkB,AANA,KAAA,OAAA,GAKA,KAAA,OAAA,GACA,KAAA,YAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,KAAK;CACrB;CAGA,IAAI,QAA2B;EAC3B,OAAO,CAAC,KAAK,MAAM;CACvB;CAEA,CAAC,OAAO,YAIL;EACC,OAAO,KAAK,KAAK,OAAO,SAAS,CAAC;CACtC;AACJ,GAiBa,IAAb,MAAmE;CAE3C;CACA;CACA;CACA;CACA;CACA;CACA;CAPpB,YACI,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AANA,KAAA,QAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,WAAW;CAC3B;CAGA,IAAI,GAA4C;EAC5C,OAAO,KAAK,WAAW;CAC3B;CAEA,CAAC,OAAO,YAAuC;EAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC;CAC5C;AACJ,GAmBa,IAAb,MAAwE;CAEhD;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CARpB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AAPA,KAAA,QAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,kBAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,WAAW;CAC3B;CAGA,IAAI,GAA4C;EAC5C,OAAO,KAAK,WAAW;CAC3B;CAEA,CAAC,OAAO,YAAuC;EAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC;CAC5C;AACJ,GAKa,IAAb,MAAmC;CAEX;CACA;CACA;CACA;CACA;CACA;CACA;CAPpB,YACI,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AANA,KAAA,QAAA,GACA,KAAA,SAAA,GACA,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,MAAc;EACd,OAAO,KAAK,MAAM;CACtB;CAGA,IAAI,OAAe;EACf,OAAO,KAAK,MAAM;CACtB;CAGA,IAAI,OAAe;EACf,OAAO,KAAK,MAAM,KAAK,QAAQ,SAAS,KAAK;CACjD;CAGA,IAAI,gBAA0E;EAC1E,OAAO,KAAK,OAAO;CACvB;AACJ,GAQa,IAAb,MAAyE;CAEjD;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CARpB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AAPA,KAAA,QAAA,GACA,KAAA,QAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,WAAW;CAC3B;CAGA,IAAI,GAA+C;EAC/C,OAAO,KAAK,WAAW;CAC3B;CAEA,CAAC,OAAO,YAA0C;EAC9C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC;CAC5C;AACJ"}
+{"version":3,"file":"results.js","names":[],"sources":["../../src/vision/results.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n * - `speed`: per-stage timings of the `predict()` call that produced it.\n */\n\nimport { type Speed } from \"./core/timing\";\nimport {\n    type ClassificationResult,\n    type DetectionResult,\n    type RGBImage,\n    type SegmentationResult,\n} from \"./types\";\n\n/**\n * Zero timings for an envelope built outside a `predict()` call.\n *\n * Hand-constructed envelopes (tests, adapters) have nothing to measure, and\n * zeros keep `speed.inference` a plain `number` at every call site instead of\n * forcing an optional check that only ever fires for synthetic data.\n */\nconst NO_SPEED: Speed = { load: 0, preprocess: 0, inference: 0, postprocess: 0 };\n\n/**\n * Bulk numpy-style view of detected boxes for a single image.\n *\n * Mirrors Ultralytics' `Boxes` interface. Coordinates in {@link xyxy} and\n * {@link xywh} are absolute pixels in the original image; the `*n` variants\n * are normalized to `[0, 1]` using `origShape`.\n */\nexport class Boxes {\n    /**\n     * @param xyxy Flat array of length `4 * N` in `[x1, y1, x2, y2, ...]` order.\n     * @param cls One class index per box, length `N`.\n     * @param conf One confidence per box, length `N`.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly xyxy: Float32Array,\n        public readonly cls: Int32Array,\n        public readonly conf: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of detected boxes. */\n    get length(): number {\n        return this.cls.length;\n    }\n\n    /** `[N, 4]` shape of the `xyxy` view. */\n    get shape(): readonly [number, number] {\n        return [this.length, 4];\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` flat array in absolute pixels. */\n    get xywh(): Float32Array {\n        const out = new Float32Array(this.xyxy.length);\n        for (let i = 0; i < this.length; i++) {\n            const x1 = this.xyxy[i * 4] as number;\n            const y1 = this.xyxy[i * 4 + 1] as number;\n            const x2 = this.xyxy[i * 4 + 2] as number;\n            const y2 = this.xyxy[i * 4 + 3] as number;\n            out[i * 4] = (x1 + x2) / 2;\n            out[i * 4 + 1] = (y1 + y2) / 2;\n            out[i * 4 + 2] = x2 - x1;\n            out[i * 4 + 3] = y2 - y1;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[x1, y1, x2, y2]` normalized to `[0, 1]`. */\n    get xyxyn(): Float32Array {\n        const [h, w] = this.origShape;\n        const out = new Float32Array(this.xyxy.length);\n        if (this.length === 0 || w <= 0 || h <= 0) return out;\n        for (let i = 0; i < this.length; i++) {\n            out[i * 4] = (this.xyxy[i * 4] as number) / w;\n            out[i * 4 + 1] = (this.xyxy[i * 4 + 1] as number) / h;\n            out[i * 4 + 2] = (this.xyxy[i * 4 + 2] as number) / w;\n            out[i * 4 + 3] = (this.xyxy[i * 4 + 3] as number) / h;\n        }\n        return out;\n    }\n\n    /** Boxes as `[N, 4]` `[cx, cy, w, h]` normalized to `[0, 1]`. */\n    get xywhn(): Float32Array {\n        const xywh = this.xywh;\n        const [h, w] = this.origShape;\n        if (this.length === 0 || w <= 0 || h <= 0) return xywh;\n        for (let i = 0; i < this.length; i++) {\n            xywh[i * 4] = (xywh[i * 4] as number) / w;\n            xywh[i * 4 + 1] = (xywh[i * 4 + 1] as number) / h;\n            xywh[i * 4 + 2] = (xywh[i * 4 + 2] as number) / w;\n            xywh[i * 4 + 3] = (xywh[i * 4 + 3] as number) / h;\n        }\n        return xywh;\n    }\n\n    /**\n     * Concatenated `[N, 6]` array of `[x1, y1, x2, y2, conf, cls]`.\n     *\n     * Matches Ultralytics' `boxes.data`.\n     */\n    get data(): Float32Array {\n        const out = new Float32Array(this.length * 6);\n        for (let i = 0; i < this.length; i++) {\n            out[i * 6] = this.xyxy[i * 4] as number;\n            out[i * 6 + 1] = this.xyxy[i * 4 + 1] as number;\n            out[i * 6 + 2] = this.xyxy[i * 4 + 2] as number;\n            out[i * 6 + 3] = this.xyxy[i * 4 + 3] as number;\n            out[i * 6 + 4] = this.conf[i] as number;\n            out[i * 6 + 5] = this.cls[i] as number;\n        }\n        return out;\n    }\n}\n\n/** One selection of the highest-probability classes, descending. */\ninterface TopK {\n    indices: Int32Array;\n    values: Float32Array;\n}\n\n/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /**\n     * Indices of the top-5 most probable classes, descending.\n     *\n     * The array is the memoised selection itself, not a copy — reading it twice\n     * hands back the same object. Treat it as read-only: writing into it edits\n     * what every later read of this `Probs` returns.\n     */\n    get top5(): Int32Array {\n        return this._top(5).indices;\n    }\n\n    /**\n     * Probabilities of the top-5 classes, descending.\n     *\n     * Shares the memoised selection with {@link Probs.top5}, under the same\n     * read-only caveat.\n     */\n    get top5conf(): Float32Array {\n        return this._top(5).values;\n    }\n\n    private _cache = new Map<number, TopK>();\n\n    /**\n     * Memoised {@link Probs._topK}.\n     *\n     * `top5` and `top5conf` are separate getters over the same selection, so a\n     * caller reading both would otherwise pay for it twice — once per frame, in\n     * a camera loop. The probabilities a `Probs` was built from do not change,\n     * so the result is computed once per `k` and kept.\n     *\n     * @param k - How many classes to select.\n     * @returns The cached selection for that `k`.\n     */\n    private _top(k: number): TopK {\n        const hit = this._cache.get(k);\n        if (hit) return hit;\n        const computed = this._topK(k);\n        this._cache.set(k, computed);\n        return computed;\n    }\n\n    /**\n     * Select the `k` highest probabilities without ordering the rest.\n     *\n     * A full sort to read five entries out of a thousand-class vector costs\n     * O(n log n) plus an index array the size of the vector; keeping `k` slots\n     * ordered by insertion and scanning once costs O(n·k) with no allocation\n     * beyond the result. Measured on 1000 classes over 2000 iterations, 134.5 µs\n     * against 1.5 µs for the same output.\n     *\n     * Ties keep the lower class index first, matching the stable sort this\n     * replaced: a candidate only displaces an entry it is strictly greater\n     * than. That is also what keeps this selection in step with the Python\n     * SDK's `np.argsort(-data, kind=\"stable\")`, where the sort is C and the\n     * cost this avoids does not arise.\n     *\n     * @param k - How many classes to select.\n     * @returns Indices and probabilities, descending by probability.\n     */\n    private _topK(k: number): TopK {\n        const size = Math.min(k, this.data.length);\n        const indices = new Int32Array(size);\n        const values = new Float32Array(size);\n        if (size === 0) return { indices, values };\n\n        values.fill(Number.NEGATIVE_INFINITY);\n        for (let i = 0; i < this.data.length; i++) {\n            const value = this.data[i] as number;\n            if (value <= (values[size - 1] as number)) continue;\n            let slot = size - 1;\n            while (slot > 0 && (values[slot - 1] as number) < value) {\n                values[slot] = values[slot - 1] as number;\n                indices[slot] = indices[slot - 1] as number;\n                slot -= 1;\n            }\n            values[slot] = value;\n            indices[slot] = i;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image envelope for a fused detect→classify pipeline.\n *\n * Structurally a {@link DetectionResults} with a second class map: every\n * detection it yields carries a populated `classification`, and the two stages\n * have their own, unrelated label spaces — a detector that finds `sheep`\n * feeding a classifier that answers `famacha_3` shares no class ids with it.\n * Merging them into one `names` record would make `cls` and\n * `classification.cls` look comparable when they are not.\n *\n * ```typescript\n * const result = (await pipeline.predict(\"flock.jpg\"))[0];\n * for (const detection of result) {\n *   console.log(detection.name, detection.conf, detection.classification?.name);\n * }\n * ```\n */\nexport class DetectClassifyResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly classifierNames: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving detections. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance detections. */\n    get(index: number): DetectionResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<DetectionResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image classification envelope (Ultralytics-style `Results`).\n */\nexport class ClassificationResults {\n    constructor(\n        public readonly probs: Probs,\n        public readonly result: ClassificationResult,\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Top-1 class index (Ultralytics-style alias). */\n    get cls(): number {\n        return this.probs.top1;\n    }\n\n    /** Top-1 confidence (Ultralytics-style alias). */\n    get conf(): number {\n        return this.probs.top1conf;\n    }\n\n    /** Top-1 class name. */\n    get name(): string {\n        return this.names[this.cls] ?? `class_${this.cls}`;\n    }\n\n    /** Per-class probability list, sorted descending (legacy field). */\n    get probabilities(): readonly ClassificationResult[\"probabilities\"][number][] {\n        return this.result.probabilities;\n    }\n}\n\n/**\n * Per-image instance-segmentation envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link SegmentationResult} entries. `boxes`\n * and `masks` mirror Ultralytics' bulk-array views.\n */\nexport class SegmentationResults implements Iterable<SegmentationResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly masks: Masks,\n        public readonly detections: readonly SegmentationResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<Speed> = NO_SPEED,\n    ) {}\n\n    /** Number of surviving instances. */\n    get length(): number {\n        return this.detections.length;\n    }\n\n    /** Index into the per-instance results. */\n    get(index: number): SegmentationResult | undefined {\n        return this.detections[index];\n    }\n\n    [Symbol.iterator](): Iterator<SegmentationResult> {\n        return this.detections[Symbol.iterator]();\n    }\n}\n"],"mappings":";AAgCA,IAAM,IAAkB;CAAE,MAAM;CAAG,YAAY;CAAG,WAAW;CAAG,aAAa;AAAE,GASlE,IAAb,MAAmB;CAQK;CACA;CACA;CACA;CAJpB,YACI,GACA,GACA,GACA,GACF;EADkB,AAHA,KAAA,OAAA,GACA,KAAA,MAAA,GACA,KAAA,OAAA,GACA,KAAA,YAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,IAAI;CACpB;CAGA,IAAI,QAAmC;EACnC,OAAO,CAAC,KAAK,QAAQ,CAAC;CAC1B;CAGA,IAAI,OAAqB;EACrB,IAAM,IAAM,IAAI,aAAa,KAAK,KAAK,MAAM;EAC7C,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAAK;GAClC,IAAM,IAAK,KAAK,KAAK,IAAI,IACnB,IAAK,KAAK,KAAK,IAAI,IAAI,IACvB,IAAK,KAAK,KAAK,IAAI,IAAI,IACvB,IAAK,KAAK,KAAK,IAAI,IAAI;GAI7B,AAHA,EAAI,IAAI,MAAM,IAAK,KAAM,GACzB,EAAI,IAAI,IAAI,MAAM,IAAK,KAAM,GAC7B,EAAI,IAAI,IAAI,KAAK,IAAK,GACtB,EAAI,IAAI,IAAI,KAAK,IAAK;EAC1B;EACA,OAAO;CACX;CAGA,IAAI,QAAsB;EACtB,IAAM,CAAC,GAAG,KAAK,KAAK,WACd,IAAM,IAAI,aAAa,KAAK,KAAK,MAAM;EAC7C,IAAI,KAAK,WAAW,KAAK,KAAK,KAAK,KAAK,GAAG,OAAO;EAClD,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAI7B,AAHA,EAAI,IAAI,KAAM,KAAK,KAAK,IAAI,KAAgB,GAC5C,EAAI,IAAI,IAAI,KAAM,KAAK,KAAK,IAAI,IAAI,KAAgB,GACpD,EAAI,IAAI,IAAI,KAAM,KAAK,KAAK,IAAI,IAAI,KAAgB,GACpD,EAAI,IAAI,IAAI,KAAM,KAAK,KAAK,IAAI,IAAI,KAAgB;EAExD,OAAO;CACX;CAGA,IAAI,QAAsB;EACtB,IAAM,IAAO,KAAK,MACZ,CAAC,GAAG,KAAK,KAAK;EACpB,IAAI,KAAK,WAAW,KAAK,KAAK,KAAK,KAAK,GAAG,OAAO;EAClD,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAI7B,AAHA,EAAK,IAAI,KAAM,EAAK,IAAI,KAAgB,GACxC,EAAK,IAAI,IAAI,KAAM,EAAK,IAAI,IAAI,KAAgB,GAChD,EAAK,IAAI,IAAI,KAAM,EAAK,IAAI,IAAI,KAAgB,GAChD,EAAK,IAAI,IAAI,KAAM,EAAK,IAAI,IAAI,KAAgB;EAEpD,OAAO;CACX;CAOA,IAAI,OAAqB;EACrB,IAAM,IAAM,IAAI,aAAa,KAAK,SAAS,CAAC;EAC5C,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAM7B,AALA,EAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAC3B,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAAI,IACnC,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAAI,IACnC,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAAI,IAAI,IACnC,EAAI,IAAI,IAAI,KAAK,KAAK,KAAK,IAC3B,EAAI,IAAI,IAAI,KAAK,KAAK,IAAI;EAE9B,OAAO;CACX;AACJ,GAaa,IAAb,MAAmB;CAEa;CAA5B,YAAY,GAAoC;EAApB,KAAA,OAAA;CAAqB;CAGjD,IAAI,SAAiB;EACjB,OAAO,KAAK,KAAK;CACrB;CAGA,IAAI,QAA2B;EAC3B,OAAO,CAAC,KAAK,MAAM;CACvB;CAGA,IAAI,OAAe;EACf,IAAI,KAAK,KAAK,WAAW,GAAG,OAAO;EACnC,IAAI,IAAO,GACP,IAAU,KAAK,KAAK;EACxB,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,KAAK,QAAQ,KAAK;GACvC,IAAM,IAAI,KAAK,KAAK;GACpB,AAAI,IAAI,MACJ,IAAO,GACP,IAAU;EAElB;EACA,OAAO;CACX;CAGA,IAAI,WAAmB;EAEnB,OADI,KAAK,KAAK,WAAW,IAAU,IAC5B,KAAK,KAAK,KAAK;CAC1B;CASA,IAAI,OAAmB;EACnB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC;CACxB;CAQA,IAAI,WAAyB;EACzB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC;CACxB;CAEA,yBAAiB,IAAI,IAAkB;CAavC,KAAa,GAAiB;EAC1B,IAAM,IAAM,KAAK,OAAO,IAAI,CAAC;EAC7B,IAAI,GAAK,OAAO;EAChB,IAAM,IAAW,KAAK,MAAM,CAAC;EAE7B,OADA,KAAK,OAAO,IAAI,GAAG,CAAQ,GACpB;CACX;CAoBA,MAAc,GAAiB;EAC3B,IAAM,IAAO,KAAK,IAAI,GAAG,KAAK,KAAK,MAAM,GACnC,IAAU,IAAI,WAAW,CAAI,GAC7B,IAAS,IAAI,aAAa,CAAI;EACpC,IAAI,MAAS,GAAG,OAAO;GAAE;GAAS;EAAO;EAEzC,EAAO,KAAK,SAAwB;EACpC,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,KAAK,QAAQ,KAAK;GACvC,IAAM,IAAQ,KAAK,KAAK;GACxB,IAAI,KAAU,EAAO,IAAO,IAAe;GAC3C,IAAI,IAAO,IAAO;GAClB,OAAO,IAAO,KAAM,EAAO,IAAO,KAAgB,IAG9C,AAFA,EAAO,KAAQ,EAAO,IAAO,IAC7B,EAAQ,KAAQ,EAAQ,IAAO,IAC/B;GAGJ,AADA,EAAO,KAAQ,GACf,EAAQ,KAAQ;EACpB;EACA,OAAO;GAAE;GAAS;EAAO;CAC7B;AACJ,GAQa,IAAb,MAAmB;CAOK;CAKA;CACA;CAPpB,YACI,GAKA,GACA,GACF;EADkB,AANA,KAAA,OAAA,GAKA,KAAA,OAAA,GACA,KAAA,YAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,KAAK;CACrB;CAGA,IAAI,QAA2B;EAC3B,OAAO,CAAC,KAAK,MAAM;CACvB;CAEA,CAAC,OAAO,YAIL;EACC,OAAO,KAAK,KAAK,OAAO,SAAS,CAAC;CACtC;AACJ,GAiBa,IAAb,MAAmE;CAE3C;CACA;CACA;CACA;CACA;CACA;CACA;CAPpB,YACI,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AANA,KAAA,QAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,WAAW;CAC3B;CAGA,IAAI,GAA4C;EAC5C,OAAO,KAAK,WAAW;CAC3B;CAEA,CAAC,OAAO,YAAuC;EAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC;CAC5C;AACJ,GAmBa,IAAb,MAAwE;CAEhD;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CARpB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AAPA,KAAA,QAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,kBAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,WAAW;CAC3B;CAGA,IAAI,GAA4C;EAC5C,OAAO,KAAK,WAAW;CAC3B;CAEA,CAAC,OAAO,YAAuC;EAC3C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC;CAC5C;AACJ,GAKa,IAAb,MAAmC;CAEX;CACA;CACA;CACA;CACA;CACA;CACA;CAPpB,YACI,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AANA,KAAA,QAAA,GACA,KAAA,SAAA,GACA,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,MAAc;EACd,OAAO,KAAK,MAAM;CACtB;CAGA,IAAI,OAAe;EACf,OAAO,KAAK,MAAM;CACtB;CAGA,IAAI,OAAe;EACf,OAAO,KAAK,MAAM,KAAK,QAAQ,SAAS,KAAK;CACjD;CAGA,IAAI,gBAA0E;EAC1E,OAAO,KAAK,OAAO;CACvB;AACJ,GAQa,IAAb,MAAyE;CAEjD;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CARpB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,IAAsC,MACtC,IAAyC,GAC3C;EADkB,AAPA,KAAA,QAAA,GACA,KAAA,QAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,YAAA,GACA,KAAA,OAAA,GACA,KAAA,QAAA;CACjB;CAGH,IAAI,SAAiB;EACjB,OAAO,KAAK,WAAW;CAC3B;CAGA,IAAI,GAA+C;EAC/C,OAAO,KAAK,WAAW;CAC3B;CAEA,CAAC,OAAO,YAA0C;EAC9C,OAAO,KAAK,WAAW,OAAO,SAAS,CAAC;CAC5C;AACJ"}

package/dist/vision/tasks/classifier.cjs

@@ -1,2 +1,2 @@
-const e=require("../core/timing.cjs"),t=require("../results.cjs"),n=require("../labels.cjs"),r=require("../core/graph.cjs"),i=require("../core/metadata.cjs"),a=require("../core/session.cjs"),o=require("../io/image.cjs"),s=require("../preprocess/image.cjs"),c=require("../preprocess/pipeline.cjs"),l=require("../postprocess/classification.cjs"),u=require("./base.cjs");var d=[.485,.456,.406],f=[.229,.224,.225],p=class p extends u.VisionTask{_labels;_names;_inputSize;_mean;_std;_applySoftmax;constructor(e,t,n,r,i,a,o){super(e),this._labels=t,this._names=n,this._inputSize=r,this._mean=i,this._std=a,this._applySoftmax=o}_pipelineCache=null;async warmup(e=1){let[t,n]=this._inputSize;for(let r=0;r<e;r++){let e=s.toFloat32Tensor(c.zeroTensorData(t,n),[1,3,n,t]);await this._session.run({[this._session.inputName]:e})}}get _pipeline(){if(this._pipelineCache===null){let[e,t]=this._inputSize;this._pipelineCache=new c.ResizePipeline(e,t,this._mean,this._std)}return this._pipelineCache}static async create(e,t={}){let o=await a.OrtSession.create(e,t),s=t.numClasses??r.classificationNumClasses(o.outputShape)??void 0,c=n.resolveLabels(t.labels??i.modelNames(o.metadata),{numClasses:s}),l={};for(let e=0;e<c.length;e++)l[e]=c[e];return new p(o,c,l,r.resolveInputSize({graphShape:o.inputShape,requested:t.inputSize,fallback:[224,224]}),t.mean??d,t.std??f,t.applySoftmax??!0)}get labels(){return this._labels}get names(){return this._names}get inputSize(){return this._inputSize}get numClasses(){return this._labels.length}async call(e,t={}){return this.predict(e,t)}async predict(n,r={}){let i=new e.SpeedTimer,a=typeof n==`string`?n:null,s=await o.loadImage(n);i.stage(`load`);let c=this._preprocess(s);i.stage(`preprocess`);let u=await this._session.run({[this._session.inputName]:c});this._pipeline.release(),i.stage(`inference`);let d=this._session.outputNames[0];if(d===void 0)throw Error(`Classifier model has no outputs.`);let f=u[d];if(f===void 0)throw Error(`Classifier model output ${d} missing from run() result.`);let p=this._postprocess(f.data),{indices:m,values:h}=l.topK(p,r.topK??null),g=[];for(let e=0;e<m.length;e++){let t=m[e],n=this._labels[t]??`class_${t}`;g.push({classId:t,className:n,probability:h[e],cls:t,name:n,conf:h[e]})}if(g.length===0)throw Error(`Classifier produced no probabilities (empty output).`);let _=g[0],v={classId:_.classId,className:_.className,confidence:_.probability,cls:_.classId,name:_.className,conf:_.probability,image:s,probabilities:g},y=[s.height,s.width],b=new t.Probs(p);return i.stage(`postprocess`),[new t.ClassificationResults(b,v,this._names,s,y,a,i.speed())]}_preprocess(e){let[t,n]=this._inputSize,{data:r}=this._pipeline.run(e);return s.toFloat32Tensor(r,[1,3,n,t])}_postprocess(e){return this._applySoftmax?l.softmax(e):new Float32Array(e)}};exports.Classifier=p;
+const e=require("../core/timing.cjs"),t=require("../results.cjs"),n=require("../labels.cjs"),r=require("../core/graph.cjs"),i=require("../core/metadata.cjs"),a=require("../core/session.cjs"),o=require("../normalization.cjs"),s=require("../io/image.cjs"),c=require("../preprocess/image.cjs"),l=require("../preprocess/pipeline.cjs"),u=require("../postprocess/classification.cjs"),d=require("./base.cjs");var f=class f extends d.VisionTask{_labels;_names;_inputSize;_mean;_std;_applySoftmax;_normalization;constructor(e,t,n,r,i,a,o,s){super(e),this._labels=t,this._names=n,this._inputSize=r,this._mean=i,this._std=a,this._applySoftmax=o,this._normalization=s}get appliesSoftmax(){return this._applySoftmax}get normalization(){return this._normalization}_pipelineCache=null;async warmup(e=1){let[t,n]=this._inputSize;for(let r=0;r<e;r++){let e=c.toFloat32Tensor(l.zeroTensorData(t,n),[1,3,n,t]);await this._session.run({[this._session.inputName]:e})}}get _pipeline(){if(this._pipelineCache===null){let[e,t]=this._inputSize;this._pipelineCache=new l.ResizePipeline(e,t,this._mean,this._std)}return this._pipelineCache}static async create(e,t={}){let s=await a.OrtSession.create(e,t),c=o.resolveNormalization(s.metadata,{normalization:t.normalization,mean:t.mean,std:t.std}),l=t.numClasses??r.classificationNumClasses(s.outputShape)??void 0,u=n.resolveLabels(t.labels??i.modelNames(s.metadata),{numClasses:l}),d={};for(let e=0;e<u.length;e++)d[e]=u[e];return new f(s,u,d,r.resolveInputSize({graphShape:s.inputShape,requested:t.inputSize,fallback:[224,224]}),c.mean,c.std,t.applySoftmax??!o.isUltralyticsClassifier(s.metadata),c.name)}get labels(){return this._labels}get names(){return this._names}get inputSize(){return this._inputSize}get numClasses(){return this._labels.length}async call(e,t={}){return this.predict(e,t)}async predict(n,r={}){let i=new e.SpeedTimer,a=typeof n==`string`?n:null,o=await s.loadImage(n);i.stage(`load`);let c=this._preprocess(o);i.stage(`preprocess`);let l=await this._session.run({[this._session.inputName]:c});this._pipeline.release(),i.stage(`inference`);let d=this._session.outputNames[0];if(d===void 0)throw Error(`Classifier model has no outputs.`);let f=l[d];if(f===void 0)throw Error(`Classifier model output ${d} missing from run() result.`);let p=this._postprocess(f.data),{indices:m,values:h}=u.topK(p,r.topK??null),g=[];for(let e=0;e<m.length;e++){let t=m[e],n=this._labels[t]??`class_${t}`;g.push({classId:t,className:n,probability:h[e],cls:t,name:n,conf:h[e]})}if(g.length===0)throw Error(`Classifier produced no probabilities (empty output).`);let _=g[0],v={classId:_.classId,className:_.className,confidence:_.probability,cls:_.classId,name:_.className,conf:_.probability,image:o,probabilities:g},y=[o.height,o.width],b=new t.Probs(p);return i.stage(`postprocess`),[new t.ClassificationResults(b,v,this._names,o,y,a,i.speed())]}_preprocess(e){let[t,n]=this._inputSize,{data:r}=this._pipeline.run(e);return c.toFloat32Tensor(r,[1,3,n,t])}_postprocess(e){return this._applySoftmax?u.softmax(e):new Float32Array(e)}};exports.Classifier=f;
 //# sourceMappingURL=classifier.cjs.map

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

@@ -1 +1 @@
-{"version":3,"file":"classifier.cjs","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { toFloat32Tensor } from \"../preprocess/image\";\nimport { ResizePipeline, zeroTensorData } from \"../preprocess/pipeline\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    private _pipelineCache: ResizePipeline | null = null;\n\n    /**\n     * Run the model once on a zero tensor, paying one-time costs up front.\n     *\n     * The first inference of a session is not representative: WebGPU compiles its\n     * shaders on it and the WASM backend faults in its arenas. Calling this while\n     * a loading spinner is still up moves that cost somewhere the user is already\n     * waiting — which matters most for a classifier running as the last step of\n     * an on-device analysis, where the delay lands right before the answer shows.\n     *\n     * @param runs How many warm-up inferences to run. One is enough for WASM;\n     *   WebGPU sometimes settles on the second.\n     */\n    async warmup(runs: number = 1): Promise<void> {\n        const [tw, th] = this._inputSize;\n        for (let i = 0; i < runs; i++) {\n            const tensor = toFloat32Tensor(zeroTensorData(tw, th), [1, 3, th, tw]);\n            await this._session.run({ [this._session.inputName]: tensor });\n        }\n    }\n\n    /**\n     * The fused preprocessing pipeline, built on first use.\n     *\n     * Lazily, because constructing it reserves the output buffer: a task built in\n     * an environment without a canvas implementation stays constructible, and only\n     * fails if it is actually asked to preprocess something.\n     */\n    private get _pipeline(): ResizePipeline {\n        if (this._pipelineCache === null) {\n            const [tw, th] = this._inputSize;\n            this._pipelineCache = new ResizePipeline(tw, th, this._mean, this._std);\n        }\n        return this._pipelineCache;\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        this._pipeline.release();\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const { data } = this._pipeline.run(image);\n        return toFloat32Tensor(data, [1, 3, th, tw]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":"gXAoBA,IAAM,EAAmD,CAAC,KAAO,KAAO,IAAK,EACvE,EAAkD,CAAC,KAAO,KAAO,IAAK,EAqE/D,EAAb,MAAa,UAAmB,EAAA,UAAW,CAGlB,QACA,OACA,WACA,MACA,KACA,cAPrB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EACF,CACE,MAAM,CAAO,EAPI,KAAA,QAAA,EACA,KAAA,OAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,KAAA,EACA,KAAA,cAAA,CAGrB,CAEA,eAAgD,KAchD,MAAM,OAAO,EAAe,EAAkB,CAC1C,GAAM,CAAC,EAAI,GAAM,KAAK,WACtB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAM,IAAK,CAC3B,IAAM,EAAS,EAAA,gBAAgB,EAAA,eAAe,EAAI,CAAE,EAAG,CAAC,EAAG,EAAG,EAAI,CAAE,CAAC,EACrE,MAAM,KAAK,SAAS,IAAI,EAAG,KAAK,SAAS,WAAY,CAAO,CAAC,CACjE,CACJ,CASA,IAAY,WAA4B,CACpC,GAAI,KAAK,iBAAmB,KAAM,CAC9B,GAAM,CAAC,EAAI,GAAM,KAAK,WACtB,KAAK,eAAiB,IAAI,EAAA,eAAe,EAAI,EAAI,KAAK,MAAO,KAAK,IAAI,CAC1E,CACA,OAAO,KAAK,cAChB,CAGA,aAAa,OAAO,EAAoB,EAA6B,CAAC,EAAwB,CAC1F,IAAM,EAAU,MAAM,EAAA,WAAW,OAAO,EAAO,CAAO,EAChD,EACF,EAAQ,YAAc,EAAA,yBAAyB,EAAQ,WAAW,GAAK,IAAA,GACrE,EAAS,EAAA,cAAc,EAAQ,QAAU,EAAA,WAAW,EAAQ,QAAQ,EAAG,CACzE,YACJ,CAAC,EACK,EAAgC,CAAC,EACvC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAO,OAAQ,IAC/B,EAAM,GAAK,EAAO,GAEtB,OAAO,IAAI,EACP,EACA,EACA,EACA,EAAA,iBAAiB,CACb,WAAY,EAAQ,WACpB,UAAW,EAAQ,UACnB,SAAU,CAAC,IAAK,GAAG,CACvB,CAAC,EACD,EAAQ,MAAQ,EAChB,EAAQ,KAAO,EACf,EAAQ,cAAgB,EAC5B,CACJ,CAGA,IAAI,QAA4B,CAC5B,OAAO,KAAK,OAChB,CAGA,IAAI,OAA0C,CAC1C,OAAO,KAAK,MAChB,CASA,IAAI,WAAuC,CACvC,OAAO,KAAK,UAChB,CAGA,IAAI,YAAqB,CACrB,OAAO,KAAK,QAAQ,MACxB,CAGA,MAAM,KACF,EACA,EAAoC,CAAC,EACL,CAChC,OAAO,KAAK,QAAQ,EAAO,CAAO,CACtC,CAGA,MAAM,QACF,EACA,EAAoC,CAAC,EACL,CAChC,IAAM,EAAQ,IAAI,EAAA,WACZ,EAAO,OAAO,GAAU,SAAW,EAAQ,KAC3C,EAAW,MAAM,EAAA,UAAU,CAAK,EACtC,EAAM,MAAM,MAAM,EAClB,IAAM,EAAS,KAAK,YAAY,CAAQ,EACxC,EAAM,MAAM,YAAY,EACxB,IAAM,EAAU,MAAM,KAAK,SAAS,IAAI,EAAG,KAAK,SAAS,WAAY,CAAO,CAAC,EAC7E,KAAK,UAAU,QAAQ,EACvB,EAAM,MAAM,WAAW,EACvB,IAAM,EAAkB,KAAK,SAAS,YAAY,GAClD,GAAI,IAAoB,IAAA,GACpB,MAAU,MAAM,kCAAkC,EAEtD,IAAM,EAAM,EAAQ,GACpB,GAAI,IAAQ,IAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C,EAEJ,IAAM,EAAY,KAAK,aAAa,EAAI,IAAoB,EAEtD,CAAE,UAAS,UAAW,EAAA,KAAK,EAAW,EAAQ,MAAQ,IAAI,EAC1D,EAAoC,CAAC,EAC3C,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,OAAQ,IAAK,CACrC,IAAM,EAAK,EAAQ,GACb,EAAY,KAAK,QAAQ,IAAO,SAAS,IAC/C,EAAc,KAAK,CACf,QAAS,EACT,YACA,YAAa,EAAO,GACpB,IAAK,EACL,KAAM,EACN,KAAM,EAAO,EACjB,CAAC,CACL,CACA,GAAI,EAAc,SAAW,EACzB,MAAU,MAAM,sDAAsD,EAG1E,IAAM,EAAM,EAAc,GACpB,EAA+B,CACjC,QAAS,EAAI,QACb,UAAW,EAAI,UACf,WAAY,EAAI,YAChB,IAAK,EAAI,QACT,KAAM,EAAI,UACV,KAAM,EAAI,YACV,MAAO,EACP,eACJ,EAEM,EAAkC,CAAC,EAAS,OAAQ,EAAS,KAAK,EAClE,EAAQ,IAAI,EAAA,MAAM,CAAS,EAEjC,OADA,EAAM,MAAM,aAAa,EAClB,CACH,IAAI,EAAA,sBACA,EACA,EACA,KAAK,OACL,EACA,EACA,EACA,EAAM,MAAM,CAChB,CACJ,CACJ,CAEA,YAAoB,EAA6B,CAC7C,GAAM,CAAC,EAAI,GAAM,KAAK,WAChB,CAAE,QAAS,KAAK,UAAU,IAAI,CAAK,EACzC,OAAO,EAAA,gBAAgB,EAAM,CAAC,EAAG,EAAG,EAAI,CAAE,CAAC,CAC/C,CAEA,aAAqB,EAAiC,CAClD,OAAO,KAAK,cAAgB,EAAA,QAAQ,CAAG,EAAI,IAAI,aAAa,CAAG,CACnE,CACJ"}
+{"version":3,"file":"classifier.cjs","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport {\n    type Normalization,\n    isUltralyticsClassifier,\n    resolveNormalization,\n} from \"../normalization\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { toFloat32Tensor } from \"../preprocess/image\";\nimport { ResizePipeline, zeroTensorData } from \"../preprocess/pipeline\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /**\n     * Which preprocessing this model expects — see {@link Normalization}.\n     *\n     * Defaults to `\"auto\"`, which reads the model's own export metadata and picks\n     * `\"ultralytics\"` (raw `[0, 1]`) for an Ultralytics classification head and\n     * `\"imagenet\"` for everything else.\n     */\n    readonly normalization?: Normalization;\n    /** Per-channel RGB mean, overriding the preset. Defaults to the preset's. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation, overriding the preset. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * Whether the model's output still needs a softmax.\n     *\n     * Left undefined (the default), this reads the model's metadata and answers\n     * `false` for an Ultralytics classification export, whose graph already ends\n     * in one — applying a second softmax to a probability vector keeps the\n     * ranking but flattens the confidences, so the top-1 stays right while every\n     * number attached to it is wrong. Detection covers that family; for any other\n     * model that already emits probabilities, pass `false` explicitly.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n        private readonly _normalization: string,\n    ) {\n        super(session);\n    }\n\n    /**\n     * Whether a softmax is applied to the model's output before ranking.\n     *\n     * Resolved once at construction. Worth reading when confidences look\n     * compressed: a second softmax over an already-normalized vector leaves the\n     * ordering intact and the numbers meaningless, which is invisible to any check\n     * that only looks at the predicted class.\n     */\n    get appliesSoftmax(): boolean {\n        return this._applySoftmax;\n    }\n\n    /**\n     * Which preprocessing this classifier applies to every image.\n     *\n     * One of the {@link Normalization} preset names, or `\"custom\"` when the caller\n     * supplied `mean`/`std` directly. Worth reading when a model underperforms:\n     * feeding a classifier a differently prepared tensor than it was trained on\n     * degrades it without throwing anything, so \"what does this assume\" is the\n     * first question.\n     */\n    get normalization(): string {\n        return this._normalization;\n    }\n\n    private _pipelineCache: ResizePipeline | null = null;\n\n    /**\n     * Run the model once on a zero tensor, paying one-time costs up front.\n     *\n     * The first inference of a session is not representative: WebGPU compiles its\n     * shaders on it and the WASM backend faults in its arenas. Calling this while\n     * a loading spinner is still up moves that cost somewhere the user is already\n     * waiting — which matters most for a classifier running as the last step of\n     * an on-device analysis, where the delay lands right before the answer shows.\n     *\n     * @param runs How many warm-up inferences to run. One is enough for WASM;\n     *   WebGPU sometimes settles on the second.\n     */\n    async warmup(runs: number = 1): Promise<void> {\n        const [tw, th] = this._inputSize;\n        for (let i = 0; i < runs; i++) {\n            const tensor = toFloat32Tensor(zeroTensorData(tw, th), [1, 3, th, tw]);\n            await this._session.run({ [this._session.inputName]: tensor });\n        }\n    }\n\n    /**\n     * The fused preprocessing pipeline, built on first use.\n     *\n     * Lazily, because constructing it reserves the output buffer: a task built in\n     * an environment without a canvas implementation stays constructible, and only\n     * fails if it is actually asked to preprocess something.\n     */\n    private get _pipeline(): ResizePipeline {\n        if (this._pipelineCache === null) {\n            const [tw, th] = this._inputSize;\n            this._pipelineCache = new ResizePipeline(tw, th, this._mean, this._std);\n        }\n        return this._pipelineCache;\n    }\n\n    /**\n     * Load the model, resolve labels, and settle the preprocessing.\n     *\n     * @param model The model source — a URL, or the bytes.\n     * @param options Labels, input size, normalization, and session options.\n     * @throws {RangeError} If `normalization` names an unknown preset, or names\n     *   one while `mean`/`std` are also given.\n     */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const normalization = resolveNormalization(session.metadata, {\n            normalization: options.normalization,\n            mean: options.mean,\n            std: options.std,\n        });\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            normalization.mean,\n            normalization.std,\n            options.applySoftmax ?? !isUltralyticsClassifier(session.metadata),\n            normalization.name,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        this._pipeline.release();\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const { data } = this._pipeline.run(image);\n        return toFloat32Tensor(data, [1, 3, th, tw]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":"kZAyGA,IAAa,EAAb,MAAa,UAAmB,EAAA,UAAW,CAGlB,QACA,OACA,WACA,MACA,KACA,cACA,eARrB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EACA,EACF,CACE,MAAM,CAAO,EARI,KAAA,QAAA,EACA,KAAA,OAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,KAAA,EACA,KAAA,cAAA,EACA,KAAA,eAAA,CAGrB,CAUA,IAAI,gBAA0B,CAC1B,OAAO,KAAK,aAChB,CAWA,IAAI,eAAwB,CACxB,OAAO,KAAK,cAChB,CAEA,eAAgD,KAchD,MAAM,OAAO,EAAe,EAAkB,CAC1C,GAAM,CAAC,EAAI,GAAM,KAAK,WACtB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAM,IAAK,CAC3B,IAAM,EAAS,EAAA,gBAAgB,EAAA,eAAe,EAAI,CAAE,EAAG,CAAC,EAAG,EAAG,EAAI,CAAE,CAAC,EACrE,MAAM,KAAK,SAAS,IAAI,EAAG,KAAK,SAAS,WAAY,CAAO,CAAC,CACjE,CACJ,CASA,IAAY,WAA4B,CACpC,GAAI,KAAK,iBAAmB,KAAM,CAC9B,GAAM,CAAC,EAAI,GAAM,KAAK,WACtB,KAAK,eAAiB,IAAI,EAAA,eAAe,EAAI,EAAI,KAAK,MAAO,KAAK,IAAI,CAC1E,CACA,OAAO,KAAK,cAChB,CAUA,aAAa,OAAO,EAAoB,EAA6B,CAAC,EAAwB,CAC1F,IAAM,EAAU,MAAM,EAAA,WAAW,OAAO,EAAO,CAAO,EAChD,EAAgB,EAAA,qBAAqB,EAAQ,SAAU,CACzD,cAAe,EAAQ,cACvB,KAAM,EAAQ,KACd,IAAK,EAAQ,GACjB,CAAC,EACK,EACF,EAAQ,YAAc,EAAA,yBAAyB,EAAQ,WAAW,GAAK,IAAA,GACrE,EAAS,EAAA,cAAc,EAAQ,QAAU,EAAA,WAAW,EAAQ,QAAQ,EAAG,CACzE,YACJ,CAAC,EACK,EAAgC,CAAC,EACvC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAO,OAAQ,IAC/B,EAAM,GAAK,EAAO,GAEtB,OAAO,IAAI,EACP,EACA,EACA,EACA,EAAA,iBAAiB,CACb,WAAY,EAAQ,WACpB,UAAW,EAAQ,UACnB,SAAU,CAAC,IAAK,GAAG,CACvB,CAAC,EACD,EAAc,KACd,EAAc,IACd,EAAQ,cAAgB,CAAC,EAAA,wBAAwB,EAAQ,QAAQ,EACjE,EAAc,IAClB,CACJ,CAGA,IAAI,QAA4B,CAC5B,OAAO,KAAK,OAChB,CAGA,IAAI,OAA0C,CAC1C,OAAO,KAAK,MAChB,CASA,IAAI,WAAuC,CACvC,OAAO,KAAK,UAChB,CAGA,IAAI,YAAqB,CACrB,OAAO,KAAK,QAAQ,MACxB,CAGA,MAAM,KACF,EACA,EAAoC,CAAC,EACL,CAChC,OAAO,KAAK,QAAQ,EAAO,CAAO,CACtC,CAGA,MAAM,QACF,EACA,EAAoC,CAAC,EACL,CAChC,IAAM,EAAQ,IAAI,EAAA,WACZ,EAAO,OAAO,GAAU,SAAW,EAAQ,KAC3C,EAAW,MAAM,EAAA,UAAU,CAAK,EACtC,EAAM,MAAM,MAAM,EAClB,IAAM,EAAS,KAAK,YAAY,CAAQ,EACxC,EAAM,MAAM,YAAY,EACxB,IAAM,EAAU,MAAM,KAAK,SAAS,IAAI,EAAG,KAAK,SAAS,WAAY,CAAO,CAAC,EAC7E,KAAK,UAAU,QAAQ,EACvB,EAAM,MAAM,WAAW,EACvB,IAAM,EAAkB,KAAK,SAAS,YAAY,GAClD,GAAI,IAAoB,IAAA,GACpB,MAAU,MAAM,kCAAkC,EAEtD,IAAM,EAAM,EAAQ,GACpB,GAAI,IAAQ,IAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C,EAEJ,IAAM,EAAY,KAAK,aAAa,EAAI,IAAoB,EAEtD,CAAE,UAAS,UAAW,EAAA,KAAK,EAAW,EAAQ,MAAQ,IAAI,EAC1D,EAAoC,CAAC,EAC3C,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,OAAQ,IAAK,CACrC,IAAM,EAAK,EAAQ,GACb,EAAY,KAAK,QAAQ,IAAO,SAAS,IAC/C,EAAc,KAAK,CACf,QAAS,EACT,YACA,YAAa,EAAO,GACpB,IAAK,EACL,KAAM,EACN,KAAM,EAAO,EACjB,CAAC,CACL,CACA,GAAI,EAAc,SAAW,EACzB,MAAU,MAAM,sDAAsD,EAG1E,IAAM,EAAM,EAAc,GACpB,EAA+B,CACjC,QAAS,EAAI,QACb,UAAW,EAAI,UACf,WAAY,EAAI,YAChB,IAAK,EAAI,QACT,KAAM,EAAI,UACV,KAAM,EAAI,YACV,MAAO,EACP,eACJ,EAEM,EAAkC,CAAC,EAAS,OAAQ,EAAS,KAAK,EAClE,EAAQ,IAAI,EAAA,MAAM,CAAS,EAEjC,OADA,EAAM,MAAM,aAAa,EAClB,CACH,IAAI,EAAA,sBACA,EACA,EACA,KAAK,OACL,EACA,EACA,EACA,EAAM,MAAM,CAChB,CACJ,CACJ,CAEA,YAAoB,EAA6B,CAC7C,GAAM,CAAC,EAAI,GAAM,KAAK,WAChB,CAAE,QAAS,KAAK,UAAU,IAAI,CAAK,EACzC,OAAO,EAAA,gBAAgB,EAAM,CAAC,EAAG,EAAG,EAAI,CAAE,CAAC,CAC/C,CAEA,aAAqB,EAAiC,CAClD,OAAO,KAAK,cAAgB,EAAA,QAAQ,CAAG,EAAI,IAAI,aAAa,CAAG,CACnE,CACJ"}

package/dist/vision/tasks/classifier.js

@@ -4,35 +4,35 @@ import { resolveLabels as r } from "../labels.js";
 import { classificationNumClasses as i, resolveInputSize as a } from "../core/graph.js";
 import { modelNames as o } from "../core/metadata.js";
 import { OrtSession as s } from "../core/session.js";
-import { loadImage as c } from "../io/image.js";
-import { toFloat32Tensor as l } from "../preprocess/image.js";
-import { ResizePipeline as u, zeroTensorData as d } from "../preprocess/pipeline.js";
-import { softmax as f, topK as p } from "../postprocess/classification.js";
-import { VisionTask as m } from "./base.js";
+import { isUltralyticsClassifier as c, resolveNormalization as l } from "../normalization.js";
+import { loadImage as u } from "../io/image.js";
+import { toFloat32Tensor as d } from "../preprocess/image.js";
+import { ResizePipeline as f, zeroTensorData as p } from "../preprocess/pipeline.js";
+import { softmax as m, topK as h } from "../postprocess/classification.js";
+import { VisionTask as g } from "./base.js";
 //#region src/vision/tasks/classifier.ts
-var h = [
-	.485,
-	.456,
-	.406
-], g = [
-	.229,
-	.224,
-	.225
-], _ = class _ extends m {
+var _ = class _ extends g {
 	_labels;
 	_names;
 	_inputSize;
 	_mean;
 	_std;
 	_applySoftmax;
-	constructor(e, t, n, r, i, a, o) {
-		super(e), this._labels = t, this._names = n, this._inputSize = r, this._mean = i, this._std = a, this._applySoftmax = o;
+	_normalization;
+	constructor(e, t, n, r, i, a, o, s) {
+		super(e), this._labels = t, this._names = n, this._inputSize = r, this._mean = i, this._std = a, this._applySoftmax = o, this._normalization = s;
+	}
+	get appliesSoftmax() {
+		return this._applySoftmax;
+	}
+	get normalization() {
+		return this._normalization;
 	}
 	_pipelineCache = null;
 	async warmup(e = 1) {
 		let [t, n] = this._inputSize;
 		for (let r = 0; r < e; r++) {
-			let e = l(d(t, n), [
+			let e = d(p(t, n), [
 				1,
 				3,
 				n,
@@ -44,18 +44,22 @@ var h = [
 	get _pipeline() {
 		if (this._pipelineCache === null) {
 			let [e, t] = this._inputSize;
-			this._pipelineCache = new u(e, t, this._mean, this._std);
+			this._pipelineCache = new f(e, t, this._mean, this._std);
 		}
 		return this._pipelineCache;
 	}
 	static async create(e, t = {}) {
-		let n = await s.create(e, t), c = t.numClasses ?? i(n.outputShape) ?? void 0, l = r(t.labels ?? o(n.metadata), { numClasses: c }), u = {};
-		for (let e = 0; e < l.length; e++) u[e] = l[e];
-		return new _(n, l, u, a({
+		let n = await s.create(e, t), u = l(n.metadata, {
+			normalization: t.normalization,
+			mean: t.mean,
+			std: t.std
+		}), d = t.numClasses ?? i(n.outputShape) ?? void 0, f = r(t.labels ?? o(n.metadata), { numClasses: d }), p = {};
+		for (let e = 0; e < f.length; e++) p[e] = f[e];
+		return new _(n, f, p, a({
 			graphShape: n.inputShape,
 			requested: t.inputSize,
 			fallback: [224, 224]
-		}), t.mean ?? h, t.std ?? g, t.applySoftmax ?? !0);
+		}), u.mean, u.std, t.applySoftmax ?? !c(n.metadata), u.name);
 	}
 	get labels() {
 		return this._labels;
@@ -73,19 +77,19 @@ var h = [
 		return this.predict(e, t);
 	}
 	async predict(r, i = {}) {
-		let a = new e(), o = typeof r == "string" ? r : null, s = await c(r);
+		let a = new e(), o = typeof r == "string" ? r : null, s = await u(r);
 		a.stage("load");
-		let l = this._preprocess(s);
+		let c = this._preprocess(s);
 		a.stage("preprocess");
-		let u = await this._session.run({ [this._session.inputName]: l });
+		let l = await this._session.run({ [this._session.inputName]: c });
 		this._pipeline.release(), a.stage("inference");
 		let d = this._session.outputNames[0];
 		if (d === void 0) throw Error("Classifier model has no outputs.");
-		let f = u[d];
+		let f = l[d];
 		if (f === void 0) throw Error(`Classifier model output ${d} missing from run() result.`);
-		let m = this._postprocess(f.data), { indices: h, values: g } = p(m, i.topK ?? null), _ = [];
-		for (let e = 0; e < h.length; e++) {
-			let t = h[e], n = this._labels[t] ?? `class_${t}`;
+		let p = this._postprocess(f.data), { indices: m, values: g } = h(p, i.topK ?? null), _ = [];
+		for (let e = 0; e < m.length; e++) {
+			let t = m[e], n = this._labels[t] ?? `class_${t}`;
 			_.push({
 				classId: t,
 				className: n,
@@ -105,12 +109,12 @@ var h = [
 			conf: v.probability,
 			image: s,
 			probabilities: _
-		}, b = [s.height, s.width], x = new n(m);
+		}, b = [s.height, s.width], x = new n(p);
 		return a.stage("postprocess"), [new t(x, y, this._names, s, b, o, a.speed())];
 	}
 	_preprocess(e) {
 		let [t, n] = this._inputSize, { data: r } = this._pipeline.run(e);
-		return l(r, [
+		return d(r, [
 			1,
 			3,
 			n,
@@ -118,7 +122,7 @@ var h = [
 		]);
 	}
 	_postprocess(e) {
-		return this._applySoftmax ? f(e) : new Float32Array(e);
+		return this._applySoftmax ? m(e) : new Float32Array(e);
 	}
 };
 //#endregion

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

@@ -1 +1 @@
-{"version":3,"file":"classifier.js","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { toFloat32Tensor } from \"../preprocess/image\";\nimport { ResizePipeline, zeroTensorData } from \"../preprocess/pipeline\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    private _pipelineCache: ResizePipeline | null = null;\n\n    /**\n     * Run the model once on a zero tensor, paying one-time costs up front.\n     *\n     * The first inference of a session is not representative: WebGPU compiles its\n     * shaders on it and the WASM backend faults in its arenas. Calling this while\n     * a loading spinner is still up moves that cost somewhere the user is already\n     * waiting — which matters most for a classifier running as the last step of\n     * an on-device analysis, where the delay lands right before the answer shows.\n     *\n     * @param runs How many warm-up inferences to run. One is enough for WASM;\n     *   WebGPU sometimes settles on the second.\n     */\n    async warmup(runs: number = 1): Promise<void> {\n        const [tw, th] = this._inputSize;\n        for (let i = 0; i < runs; i++) {\n            const tensor = toFloat32Tensor(zeroTensorData(tw, th), [1, 3, th, tw]);\n            await this._session.run({ [this._session.inputName]: tensor });\n        }\n    }\n\n    /**\n     * The fused preprocessing pipeline, built on first use.\n     *\n     * Lazily, because constructing it reserves the output buffer: a task built in\n     * an environment without a canvas implementation stays constructible, and only\n     * fails if it is actually asked to preprocess something.\n     */\n    private get _pipeline(): ResizePipeline {\n        if (this._pipelineCache === null) {\n            const [tw, th] = this._inputSize;\n            this._pipelineCache = new ResizePipeline(tw, th, this._mean, this._std);\n        }\n        return this._pipelineCache;\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        this._pipeline.release();\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const { data } = this._pipeline.run(image);\n        return toFloat32Tensor(data, [1, 3, th, tw]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":";;;;;;;;;;;;AAoBA,IAAM,IAAmD;CAAC;CAAO;CAAO;AAAK,GACvE,IAAkD;CAAC;CAAO;CAAO;AAAK,GAqE/D,IAAb,MAAa,UAAmB,EAAW;CAGlB;CACA;CACA;CACA;CACA;CACA;CAPrB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,GACF;EADmB,AAEjB,MAAM,CAAO,GAPI,KAAA,UAAA,GACA,KAAA,SAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,OAAA,GACA,KAAA,gBAAA;CAGrB;CAEA,iBAAgD;CAchD,MAAM,OAAO,IAAe,GAAkB;EAC1C,IAAM,CAAC,GAAI,KAAM,KAAK;EACtB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAM,KAAK;GAC3B,IAAM,IAAS,EAAgB,EAAe,GAAI,CAAE,GAAG;IAAC;IAAG;IAAG;IAAI;GAAE,CAAC;GACrE,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EACjE;CACJ;CASA,IAAY,YAA4B;EACpC,IAAI,KAAK,mBAAmB,MAAM;GAC9B,IAAM,CAAC,GAAI,KAAM,KAAK;GACtB,KAAK,iBAAiB,IAAI,EAAe,GAAI,GAAI,KAAK,OAAO,KAAK,IAAI;EAC1E;EACA,OAAO,KAAK;CAChB;CAGA,aAAa,OAAO,GAAoB,IAA6B,CAAC,GAAwB;EAC1F,IAAM,IAAU,MAAM,EAAW,OAAO,GAAO,CAAO,GAChD,IACF,EAAQ,cAAc,EAAyB,EAAQ,WAAW,KAAK,KAAA,GACrE,IAAS,EAAc,EAAQ,UAAU,EAAW,EAAQ,QAAQ,GAAG,EACzE,cACJ,CAAC,GACK,IAAgC,CAAC;EACvC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAO,QAAQ,KAC/B,EAAM,KAAK,EAAO;EAEtB,OAAO,IAAI,EACP,GACA,GACA,GACA,EAAiB;GACb,YAAY,EAAQ;GACpB,WAAW,EAAQ;GACnB,UAAU,CAAC,KAAK,GAAG;EACvB,CAAC,GACD,EAAQ,QAAQ,GAChB,EAAQ,OAAO,GACf,EAAQ,gBAAgB,EAC5B;CACJ;CAGA,IAAI,SAA4B;EAC5B,OAAO,KAAK;CAChB;CAGA,IAAI,QAA0C;EAC1C,OAAO,KAAK;CAChB;CASA,IAAI,YAAuC;EACvC,OAAO,KAAK;CAChB;CAGA,IAAI,aAAqB;EACrB,OAAO,KAAK,QAAQ;CACxB;CAGA,MAAM,KACF,GACA,IAAoC,CAAC,GACL;EAChC,OAAO,KAAK,QAAQ,GAAO,CAAO;CACtC;CAGA,MAAM,QACF,GACA,IAAoC,CAAC,GACL;EAChC,IAAM,IAAQ,IAAI,EAAW,GACvB,IAAO,OAAO,KAAU,WAAW,IAAQ,MAC3C,IAAW,MAAM,EAAU,CAAK;EACtC,EAAM,MAAM,MAAM;EAClB,IAAM,IAAS,KAAK,YAAY,CAAQ;EACxC,EAAM,MAAM,YAAY;EACxB,IAAM,IAAU,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EAE7E,AADA,KAAK,UAAU,QAAQ,GACvB,EAAM,MAAM,WAAW;EACvB,IAAM,IAAkB,KAAK,SAAS,YAAY;EAClD,IAAI,MAAoB,KAAA,GACpB,MAAU,MAAM,kCAAkC;EAEtD,IAAM,IAAM,EAAQ;EACpB,IAAI,MAAQ,KAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C;EAEJ,IAAM,IAAY,KAAK,aAAa,EAAI,IAAoB,GAEtD,EAAE,YAAS,cAAW,EAAK,GAAW,EAAQ,QAAQ,IAAI,GAC1D,IAAoC,CAAC;EAC3C,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,QAAQ,KAAK;GACrC,IAAM,IAAK,EAAQ,IACb,IAAY,KAAK,QAAQ,MAAO,SAAS;GAC/C,EAAc,KAAK;IACf,SAAS;IACT;IACA,aAAa,EAAO;IACpB,KAAK;IACL,MAAM;IACN,MAAM,EAAO;GACjB,CAAC;EACL;EACA,IAAI,EAAc,WAAW,GACzB,MAAU,MAAM,sDAAsD;EAG1E,IAAM,IAAM,EAAc,IACpB,IAA+B;GACjC,SAAS,EAAI;GACb,WAAW,EAAI;GACf,YAAY,EAAI;GAChB,KAAK,EAAI;GACT,MAAM,EAAI;GACV,MAAM,EAAI;GACV,OAAO;GACP;EACJ,GAEM,IAAkC,CAAC,EAAS,QAAQ,EAAS,KAAK,GAClE,IAAQ,IAAI,EAAM,CAAS;EAEjC,OADA,EAAM,MAAM,aAAa,GAClB,CACH,IAAI,EACA,GACA,GACA,KAAK,QACL,GACA,GACA,GACA,EAAM,MAAM,CAChB,CACJ;CACJ;CAEA,YAAoB,GAA6B;EAC7C,IAAM,CAAC,GAAI,KAAM,KAAK,YAChB,EAAE,YAAS,KAAK,UAAU,IAAI,CAAK;EACzC,OAAO,EAAgB,GAAM;GAAC;GAAG;GAAG;GAAI;EAAE,CAAC;CAC/C;CAEA,aAAqB,GAAiC;EAClD,OAAO,KAAK,gBAAgB,EAAQ,CAAG,IAAI,IAAI,aAAa,CAAG;CACnE;AACJ"}
+{"version":3,"file":"classifier.js","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport {\n    type Normalization,\n    isUltralyticsClassifier,\n    resolveNormalization,\n} from \"../normalization\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { toFloat32Tensor } from \"../preprocess/image\";\nimport { ResizePipeline, zeroTensorData } from \"../preprocess/pipeline\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /**\n     * Which preprocessing this model expects — see {@link Normalization}.\n     *\n     * Defaults to `\"auto\"`, which reads the model's own export metadata and picks\n     * `\"ultralytics\"` (raw `[0, 1]`) for an Ultralytics classification head and\n     * `\"imagenet\"` for everything else.\n     */\n    readonly normalization?: Normalization;\n    /** Per-channel RGB mean, overriding the preset. Defaults to the preset's. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation, overriding the preset. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * Whether the model's output still needs a softmax.\n     *\n     * Left undefined (the default), this reads the model's metadata and answers\n     * `false` for an Ultralytics classification export, whose graph already ends\n     * in one — applying a second softmax to a probability vector keeps the\n     * ranking but flattens the confidences, so the top-1 stays right while every\n     * number attached to it is wrong. Detection covers that family; for any other\n     * model that already emits probabilities, pass `false` explicitly.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n        private readonly _normalization: string,\n    ) {\n        super(session);\n    }\n\n    /**\n     * Whether a softmax is applied to the model's output before ranking.\n     *\n     * Resolved once at construction. Worth reading when confidences look\n     * compressed: a second softmax over an already-normalized vector leaves the\n     * ordering intact and the numbers meaningless, which is invisible to any check\n     * that only looks at the predicted class.\n     */\n    get appliesSoftmax(): boolean {\n        return this._applySoftmax;\n    }\n\n    /**\n     * Which preprocessing this classifier applies to every image.\n     *\n     * One of the {@link Normalization} preset names, or `\"custom\"` when the caller\n     * supplied `mean`/`std` directly. Worth reading when a model underperforms:\n     * feeding a classifier a differently prepared tensor than it was trained on\n     * degrades it without throwing anything, so \"what does this assume\" is the\n     * first question.\n     */\n    get normalization(): string {\n        return this._normalization;\n    }\n\n    private _pipelineCache: ResizePipeline | null = null;\n\n    /**\n     * Run the model once on a zero tensor, paying one-time costs up front.\n     *\n     * The first inference of a session is not representative: WebGPU compiles its\n     * shaders on it and the WASM backend faults in its arenas. Calling this while\n     * a loading spinner is still up moves that cost somewhere the user is already\n     * waiting — which matters most for a classifier running as the last step of\n     * an on-device analysis, where the delay lands right before the answer shows.\n     *\n     * @param runs How many warm-up inferences to run. One is enough for WASM;\n     *   WebGPU sometimes settles on the second.\n     */\n    async warmup(runs: number = 1): Promise<void> {\n        const [tw, th] = this._inputSize;\n        for (let i = 0; i < runs; i++) {\n            const tensor = toFloat32Tensor(zeroTensorData(tw, th), [1, 3, th, tw]);\n            await this._session.run({ [this._session.inputName]: tensor });\n        }\n    }\n\n    /**\n     * The fused preprocessing pipeline, built on first use.\n     *\n     * Lazily, because constructing it reserves the output buffer: a task built in\n     * an environment without a canvas implementation stays constructible, and only\n     * fails if it is actually asked to preprocess something.\n     */\n    private get _pipeline(): ResizePipeline {\n        if (this._pipelineCache === null) {\n            const [tw, th] = this._inputSize;\n            this._pipelineCache = new ResizePipeline(tw, th, this._mean, this._std);\n        }\n        return this._pipelineCache;\n    }\n\n    /**\n     * Load the model, resolve labels, and settle the preprocessing.\n     *\n     * @param model The model source — a URL, or the bytes.\n     * @param options Labels, input size, normalization, and session options.\n     * @throws {RangeError} If `normalization` names an unknown preset, or names\n     *   one while `mean`/`std` are also given.\n     */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const normalization = resolveNormalization(session.metadata, {\n            normalization: options.normalization,\n            mean: options.mean,\n            std: options.std,\n        });\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            normalization.mean,\n            normalization.std,\n            options.applySoftmax ?? !isUltralyticsClassifier(session.metadata),\n            normalization.name,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        this._pipeline.release();\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const { data } = this._pipeline.run(image);\n        return toFloat32Tensor(data, [1, 3, th, tw]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":";;;;;;;;;;;;;AAyGA,IAAa,IAAb,MAAa,UAAmB,EAAW;CAGlB;CACA;CACA;CACA;CACA;CACA;CACA;CARrB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,GACA,GACF;EADmB,AAEjB,MAAM,CAAO,GARI,KAAA,UAAA,GACA,KAAA,SAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,OAAA,GACA,KAAA,gBAAA,GACA,KAAA,iBAAA;CAGrB;CAUA,IAAI,iBAA0B;EAC1B,OAAO,KAAK;CAChB;CAWA,IAAI,gBAAwB;EACxB,OAAO,KAAK;CAChB;CAEA,iBAAgD;CAchD,MAAM,OAAO,IAAe,GAAkB;EAC1C,IAAM,CAAC,GAAI,KAAM,KAAK;EACtB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAM,KAAK;GAC3B,IAAM,IAAS,EAAgB,EAAe,GAAI,CAAE,GAAG;IAAC;IAAG;IAAG;IAAI;GAAE,CAAC;GACrE,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EACjE;CACJ;CASA,IAAY,YAA4B;EACpC,IAAI,KAAK,mBAAmB,MAAM;GAC9B,IAAM,CAAC,GAAI,KAAM,KAAK;GACtB,KAAK,iBAAiB,IAAI,EAAe,GAAI,GAAI,KAAK,OAAO,KAAK,IAAI;EAC1E;EACA,OAAO,KAAK;CAChB;CAUA,aAAa,OAAO,GAAoB,IAA6B,CAAC,GAAwB;EAC1F,IAAM,IAAU,MAAM,EAAW,OAAO,GAAO,CAAO,GAChD,IAAgB,EAAqB,EAAQ,UAAU;GACzD,eAAe,EAAQ;GACvB,MAAM,EAAQ;GACd,KAAK,EAAQ;EACjB,CAAC,GACK,IACF,EAAQ,cAAc,EAAyB,EAAQ,WAAW,KAAK,KAAA,GACrE,IAAS,EAAc,EAAQ,UAAU,EAAW,EAAQ,QAAQ,GAAG,EACzE,cACJ,CAAC,GACK,IAAgC,CAAC;EACvC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAO,QAAQ,KAC/B,EAAM,KAAK,EAAO;EAEtB,OAAO,IAAI,EACP,GACA,GACA,GACA,EAAiB;GACb,YAAY,EAAQ;GACpB,WAAW,EAAQ;GACnB,UAAU,CAAC,KAAK,GAAG;EACvB,CAAC,GACD,EAAc,MACd,EAAc,KACd,EAAQ,gBAAgB,CAAC,EAAwB,EAAQ,QAAQ,GACjE,EAAc,IAClB;CACJ;CAGA,IAAI,SAA4B;EAC5B,OAAO,KAAK;CAChB;CAGA,IAAI,QAA0C;EAC1C,OAAO,KAAK;CAChB;CASA,IAAI,YAAuC;EACvC,OAAO,KAAK;CAChB;CAGA,IAAI,aAAqB;EACrB,OAAO,KAAK,QAAQ;CACxB;CAGA,MAAM,KACF,GACA,IAAoC,CAAC,GACL;EAChC,OAAO,KAAK,QAAQ,GAAO,CAAO;CACtC;CAGA,MAAM,QACF,GACA,IAAoC,CAAC,GACL;EAChC,IAAM,IAAQ,IAAI,EAAW,GACvB,IAAO,OAAO,KAAU,WAAW,IAAQ,MAC3C,IAAW,MAAM,EAAU,CAAK;EACtC,EAAM,MAAM,MAAM;EAClB,IAAM,IAAS,KAAK,YAAY,CAAQ;EACxC,EAAM,MAAM,YAAY;EACxB,IAAM,IAAU,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EAE7E,AADA,KAAK,UAAU,QAAQ,GACvB,EAAM,MAAM,WAAW;EACvB,IAAM,IAAkB,KAAK,SAAS,YAAY;EAClD,IAAI,MAAoB,KAAA,GACpB,MAAU,MAAM,kCAAkC;EAEtD,IAAM,IAAM,EAAQ;EACpB,IAAI,MAAQ,KAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C;EAEJ,IAAM,IAAY,KAAK,aAAa,EAAI,IAAoB,GAEtD,EAAE,YAAS,cAAW,EAAK,GAAW,EAAQ,QAAQ,IAAI,GAC1D,IAAoC,CAAC;EAC3C,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,QAAQ,KAAK;GACrC,IAAM,IAAK,EAAQ,IACb,IAAY,KAAK,QAAQ,MAAO,SAAS;GAC/C,EAAc,KAAK;IACf,SAAS;IACT;IACA,aAAa,EAAO;IACpB,KAAK;IACL,MAAM;IACN,MAAM,EAAO;GACjB,CAAC;EACL;EACA,IAAI,EAAc,WAAW,GACzB,MAAU,MAAM,sDAAsD;EAG1E,IAAM,IAAM,EAAc,IACpB,IAA+B;GACjC,SAAS,EAAI;GACb,WAAW,EAAI;GACf,YAAY,EAAI;GAChB,KAAK,EAAI;GACT,MAAM,EAAI;GACV,MAAM,EAAI;GACV,OAAO;GACP;EACJ,GAEM,IAAkC,CAAC,EAAS,QAAQ,EAAS,KAAK,GAClE,IAAQ,IAAI,EAAM,CAAS;EAEjC,OADA,EAAM,MAAM,aAAa,GAClB,CACH,IAAI,EACA,GACA,GACA,KAAK,QACL,GACA,GACA,GACA,EAAM,MAAM,CAChB,CACJ;CACJ;CAEA,YAAoB,GAA6B;EAC7C,IAAM,CAAC,GAAI,KAAM,KAAK,YAChB,EAAE,YAAS,KAAK,UAAU,IAAI,CAAK;EACzC,OAAO,EAAgB,GAAM;GAAC;GAAG;GAAG;GAAI;EAAE,CAAC;CAC/C;CAEA,aAAqB,GAAiC;EAClD,OAAO,KAAK,gBAAgB,EAAQ,CAAG,IAAI,IAAI,aAAa,CAAG;CACnE;AACJ"}

package/dist/vision.cjs

@@ -1 +1 @@
-Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});const e=require("./vision/use-camera-stream.cjs"),t=require("./vision/core/exceptions.cjs"),n=require("./vision/types.cjs"),r=require("./vision/core/timing.cjs"),i=require("./vision/results.cjs"),a=require("./vision/labels.cjs"),o=require("./vision/core/graph.cjs"),s=require("./vision/core/metadata.cjs"),c=require("./vision/core/providers.cjs"),l=require("./vision/core/session.cjs"),u=require("./vision/io/image.cjs"),d=require("./vision/fusion.cjs"),f=require("./vision/preprocess/image.cjs"),p=require("./vision/preprocess/pipeline.cjs"),m=require("./vision/postprocess/classification.cjs"),h=require("./vision/postprocess/detection.cjs"),g=require("./vision/postprocess/segmentation.cjs"),_=require("./vision/tasks/base.cjs"),v=require("./vision/tasks/classifier.cjs"),y=require("./vision/tasks/detectClassify.cjs"),b=require("./vision/tasks/detector.cjs"),x=require("./vision/tasks/segmenter.cjs"),S=require("./vision/index.cjs"),C=require("./vision/luminance.cjs"),w=require("./vision/use-live-luminance.cjs");exports.BoundingBox=n.BoundingBox,exports.Boxes=i.Boxes,exports.COCO_CLASSES=a.COCO_CLASSES,exports.ClassificationResults=i.ClassificationResults,exports.Classifier=v.Classifier,exports.DEFAULT_PROVIDERS=c.DEFAULT_PROVIDERS,exports.DetectClassify=y.DetectClassify,exports.DetectClassifyResults=i.DetectClassifyResults,exports.DetectionResults=i.DetectionResults,exports.Detector=b.Detector,exports.FUSION_KIND_DETECT_CLASSIFY=d.FUSION_KIND_DETECT_CLASSIFY,exports.FusionError=t.FusionError,exports.INPUT_IMAGE=d.INPUT_IMAGE,exports.INPUT_PAD=d.INPUT_PAD,exports.INPUT_SCALE=d.INPUT_SCALE,exports.INPUT_SOURCE=d.INPUT_SOURCE,exports.ImageLoadError=t.ImageLoadError,exports.InferenceError=t.InferenceError,exports.LUMINANCE_SAMPLE_MAX_EDGE=C.LUMINANCE_SAMPLE_MAX_EDGE,exports.LabelMapError=t.LabelMapError,exports.LetterboxPipeline=p.LetterboxPipeline,exports.LowLuminanceError=C.LowLuminanceError,exports.METADATA_PREFIX=d.METADATA_PREFIX,exports.Mask=n.Mask,exports.Masks=i.Masks,exports.ModelLoadError=t.ModelLoadError,exports.NoDetectionsError=t.NoDetectionsError,exports.OUTPUT_BOXES=d.OUTPUT_BOXES,exports.OUTPUT_CLASSES=d.OUTPUT_CLASSES,exports.OUTPUT_NUM_DETECTIONS=d.OUTPUT_NUM_DETECTIONS,exports.OUTPUT_PROBS=d.OUTPUT_PROBS,exports.OUTPUT_SCORES=d.OUTPUT_SCORES,exports.OrtSession=l.OrtSession,exports.OrtVisionError=t.OrtVisionError,exports.Probs=i.Probs,exports.ProviderNotAvailableError=t.ProviderNotAvailableError,exports.RGBImage=n.RGBImage,exports.ResizePipeline=p.ResizePipeline,exports.SegmentationResults=i.SegmentationResults,exports.Segmenter=x.Segmenter,exports.SpeedTimer=r.SpeedTimer,exports.VERSION=S.VERSION,exports.VisionTask=_.VisionTask,exports.batchedNms=h.batchedNms,exports.classificationNumClasses=o.classificationNumClasses,exports.computeImageLuminance=C.computeImageLuminance,exports.declaredShapesFrom=o.declaredShapesFrom,exports.decodeYolo=h.decodeYolo,exports.decodeYoloAnchors=h.decodeYoloAnchors,exports.decodeYoloSeg=g.decodeYoloSeg,exports.defaultLabels=a.defaultLabels,exports.detectionNumClasses=o.detectionNumClasses,exports.fromCv2=f.fromCv2,exports.isLuminanceAcceptable=C.isLuminanceAcceptable,exports.letterbox=f.letterbox,exports.letterboxToTensorData=p.letterboxToTensorData,exports.loadImage=u.loadImage,exports.modelNames=s.modelNames,exports.nms=h.nms,exports.normalize=f.normalize,exports.parseNames=s.parseNames,exports.readFusionSpec=d.readFusionSpec,exports.readModelMetadata=s.readModelMetadata,exports.requireDetections=_.requireDetections,exports.resize=f.resize,exports.resizeToTensorData=p.resizeToTensorData,exports.resolveInputSize=o.resolveInputSize,exports.resolveLabels=a.resolveLabels,exports.resolveProviders=c.resolveProviders,exports.softmax=m.softmax,exports.spatialInputSize=o.spatialInputSize,exports.toCHW=f.toCHW,exports.toCv2=f.toCv2,exports.toFloat32=f.toFloat32,exports.toFloat32Tensor=f.toFloat32Tensor,exports.toTensor=f.toTensor,exports.topK=m.topK,exports.useCameraStream=e.useCameraStream,exports.useLiveLuminance=w.useLiveLuminance,exports.writePlanarFloat32=p.writePlanarFloat32,exports.zeroTensorData=p.zeroTensorData;
+Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});const e=require("./vision/use-camera-stream.cjs"),t=require("./vision/core/exceptions.cjs"),n=require("./vision/types.cjs"),r=require("./vision/core/timing.cjs"),i=require("./vision/results.cjs"),a=require("./vision/labels.cjs"),o=require("./vision/core/graph.cjs"),s=require("./vision/core/metadata.cjs"),c=require("./vision/core/providers.cjs"),l=require("./vision/core/session.cjs"),u=require("./vision/normalization.cjs"),d=require("./vision/io/image.cjs"),f=require("./vision/fusion.cjs"),p=require("./vision/preprocess/image.cjs"),m=require("./vision/preprocess/pipeline.cjs"),h=require("./vision/postprocess/classification.cjs"),g=require("./vision/postprocess/detection.cjs"),_=require("./vision/postprocess/segmentation.cjs"),v=require("./vision/tasks/base.cjs"),y=require("./vision/tasks/classifier.cjs"),b=require("./vision/tasks/detectClassify.cjs"),x=require("./vision/tasks/detector.cjs"),S=require("./vision/tasks/segmenter.cjs"),C=require("./vision/index.cjs"),w=require("./vision/luminance.cjs"),T=require("./vision/use-live-luminance.cjs");exports.BoundingBox=n.BoundingBox,exports.Boxes=i.Boxes,exports.COCO_CLASSES=a.COCO_CLASSES,exports.CUSTOM_NORMALIZATION=u.CUSTOM_NORMALIZATION,exports.ClassificationResults=i.ClassificationResults,exports.Classifier=y.Classifier,exports.DEFAULT_PROVIDERS=c.DEFAULT_PROVIDERS,exports.DetectClassify=b.DetectClassify,exports.DetectClassifyResults=i.DetectClassifyResults,exports.DetectionResults=i.DetectionResults,exports.Detector=x.Detector,exports.FUSION_KIND_DETECT_CLASSIFY=f.FUSION_KIND_DETECT_CLASSIFY,exports.FusionError=t.FusionError,exports.IDENTITY_MEAN=u.IDENTITY_MEAN,exports.IDENTITY_STD=u.IDENTITY_STD,exports.IMAGENET_MEAN=u.IMAGENET_MEAN,exports.IMAGENET_STD=u.IMAGENET_STD,exports.INPUT_IMAGE=f.INPUT_IMAGE,exports.INPUT_PAD=f.INPUT_PAD,exports.INPUT_SCALE=f.INPUT_SCALE,exports.INPUT_SOURCE=f.INPUT_SOURCE,exports.ImageLoadError=t.ImageLoadError,exports.InferenceError=t.InferenceError,exports.LUMINANCE_SAMPLE_MAX_EDGE=w.LUMINANCE_SAMPLE_MAX_EDGE,exports.LabelMapError=t.LabelMapError,exports.LetterboxPipeline=m.LetterboxPipeline,exports.LowLuminanceError=w.LowLuminanceError,exports.METADATA_PREFIX=f.METADATA_PREFIX,exports.Mask=n.Mask,exports.Masks=i.Masks,exports.ModelLoadError=t.ModelLoadError,exports.NoDetectionsError=t.NoDetectionsError,exports.OUTPUT_BOXES=f.OUTPUT_BOXES,exports.OUTPUT_CLASSES=f.OUTPUT_CLASSES,exports.OUTPUT_NUM_DETECTIONS=f.OUTPUT_NUM_DETECTIONS,exports.OUTPUT_PROBS=f.OUTPUT_PROBS,exports.OUTPUT_SCORES=f.OUTPUT_SCORES,exports.OrtSession=l.OrtSession,exports.OrtVisionError=t.OrtVisionError,exports.Probs=i.Probs,exports.ProviderNotAvailableError=t.ProviderNotAvailableError,exports.RGBImage=n.RGBImage,exports.ResizePipeline=m.ResizePipeline,exports.SegmentationResults=i.SegmentationResults,exports.Segmenter=S.Segmenter,exports.SpeedTimer=r.SpeedTimer,exports.VERSION=C.VERSION,exports.VisionTask=v.VisionTask,exports.batchedNms=g.batchedNms,exports.classificationNumClasses=o.classificationNumClasses,exports.computeImageLuminance=w.computeImageLuminance,exports.declaredShapesFrom=o.declaredShapesFrom,exports.decodeYolo=g.decodeYolo,exports.decodeYoloAnchors=g.decodeYoloAnchors,exports.decodeYoloSeg=_.decodeYoloSeg,exports.defaultLabels=a.defaultLabels,exports.detectProviders=c.detectProviders,exports.detectionNumClasses=o.detectionNumClasses,exports.fromCv2=p.fromCv2,exports.isLuminanceAcceptable=w.isLuminanceAcceptable,exports.isUltralyticsClassifier=u.isUltralyticsClassifier,exports.letterbox=p.letterbox,exports.letterboxToTensorData=m.letterboxToTensorData,exports.loadImage=d.loadImage,exports.modelNames=s.modelNames,exports.nms=g.nms,exports.normalize=p.normalize,exports.parseNames=s.parseNames,exports.readFusionSpec=f.readFusionSpec,exports.readModelMetadata=s.readModelMetadata,exports.requireDetections=v.requireDetections,exports.resize=p.resize,exports.resizeToTensorData=m.resizeToTensorData,exports.resolveInputSize=o.resolveInputSize,exports.resolveLabels=a.resolveLabels,exports.resolveNormalization=u.resolveNormalization,exports.resolveProviders=c.resolveProviders,exports.softmax=h.softmax,exports.spatialInputSize=o.spatialInputSize,exports.toCHW=p.toCHW,exports.toCv2=p.toCv2,exports.toFloat32=p.toFloat32,exports.toFloat32Tensor=p.toFloat32Tensor,exports.toTensor=p.toTensor,exports.topK=h.topK,exports.useCameraStream=e.useCameraStream,exports.useLiveLuminance=T.useLiveLuminance,exports.writePlanarFloat32=m.writePlanarFloat32,exports.zeroTensorData=m.zeroTensorData;