tempest-react-sdk 0.38.2 → 0.39.0

package/dist/vision/preprocess/pipeline.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"pipeline.cjs","names":[],"sources":["../../../src/vision/preprocess/pipeline.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Fused letterbox → CHW float32 pipeline with reusable buffers.\n *\n * The composable primitives in {@link ./image.js} each allocate and each walk\n * their input end to end, which is the right shape for a library but the wrong\n * shape for a video loop. Chaining them costs eleven full-buffer passes and six\n * large allocations per frame:\n *\n * `getImageData` → RGBA→RGB → RGB→RGBA → `putImageData` → `drawImage` →\n * `getImageData` → RGBA→RGB → fill → row copies → `toFloat32` → `toCHW`.\n *\n * This module collapses the second half of that into two: one `drawImage` that\n * resizes *and* positions the content inside the padded target in a single\n * accelerated operation, and one loop that reads the resulting RGBA and writes\n * planar float32 directly. The intermediate `RGBImage` at target size, the fill\n * loop, the row copies and the two 4.9 MB `Float32Array` allocations all go\n * away.\n *\n * The primitives stay exactly as they are — they are public API and they are\n * what makes a custom pipeline writable. This is the fast path the built-in\n * tasks take.\n */\n\nimport {\n    createCanvas,\n    get2DContext,\n    rgbToImageData,\n    type Canvas2D,\n    type Context2D,\n} from \"../core/canvas\";\nimport type { RGBImage } from \"../types\";\n\nconst INV_255 = 1 / 255;\n\n/** Geometry of a letterbox, plus the planar tensor data it produced. */\nexport interface FusedLetterboxResult {\n    /** CHW float32 in `[0, 1]`, length `3 * targetHeight * targetWidth`. */\n    readonly data: Float32Array;\n    /** Factor applied to the original image (`< 1` if downscaled). */\n    readonly scale: number;\n    /** Horizontal padding in pixels. */\n    readonly padLeft: number;\n    /** Vertical padding in pixels. */\n    readonly padTop: number;\n    /**\n     * Whether {@link data} is the pipeline's reusable buffer.\n     *\n     * `true` means the next {@link LetterboxPipeline.run} overwrites it, so a\n     * caller keeping the values past its own inference has to copy them.\n     */\n    readonly reused: boolean;\n}\n\n/**\n * Reusable letterbox → tensor pipeline for one target resolution.\n *\n * Holds a target canvas and an output buffer across calls, so a steady stream\n * of frames at the same size allocates nothing. Create one per task, not per\n * frame.\n */\nexport class LetterboxPipeline {\n    private readonly _targetWidth: number;\n    private readonly _targetHeight: number;\n    private readonly _fill: readonly [number, number, number];\n    private readonly _target: Canvas2D;\n    private readonly _targetContext: Context2D;\n    private readonly _buffer: Float32Array;\n    private _source: Canvas2D | null = null;\n    private _sourceContext: Context2D | null = null;\n    private _bufferInUse = false;\n\n    /**\n     * @param targetWidth Model input width in pixels.\n     * @param targetHeight Model input height in pixels.\n     * @param fill RGB padding colour; defaults to YOLO grey.\n     */\n    constructor(\n        targetWidth: number,\n        targetHeight: number,\n        fill: readonly [number, number, number] = [114, 114, 114],\n    ) {\n        if (targetWidth <= 0 || targetHeight <= 0) {\n            throw new Error(`Invalid letterbox target ${targetWidth}x${targetHeight}.`);\n        }\n        this._targetWidth = targetWidth;\n        this._targetHeight = targetHeight;\n        this._fill = fill;\n        this._target = createCanvas(targetWidth, targetHeight);\n        this._targetContext = get2DContext(this._target, { willReadFrequently: true });\n        this._targetContext.imageSmoothingEnabled = true;\n        this._targetContext.imageSmoothingQuality = \"high\";\n        this._buffer = new Float32Array(3 * targetHeight * targetWidth);\n    }\n\n    /** The `[width, height]` this pipeline letterboxes into. */\n    get targetSize(): readonly [number, number] {\n        return [this._targetWidth, this._targetHeight];\n    }\n\n    /**\n     * Letterbox an image and write it as planar float32.\n     *\n     * The returned buffer is reused between calls unless a previous result is\n     * still checked out — {@link release} marks it free again. A second `run`\n     * before the first is released allocates a fresh buffer rather than\n     * corrupting it, so concurrent `predict()` calls on one task stay correct at\n     * the cost of the allocation they were trying to avoid.\n     *\n     * @param image Source image in the SDK's canonical HWC RGB layout.\n     */\n    run(image: RGBImage): FusedLetterboxResult {\n        const targetWidth = this._targetWidth;\n        const targetHeight = this._targetHeight;\n        const scale = Math.min(targetWidth / image.width, targetHeight / image.height);\n        const scaledWidth = Math.round(image.width * scale);\n        const scaledHeight = Math.round(image.height * scale);\n        const padLeft = Math.floor((targetWidth - scaledWidth) / 2);\n        const padTop = Math.floor((targetHeight - scaledHeight) / 2);\n\n        const source = this._ensureSource(image.width, image.height);\n        source.putImageData(rgbToImageData(image), 0, 0);\n\n        const context = this._targetContext;\n        if (\n            padLeft > 0 ||\n            padTop > 0 ||\n            scaledWidth !== targetWidth ||\n            scaledHeight !== targetHeight\n        ) {\n            context.fillStyle = `rgb(${this._fill[0]},${this._fill[1]},${this._fill[2]})`;\n            context.fillRect(0, 0, targetWidth, targetHeight);\n        }\n        context.drawImage(\n            this._source as CanvasImageSource,\n            0,\n            0,\n            image.width,\n            image.height,\n            padLeft,\n            padTop,\n            scaledWidth,\n            scaledHeight,\n        );\n\n        const rgba = context.getImageData(0, 0, targetWidth, targetHeight).data;\n        const reused = !this._bufferInUse;\n        const data = reused ? this._buffer : new Float32Array(3 * targetHeight * targetWidth);\n        this._bufferInUse = true;\n\n        const plane = targetWidth * targetHeight;\n        for (let pixel = 0, offset = 0; pixel < plane; pixel++, offset += 4) {\n            data[pixel] = (rgba[offset] as number) * INV_255;\n            data[plane + pixel] = (rgba[offset + 1] as number) * INV_255;\n            data[2 * plane + pixel] = (rgba[offset + 2] as number) * INV_255;\n        }\n\n        return { data, scale, padLeft, padTop, reused };\n    }\n\n    /**\n     * Mark the reusable buffer free again.\n     *\n     * Call it once the tensor built from a {@link run} result has been handed to\n     * ONNX Runtime and the run has resolved — after that the values are inside\n     * the WASM heap and the buffer can be overwritten.\n     */\n    release(): void {\n        this._bufferInUse = false;\n    }\n\n    /**\n     * Grow the scratch source canvas to fit an image, reusing it when possible.\n     *\n     * A canvas is only reallocated when a frame arrives at a different size than\n     * the last one, which for a camera or video source is never after the first.\n     *\n     * @param width Source width in pixels.\n     * @param height Source height in pixels.\n     */\n    private _ensureSource(width: number, height: number): Context2D {\n        if (\n            this._source === null ||\n            this._source.width !== width ||\n            this._source.height !== height\n        ) {\n            this._source = createCanvas(width, height);\n            this._sourceContext = get2DContext(this._source);\n        }\n        return this._sourceContext as Context2D;\n    }\n}\n\n/**\n * Build a zero-filled CHW tensor payload for a warm-up run.\n *\n * @param width Model input width in pixels.\n * @param height Model input height in pixels.\n */\nexport function zeroTensorData(width: number, height: number): Float32Array {\n    return new Float32Array(3 * height * width);\n}\n\n/**\n * Letterbox an image into planar float32 without keeping any state.\n *\n * The allocation-free path is {@link LetterboxPipeline}; this is the one-shot\n * form, for a caller who wants the fused behaviour without owning a pipeline.\n *\n * @param image Source image in the SDK's canonical HWC RGB layout.\n * @param targetWidth Model input width in pixels.\n * @param targetHeight Model input height in pixels.\n * @param fill RGB padding colour; defaults to YOLO grey.\n */\nexport function letterboxToTensorData(\n    image: RGBImage,\n    targetWidth: number,\n    targetHeight: number,\n    fill: readonly [number, number, number] = [114, 114, 114],\n): FusedLetterboxResult {\n    return new LetterboxPipeline(targetWidth, targetHeight, fill).run(image);\n}\n"],"mappings":"sCAiCA,IAAM,EAAU,EAAI,IA4BP,EAAb,KAA+B,CAC3B,aACA,cACA,MACA,QACA,eACA,QACA,QAAmC,KACnC,eAA2C,KAC3C,aAAuB,GAOvB,YACI,EACA,EACA,EAA0C,CAAC,IAAK,IAAK,GAAG,EAC1D,CACE,GAAI,GAAe,GAAK,GAAgB,EACpC,MAAU,MAAM,4BAA4B,EAAY,GAAG,EAAa,EAAE,EAE9E,KAAK,aAAe,EACpB,KAAK,cAAgB,EACrB,KAAK,MAAQ,EACb,KAAK,QAAU,EAAA,aAAa,EAAa,CAAY,EACrD,KAAK,eAAiB,EAAA,aAAa,KAAK,QAAS,CAAE,mBAAoB,EAAK,CAAC,EAC7E,KAAK,eAAe,sBAAwB,GAC5C,KAAK,eAAe,sBAAwB,OAC5C,KAAK,QAAU,IAAI,aAAa,EAAI,EAAe,CAAW,CAClE,CAGA,IAAI,YAAwC,CACxC,MAAO,CAAC,KAAK,aAAc,KAAK,aAAa,CACjD,CAaA,IAAI,EAAuC,CACvC,IAAM,EAAc,KAAK,aACnB,EAAe,KAAK,cACpB,EAAQ,KAAK,IAAI,EAAc,EAAM,MAAO,EAAe,EAAM,MAAM,EACvE,EAAc,KAAK,MAAM,EAAM,MAAQ,CAAK,EAC5C,EAAe,KAAK,MAAM,EAAM,OAAS,CAAK,EAC9C,EAAU,KAAK,OAAO,EAAc,GAAe,CAAC,EACpD,EAAS,KAAK,OAAO,EAAe,GAAgB,CAAC,EAG3D,KADoB,cAAc,EAAM,MAAO,EAAM,MACrD,CAAA,CAAO,aAAa,EAAA,eAAe,CAAK,EAAG,EAAG,CAAC,EAE/C,IAAM,EAAU,KAAK,gBAEjB,EAAU,GACV,EAAS,GACT,IAAgB,GAChB,IAAiB,KAEjB,EAAQ,UAAY,OAAO,KAAK,MAAM,GAAG,GAAG,KAAK,MAAM,GAAG,GAAG,KAAK,MAAM,GAAG,GAC3E,EAAQ,SAAS,EAAG,EAAG,EAAa,CAAY,GAEpD,EAAQ,UACJ,KAAK,QACL,EACA,EACA,EAAM,MACN,EAAM,OACN,EACA,EACA,EACA,CACJ,EAEA,IAAM,EAAO,EAAQ,aAAa,EAAG,EAAG,EAAa,CAAY,CAAC,CAAC,KAC7D,EAAS,CAAC,KAAK,aACf,EAAO,EAAS,KAAK,QAAU,IAAI,aAAa,EAAI,EAAe,CAAW,EACpF,KAAK,aAAe,GAEpB,IAAM,EAAQ,EAAc,EAC5B,IAAK,IAAI,EAAQ,EAAG,EAAS,EAAG,EAAQ,EAAO,IAAS,GAAU,EAC9D,EAAK,GAAU,EAAK,GAAqB,EACzC,EAAK,EAAQ,GAAU,EAAK,EAAS,GAAgB,EACrD,EAAK,EAAI,EAAQ,GAAU,EAAK,EAAS,GAAgB,EAG7D,MAAO,CAAE,OAAM,QAAO,UAAS,SAAQ,QAAO,CAClD,CASA,SAAgB,CACZ,KAAK,aAAe,EACxB,CAWA,cAAsB,EAAe,EAA2B,CAS5D,OAPI,KAAK,UAAY,MACjB,KAAK,QAAQ,QAAU,GACvB,KAAK,QAAQ,SAAW,KAExB,KAAK,QAAU,EAAA,aAAa,EAAO,CAAM,EACzC,KAAK,eAAiB,EAAA,aAAa,KAAK,OAAO,GAE5C,KAAK,cAChB,CACJ,EAQA,SAAgB,EAAe,EAAe,EAA8B,CACxE,OAAO,IAAI,aAAa,EAAI,EAAS,CAAK,CAC9C,CAaA,SAAgB,EACZ,EACA,EACA,EACA,EAA0C,CAAC,IAAK,IAAK,GAAG,EACpC,CACpB,OAAO,IAAI,EAAkB,EAAa,EAAc,CAAI,CAAC,CAAC,IAAI,CAAK,CAC3E"}

package/dist/vision/preprocess/pipeline.js

@@ -0,0 +1,61 @@
+import { createCanvas as e, get2DContext as t, rgbToImageData as n } from "../core/canvas.js";
+//#region src/vision/preprocess/pipeline.ts
+var r = 1 / 255, i = class {
+	_targetWidth;
+	_targetHeight;
+	_fill;
+	_target;
+	_targetContext;
+	_buffer;
+	_source = null;
+	_sourceContext = null;
+	_bufferInUse = !1;
+	constructor(n, r, i = [
+		114,
+		114,
+		114
+	]) {
+		if (n <= 0 || r <= 0) throw Error(`Invalid letterbox target ${n}x${r}.`);
+		this._targetWidth = n, this._targetHeight = r, this._fill = i, this._target = e(n, r), this._targetContext = t(this._target, { willReadFrequently: !0 }), this._targetContext.imageSmoothingEnabled = !0, this._targetContext.imageSmoothingQuality = "high", this._buffer = new Float32Array(3 * r * n);
+	}
+	get targetSize() {
+		return [this._targetWidth, this._targetHeight];
+	}
+	run(e) {
+		let t = this._targetWidth, i = this._targetHeight, a = Math.min(t / e.width, i / e.height), o = Math.round(e.width * a), s = Math.round(e.height * a), c = Math.floor((t - o) / 2), l = Math.floor((i - s) / 2);
+		this._ensureSource(e.width, e.height).putImageData(n(e), 0, 0);
+		let u = this._targetContext;
+		(c > 0 || l > 0 || o !== t || s !== i) && (u.fillStyle = `rgb(${this._fill[0]},${this._fill[1]},${this._fill[2]})`, u.fillRect(0, 0, t, i)), u.drawImage(this._source, 0, 0, e.width, e.height, c, l, o, s);
+		let d = u.getImageData(0, 0, t, i).data, f = !this._bufferInUse, p = f ? this._buffer : new Float32Array(3 * i * t);
+		this._bufferInUse = !0;
+		let m = t * i;
+		for (let e = 0, t = 0; e < m; e++, t += 4) p[e] = d[t] * r, p[m + e] = d[t + 1] * r, p[2 * m + e] = d[t + 2] * r;
+		return {
+			data: p,
+			scale: a,
+			padLeft: c,
+			padTop: l,
+			reused: f
+		};
+	}
+	release() {
+		this._bufferInUse = !1;
+	}
+	_ensureSource(n, r) {
+		return (this._source === null || this._source.width !== n || this._source.height !== r) && (this._source = e(n, r), this._sourceContext = t(this._source)), this._sourceContext;
+	}
+};
+function a(e, t) {
+	return new Float32Array(3 * t * e);
+}
+function o(e, t, n, r = [
+	114,
+	114,
+	114
+]) {
+	return new i(t, n, r).run(e);
+}
+//#endregion
+export { i as LetterboxPipeline, o as letterboxToTensorData, a as zeroTensorData };
+
+//# sourceMappingURL=pipeline.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"pipeline.js","names":[],"sources":["../../../src/vision/preprocess/pipeline.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Fused letterbox → CHW float32 pipeline with reusable buffers.\n *\n * The composable primitives in {@link ./image.js} each allocate and each walk\n * their input end to end, which is the right shape for a library but the wrong\n * shape for a video loop. Chaining them costs eleven full-buffer passes and six\n * large allocations per frame:\n *\n * `getImageData` → RGBA→RGB → RGB→RGBA → `putImageData` → `drawImage` →\n * `getImageData` → RGBA→RGB → fill → row copies → `toFloat32` → `toCHW`.\n *\n * This module collapses the second half of that into two: one `drawImage` that\n * resizes *and* positions the content inside the padded target in a single\n * accelerated operation, and one loop that reads the resulting RGBA and writes\n * planar float32 directly. The intermediate `RGBImage` at target size, the fill\n * loop, the row copies and the two 4.9 MB `Float32Array` allocations all go\n * away.\n *\n * The primitives stay exactly as they are — they are public API and they are\n * what makes a custom pipeline writable. This is the fast path the built-in\n * tasks take.\n */\n\nimport {\n    createCanvas,\n    get2DContext,\n    rgbToImageData,\n    type Canvas2D,\n    type Context2D,\n} from \"../core/canvas\";\nimport type { RGBImage } from \"../types\";\n\nconst INV_255 = 1 / 255;\n\n/** Geometry of a letterbox, plus the planar tensor data it produced. */\nexport interface FusedLetterboxResult {\n    /** CHW float32 in `[0, 1]`, length `3 * targetHeight * targetWidth`. */\n    readonly data: Float32Array;\n    /** Factor applied to the original image (`< 1` if downscaled). */\n    readonly scale: number;\n    /** Horizontal padding in pixels. */\n    readonly padLeft: number;\n    /** Vertical padding in pixels. */\n    readonly padTop: number;\n    /**\n     * Whether {@link data} is the pipeline's reusable buffer.\n     *\n     * `true` means the next {@link LetterboxPipeline.run} overwrites it, so a\n     * caller keeping the values past its own inference has to copy them.\n     */\n    readonly reused: boolean;\n}\n\n/**\n * Reusable letterbox → tensor pipeline for one target resolution.\n *\n * Holds a target canvas and an output buffer across calls, so a steady stream\n * of frames at the same size allocates nothing. Create one per task, not per\n * frame.\n */\nexport class LetterboxPipeline {\n    private readonly _targetWidth: number;\n    private readonly _targetHeight: number;\n    private readonly _fill: readonly [number, number, number];\n    private readonly _target: Canvas2D;\n    private readonly _targetContext: Context2D;\n    private readonly _buffer: Float32Array;\n    private _source: Canvas2D | null = null;\n    private _sourceContext: Context2D | null = null;\n    private _bufferInUse = false;\n\n    /**\n     * @param targetWidth Model input width in pixels.\n     * @param targetHeight Model input height in pixels.\n     * @param fill RGB padding colour; defaults to YOLO grey.\n     */\n    constructor(\n        targetWidth: number,\n        targetHeight: number,\n        fill: readonly [number, number, number] = [114, 114, 114],\n    ) {\n        if (targetWidth <= 0 || targetHeight <= 0) {\n            throw new Error(`Invalid letterbox target ${targetWidth}x${targetHeight}.`);\n        }\n        this._targetWidth = targetWidth;\n        this._targetHeight = targetHeight;\n        this._fill = fill;\n        this._target = createCanvas(targetWidth, targetHeight);\n        this._targetContext = get2DContext(this._target, { willReadFrequently: true });\n        this._targetContext.imageSmoothingEnabled = true;\n        this._targetContext.imageSmoothingQuality = \"high\";\n        this._buffer = new Float32Array(3 * targetHeight * targetWidth);\n    }\n\n    /** The `[width, height]` this pipeline letterboxes into. */\n    get targetSize(): readonly [number, number] {\n        return [this._targetWidth, this._targetHeight];\n    }\n\n    /**\n     * Letterbox an image and write it as planar float32.\n     *\n     * The returned buffer is reused between calls unless a previous result is\n     * still checked out — {@link release} marks it free again. A second `run`\n     * before the first is released allocates a fresh buffer rather than\n     * corrupting it, so concurrent `predict()` calls on one task stay correct at\n     * the cost of the allocation they were trying to avoid.\n     *\n     * @param image Source image in the SDK's canonical HWC RGB layout.\n     */\n    run(image: RGBImage): FusedLetterboxResult {\n        const targetWidth = this._targetWidth;\n        const targetHeight = this._targetHeight;\n        const scale = Math.min(targetWidth / image.width, targetHeight / image.height);\n        const scaledWidth = Math.round(image.width * scale);\n        const scaledHeight = Math.round(image.height * scale);\n        const padLeft = Math.floor((targetWidth - scaledWidth) / 2);\n        const padTop = Math.floor((targetHeight - scaledHeight) / 2);\n\n        const source = this._ensureSource(image.width, image.height);\n        source.putImageData(rgbToImageData(image), 0, 0);\n\n        const context = this._targetContext;\n        if (\n            padLeft > 0 ||\n            padTop > 0 ||\n            scaledWidth !== targetWidth ||\n            scaledHeight !== targetHeight\n        ) {\n            context.fillStyle = `rgb(${this._fill[0]},${this._fill[1]},${this._fill[2]})`;\n            context.fillRect(0, 0, targetWidth, targetHeight);\n        }\n        context.drawImage(\n            this._source as CanvasImageSource,\n            0,\n            0,\n            image.width,\n            image.height,\n            padLeft,\n            padTop,\n            scaledWidth,\n            scaledHeight,\n        );\n\n        const rgba = context.getImageData(0, 0, targetWidth, targetHeight).data;\n        const reused = !this._bufferInUse;\n        const data = reused ? this._buffer : new Float32Array(3 * targetHeight * targetWidth);\n        this._bufferInUse = true;\n\n        const plane = targetWidth * targetHeight;\n        for (let pixel = 0, offset = 0; pixel < plane; pixel++, offset += 4) {\n            data[pixel] = (rgba[offset] as number) * INV_255;\n            data[plane + pixel] = (rgba[offset + 1] as number) * INV_255;\n            data[2 * plane + pixel] = (rgba[offset + 2] as number) * INV_255;\n        }\n\n        return { data, scale, padLeft, padTop, reused };\n    }\n\n    /**\n     * Mark the reusable buffer free again.\n     *\n     * Call it once the tensor built from a {@link run} result has been handed to\n     * ONNX Runtime and the run has resolved — after that the values are inside\n     * the WASM heap and the buffer can be overwritten.\n     */\n    release(): void {\n        this._bufferInUse = false;\n    }\n\n    /**\n     * Grow the scratch source canvas to fit an image, reusing it when possible.\n     *\n     * A canvas is only reallocated when a frame arrives at a different size than\n     * the last one, which for a camera or video source is never after the first.\n     *\n     * @param width Source width in pixels.\n     * @param height Source height in pixels.\n     */\n    private _ensureSource(width: number, height: number): Context2D {\n        if (\n            this._source === null ||\n            this._source.width !== width ||\n            this._source.height !== height\n        ) {\n            this._source = createCanvas(width, height);\n            this._sourceContext = get2DContext(this._source);\n        }\n        return this._sourceContext as Context2D;\n    }\n}\n\n/**\n * Build a zero-filled CHW tensor payload for a warm-up run.\n *\n * @param width Model input width in pixels.\n * @param height Model input height in pixels.\n */\nexport function zeroTensorData(width: number, height: number): Float32Array {\n    return new Float32Array(3 * height * width);\n}\n\n/**\n * Letterbox an image into planar float32 without keeping any state.\n *\n * The allocation-free path is {@link LetterboxPipeline}; this is the one-shot\n * form, for a caller who wants the fused behaviour without owning a pipeline.\n *\n * @param image Source image in the SDK's canonical HWC RGB layout.\n * @param targetWidth Model input width in pixels.\n * @param targetHeight Model input height in pixels.\n * @param fill RGB padding colour; defaults to YOLO grey.\n */\nexport function letterboxToTensorData(\n    image: RGBImage,\n    targetWidth: number,\n    targetHeight: number,\n    fill: readonly [number, number, number] = [114, 114, 114],\n): FusedLetterboxResult {\n    return new LetterboxPipeline(targetWidth, targetHeight, fill).run(image);\n}\n"],"mappings":";;AAiCA,IAAM,IAAU,IAAI,KA4BP,IAAb,MAA+B;CAC3B;CACA;CACA;CACA;CACA;CACA;CACA,UAAmC;CACnC,iBAA2C;CAC3C,eAAuB;CAOvB,YACI,GACA,GACA,IAA0C;EAAC;EAAK;EAAK;CAAG,GAC1D;EACE,IAAI,KAAe,KAAK,KAAgB,GACpC,MAAU,MAAM,4BAA4B,EAAY,GAAG,EAAa,EAAE;EAS9E,AAPA,KAAK,eAAe,GACpB,KAAK,gBAAgB,GACrB,KAAK,QAAQ,GACb,KAAK,UAAU,EAAa,GAAa,CAAY,GACrD,KAAK,iBAAiB,EAAa,KAAK,SAAS,EAAE,oBAAoB,GAAK,CAAC,GAC7E,KAAK,eAAe,wBAAwB,IAC5C,KAAK,eAAe,wBAAwB,QAC5C,KAAK,UAAU,IAAI,aAAa,IAAI,IAAe,CAAW;CAClE;CAGA,IAAI,aAAwC;EACxC,OAAO,CAAC,KAAK,cAAc,KAAK,aAAa;CACjD;CAaA,IAAI,GAAuC;EACvC,IAAM,IAAc,KAAK,cACnB,IAAe,KAAK,eACpB,IAAQ,KAAK,IAAI,IAAc,EAAM,OAAO,IAAe,EAAM,MAAM,GACvE,IAAc,KAAK,MAAM,EAAM,QAAQ,CAAK,GAC5C,IAAe,KAAK,MAAM,EAAM,SAAS,CAAK,GAC9C,IAAU,KAAK,OAAO,IAAc,KAAe,CAAC,GACpD,IAAS,KAAK,OAAO,IAAe,KAAgB,CAAC;EAG3D,KADoB,cAAc,EAAM,OAAO,EAAM,MACrD,CAAA,CAAO,aAAa,EAAe,CAAK,GAAG,GAAG,CAAC;EAE/C,IAAM,IAAU,KAAK;EAUrB,CARI,IAAU,KACV,IAAS,KACT,MAAgB,KAChB,MAAiB,OAEjB,EAAQ,YAAY,OAAO,KAAK,MAAM,GAAG,GAAG,KAAK,MAAM,GAAG,GAAG,KAAK,MAAM,GAAG,IAC3E,EAAQ,SAAS,GAAG,GAAG,GAAa,CAAY,IAEpD,EAAQ,UACJ,KAAK,SACL,GACA,GACA,EAAM,OACN,EAAM,QACN,GACA,GACA,GACA,CACJ;EAEA,IAAM,IAAO,EAAQ,aAAa,GAAG,GAAG,GAAa,CAAY,CAAC,CAAC,MAC7D,IAAS,CAAC,KAAK,cACf,IAAO,IAAS,KAAK,UAAU,IAAI,aAAa,IAAI,IAAe,CAAW;EACpF,KAAK,eAAe;EAEpB,IAAM,IAAQ,IAAc;EAC5B,KAAK,IAAI,IAAQ,GAAG,IAAS,GAAG,IAAQ,GAAO,KAAS,KAAU,GAG9D,AAFA,EAAK,KAAU,EAAK,KAAqB,GACzC,EAAK,IAAQ,KAAU,EAAK,IAAS,KAAgB,GACrD,EAAK,IAAI,IAAQ,KAAU,EAAK,IAAS,KAAgB;EAG7D,OAAO;GAAE;GAAM;GAAO;GAAS;GAAQ;EAAO;CAClD;CASA,UAAgB;EACZ,KAAK,eAAe;CACxB;CAWA,cAAsB,GAAe,GAA2B;EAS5D,QAPI,KAAK,YAAY,QACjB,KAAK,QAAQ,UAAU,KACvB,KAAK,QAAQ,WAAW,OAExB,KAAK,UAAU,EAAa,GAAO,CAAM,GACzC,KAAK,iBAAiB,EAAa,KAAK,OAAO,IAE5C,KAAK;CAChB;AACJ;AAQA,SAAgB,EAAe,GAAe,GAA8B;CACxE,OAAO,IAAI,aAAa,IAAI,IAAS,CAAK;AAC9C;AAaA,SAAgB,EACZ,GACA,GACA,GACA,IAA0C;CAAC;CAAK;CAAK;AAAG,GACpC;CACpB,OAAO,IAAI,EAAkB,GAAa,GAAc,CAAI,CAAC,CAAC,IAAI,CAAK;AAC3E"}

package/dist/vision/results.cjs

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

package/dist/vision/results.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"results.cjs","names":[],"sources":["../../src/vision/results.ts"],"sourcesContent":["/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n * - `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/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._topK(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._topK(5).values;\n    }\n\n    private _topK(k: number): { indices: Int32Array; values: Float32Array } {\n        const n = Math.min(k, this.data.length);\n        const order: number[] = [];\n        for (let i = 0; i < this.data.length; i++) order.push(i);\n        order.sort((a, b) => (this.data[b] as number) - (this.data[a] as number));\n        const indices = new Int32Array(n);\n        const values = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            indices[i] = order[i] as number;\n            values[i] = this.data[order[i] as number] as number;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<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":"AA+BA,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,EAOa,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,CAGA,IAAI,MAAmB,CACnB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC,OACzB,CAGA,IAAI,UAAyB,CACzB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC,MACzB,CAEA,MAAc,EAA0D,CACpE,IAAM,EAAI,KAAK,IAAI,EAAG,KAAK,KAAK,MAAM,EAChC,EAAkB,CAAC,EACzB,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,KAAK,OAAQ,IAAK,EAAM,KAAK,CAAC,EACvD,EAAM,MAAM,EAAG,IAAO,KAAK,KAAK,GAAiB,KAAK,KAAK,EAAa,EACxE,IAAM,EAAU,IAAI,WAAW,CAAC,EAC1B,EAAS,IAAI,aAAa,CAAC,EACjC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IACnB,EAAQ,GAAK,EAAM,GACnB,EAAO,GAAK,KAAK,KAAK,EAAM,IAEhC,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,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/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._topK(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._topK(5).values;\n    }\n\n    private _topK(k: number): { indices: Int32Array; values: Float32Array } {\n        const n = Math.min(k, this.data.length);\n        const order: number[] = [];\n        for (let i = 0; i < this.data.length; i++) order.push(i);\n        order.sort((a, b) => (this.data[b] as number) - (this.data[a] as number));\n        const indices = new Int32Array(n);\n        const values = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            indices[i] = order[i] as number;\n            values[i] = this.data[order[i] as number] as number;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<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,EAOa,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,CAGA,IAAI,MAAmB,CACnB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC,OACzB,CAGA,IAAI,UAAyB,CACzB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC,MACzB,CAEA,MAAc,EAA0D,CACpE,IAAM,EAAI,KAAK,IAAI,EAAG,KAAK,KAAK,MAAM,EAChC,EAAkB,CAAC,EACzB,IAAK,IAAI,EAAI,EAAG,EAAI,KAAK,KAAK,OAAQ,IAAK,EAAM,KAAK,CAAC,EACvD,EAAM,MAAM,EAAG,IAAO,KAAK,KAAK,GAAiB,KAAK,KAAK,EAAa,EACxE,IAAM,EAAU,IAAI,WAAW,CAAC,EAC1B,EAAS,IAAI,aAAa,CAAC,EACjC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IACnB,EAAQ,GAAK,EAAM,GACnB,EAAO,GAAK,KAAK,KAAK,EAAM,IAEhC,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

@@ -120,6 +120,27 @@ var e = {
 		return this.detections[Symbol.iterator]();
 	}
 }, a = class {
+	boxes;
+	detections;
+	names;
+	classifierNames;
+	origImg;
+	origShape;
+	path;
+	speed;
+	constructor(t, n, r, i, a, o, s = null, c = e) {
+		this.boxes = t, this.detections = n, this.names = r, this.classifierNames = i, this.origImg = a, this.origShape = o, this.path = s, this.speed = c;
+	}
+	get length() {
+		return this.detections.length;
+	}
+	get(e) {
+		return this.detections[e];
+	}
+	[Symbol.iterator]() {
+		return this.detections[Symbol.iterator]();
+	}
+}, o = class {
 	probs;
 	result;
 	names;
@@ -142,7 +163,7 @@ var e = {
 	get probabilities() {
 		return this.result.probabilities;
 	}
-}, o = class {
+}, s = class {
 	boxes;
 	masks;
 	detections;
@@ -165,6 +186,6 @@ var e = {
 	}
 };
 //#endregion
-export { t as Boxes, a as ClassificationResults, i as DetectionResults, r as Masks, n as Probs, o as SegmentationResults };
+export { t as Boxes, o as ClassificationResults, a as DetectClassifyResults, i as DetectionResults, r as Masks, n as Probs, s as SegmentationResults };
 
 //# sourceMappingURL=results.js.map

package/dist/vision/results.js.map

@@ -1 +1 @@
-{"version":3,"file":"results.js","names":[],"sources":["../../src/vision/results.ts"],"sourcesContent":["/**\n * Per-image result envelopes — Ultralytics-style `Results` for the SDK.\n *\n * Each `predict()` call returns a 1-element array of these envelopes,\n * mirroring `YOLO(\"img.jpg\")`. Each envelope holds:\n *\n * - A bulk-array view of the predictions (`Boxes`, `Probs`, `Masks`) with\n *   the exact attribute names Ultralytics uses (`xyxy`, `xywh`, `xyxyn`,\n *   `xywhn`, `cls`, `conf`, `data`, `top1`, `top5`).\n * - Per-instance dataclasses (`DetectionResult`, `SegmentationResult`,\n *   `ClassProbability`) for callers who prefer the OO interface.\n * - `names`: `Record<number, string>` matching Ultralytics' `model.names`.\n * - `origImg` / `origShape` / `path`: provenance for the original input.\n * - `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/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._topK(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._topK(5).values;\n    }\n\n    private _topK(k: number): { indices: Int32Array; values: Float32Array } {\n        const n = Math.min(k, this.data.length);\n        const order: number[] = [];\n        for (let i = 0; i < this.data.length; i++) order.push(i);\n        order.sort((a, b) => (this.data[b] as number) - (this.data[a] as number));\n        const indices = new Int32Array(n);\n        const values = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            indices[i] = order[i] as number;\n            values[i] = this.data[order[i] as number] as number;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<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":";AA+BA,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,GAOa,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;CAGA,IAAI,OAAmB;EACnB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC;CACzB;CAGA,IAAI,WAAyB;EACzB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC;CACzB;CAEA,MAAc,GAA0D;EACpE,IAAM,IAAI,KAAK,IAAI,GAAG,KAAK,KAAK,MAAM,GAChC,IAAkB,CAAC;EACzB,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,KAAK,QAAQ,KAAK,EAAM,KAAK,CAAC;EACvD,EAAM,MAAM,GAAG,MAAO,KAAK,KAAK,KAAiB,KAAK,KAAK,EAAa;EACxE,IAAM,IAAU,IAAI,WAAW,CAAC,GAC1B,IAAS,IAAI,aAAa,CAAC;EACjC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAEnB,AADA,EAAQ,KAAK,EAAM,IACnB,EAAO,KAAK,KAAK,KAAK,EAAM;EAEhC,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,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/**\n * Top-k classification probabilities for a single image.\n *\n * Mirrors Ultralytics' `Probs` interface.\n */\nexport class Probs {\n    /** @param data `[numClasses]` per-class probabilities, indexed by class id. */\n    constructor(public readonly data: Float32Array) {}\n\n    /** Number of classes. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[numClasses]` shape of the underlying vector. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    /** Index of the most probable class. */\n    get top1(): number {\n        if (this.data.length === 0) return 0;\n        let best = 0;\n        let bestVal = this.data[0] as number;\n        for (let i = 1; i < this.data.length; i++) {\n            const v = this.data[i] as number;\n            if (v > bestVal) {\n                best = i;\n                bestVal = v;\n            }\n        }\n        return best;\n    }\n\n    /** Probability of the top-1 class. */\n    get top1conf(): number {\n        if (this.data.length === 0) return 0;\n        return this.data[this.top1] as number;\n    }\n\n    /** Indices of the top-5 most probable classes, descending. */\n    get top5(): Int32Array {\n        return this._topK(5).indices;\n    }\n\n    /** Probabilities of the top-5 classes, descending. */\n    get top5conf(): Float32Array {\n        return this._topK(5).values;\n    }\n\n    private _topK(k: number): { indices: Int32Array; values: Float32Array } {\n        const n = Math.min(k, this.data.length);\n        const order: number[] = [];\n        for (let i = 0; i < this.data.length; i++) order.push(i);\n        order.sort((a, b) => (this.data[b] as number) - (this.data[a] as number));\n        const indices = new Int32Array(n);\n        const values = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            indices[i] = order[i] as number;\n            values[i] = this.data[order[i] as number] as number;\n        }\n        return { indices, values };\n    }\n}\n\n/**\n * Per-instance binary masks for a single image.\n *\n * Each mask is cropped to its instance's bounding box. To paint masks onto\n * a full-image canvas, use `xyxy[i]` as the top-left target.\n */\nexport class Masks {\n    /**\n     * @param data Per-instance binary masks (`Mask` objects from `types.ts`).\n     * @param xyxy Flat `[N, 4]` of bounding-box coordinates in original pixels.\n     * @param origShape `[height, width]` of the original image.\n     */\n    constructor(\n        public readonly data: ReadonlyArray<{\n            readonly data: Uint8Array;\n            readonly width: number;\n            readonly height: number;\n        }>,\n        public readonly xyxy: Float32Array,\n        public readonly origShape: readonly [number, number],\n    ) {}\n\n    /** Number of instance masks. */\n    get length(): number {\n        return this.data.length;\n    }\n\n    /** `[N]` shape of the masks collection. */\n    get shape(): readonly [number] {\n        return [this.length];\n    }\n\n    [Symbol.iterator](): Iterator<{\n        readonly data: Uint8Array;\n        readonly width: number;\n        readonly height: number;\n    }> {\n        return this.data[Symbol.iterator]();\n    }\n}\n\n/**\n * Per-image detection envelope (Ultralytics-style `Results`).\n *\n * Iterating yields per-instance {@link DetectionResult} entries, so legacy\n * code that did `for (const d of detector.predict(img))` only needs an\n * extra `[0]` to bridge:\n *\n * ```typescript\n * for (const d of (await detector.predict(img))[0]) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n *\n * For numpy-style bulk access, use the `boxes` collection.\n */\nexport class DetectionResults implements Iterable<DetectionResult> {\n    constructor(\n        public readonly boxes: Boxes,\n        public readonly detections: readonly DetectionResult[],\n        public readonly names: Readonly<Record<number, string>>,\n        public readonly origImg: RGBImage,\n        public readonly origShape: readonly [number, number],\n        public readonly path: string | null = null,\n        public readonly speed: Readonly<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,GAOa,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;CAGA,IAAI,OAAmB;EACnB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC;CACzB;CAGA,IAAI,WAAyB;EACzB,OAAO,KAAK,MAAM,CAAC,CAAC,CAAC;CACzB;CAEA,MAAc,GAA0D;EACpE,IAAM,IAAI,KAAK,IAAI,GAAG,KAAK,KAAK,MAAM,GAChC,IAAkB,CAAC;EACzB,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,KAAK,QAAQ,KAAK,EAAM,KAAK,CAAC;EACvD,EAAM,MAAM,GAAG,MAAO,KAAK,KAAK,KAAiB,KAAK,KAAK,EAAa;EACxE,IAAM,IAAU,IAAI,WAAW,CAAC,GAC1B,IAAS,IAAI,aAAa,CAAC;EACjC,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAEnB,AADA,EAAQ,KAAK,EAAM,IACnB,EAAO,KAAK,KAAK,KAAK,EAAM;EAEhC,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/base.cjs

@@ -1,2 +1,2 @@
-var e=class{_session;constructor(e){this._session=e}get session(){return this._session}};exports.VisionTask=e;
+const e=require("../core/exceptions.cjs");var t=class{_session;constructor(e){this._session=e}get session(){return this._session}};function n(e){return e.toFixed(6).replace(/0+$/,``).replace(/\.$/,``)}function r(t,r){if(!(!r.raiseOnEmpty||t>0))throw new e.NoDetectionsError(`No detections${r.path?` in ${r.path}`:``}${r.classes===void 0?``:` among classes [${[...r.classes].sort((e,t)=>e-t).join(`, `)}]`}: nothing cleared confThreshold=${n(r.confThreshold)}.`)}exports.VisionTask=t,exports.requireDetections=r;
 //# sourceMappingURL=base.cjs.map

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

@@ -1 +1 @@
-{"version":3,"file":"base.cjs","names":[],"sources":["../../../src/vision/tasks/base.ts"],"sourcesContent":["/**\n * Common foundation for task-oriented vision SDK objects.\n *\n * The base only owns the {@link OrtSession} — label resolution lives in each\n * subclass because how `numClasses` is read from the model differs per task.\n */\n\nimport type { OrtSession } from \"../core/session\";\n\nexport abstract class VisionTask {\n    protected constructor(protected readonly _session: OrtSession) {}\n\n    /** The underlying {@link OrtSession} used to run inference. */\n    get session(): OrtSession {\n        return this._session;\n    }\n}\n"],"mappings":"AASA,IAAsB,EAAtB,KAAiC,CACY,SAAzC,YAAsB,EAAyC,CAAtB,KAAA,SAAA,CAAuB,CAGhE,IAAI,SAAsB,CACtB,OAAO,KAAK,QAChB,CACJ"}
+{"version":3,"file":"base.cjs","names":[],"sources":["../../../src/vision/tasks/base.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Common foundation for task-oriented vision SDK objects.\n *\n * The base only owns the {@link OrtSession} — label resolution lives in each\n * subclass because how `numClasses` is read from the model differs per task.\n */\n\nimport { NoDetectionsError } from \"../core/exceptions\";\nimport type { OrtSession } from \"../core/session\";\n\nexport abstract class VisionTask {\n    protected constructor(protected readonly _session: OrtSession) {}\n\n    /** The underlying {@link OrtSession} used to run inference. */\n    get session(): OrtSession {\n        return this._session;\n    }\n}\n\n/**\n * Render a confidence threshold the way the Python SDK renders it.\n *\n * JavaScript and Python disagree on how a number becomes text. A whole\n * threshold is `1` here and `1.0` there; JavaScript holds off on exponent\n * notation until `1e-7` while Python switches at `1e-5`. A fused pipeline is\n * built once and runs under both runtimes from the same file, so a message that\n * quotes the threshold has to quote it identically — otherwise the two SDKs\n * describe the same run with two different numbers.\n *\n * Six decimals with the trailing zeros trimmed covers every threshold a caller\n * can meaningfully set and agrees byte for byte with `_format_threshold` in the\n * Python SDK's `tasks/base.py`. The pairing is fixed by a shared table in both\n * test suites, so a change on one side that is not mirrored on the other fails.\n *\n * @param value The threshold to render.\n * @returns The threshold as text, without trailing zeros or a trailing dot.\n */\nfunction formatThreshold(value: number): string {\n    return value.toFixed(6).replace(/0+$/, \"\").replace(/\\.$/, \"\");\n}\n\n/**\n * Turn an empty result into an error, when the caller asked for that.\n *\n * Shared by every task that can come back with nothing — {@link Detector},\n * {@link Segmenter} and {@link DetectClassify} — so the three agree on when\n * they throw and on what the message says. The message names the two settings\n * that decide the outcome, because \"no detections\" on its own leaves the reader\n * unable to tell a blank image from a threshold set too high.\n *\n * @param count How many detections survived every filter.\n * @param options The flag for this call, the threshold actually applied (after\n *   any per-call override), the class allowlist if one narrowed the search, and\n *   the source path when the input was one.\n * @throws {@link NoDetectionsError} when the flag is set and `count` is zero.\n */\nexport function requireDetections(\n    count: number,\n    options: {\n        readonly raiseOnEmpty: boolean;\n        readonly confThreshold: number;\n        readonly classes: readonly number[] | undefined;\n        readonly path: string | null;\n    },\n): void {\n    if (!options.raiseOnEmpty || count > 0) return;\n    const where = options.path ? ` in ${options.path}` : \"\";\n    const narrowed =\n        options.classes === undefined\n            ? \"\"\n            : ` among classes [${[...options.classes].sort((a, b) => a - b).join(\", \")}]`;\n    throw new NoDetectionsError(\n        `No detections${where}${narrowed}: nothing cleared confThreshold=${formatThreshold(options.confThreshold)}.`,\n    );\n}\n"],"mappings":"0CAWA,IAAsB,EAAtB,KAAiC,CACY,SAAzC,YAAsB,EAAyC,CAAtB,KAAA,SAAA,CAAuB,CAGhE,IAAI,SAAsB,CACtB,OAAO,KAAK,QAChB,CACJ,EAoBA,SAAS,EAAgB,EAAuB,CAC5C,OAAO,EAAM,QAAQ,CAAC,CAAC,CAAC,QAAQ,MAAO,EAAE,CAAC,CAAC,QAAQ,MAAO,EAAE,CAChE,CAiBA,SAAgB,EACZ,EACA,EAMI,CACA,MAAC,EAAQ,cAAgB,EAAQ,GAMrC,MAAM,IAAI,EAAA,kBACN,gBANU,EAAQ,KAAO,OAAO,EAAQ,OAAS,KAEjD,EAAQ,UAAY,IAAA,GACd,GACA,mBAAmB,CAAC,GAAG,EAAQ,OAAO,CAAC,CAAC,MAAM,EAAG,IAAM,EAAI,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,GAE9C,kCAAkC,EAAgB,EAAQ,aAAa,EAAE,EAC9G,CACJ"}

package/dist/vision/tasks/base.js

@@ -1,5 +1,6 @@
+import { NoDetectionsError as e } from "../core/exceptions.js";
 //#region src/vision/tasks/base.ts
-var e = class {
+var t = class {
 	_session;
 	constructor(e) {
 		this._session = e;
@@ -8,7 +9,13 @@ var e = class {
 		return this._session;
 	}
 };
+function n(e) {
+	return e.toFixed(6).replace(/0+$/, "").replace(/\.$/, "");
+}
+function r(t, r) {
+	if (!(!r.raiseOnEmpty || t > 0)) throw new e(`No detections${r.path ? ` in ${r.path}` : ""}${r.classes === void 0 ? "" : ` among classes [${[...r.classes].sort((e, t) => e - t).join(", ")}]`}: nothing cleared confThreshold=${n(r.confThreshold)}.`);
+}
 //#endregion
-export { e as VisionTask };
+export { t as VisionTask, r as requireDetections };
 
 //# sourceMappingURL=base.js.map

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

@@ -1 +1 @@
-{"version":3,"file":"base.js","names":[],"sources":["../../../src/vision/tasks/base.ts"],"sourcesContent":["/**\n * Common foundation for task-oriented vision SDK objects.\n *\n * The base only owns the {@link OrtSession} — label resolution lives in each\n * subclass because how `numClasses` is read from the model differs per task.\n */\n\nimport type { OrtSession } from \"../core/session\";\n\nexport abstract class VisionTask {\n    protected constructor(protected readonly _session: OrtSession) {}\n\n    /** The underlying {@link OrtSession} used to run inference. */\n    get session(): OrtSession {\n        return this._session;\n    }\n}\n"],"mappings":";AASA,IAAsB,IAAtB,MAAiC;CACY;CAAzC,YAAsB,GAAyC;EAAtB,KAAA,WAAA;CAAuB;CAGhE,IAAI,UAAsB;EACtB,OAAO,KAAK;CAChB;AACJ"}
+{"version":3,"file":"base.js","names":[],"sources":["../../../src/vision/tasks/base.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Common foundation for task-oriented vision SDK objects.\n *\n * The base only owns the {@link OrtSession} — label resolution lives in each\n * subclass because how `numClasses` is read from the model differs per task.\n */\n\nimport { NoDetectionsError } from \"../core/exceptions\";\nimport type { OrtSession } from \"../core/session\";\n\nexport abstract class VisionTask {\n    protected constructor(protected readonly _session: OrtSession) {}\n\n    /** The underlying {@link OrtSession} used to run inference. */\n    get session(): OrtSession {\n        return this._session;\n    }\n}\n\n/**\n * Render a confidence threshold the way the Python SDK renders it.\n *\n * JavaScript and Python disagree on how a number becomes text. A whole\n * threshold is `1` here and `1.0` there; JavaScript holds off on exponent\n * notation until `1e-7` while Python switches at `1e-5`. A fused pipeline is\n * built once and runs under both runtimes from the same file, so a message that\n * quotes the threshold has to quote it identically — otherwise the two SDKs\n * describe the same run with two different numbers.\n *\n * Six decimals with the trailing zeros trimmed covers every threshold a caller\n * can meaningfully set and agrees byte for byte with `_format_threshold` in the\n * Python SDK's `tasks/base.py`. The pairing is fixed by a shared table in both\n * test suites, so a change on one side that is not mirrored on the other fails.\n *\n * @param value The threshold to render.\n * @returns The threshold as text, without trailing zeros or a trailing dot.\n */\nfunction formatThreshold(value: number): string {\n    return value.toFixed(6).replace(/0+$/, \"\").replace(/\\.$/, \"\");\n}\n\n/**\n * Turn an empty result into an error, when the caller asked for that.\n *\n * Shared by every task that can come back with nothing — {@link Detector},\n * {@link Segmenter} and {@link DetectClassify} — so the three agree on when\n * they throw and on what the message says. The message names the two settings\n * that decide the outcome, because \"no detections\" on its own leaves the reader\n * unable to tell a blank image from a threshold set too high.\n *\n * @param count How many detections survived every filter.\n * @param options The flag for this call, the threshold actually applied (after\n *   any per-call override), the class allowlist if one narrowed the search, and\n *   the source path when the input was one.\n * @throws {@link NoDetectionsError} when the flag is set and `count` is zero.\n */\nexport function requireDetections(\n    count: number,\n    options: {\n        readonly raiseOnEmpty: boolean;\n        readonly confThreshold: number;\n        readonly classes: readonly number[] | undefined;\n        readonly path: string | null;\n    },\n): void {\n    if (!options.raiseOnEmpty || count > 0) return;\n    const where = options.path ? ` in ${options.path}` : \"\";\n    const narrowed =\n        options.classes === undefined\n            ? \"\"\n            : ` among classes [${[...options.classes].sort((a, b) => a - b).join(\", \")}]`;\n    throw new NoDetectionsError(\n        `No detections${where}${narrowed}: nothing cleared confThreshold=${formatThreshold(options.confThreshold)}.`,\n    );\n}\n"],"mappings":";;AAWA,IAAsB,IAAtB,MAAiC;CACY;CAAzC,YAAsB,GAAyC;EAAtB,KAAA,WAAA;CAAuB;CAGhE,IAAI,UAAsB;EACtB,OAAO,KAAK;CAChB;AACJ;AAoBA,SAAS,EAAgB,GAAuB;CAC5C,OAAO,EAAM,QAAQ,CAAC,CAAC,CAAC,QAAQ,OAAO,EAAE,CAAC,CAAC,QAAQ,OAAO,EAAE;AAChE;AAiBA,SAAgB,EACZ,GACA,GAMI;CACA,OAAC,EAAQ,gBAAgB,IAAQ,IAMrC,MAAM,IAAI,EACN,gBANU,EAAQ,OAAO,OAAO,EAAQ,SAAS,KAEjD,EAAQ,YAAY,KAAA,IACd,KACA,mBAAmB,CAAC,GAAG,EAAQ,OAAO,CAAC,CAAC,MAAM,GAAG,MAAM,IAAI,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,GAE9C,kCAAkC,EAAgB,EAAQ,aAAa,EAAE,EAC9G;AACJ"}

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

@@ -1 +1 @@
-{"version":3,"file":"classifier.cjs","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { 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 { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\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    /** 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        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 resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":"wUAkBA,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,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,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,EAAU,EAAA,OAAO,EAAO,EAAI,CAAE,EAGpC,OAAO,EAAA,gBADK,EAAA,MADO,EAAA,UAAU,EAAS,KAAK,MAAO,KAAK,IACrC,EAAY,EAAQ,MAAO,EAAQ,OAAQ,CACtC,EAAK,CAAC,EAAG,EAAG,EAAQ,OAAQ,EAAQ,KAAK,CAAC,CACrE,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 { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\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    /** 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        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 resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":"wUAmBA,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,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,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,EAAU,EAAA,OAAO,EAAO,EAAI,CAAE,EAGpC,OAAO,EAAA,gBADK,EAAA,MADO,EAAA,UAAU,EAAS,KAAK,MAAO,KAAK,IACrC,EAAY,EAAQ,MAAO,EAAQ,OAAQ,CACtC,EAAK,CAAC,EAAG,EAAG,EAAQ,OAAQ,EAAQ,KAAK,CAAC,CACrE,CAEA,aAAqB,EAAiC,CAClD,OAAO,KAAK,cAAgB,EAAA,QAAQ,CAAG,EAAI,IAAI,aAAa,CAAG,CACnE,CACJ"}

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

@@ -1 +1 @@
-{"version":3,"file":"classifier.js","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { 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 { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\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    /** 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        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 resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":";;;;;;;;;;;AAkBA,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;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;EAC7E,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,IAAU,EAAO,GAAO,GAAI,CAAE;EAGpC,OAAO,EADK,EADO,EAAU,GAAS,KAAK,OAAO,KAAK,IACrC,GAAY,EAAQ,OAAO,EAAQ,QAAQ,CACtC,GAAK;GAAC;GAAG;GAAG,EAAQ;GAAQ,EAAQ;EAAK,CAAC;CACrE;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 { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\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    /** 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        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 resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":";;;;;;;;;;;AAmBA,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;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;EAC7E,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,IAAU,EAAO,GAAO,GAAI,CAAE;EAGpC,OAAO,EADK,EADO,EAAU,GAAS,KAAK,OAAO,KAAK,IACrC,GAAY,EAAQ,OAAO,EAAQ,QAAQ,CACtC,GAAK;GAAC;GAAG;GAAG,EAAQ;GAAQ,EAAQ;EAAK,CAAC;CACrE;CAEA,aAAqB,GAAiC;EAClD,OAAO,KAAK,gBAAgB,EAAQ,CAAG,IAAI,IAAI,aAAa,CAAG;CACnE;AACJ"}

package/dist/vision/tasks/detectClassify.cjs

@@ -0,0 +1,2 @@
+const e=require("../core/exceptions.cjs"),t=require("../types.cjs"),n=require("../core/timing.cjs"),r=require("../results.cjs"),i=require("../labels.cjs"),a=require("../core/session.cjs"),o=require("../io/image.cjs"),s=require("../fusion.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{_spec;_labels;_names;_classifierLabels;_classifierNames;_raiseOnEmpty;constructor(e,t,n,r,i,a,o){super(e),this._spec=t,this._labels=n,this._names=r,this._classifierLabels=i,this._classifierNames=a,this._raiseOnEmpty=o}_pipelineCache=null;async warmup(e=1){let[t,n]=this._spec.inputSize;for(let r=0;r<e;r++){let e={[s.INPUT_IMAGE]:c.toFloat32Tensor(l.zeroTensorData(t,n),[1,3,n,t])};this._spec.needsSourceImage&&(e[s.INPUT_SOURCE]=c.toFloat32Tensor(l.zeroTensorData(t,n),[1,3,n,t]),e[s.INPUT_SCALE]=c.toFloat32Tensor(new Float32Array([1]),[1]),e[s.INPUT_PAD]=c.toFloat32Tensor(new Float32Array([0,0]),[2])),await this._session.run(e)}}get _pipeline(){if(this._pipelineCache===null){let[e,t]=this._spec.inputSize;this._pipelineCache=new l.LetterboxPipeline(e,t)}return this._pipelineCache}static async create(t,n={}){let r=await a.OrtSession.create(t,n),o=s.readFusionSpec(r.metadata);if(o===null)throw new e.FusionError(`This model carries no fused-pipeline metadata, so DetectClassify cannot tell how to drive it. Build one with ort_vision_sdk.compose.fuse_detect_classify, or load a plain model with Detector/Classifier instead.`);let c=i.resolveLabels(n.labels??o.detectorNames??`coco`),l=i.resolveLabels(n.classifierLabels??o.classifierNames,{numClasses:p(r)??void 0});return new f(r,o,c,m(c),l,m(l),n.raiseOnEmpty??!1)}get spec(){return this._spec}get inputSize(){return this._spec.inputSize}get labels(){return this._labels}get names(){return this._names}get classifierLabels(){return this._classifierLabels}get classifierNames(){return this._classifierNames}async call(e,t={}){return this.predict(e,t)}async predict(e,t={}){let i=new n.SpeedTimer,a=typeof e==`string`?e:null,c=await o.loadImage(e);i.stage(`load`);let{feeds:l,scale:u,padLeft:f,padTop:p}=this._preprocess(c);i.stage(`preprocess`);let m=await this._session.run(l);this._pipeline.release(),i.stage(`inference`);let v=h(m,s.OUTPUT_PROBS),S=g(m,s.OUTPUT_BOXES),C=g(m,s.OUTPUT_SCORES),w=_(m,s.OUTPUT_CLASSES),T=v.data,E=_(m,`num_detections`)[0]??0,D=Math.min(E,Math.floor(S.length/4)),O=v.dims[v.dims.length-1]??0,k=t.classes===void 0?null:new Set(t.classes),A=t.confThreshold??0,j=[];for(let e=0;e<D;e++){let n=w[e]??0,r=C[e]??0;if(r<A||k!==null&&!k.has(n))continue;let i=this._toOriginal(S,e,{scale:u,padLeft:f,padTop:p,original:c}),a=y(c,i);j.push(b(n,this._names[n]??`class_${n}`,r,i,a,this._classify(T.subarray(e*O,(e+1)*O),a,t.topK)))}d.requireDetections(j.length,{raiseOnEmpty:t.raiseOnEmpty??this._raiseOnEmpty,confThreshold:Math.max(A,this._spec.confThreshold),classes:t.classes,path:a});let M=[c.height,c.width];return i.stage(`postprocess`),[new r.DetectClassifyResults(x(j,M),j,this._names,this._classifierNames,c,M,a,i.speed())]}_preprocess(e){let[t,n]=this._spec.inputSize,r=this._pipeline.run(e),i={[s.INPUT_IMAGE]:c.toFloat32Tensor(r.data,[1,3,n,t])};return this._spec.needsSourceImage&&(i[s.INPUT_SOURCE]=v(e),i[s.INPUT_SCALE]=c.toFloat32Tensor(new Float32Array([r.scale]),[1]),i[s.INPUT_PAD]=c.toFloat32Tensor(new Float32Array([r.padLeft,r.padTop]),[2])),{feeds:i,scale:r.scale,padLeft:r.padLeft,padTop:r.padTop}}_toOriginal(e,n,r){let{scale:i,padLeft:a,padTop:o,original:s}=r,c=t=>e[n*4+t]??0,l=e=>Math.min(Math.max(e,0),s.width),u=e=>Math.min(Math.max(e,0),s.height);return new t.BoundingBox(l((c(0)-a)/i),u((c(1)-o)/i),l((c(2)-a)/i),u((c(3)-o)/i))}_classify(e,t,n){let{indices:r,values:i}=u.topK(this._spec.applySoftmax?u.softmax(e):e,n??null),a=[];for(let e=0;e<r.length;e++){let t=r[e]??0,n=i[e]??0,o=this._classifierLabels[t]??`class_${t}`;a.push({classId:t,className:o,probability:n,cls:t,name:o,conf:n})}let o=a[0]??{classId:0,className:`class_0`,probability:0,cls:0,name:`class_0`,conf:0};return{classId:o.classId,className:o.className,confidence:o.probability,cls:o.classId,name:o.className,conf:o.probability,image:t,probabilities:a}}};function p(e){let t=e.outputNames.indexOf(s.OUTPUT_PROBS);if(t<0)return null;let n=e.outputShapes[t];return n===void 0||n.length===0?null:n[n.length-1]??null}function m(e){let t={};for(let n=0;n<e.length;n++)t[n]=e[n];return t}function h(t,n){let r=t[n];if(r===void 0)throw new e.FusionError(`The fused pipeline is missing its '${n}' output.`);return r}function g(e,t){return h(e,t).data}function _(e,t){let n=h(e,t).data,r=[];for(let e=0;e<n.length;e++)r.push(Number(n[e]));return r}function v(e){return c.toFloat32Tensor(c.toCHW(c.toFloat32(e),e.width,e.height,3),[1,3,e.height,e.width])}function y(e,n){let[r,i,a,o]=n.asIntXyxy(),s=Math.max(0,r),c=Math.max(0,i),l=Math.min(e.width,a),u=Math.min(e.height,o);if(l<=s||u<=c)return new t.RGBImage(new Uint8Array,0,0);let d=l-s,f=u-c,p=new Uint8Array(d*f*3);for(let t=0;t<f;t++){let n=((c+t)*e.width+s)*3;p.set(e.data.subarray(n,n+d*3),t*d*3)}return new t.RGBImage(p,d,f)}function b(e,t,n,r,i,a){return{classId:e,className:t,confidence:n,bbox:r,cls:e,name:t,conf:n,box:r,croppedImage:i,classification:a}}function x(e,t){let n=new Float32Array(e.length*4),i=new Int32Array(e.length),a=new Float32Array(e.length);return e.forEach((e,t)=>{let[r,o,s,c]=e.bbox.xyxy;n[t*4]=r,n[t*4+1]=o,n[t*4+2]=s,n[t*4+3]=c,i[t]=e.classId,a[t]=e.confidence}),new r.Boxes(n,i,a,t)}exports.DetectClassify=f;
+//# sourceMappingURL=detectClassify.cjs.map