tempest-react-sdk 0.38.3 → 0.39.1

package/dist/vision/tasks/segmenter.js

@@ -1,16 +1,17 @@
 import { Mask as e, RGBImage as t } from "../types.js";
 import { SpeedTimer as n } from "../core/timing.js";
 import { Boxes as r, Masks as i, SegmentationResults as a } from "../results.js";
-import { resolveLabels as o } from "../labels.js";
-import { detectionNumClasses as s, resolveInputSize as c } from "../core/graph.js";
-import { modelNames as l } from "../core/metadata.js";
-import { OrtSession as u } from "../core/session.js";
-import { loadImage as d } from "../io/image.js";
-import { letterbox as f, toCHW as p, toFloat32 as m, toFloat32Tensor as h } from "../preprocess/image.js";
+import { defaultLabels as o, resolveLabels as s } from "../labels.js";
+import { detectionNumClasses as c, resolveInputSize as l } from "../core/graph.js";
+import { modelNames as u } from "../core/metadata.js";
+import { OrtSession as d } from "../core/session.js";
+import { loadImage as f } from "../io/image.js";
+import { toFloat32Tensor as p } from "../preprocess/image.js";
+import { LetterboxPipeline as m, zeroTensorData as h } from "../preprocess/pipeline.js";
 import { decodeYoloSeg as g } from "../postprocess/segmentation.js";
-import { VisionTask as _ } from "./base.js";
+import { VisionTask as _, requireDetections as v } from "./base.js";
 //#region src/vision/tasks/segmenter.ts
-var v = class v extends _ {
+var y = class y extends _ {
 	_head;
 	_labels;
 	_names;
@@ -19,19 +20,36 @@ var v = class v extends _ {
 	_iouThreshold;
 	_maxDetections;
 	_maskThreshold;
-	constructor(e, t, n, r, i, a, o, s, c) {
-		super(e), this._head = t, this._labels = n, this._names = r, this._inputSize = i, this._confThreshold = a, this._iouThreshold = o, this._maxDetections = s, this._maskThreshold = c;
+	_raiseOnEmpty;
+	constructor(e, t, n, r, i, a, o, s, c, l) {
+		super(e), this._head = t, this._labels = n, this._names = r, this._inputSize = i, this._confThreshold = a, this._iouThreshold = o, this._maxDetections = s, this._maskThreshold = c, this._raiseOnEmpty = l;
+	}
+	_pipelineCache = null;
+	async warmup(e = 1) {
+		let [t, n] = this._inputSize;
+		for (let r = 0; r < e; r++) {
+			let e = p(h(t, n), [
+				1,
+				3,
+				n,
+				t
+			]);
+			await this._session.run({ [this._session.inputName]: e });
+		}
+	}
+	get _pipeline() {
+		return this._pipelineCache === null && (this._pipelineCache = new m(this._inputSize[0], this._inputSize[1])), this._pipelineCache;
 	}
 	static async create(e, t = {}) {
 		let n = t.head ?? "yolo-seg";
 		if (n !== "yolo-seg") throw Error(`Unsupported segmenter head '${n}'. Supported: 'yolo-seg'.`);
-		let r = await u.create(e, t), i = o(t.labels ?? l(r.metadata) ?? "coco", { numClasses: t.numClasses ?? s(r.outputShape) ?? void 0 }), a = {};
-		for (let e = 0; e < i.length; e++) a[e] = i[e];
-		return new v(r, n, i, a, c({
+		let r = await d.create(e, t), i = t.numClasses ?? c(r.outputShape) ?? void 0, a = s(t.labels ?? u(r.metadata) ?? o(i), { numClasses: i }), f = {};
+		for (let e = 0; e < a.length; e++) f[e] = a[e];
+		return new y(r, n, a, f, l({
 			graphShape: r.inputShape,
 			requested: t.inputSize,
 			fallback: [640, 640]
-		}), t.confThreshold ?? .25, t.iouThreshold ?? .45, t.maxDetections ?? 300, t.maskThreshold ?? .5);
+		}), t.confThreshold ?? .25, t.iouThreshold ?? .45, t.maxDetections ?? 300, t.maskThreshold ?? .5, t.raiseOnEmpty ?? !1);
 	}
 	get head() {
 		return this._head;
@@ -52,13 +70,13 @@ var v = class v extends _ {
 		return this.predict(e, t);
 	}
 	async predict(e, t = {}) {
-		let r = new n(), i = typeof e == "string" ? e : null, o = await d(e);
+		let r = new n(), i = typeof e == "string" ? e : null, o = await f(e);
 		r.stage("load");
 		let { tensor: s, scale: c, padLeft: l, padTop: u } = this._preprocess(o);
 		r.stage("preprocess");
-		let f = await this._session.run({ [this._session.inputName]: s });
-		r.stage("inference");
-		let { perAnchor: p, prototypes: m } = this._splitOutputs(f), h = g(p.data, p.dims, m.data, m.dims, {
+		let d = await this._session.run({ [this._session.inputName]: s });
+		this._pipeline.release(), r.stage("inference");
+		let { perAnchor: p, prototypes: m } = this._splitOutputs(d), h = t.confThreshold ?? this._confThreshold, _ = g(p.data, p.dims, m.data, m.dims, {
 			numClasses: this._labels.length,
 			inputWidth: this._inputSize[0],
 			inputHeight: this._inputSize[1],
@@ -67,24 +85,31 @@ var v = class v extends _ {
 			padLeft: l,
 			padTop: u,
 			scale: c,
-			confThreshold: t.confThreshold ?? this._confThreshold,
+			confThreshold: h,
 			iouThreshold: t.iouThreshold ?? this._iouThreshold,
 			maxDetections: this._maxDetections,
 			maskThreshold: this._maskThreshold
-		}), _ = (t.classes === void 0 ? h : (() => {
+		}), y = t.classes === void 0 ? _ : (() => {
 			let e = new Set(t.classes);
-			return h.filter((t) => e.has(t.classId));
-		})()).map((e) => this._buildResult(o, e.bbox, e.classId, e.confidence, e.mask)), v = [o.height, o.width], y = this._buildBoxes(_, v), b = this._buildMasks(_, v);
-		return r.stage("postprocess"), [new a(y, b, _, this._names, o, v, i, r.speed())];
+			return _.filter((t) => e.has(t.classId));
+		})();
+		v(y.length, {
+			raiseOnEmpty: t.raiseOnEmpty ?? this._raiseOnEmpty,
+			confThreshold: h,
+			classes: t.classes,
+			path: i
+		});
+		let b = y.map((e) => this._buildResult(o, e.bbox, e.classId, e.confidence, e.mask)), x = [o.height, o.width], S = this._buildBoxes(b, x), C = this._buildMasks(b, x);
+		return r.stage("postprocess"), [new a(S, C, b, this._names, o, x, i, r.speed())];
 	}
 	_preprocess(e) {
-		let [t, n] = this._inputSize, r = f(e, t, n);
+		let [t, n] = this._inputSize, r = this._pipeline.run(e);
 		return {
-			tensor: h(p(m(r.image), r.image.width, r.image.height, 3), [
+			tensor: p(r.data, [
 				1,
 				3,
-				r.image.height,
-				r.image.width
+				n,
+				t
 			]),
 			scale: r.scale,
 			padLeft: r.padLeft,
@@ -155,6 +180,6 @@ var v = class v extends _ {
 	}
 };
 //#endregion
-export { v as Segmenter };
+export { y as Segmenter };
 
 //# sourceMappingURL=segmenter.js.map

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

@@ -1 +1 @@
-{"version":3,"file":"segmenter.js","names":[],"sources":["../../../src/vision/tasks/segmenter.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Instance-segmentation task using YOLO seg ONNX models (v8-seg / v11-seg / ...).\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\n\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { detectionNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { decodeYoloSeg } from \"../postprocess/segmentation\";\nimport { letterbox, toCHW, toFloat32, toFloat32Tensor } from \"../preprocess/image\";\nimport { Boxes, Masks, SegmentationResults } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type BoundingBox, type SegmentationResult, Mask, RGBImage } from \"../types\";\n\n/**\n * Decoder family for the segmentation head.\n *\n * - `\"yolo-seg\"`: YOLO instance-segmentation head with two outputs —\n *   `[1, 4 + nc + nm, N]` per-anchor predictions plus `[1, nm, mh, mw]`\n *   prototype masks. Covers YOLOv8-seg, v11-seg, v26-seg.\n *\n * The SDK does **not** auto-detect this — the caller is responsible for\n * picking a head that matches their export.\n */\nexport type SegmenterHead = \"yolo-seg\";\n\nexport interface SegmenterOptions extends OrtSessionOptions {\n    /**\n     * Decoder family for the segmentation head. Default `\"yolo-seg\"` covers\n     * YOLOv8-seg/v11-seg/v26-seg.\n     */\n    readonly head?: SegmenterHead;\n    /** Class label spec — see {@link resolveLabels}. Defaults to the COCO 80-class preset. */\n    readonly labels?: LabelSpec;\n    /** Number of classes — used to validate the supplied labels. */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels for letterboxing.\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 `[640, 640]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Default minimum class score to keep a candidate. */\n    readonly confThreshold?: number;\n    /** Default IoU threshold for non-maximum suppression. */\n    readonly iouThreshold?: number;\n    /** Maximum number of instances per image. */\n    readonly maxDetections?: number;\n    /** Probability cutoff applied to soft masks. Defaults to `0.5`. */\n    readonly maskThreshold?: number;\n}\n\nexport interface SegmenterPredictOptions {\n    readonly confThreshold?: number;\n    readonly iouThreshold?: number;\n    /**\n     * If set, keep only instances whose `classId` is in this list.\n     * Mirrors Ultralytics' `model.predict(img, classes=[0, 16])`.\n     */\n    readonly classes?: readonly number[];\n}\n\n/**\n * Instance segmenter for YOLO seg ONNX models (v8-seg / v11-seg / ...).\n *\n * The model is expected to expose two outputs:\n *\n * 1. `output0`: `(1, 4 + numClasses + numMaskCoefs, numAnchors)` — per-anchor\n *    predictions (boxes, class scores, mask coefficients).\n * 2. `output1`: `(1, numMaskCoefs, maskH, maskW)` — prototype masks.\n *\n * `predict()` returns `Promise<SegmentationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes:\n *\n * - `boxes`: bulk numpy view (`xyxy`, `xywh`, `xyxyn`, `xywhn`, `cls`, `conf`).\n * - `masks`: per-instance binary masks cropped to each box.\n * - per-instance {@link SegmentationResult} via iteration.\n *\n * @example\n * ```typescript\n * const seg = await Segmenter.create(\"/models/yolov8n-seg.onnx\");\n * const r = (await seg.predict(\"/images/street.jpg\"))[0];\n * for (const inst of r) {\n *   console.log(inst.cls, inst.conf, inst.box.xyxy);\n * }\n * ```\n */\nexport class Segmenter extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _head: SegmenterHead,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _confThreshold: number,\n        private readonly _iouThreshold: number,\n        private readonly _maxDetections: number,\n        private readonly _maskThreshold: number,\n    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: SegmenterOptions = {}): Promise<Segmenter> {\n        const head: SegmenterHead = options.head ?? \"yolo-seg\";\n        if (head !== \"yolo-seg\") {\n            throw new Error(`Unsupported segmenter head '${head}'. Supported: 'yolo-seg'.`);\n        }\n        const session = await OrtSession.create(model, options);\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata) ?? \"coco\", {\n            numClasses: options.numClasses ?? detectionNumClasses(session.outputShape) ?? undefined,\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 Segmenter(\n            session,\n            head,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [640, 640],\n            }),\n            options.confThreshold ?? 0.25,\n            options.iouThreshold ?? 0.45,\n            options.maxDetections ?? 300,\n            options.maskThreshold ?? 0.5,\n        );\n    }\n\n    /** The decoder family used to interpret the model's output. */\n    get head(): SegmenterHead {\n        return this._head;\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 predicts. */\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: SegmenterPredictOptions = {},\n    ): Promise<SegmentationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run instance segmentation on a single image. */\n    async predict(\n        image: ImageInput,\n        options: SegmenterPredictOptions = {},\n    ): Promise<SegmentationResults[]> {\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, scale, padLeft, padTop } = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        timer.stage(\"inference\");\n\n        const { perAnchor, prototypes } = this._splitOutputs(outputs);\n\n        const decodedAll = decodeYoloSeg(\n            perAnchor.data as Float32Array,\n            perAnchor.dims,\n            prototypes.data as Float32Array,\n            prototypes.dims,\n            {\n                numClasses: this._labels.length,\n                inputWidth: this._inputSize[0],\n                inputHeight: this._inputSize[1],\n                originalWidth: original.width,\n                originalHeight: original.height,\n                padLeft,\n                padTop,\n                scale,\n                confThreshold: options.confThreshold ?? this._confThreshold,\n                iouThreshold: options.iouThreshold ?? this._iouThreshold,\n                maxDetections: this._maxDetections,\n                maskThreshold: this._maskThreshold,\n            },\n        );\n\n        const decoded =\n            options.classes !== undefined\n                ? (() => {\n                      const allowed = new Set(options.classes);\n                      return decodedAll.filter((d) => allowed.has(d.classId));\n                  })()\n                : decodedAll;\n\n        const detections = decoded.map((d) =>\n            this._buildResult(original, d.bbox, d.classId, d.confidence, d.mask),\n        );\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const boxes = this._buildBoxes(detections, orig);\n        const masks = this._buildMasks(detections, orig);\n        timer.stage(\"postprocess\");\n        return [\n            new SegmentationResults(\n                boxes,\n                masks,\n                detections,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): {\n        tensor: ort.Tensor;\n        scale: number;\n        padLeft: number;\n        padTop: number;\n    } {\n        const [tw, th] = this._inputSize;\n        const lb = letterbox(image, tw, th);\n        const f32 = toFloat32(lb.image);\n        const chw = toCHW(f32, lb.image.width, lb.image.height, 3);\n        return {\n            tensor: toFloat32Tensor(chw, [1, 3, lb.image.height, lb.image.width]),\n            scale: lb.scale,\n            padLeft: lb.padLeft,\n            padTop: lb.padTop,\n        };\n    }\n\n    private _splitOutputs(outputs: Record<string, ort.Tensor>): {\n        perAnchor: ort.Tensor;\n        prototypes: ort.Tensor;\n    } {\n        let perAnchor: ort.Tensor | undefined;\n        let prototypes: ort.Tensor | undefined;\n        for (const name of this._session.outputNames) {\n            const t = outputs[name];\n            if (t === undefined) continue;\n            if (t.dims.length === 3 && perAnchor === undefined) {\n                perAnchor = t;\n            } else if (t.dims.length === 4 && prototypes === undefined) {\n                prototypes = t;\n            }\n        }\n        if (perAnchor === undefined || prototypes === undefined) {\n            const shapes = this._session.outputNames.map(\n                (n) => `${n}: ${JSON.stringify(outputs[n]?.dims ?? [])}`,\n            );\n            throw new Error(\n                `Segmenter expected one 3-D and one 4-D output, got [${shapes.join(\", \")}].`,\n            );\n        }\n        return { perAnchor, prototypes };\n    }\n\n    private _buildResult(\n        original: RGBImage,\n        bbox: BoundingBox,\n        classId: number,\n        confidence: number,\n        mask: Mask,\n    ): SegmentationResult {\n        const [x1, y1, x2, y2] = bbox.asIntXyxy();\n        const cx1 = Math.max(0, x1);\n        const cy1 = Math.max(0, y1);\n        const cx2 = Math.min(original.width, x2);\n        const cy2 = Math.min(original.height, y2);\n\n        let segmentedImage: RGBImage;\n        let finalMask = mask;\n        if (cx2 > cx1 && cy2 > cy1 && mask.data.length > 0) {\n            const cropW = cx2 - cx1;\n            const cropH = cy2 - cy1;\n            const mw = Math.min(mask.width, cropW);\n            const mh = Math.min(mask.height, cropH);\n            const segData = new Uint8Array(mw * mh * 3);\n            for (let row = 0; row < mh; row++) {\n                const srcRowOffset = ((cy1 + row) * original.width + cx1) * 3;\n                const dstRowOffset = row * mw * 3;\n                const maskRowOffset = row * mask.width;\n                for (let col = 0; col < mw; col++) {\n                    const m = mask.data[maskRowOffset + col];\n                    if (m !== 0) {\n                        const s = srcRowOffset + col * 3;\n                        const d = dstRowOffset + col * 3;\n                        segData[d] = original.data[s];\n                        segData[d + 1] = original.data[s + 1];\n                        segData[d + 2] = original.data[s + 2];\n                    }\n                }\n            }\n            segmentedImage = new RGBImage(segData, mw, mh);\n            if (mw !== mask.width || mh !== mask.height) {\n                const trimmed = new Uint8Array(mw * mh);\n                for (let row = 0; row < mh; row++) {\n                    trimmed.set(\n                        mask.data.subarray(row * mask.width, row * mask.width + mw),\n                        row * mw,\n                    );\n                }\n                finalMask = new Mask(trimmed, mw, mh);\n            }\n        } else {\n            finalMask = new Mask(new Uint8Array(0), 0, 0);\n            segmentedImage = new RGBImage(new Uint8Array(0), 0, 0);\n        }\n\n        const className = this._names[classId] ?? `class_${classId}`;\n\n        return {\n            classId,\n            className,\n            confidence,\n            bbox,\n            cls: classId,\n            name: className,\n            conf: confidence,\n            box: bbox,\n            mask: finalMask,\n            segmentedImage,\n        };\n    }\n\n    private _buildBoxes(\n        detections: readonly SegmentationResult[],\n        origShape: readonly [number, number],\n    ): Boxes {\n        const n = detections.length;\n        const xyxy = new Float32Array(n * 4);\n        const cls = new Int32Array(n);\n        const conf = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            const d = detections[i] as SegmentationResult;\n            xyxy[i * 4] = d.bbox.x1;\n            xyxy[i * 4 + 1] = d.bbox.y1;\n            xyxy[i * 4 + 2] = d.bbox.x2;\n            xyxy[i * 4 + 3] = d.bbox.y2;\n            cls[i] = d.classId;\n            conf[i] = d.confidence;\n        }\n        return new Boxes(xyxy, cls, conf, origShape);\n    }\n\n    private _buildMasks(\n        detections: readonly SegmentationResult[],\n        origShape: readonly [number, number],\n    ): Masks {\n        const xyxy = new Float32Array(detections.length * 4);\n        for (let i = 0; i < detections.length; i++) {\n            const d = detections[i] as SegmentationResult;\n            xyxy[i * 4] = d.bbox.x1;\n            xyxy[i * 4 + 1] = d.bbox.y1;\n            xyxy[i * 4 + 2] = d.bbox.x2;\n            xyxy[i * 4 + 3] = d.bbox.y2;\n        }\n        return new Masks(\n            detections.map((d) => d.mask),\n            xyxy,\n            origShape,\n        );\n    }\n}\n"],"mappings":";;;;;;;;;;;;AA+FA,IAAa,IAAb,MAAa,UAAkB,EAAW;CAGjB;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CATrB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,GACA,GACA,GACF;EADmB,AAEjB,MAAM,CAAO,GATI,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,SAAA,GACA,KAAA,aAAA,GACA,KAAA,iBAAA,GACA,KAAA,gBAAA,GACA,KAAA,iBAAA,GACA,KAAA,iBAAA;CAGrB;CAGA,aAAa,OAAO,GAAoB,IAA4B,CAAC,GAAuB;EACxF,IAAM,IAAsB,EAAQ,QAAQ;EAC5C,IAAI,MAAS,YACT,MAAU,MAAM,+BAA+B,EAAK,0BAA0B;EAElF,IAAM,IAAU,MAAM,EAAW,OAAO,GAAO,CAAO,GAChD,IAAS,EAAc,EAAQ,UAAU,EAAW,EAAQ,QAAQ,KAAK,QAAQ,EACnF,YAAY,EAAQ,cAAc,EAAoB,EAAQ,WAAW,KAAK,KAAA,EAClF,CAAC,GACK,IAAgC,CAAC;EACvC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAO,QAAQ,KAC/B,EAAM,KAAK,EAAO;EAEtB,OAAO,IAAI,EACP,GACA,GACA,GACA,GACA,EAAiB;GACb,YAAY,EAAQ;GACpB,WAAW,EAAQ;GACnB,UAAU,CAAC,KAAK,GAAG;EACvB,CAAC,GACD,EAAQ,iBAAiB,KACzB,EAAQ,gBAAgB,KACxB,EAAQ,iBAAiB,KACzB,EAAQ,iBAAiB,EAC7B;CACJ;CAGA,IAAI,OAAsB;EACtB,OAAO,KAAK;CAChB;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,IAAmC,CAAC,GACN;EAC9B,OAAO,KAAK,QAAQ,GAAO,CAAO;CACtC;CAGA,MAAM,QACF,GACA,IAAmC,CAAC,GACN;EAC9B,IAAM,IAAQ,IAAI,EAAW,GACvB,IAAO,OAAO,KAAU,WAAW,IAAQ,MAC3C,IAAW,MAAM,EAAU,CAAK;EACtC,EAAM,MAAM,MAAM;EAClB,IAAM,EAAE,WAAQ,UAAO,YAAS,cAAW,KAAK,YAAY,CAAQ;EACpE,EAAM,MAAM,YAAY;EACxB,IAAM,IAAU,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EAC7E,EAAM,MAAM,WAAW;EAEvB,IAAM,EAAE,cAAW,kBAAe,KAAK,cAAc,CAAO,GAEtD,IAAa,EACf,EAAU,MACV,EAAU,MACV,EAAW,MACX,EAAW,MACX;GACI,YAAY,KAAK,QAAQ;GACzB,YAAY,KAAK,WAAW;GAC5B,aAAa,KAAK,WAAW;GAC7B,eAAe,EAAS;GACxB,gBAAgB,EAAS;GACzB;GACA;GACA;GACA,eAAe,EAAQ,iBAAiB,KAAK;GAC7C,cAAc,EAAQ,gBAAgB,KAAK;GAC3C,eAAe,KAAK;GACpB,eAAe,KAAK;EACxB,CACJ,GAUM,KAPF,EAAQ,YAAY,KAAA,IAKd,WAJO;GACH,IAAM,IAAU,IAAI,IAAI,EAAQ,OAAO;GACvC,OAAO,EAAW,QAAQ,MAAM,EAAQ,IAAI,EAAE,OAAO,CAAC;EAC1D,EAAA,CAAG,EACH,CAEiB,KAAK,MAC5B,KAAK,aAAa,GAAU,EAAE,MAAM,EAAE,SAAS,EAAE,YAAY,EAAE,IAAI,CACvE,GAEM,IAAkC,CAAC,EAAS,QAAQ,EAAS,KAAK,GAClE,IAAQ,KAAK,YAAY,GAAY,CAAI,GACzC,IAAQ,KAAK,YAAY,GAAY,CAAI;EAE/C,OADA,EAAM,MAAM,aAAa,GAClB,CACH,IAAI,EACA,GACA,GACA,GACA,KAAK,QACL,GACA,GACA,GACA,EAAM,MAAM,CAChB,CACJ;CACJ;CAEA,YAAoB,GAKlB;EACE,IAAM,CAAC,GAAI,KAAM,KAAK,YAChB,IAAK,EAAU,GAAO,GAAI,CAAE;EAGlC,OAAO;GACH,QAAQ,EAFA,EADA,EAAU,EAAG,KACP,GAAK,EAAG,MAAM,OAAO,EAAG,MAAM,QAAQ,CAE5B,GAAK;IAAC;IAAG;IAAG,EAAG,MAAM;IAAQ,EAAG,MAAM;GAAK,CAAC;GACpE,OAAO,EAAG;GACV,SAAS,EAAG;GACZ,QAAQ,EAAG;EACf;CACJ;CAEA,cAAsB,GAGpB;EACE,IAAI,GACA;EACJ,KAAK,IAAM,KAAQ,KAAK,SAAS,aAAa;GAC1C,IAAM,IAAI,EAAQ;GACd,MAAM,KAAA,MACN,EAAE,KAAK,WAAW,KAAK,MAAc,KAAA,IACrC,IAAY,IACL,EAAE,KAAK,WAAW,KAAK,MAAe,KAAA,MAC7C,IAAa;EAErB;EACA,IAAI,MAAc,KAAA,KAAa,MAAe,KAAA,GAAW;GACrD,IAAM,IAAS,KAAK,SAAS,YAAY,KACpC,MAAM,GAAG,EAAE,IAAI,KAAK,UAAU,EAAQ,EAAE,EAAE,QAAQ,CAAC,CAAC,GACzD;GACA,MAAU,MACN,uDAAuD,EAAO,KAAK,IAAI,EAAE,GAC7E;EACJ;EACA,OAAO;GAAE;GAAW;EAAW;CACnC;CAEA,aACI,GACA,GACA,GACA,GACA,GACkB;EAClB,IAAM,CAAC,GAAI,GAAI,GAAI,KAAM,EAAK,UAAU,GAClC,IAAM,KAAK,IAAI,GAAG,CAAE,GACpB,IAAM,KAAK,IAAI,GAAG,CAAE,GACpB,IAAM,KAAK,IAAI,EAAS,OAAO,CAAE,GACjC,IAAM,KAAK,IAAI,EAAS,QAAQ,CAAE,GAEpC,GACA,IAAY;EAChB,IAAI,IAAM,KAAO,IAAM,KAAO,EAAK,KAAK,SAAS,GAAG;GAChD,IAAM,IAAQ,IAAM,GACd,IAAQ,IAAM,GACd,IAAK,KAAK,IAAI,EAAK,OAAO,CAAK,GAC/B,IAAK,KAAK,IAAI,EAAK,QAAQ,CAAK,GAChC,IAAU,IAAI,WAAW,IAAK,IAAK,CAAC;GAC1C,KAAK,IAAI,IAAM,GAAG,IAAM,GAAI,KAAO;IAC/B,IAAM,MAAiB,IAAM,KAAO,EAAS,QAAQ,KAAO,GACtD,IAAe,IAAM,IAAK,GAC1B,IAAgB,IAAM,EAAK;IACjC,KAAK,IAAI,IAAM,GAAG,IAAM,GAAI,KAExB,IADU,EAAK,KAAK,IAAgB,OAC1B,GAAG;KACT,IAAM,IAAI,IAAe,IAAM,GACzB,IAAI,IAAe,IAAM;KAG/B,AAFA,EAAQ,KAAK,EAAS,KAAK,IAC3B,EAAQ,IAAI,KAAK,EAAS,KAAK,IAAI,IACnC,EAAQ,IAAI,KAAK,EAAS,KAAK,IAAI;IACvC;GAER;GAEA,IADA,IAAiB,IAAI,EAAS,GAAS,GAAI,CAAE,GACzC,MAAO,EAAK,SAAS,MAAO,EAAK,QAAQ;IACzC,IAAM,IAAU,IAAI,WAAW,IAAK,CAAE;IACtC,KAAK,IAAI,IAAM,GAAG,IAAM,GAAI,KACxB,EAAQ,IACJ,EAAK,KAAK,SAAS,IAAM,EAAK,OAAO,IAAM,EAAK,QAAQ,CAAE,GAC1D,IAAM,CACV;IAEJ,IAAY,IAAI,EAAK,GAAS,GAAI,CAAE;GACxC;EACJ,OAEI,AADA,IAAY,IAAI,kBAAK,IAAI,WAAY,GAAG,GAAG,CAAC,GAC5C,IAAiB,IAAI,kBAAS,IAAI,WAAY,GAAG,GAAG,CAAC;EAGzD,IAAM,IAAY,KAAK,OAAO,MAAY,SAAS;EAEnD,OAAO;GACH;GACA;GACA;GACA;GACA,KAAK;GACL,MAAM;GACN,MAAM;GACN,KAAK;GACL,MAAM;GACN;EACJ;CACJ;CAEA,YACI,GACA,GACK;EACL,IAAM,IAAI,EAAW,QACf,IAAO,IAAI,aAAa,IAAI,CAAC,GAC7B,IAAM,IAAI,WAAW,CAAC,GACtB,IAAO,IAAI,aAAa,CAAC;EAC/B,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;GACxB,IAAM,IAAI,EAAW;GAMrB,AALA,EAAK,IAAI,KAAK,EAAE,KAAK,IACrB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAI,KAAK,EAAE,SACX,EAAK,KAAK,EAAE;EAChB;EACA,OAAO,IAAI,EAAM,GAAM,GAAK,GAAM,CAAS;CAC/C;CAEA,YACI,GACA,GACK;EACL,IAAM,IAAO,IAAI,aAAa,EAAW,SAAS,CAAC;EACnD,KAAK,IAAI,IAAI,GAAG,IAAI,EAAW,QAAQ,KAAK;GACxC,IAAM,IAAI,EAAW;GAIrB,AAHA,EAAK,IAAI,KAAK,EAAE,KAAK,IACrB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK;EAC7B;EACA,OAAO,IAAI,EACP,EAAW,KAAK,MAAM,EAAE,IAAI,GAC5B,GACA,CACJ;CACJ;AACJ"}
+{"version":3,"file":"segmenter.js","names":[],"sources":["../../../src/vision/tasks/segmenter.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Instance-segmentation task using YOLO seg ONNX models (v8-seg / v11-seg / ...).\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\n\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { detectionNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, defaultLabels, resolveLabels } from \"../labels\";\nimport { decodeYoloSeg } from \"../postprocess/segmentation\";\nimport { toFloat32Tensor } from \"../preprocess/image\";\nimport { LetterboxPipeline, zeroTensorData } from \"../preprocess/pipeline\";\nimport { Boxes, Masks, SegmentationResults } from \"../results\";\nimport { VisionTask, requireDetections } from \"./base\";\nimport { type BoundingBox, type SegmentationResult, Mask, RGBImage } from \"../types\";\n\n/**\n * Decoder family for the segmentation head.\n *\n * - `\"yolo-seg\"`: YOLO instance-segmentation head with two outputs —\n *   `[1, 4 + nc + nm, N]` per-anchor predictions plus `[1, nm, mh, mw]`\n *   prototype masks. Covers YOLOv8-seg, v11-seg, v26-seg.\n *\n * The SDK does **not** auto-detect this — the caller is responsible for\n * picking a head that matches their export.\n */\nexport type SegmenterHead = \"yolo-seg\";\n\nexport interface SegmenterOptions extends OrtSessionOptions {\n    /**\n     * Decoder family for the segmentation head. Default `\"yolo-seg\"` covers\n     * YOLOv8-seg/v11-seg/v26-seg.\n     */\n    readonly head?: SegmenterHead;\n    /** Class label spec — see {@link resolveLabels}. Defaults to the COCO 80-class preset. */\n    readonly labels?: LabelSpec;\n    /** Number of classes — used to validate the supplied labels. */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels for letterboxing.\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 `[640, 640]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Default minimum class score to keep a candidate. */\n    readonly confThreshold?: number;\n    /** Default IoU threshold for non-maximum suppression. */\n    readonly iouThreshold?: number;\n    /** Maximum number of instances per image. */\n    readonly maxDetections?: number;\n    /**\n     * If `true`, a run that finds nothing throws {@link NoDetectionsError}\n     * instead of returning an empty envelope. Default `false`, because looking\n     * and finding nothing is a successful inference. Turn it on when an empty\n     * result means the surrounding pipeline should stop rather than carry on with\n     * zero rows. Can be overridden per `predict` call.\n     */\n    readonly raiseOnEmpty?: boolean;\n    /** Probability cutoff applied to soft masks. Defaults to `0.5`. */\n    readonly maskThreshold?: number;\n}\n\nexport interface SegmenterPredictOptions {\n    readonly confThreshold?: number;\n    readonly iouThreshold?: number;\n    /**\n     * If set, keep only instances whose `classId` is in this list.\n     * Mirrors Ultralytics' `model.predict(img, classes=[0, 16])`.\n     */\n    readonly classes?: readonly number[];\n    /** Override the constructor's `raiseOnEmpty` setting for this call. */\n    readonly raiseOnEmpty?: boolean;\n}\n\n/**\n * Instance segmenter for YOLO seg ONNX models (v8-seg / v11-seg / ...).\n *\n * The model is expected to expose two outputs:\n *\n * 1. `output0`: `(1, 4 + numClasses + numMaskCoefs, numAnchors)` — per-anchor\n *    predictions (boxes, class scores, mask coefficients).\n * 2. `output1`: `(1, numMaskCoefs, maskH, maskW)` — prototype masks.\n *\n * `predict()` returns `Promise<SegmentationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes:\n *\n * - `boxes`: bulk numpy view (`xyxy`, `xywh`, `xyxyn`, `xywhn`, `cls`, `conf`).\n * - `masks`: per-instance binary masks cropped to each box.\n * - per-instance {@link SegmentationResult} via iteration.\n *\n * @example\n * ```typescript\n * const seg = await Segmenter.create(\"/models/yolov8n-seg.onnx\");\n * const r = (await seg.predict(\"/images/street.jpg\"))[0];\n * for (const inst of r) {\n *   console.log(inst.cls, inst.conf, inst.box.xyxy);\n * }\n * ```\n */\nexport class Segmenter extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _head: SegmenterHead,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _confThreshold: number,\n        private readonly _iouThreshold: number,\n        private readonly _maxDetections: number,\n        private readonly _maskThreshold: number,\n        private readonly _raiseOnEmpty: boolean,\n    ) {\n        super(session);\n    }\n\n    private _pipelineCache: LetterboxPipeline | null = null;\n\n    /**\n     * Run the model once on a zero-filled tensor, paying one-time costs up front.\n     *\n     * The first inference of a session is not representative: WebGPU compiles its\n     * shaders on it and the WASM backend faults in its arenas, which on a phone\n     * can turn the first frame into seconds while every later frame is tens of\n     * milliseconds. Calling this while a loading spinner is still up moves that\n     * cost somewhere the user is already waiting.\n     *\n     * @param runs How many warm-up inferences to run. One is enough for WASM;\n     *   WebGPU sometimes settles on the second.\n     */\n    async warmup(runs: number = 1): Promise<void> {\n        const [tw, th] = this._inputSize;\n        for (let i = 0; i < runs; i++) {\n            const tensor = toFloat32Tensor(zeroTensorData(tw, th), [1, 3, th, tw]);\n            await this._session.run({ [this._session.inputName]: tensor });\n        }\n    }\n\n    /**\n     * The fused preprocessing pipeline, built on first use.\n     *\n     * Lazily, because constructing it allocates canvases: a task built in an\n     * environment without a canvas implementation stays constructible, and only\n     * fails if it is actually asked to preprocess something.\n     */\n    private get _pipeline(): LetterboxPipeline {\n        if (this._pipelineCache === null) {\n            this._pipelineCache = new LetterboxPipeline(this._inputSize[0], this._inputSize[1]);\n        }\n        return this._pipelineCache;\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: SegmenterOptions = {}): Promise<Segmenter> {\n        const head: SegmenterHead = options.head ?? \"yolo-seg\";\n        if (head !== \"yolo-seg\") {\n            throw new Error(`Unsupported segmenter head '${head}'. Supported: 'yolo-seg'.`);\n        }\n        const session = await OrtSession.create(model, options);\n        const numClasses =\n            options.numClasses ?? detectionNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(\n            options.labels ?? modelNames(session.metadata) ?? defaultLabels(numClasses),\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 Segmenter(\n            session,\n            head,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [640, 640],\n            }),\n            options.confThreshold ?? 0.25,\n            options.iouThreshold ?? 0.45,\n            options.maxDetections ?? 300,\n            options.maskThreshold ?? 0.5,\n            options.raiseOnEmpty ?? false,\n        );\n    }\n\n    /** The decoder family used to interpret the model's output. */\n    get head(): SegmenterHead {\n        return this._head;\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 predicts. */\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: SegmenterPredictOptions = {},\n    ): Promise<SegmentationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run instance segmentation on a single image. */\n    async predict(\n        image: ImageInput,\n        options: SegmenterPredictOptions = {},\n    ): Promise<SegmentationResults[]> {\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, scale, padLeft, padTop } = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        this._pipeline.release();\n        timer.stage(\"inference\");\n\n        const { perAnchor, prototypes } = this._splitOutputs(outputs);\n\n        const threshold = options.confThreshold ?? this._confThreshold;\n        const decodedAll = decodeYoloSeg(\n            perAnchor.data as Float32Array,\n            perAnchor.dims,\n            prototypes.data as Float32Array,\n            prototypes.dims,\n            {\n                numClasses: this._labels.length,\n                inputWidth: this._inputSize[0],\n                inputHeight: this._inputSize[1],\n                originalWidth: original.width,\n                originalHeight: original.height,\n                padLeft,\n                padTop,\n                scale,\n                confThreshold: threshold,\n                iouThreshold: options.iouThreshold ?? this._iouThreshold,\n                maxDetections: this._maxDetections,\n                maskThreshold: this._maskThreshold,\n            },\n        );\n\n        const decoded =\n            options.classes !== undefined\n                ? (() => {\n                      const allowed = new Set(options.classes);\n                      return decodedAll.filter((d) => allowed.has(d.classId));\n                  })()\n                : decodedAll;\n\n        requireDetections(decoded.length, {\n            raiseOnEmpty: options.raiseOnEmpty ?? this._raiseOnEmpty,\n            confThreshold: threshold,\n            classes: options.classes,\n            path,\n        });\n\n        const detections = decoded.map((d) =>\n            this._buildResult(original, d.bbox, d.classId, d.confidence, d.mask),\n        );\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const boxes = this._buildBoxes(detections, orig);\n        const masks = this._buildMasks(detections, orig);\n        timer.stage(\"postprocess\");\n        return [\n            new SegmentationResults(\n                boxes,\n                masks,\n                detections,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): {\n        tensor: ort.Tensor;\n        scale: number;\n        padLeft: number;\n        padTop: number;\n    } {\n        const [tw, th] = this._inputSize;\n        const fused = this._pipeline.run(image);\n        return {\n            tensor: toFloat32Tensor(fused.data, [1, 3, th, tw]),\n            scale: fused.scale,\n            padLeft: fused.padLeft,\n            padTop: fused.padTop,\n        };\n    }\n\n    private _splitOutputs(outputs: Record<string, ort.Tensor>): {\n        perAnchor: ort.Tensor;\n        prototypes: ort.Tensor;\n    } {\n        let perAnchor: ort.Tensor | undefined;\n        let prototypes: ort.Tensor | undefined;\n        for (const name of this._session.outputNames) {\n            const t = outputs[name];\n            if (t === undefined) continue;\n            if (t.dims.length === 3 && perAnchor === undefined) {\n                perAnchor = t;\n            } else if (t.dims.length === 4 && prototypes === undefined) {\n                prototypes = t;\n            }\n        }\n        if (perAnchor === undefined || prototypes === undefined) {\n            const shapes = this._session.outputNames.map(\n                (n) => `${n}: ${JSON.stringify(outputs[n]?.dims ?? [])}`,\n            );\n            throw new Error(\n                `Segmenter expected one 3-D and one 4-D output, got [${shapes.join(\", \")}].`,\n            );\n        }\n        return { perAnchor, prototypes };\n    }\n\n    private _buildResult(\n        original: RGBImage,\n        bbox: BoundingBox,\n        classId: number,\n        confidence: number,\n        mask: Mask,\n    ): SegmentationResult {\n        const [x1, y1, x2, y2] = bbox.asIntXyxy();\n        const cx1 = Math.max(0, x1);\n        const cy1 = Math.max(0, y1);\n        const cx2 = Math.min(original.width, x2);\n        const cy2 = Math.min(original.height, y2);\n\n        let segmentedImage: RGBImage;\n        let finalMask = mask;\n        if (cx2 > cx1 && cy2 > cy1 && mask.data.length > 0) {\n            const cropW = cx2 - cx1;\n            const cropH = cy2 - cy1;\n            const mw = Math.min(mask.width, cropW);\n            const mh = Math.min(mask.height, cropH);\n            const segData = new Uint8Array(mw * mh * 3);\n            for (let row = 0; row < mh; row++) {\n                const srcRowOffset = ((cy1 + row) * original.width + cx1) * 3;\n                const dstRowOffset = row * mw * 3;\n                const maskRowOffset = row * mask.width;\n                for (let col = 0; col < mw; col++) {\n                    const m = mask.data[maskRowOffset + col];\n                    if (m !== 0) {\n                        const s = srcRowOffset + col * 3;\n                        const d = dstRowOffset + col * 3;\n                        segData[d] = original.data[s];\n                        segData[d + 1] = original.data[s + 1];\n                        segData[d + 2] = original.data[s + 2];\n                    }\n                }\n            }\n            segmentedImage = new RGBImage(segData, mw, mh);\n            if (mw !== mask.width || mh !== mask.height) {\n                const trimmed = new Uint8Array(mw * mh);\n                for (let row = 0; row < mh; row++) {\n                    trimmed.set(\n                        mask.data.subarray(row * mask.width, row * mask.width + mw),\n                        row * mw,\n                    );\n                }\n                finalMask = new Mask(trimmed, mw, mh);\n            }\n        } else {\n            finalMask = new Mask(new Uint8Array(0), 0, 0);\n            segmentedImage = new RGBImage(new Uint8Array(0), 0, 0);\n        }\n\n        const className = this._names[classId] ?? `class_${classId}`;\n\n        return {\n            classId,\n            className,\n            confidence,\n            bbox,\n            cls: classId,\n            name: className,\n            conf: confidence,\n            box: bbox,\n            mask: finalMask,\n            segmentedImage,\n        };\n    }\n\n    private _buildBoxes(\n        detections: readonly SegmentationResult[],\n        origShape: readonly [number, number],\n    ): Boxes {\n        const n = detections.length;\n        const xyxy = new Float32Array(n * 4);\n        const cls = new Int32Array(n);\n        const conf = new Float32Array(n);\n        for (let i = 0; i < n; i++) {\n            const d = detections[i] as SegmentationResult;\n            xyxy[i * 4] = d.bbox.x1;\n            xyxy[i * 4 + 1] = d.bbox.y1;\n            xyxy[i * 4 + 2] = d.bbox.x2;\n            xyxy[i * 4 + 3] = d.bbox.y2;\n            cls[i] = d.classId;\n            conf[i] = d.confidence;\n        }\n        return new Boxes(xyxy, cls, conf, origShape);\n    }\n\n    private _buildMasks(\n        detections: readonly SegmentationResult[],\n        origShape: readonly [number, number],\n    ): Masks {\n        const xyxy = new Float32Array(detections.length * 4);\n        for (let i = 0; i < detections.length; i++) {\n            const d = detections[i] as SegmentationResult;\n            xyxy[i * 4] = d.bbox.x1;\n            xyxy[i * 4 + 1] = d.bbox.y1;\n            xyxy[i * 4 + 2] = d.bbox.x2;\n            xyxy[i * 4 + 3] = d.bbox.y2;\n        }\n        return new Masks(\n            detections.map((d) => d.mask),\n            xyxy,\n            origShape,\n        );\n    }\n}\n"],"mappings":";;;;;;;;;;;;;AA0GA,IAAa,IAAb,MAAa,UAAkB,EAAW;CAGjB;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CACA;CAVrB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,GACA,GACA,GACA,GACF;EADmB,AAEjB,MAAM,CAAO,GAVI,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,SAAA,GACA,KAAA,aAAA,GACA,KAAA,iBAAA,GACA,KAAA,gBAAA,GACA,KAAA,iBAAA,GACA,KAAA,iBAAA,GACA,KAAA,gBAAA;CAGrB;CAEA,iBAAmD;CAcnD,MAAM,OAAO,IAAe,GAAkB;EAC1C,IAAM,CAAC,GAAI,KAAM,KAAK;EACtB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAM,KAAK;GAC3B,IAAM,IAAS,EAAgB,EAAe,GAAI,CAAE,GAAG;IAAC;IAAG;IAAG;IAAI;GAAE,CAAC;GACrE,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EACjE;CACJ;CASA,IAAY,YAA+B;EAIvC,OAHI,KAAK,mBAAmB,SACxB,KAAK,iBAAiB,IAAI,EAAkB,KAAK,WAAW,IAAI,KAAK,WAAW,EAAE,IAE/E,KAAK;CAChB;CAGA,aAAa,OAAO,GAAoB,IAA4B,CAAC,GAAuB;EACxF,IAAM,IAAsB,EAAQ,QAAQ;EAC5C,IAAI,MAAS,YACT,MAAU,MAAM,+BAA+B,EAAK,0BAA0B;EAElF,IAAM,IAAU,MAAM,EAAW,OAAO,GAAO,CAAO,GAChD,IACF,EAAQ,cAAc,EAAoB,EAAQ,WAAW,KAAK,KAAA,GAChE,IAAS,EACX,EAAQ,UAAU,EAAW,EAAQ,QAAQ,KAAK,EAAc,CAAU,GAC1E,EAAE,cAAW,CACjB,GACM,IAAgC,CAAC;EACvC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAO,QAAQ,KAC/B,EAAM,KAAK,EAAO;EAEtB,OAAO,IAAI,EACP,GACA,GACA,GACA,GACA,EAAiB;GACb,YAAY,EAAQ;GACpB,WAAW,EAAQ;GACnB,UAAU,CAAC,KAAK,GAAG;EACvB,CAAC,GACD,EAAQ,iBAAiB,KACzB,EAAQ,gBAAgB,KACxB,EAAQ,iBAAiB,KACzB,EAAQ,iBAAiB,IACzB,EAAQ,gBAAgB,EAC5B;CACJ;CAGA,IAAI,OAAsB;EACtB,OAAO,KAAK;CAChB;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,IAAmC,CAAC,GACN;EAC9B,OAAO,KAAK,QAAQ,GAAO,CAAO;CACtC;CAGA,MAAM,QACF,GACA,IAAmC,CAAC,GACN;EAC9B,IAAM,IAAQ,IAAI,EAAW,GACvB,IAAO,OAAO,KAAU,WAAW,IAAQ,MAC3C,IAAW,MAAM,EAAU,CAAK;EACtC,EAAM,MAAM,MAAM;EAClB,IAAM,EAAE,WAAQ,UAAO,YAAS,cAAW,KAAK,YAAY,CAAQ;EACpE,EAAM,MAAM,YAAY;EACxB,IAAM,IAAU,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EAE7E,AADA,KAAK,UAAU,QAAQ,GACvB,EAAM,MAAM,WAAW;EAEvB,IAAM,EAAE,cAAW,kBAAe,KAAK,cAAc,CAAO,GAEtD,IAAY,EAAQ,iBAAiB,KAAK,gBAC1C,IAAa,EACf,EAAU,MACV,EAAU,MACV,EAAW,MACX,EAAW,MACX;GACI,YAAY,KAAK,QAAQ;GACzB,YAAY,KAAK,WAAW;GAC5B,aAAa,KAAK,WAAW;GAC7B,eAAe,EAAS;GACxB,gBAAgB,EAAS;GACzB;GACA;GACA;GACA,eAAe;GACf,cAAc,EAAQ,gBAAgB,KAAK;GAC3C,eAAe,KAAK;GACpB,eAAe,KAAK;EACxB,CACJ,GAEM,IACF,EAAQ,YAAY,KAAA,IAKd,WAJO;GACH,IAAM,IAAU,IAAI,IAAI,EAAQ,OAAO;GACvC,OAAO,EAAW,QAAQ,MAAM,EAAQ,IAAI,EAAE,OAAO,CAAC;EAC1D,EAAA,CAAG;EAGb,EAAkB,EAAQ,QAAQ;GAC9B,cAAc,EAAQ,gBAAgB,KAAK;GAC3C,eAAe;GACf,SAAS,EAAQ;GACjB;EACJ,CAAC;EAED,IAAM,IAAa,EAAQ,KAAK,MAC5B,KAAK,aAAa,GAAU,EAAE,MAAM,EAAE,SAAS,EAAE,YAAY,EAAE,IAAI,CACvE,GAEM,IAAkC,CAAC,EAAS,QAAQ,EAAS,KAAK,GAClE,IAAQ,KAAK,YAAY,GAAY,CAAI,GACzC,IAAQ,KAAK,YAAY,GAAY,CAAI;EAE/C,OADA,EAAM,MAAM,aAAa,GAClB,CACH,IAAI,EACA,GACA,GACA,GACA,KAAK,QACL,GACA,GACA,GACA,EAAM,MAAM,CAChB,CACJ;CACJ;CAEA,YAAoB,GAKlB;EACE,IAAM,CAAC,GAAI,KAAM,KAAK,YAChB,IAAQ,KAAK,UAAU,IAAI,CAAK;EACtC,OAAO;GACH,QAAQ,EAAgB,EAAM,MAAM;IAAC;IAAG;IAAG;IAAI;GAAE,CAAC;GAClD,OAAO,EAAM;GACb,SAAS,EAAM;GACf,QAAQ,EAAM;EAClB;CACJ;CAEA,cAAsB,GAGpB;EACE,IAAI,GACA;EACJ,KAAK,IAAM,KAAQ,KAAK,SAAS,aAAa;GAC1C,IAAM,IAAI,EAAQ;GACd,MAAM,KAAA,MACN,EAAE,KAAK,WAAW,KAAK,MAAc,KAAA,IACrC,IAAY,IACL,EAAE,KAAK,WAAW,KAAK,MAAe,KAAA,MAC7C,IAAa;EAErB;EACA,IAAI,MAAc,KAAA,KAAa,MAAe,KAAA,GAAW;GACrD,IAAM,IAAS,KAAK,SAAS,YAAY,KACpC,MAAM,GAAG,EAAE,IAAI,KAAK,UAAU,EAAQ,EAAE,EAAE,QAAQ,CAAC,CAAC,GACzD;GACA,MAAU,MACN,uDAAuD,EAAO,KAAK,IAAI,EAAE,GAC7E;EACJ;EACA,OAAO;GAAE;GAAW;EAAW;CACnC;CAEA,aACI,GACA,GACA,GACA,GACA,GACkB;EAClB,IAAM,CAAC,GAAI,GAAI,GAAI,KAAM,EAAK,UAAU,GAClC,IAAM,KAAK,IAAI,GAAG,CAAE,GACpB,IAAM,KAAK,IAAI,GAAG,CAAE,GACpB,IAAM,KAAK,IAAI,EAAS,OAAO,CAAE,GACjC,IAAM,KAAK,IAAI,EAAS,QAAQ,CAAE,GAEpC,GACA,IAAY;EAChB,IAAI,IAAM,KAAO,IAAM,KAAO,EAAK,KAAK,SAAS,GAAG;GAChD,IAAM,IAAQ,IAAM,GACd,IAAQ,IAAM,GACd,IAAK,KAAK,IAAI,EAAK,OAAO,CAAK,GAC/B,IAAK,KAAK,IAAI,EAAK,QAAQ,CAAK,GAChC,IAAU,IAAI,WAAW,IAAK,IAAK,CAAC;GAC1C,KAAK,IAAI,IAAM,GAAG,IAAM,GAAI,KAAO;IAC/B,IAAM,MAAiB,IAAM,KAAO,EAAS,QAAQ,KAAO,GACtD,IAAe,IAAM,IAAK,GAC1B,IAAgB,IAAM,EAAK;IACjC,KAAK,IAAI,IAAM,GAAG,IAAM,GAAI,KAExB,IADU,EAAK,KAAK,IAAgB,OAC1B,GAAG;KACT,IAAM,IAAI,IAAe,IAAM,GACzB,IAAI,IAAe,IAAM;KAG/B,AAFA,EAAQ,KAAK,EAAS,KAAK,IAC3B,EAAQ,IAAI,KAAK,EAAS,KAAK,IAAI,IACnC,EAAQ,IAAI,KAAK,EAAS,KAAK,IAAI;IACvC;GAER;GAEA,IADA,IAAiB,IAAI,EAAS,GAAS,GAAI,CAAE,GACzC,MAAO,EAAK,SAAS,MAAO,EAAK,QAAQ;IACzC,IAAM,IAAU,IAAI,WAAW,IAAK,CAAE;IACtC,KAAK,IAAI,IAAM,GAAG,IAAM,GAAI,KACxB,EAAQ,IACJ,EAAK,KAAK,SAAS,IAAM,EAAK,OAAO,IAAM,EAAK,QAAQ,CAAE,GAC1D,IAAM,CACV;IAEJ,IAAY,IAAI,EAAK,GAAS,GAAI,CAAE;GACxC;EACJ,OAEI,AADA,IAAY,IAAI,kBAAK,IAAI,WAAY,GAAG,GAAG,CAAC,GAC5C,IAAiB,IAAI,kBAAS,IAAI,WAAY,GAAG,GAAG,CAAC;EAGzD,IAAM,IAAY,KAAK,OAAO,MAAY,SAAS;EAEnD,OAAO;GACH;GACA;GACA;GACA;GACA,KAAK;GACL,MAAM;GACN,MAAM;GACN,KAAK;GACL,MAAM;GACN;EACJ;CACJ;CAEA,YACI,GACA,GACK;EACL,IAAM,IAAI,EAAW,QACf,IAAO,IAAI,aAAa,IAAI,CAAC,GAC7B,IAAM,IAAI,WAAW,CAAC,GACtB,IAAO,IAAI,aAAa,CAAC;EAC/B,KAAK,IAAI,IAAI,GAAG,IAAI,GAAG,KAAK;GACxB,IAAM,IAAI,EAAW;GAMrB,AALA,EAAK,IAAI,KAAK,EAAE,KAAK,IACrB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAI,KAAK,EAAE,SACX,EAAK,KAAK,EAAE;EAChB;EACA,OAAO,IAAI,EAAM,GAAM,GAAK,GAAM,CAAS;CAC/C;CAEA,YACI,GACA,GACK;EACL,IAAM,IAAO,IAAI,aAAa,EAAW,SAAS,CAAC;EACnD,KAAK,IAAI,IAAI,GAAG,IAAI,EAAW,QAAQ,KAAK;GACxC,IAAM,IAAI,EAAW;GAIrB,AAHA,EAAK,IAAI,KAAK,EAAE,KAAK,IACrB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK,IACzB,EAAK,IAAI,IAAI,KAAK,EAAE,KAAK;EAC7B;EACA,OAAO,IAAI,EACP,EAAW,KAAK,MAAM,EAAE,IAAI,GAC5B,GACA,CACJ;CACJ;AACJ"}

package/dist/vision/types.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"types.cjs","names":[],"sources":["../../src/vision/types.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Public output types returned by the SDK's vision tasks.\n *\n * These types form the contract between the SDK and its callers. They mirror\n * the Python `ort-vision-sdk` output dataclasses 1-to-1.\n *\n * Naming is intentionally compatible with the Ultralytics / torchvision idiom\n * (`cls`, `conf`, `box`, `xyxy`, `xywh`, normalized variants) so code ported\n * from those projects keeps working with minimal edits. The original verbose\n * names (`classId`, `className`, `confidence`, `bbox`) are still populated for\n * backwards compatibility.\n */\n\nimport { ImageLoadError } from \"./core/exceptions\";\n\n/**\n * HWC RGB uint8 image — the canonical image format used across the SDK.\n *\n * `data.length` must equal `width * height * 3`. The buffer is laid out row\n * by row, top-to-bottom, with each pixel as `[R, G, B]`.\n */\nexport class RGBImage {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height * 3) {\n            throw new ImageLoadError(\n                `RGBImage data length ${data.length} does not match width * height * 3 = ${\n                    width * height * 3\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Axis-aligned bounding box in absolute pixel coordinates (xyxy format).\n *\n * Coordinates refer to the original input image (before any internal resize),\n * so callers can map detections back onto their source image without any\n * additional bookkeeping.\n */\nexport class BoundingBox {\n    constructor(\n        public readonly x1: number,\n        public readonly y1: number,\n        public readonly x2: number,\n        public readonly y2: number,\n    ) {}\n\n    /** Box width in pixels (clamped to non-negative). */\n    get width(): number {\n        return Math.max(0, this.x2 - this.x1);\n    }\n\n    /** Box height in pixels (clamped to non-negative). */\n    get height(): number {\n        return Math.max(0, this.y2 - this.y1);\n    }\n\n    /** Box area in pixels squared. */\n    get area(): number {\n        return this.width * this.height;\n    }\n\n    /** The box as `[x1, y1, x2, y2]` in absolute pixels (Ultralytics-style). */\n    get xyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` with `(cx, cy)` at the center.\n     *\n     * Matches Ultralytics' `boxes.xywh` and YOLO's native head format. For the\n     * top-left `[x, y, w, h]` convention, use {@link asXywh}.\n     */\n    get xywh(): readonly [number, number, number, number] {\n        return [(this.x1 + this.x2) / 2, (this.y1 + this.y2) / 2, this.width, this.height];\n    }\n\n    /**\n     * The box as `[x1, y1, x2, y2]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xyxyn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        return [this.x1 / w, this.y1 / h, this.x2 / w, this.y2 / h];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xywhn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        const [cx, cy, bw, bh] = this.xywh;\n        return [cx / w, cy / h, bw / w, bh / h];\n    }\n\n    /** Returns `[x1, y1, x2, y2]`. */\n    asXyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * Returns `[x, y, width, height]` with `(x, y)` at the **top-left**.\n     *\n     * Note: this is the top-left convention. Ultralytics' `xywh` getter uses\n     * **center** coordinates — for that, read {@link xywh}.\n     */\n    asXywh(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.width, this.height];\n    }\n\n    /** Returns `[x1, y1, x2, y2]` truncated to integers, useful for slicing arrays. */\n    asIntXyxy(): readonly [number, number, number, number] {\n        return [Math.trunc(this.x1), Math.trunc(this.y1), Math.trunc(this.x2), Math.trunc(this.y2)];\n    }\n}\n\n/**\n * Probability assigned to a single class for a classification prediction.\n *\n * `cls` / `name` / `conf` are Ultralytics-style aliases populated alongside\n * the verbose `classId` / `className` / `probability` fields.\n */\nexport interface ClassProbability {\n    readonly classId: number;\n    readonly className: string;\n    readonly probability: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `probability` (Ultralytics-style). */\n    readonly conf: number;\n}\n\n/**\n * Output of an image classification inference.\n */\nexport interface ClassificationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** The original input image as an HWC RGB uint8 array. */\n    readonly image: RGBImage;\n    /**\n     * Probabilities per class, sorted in descending order. The first entry\n     * mirrors `classId`, `className`, and `confidence`. When `topK` was passed\n     * to `predict`, the array is truncated to that length.\n     */\n    readonly probabilities: readonly ClassProbability[];\n}\n\n/**\n * Single detected object produced by an object-detection model.\n */\nexport interface DetectionResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * The original image cropped to `bbox`, HWC RGB uint8. Empty boxes\n     * (zero area) yield a zero-sized `RGBImage`.\n     */\n    readonly croppedImage: RGBImage;\n}\n\n/**\n * Single-channel binary or grayscale mask, laid out row-major.\n *\n * `data.length` must equal `width * height`. For binary masks, values are\n * `0` (background) or `255` (foreground); soft masks may use the full\n * `[0, 255]` range.\n */\nexport class Mask {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height) {\n            throw new ImageLoadError(\n                `Mask data length ${data.length} does not match width * height = ${\n                    width * height\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Single segmented instance produced by an instance-segmentation model.\n *\n * Mirrors {@link DetectionResult} and adds the per-instance binary mask\n * plus a \"ready-to-display\" background-removed crop.\n */\nexport interface SegmentationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * Binary mask cropped to `bbox`. Values are `0` (background) or `255`\n     * (foreground). Empty boxes yield a zero-sized `Mask`.\n     */\n    readonly mask: Mask;\n    /**\n     * The original image cropped to `bbox` with background pixels (where\n     * `mask.data[i] === 0`) zeroed out. Empty boxes yield a zero-sized\n     * `RGBImage`.\n     */\n    readonly segmentedImage: RGBImage;\n}\n"],"mappings":"yCAsBA,IAAa,EAAb,KAAsB,CAEE,KACA,MACA,OAHpB,YACI,EACA,EACA,EACF,CACE,GAJgB,KAAA,KAAA,EACA,KAAA,MAAA,EACA,KAAA,OAAA,EAEZ,EAAK,SAAW,EAAQ,EAAS,EACjC,MAAM,IAAI,EAAA,eACN,wBAAwB,EAAK,OAAO,uCAChC,EAAQ,EAAS,EACpB,EACL,CAER,CACJ,EASa,EAAb,KAAyB,CAED,GACA,GACA,GACA,GAJpB,YACI,EACA,EACA,EACA,EACF,CAJkB,KAAA,GAAA,EACA,KAAA,GAAA,EACA,KAAA,GAAA,EACA,KAAA,GAAA,CACjB,CAGH,IAAI,OAAgB,CAChB,OAAO,KAAK,IAAI,EAAG,KAAK,GAAK,KAAK,EAAE,CACxC,CAGA,IAAI,QAAiB,CACjB,OAAO,KAAK,IAAI,EAAG,KAAK,GAAK,KAAK,EAAE,CACxC,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAQ,KAAK,MAC7B,CAGA,IAAI,MAAkD,CAClD,MAAO,CAAC,KAAK,GAAI,KAAK,GAAI,KAAK,GAAI,KAAK,EAAE,CAC9C,CAQA,IAAI,MAAkD,CAClD,MAAO,EAAE,KAAK,GAAK,KAAK,IAAM,GAAI,KAAK,GAAK,KAAK,IAAM,EAAG,KAAK,MAAO,KAAK,MAAM,CACrF,CAOA,MAAM,EAAiF,CACnF,GAAM,CAAC,EAAG,GAAK,EAEf,OADI,GAAK,GAAK,GAAK,EAAU,CAAC,EAAG,EAAG,EAAG,CAAC,EACjC,CAAC,KAAK,GAAK,EAAG,KAAK,GAAK,EAAG,KAAK,GAAK,EAAG,KAAK,GAAK,CAAC,CAC9D,CAOA,MAAM,EAAiF,CACnF,GAAM,CAAC,EAAG,GAAK,EACf,GAAI,GAAK,GAAK,GAAK,EAAG,MAAO,CAAC,EAAG,EAAG,EAAG,CAAC,EACxC,GAAM,CAAC,EAAI,EAAI,EAAI,GAAM,KAAK,KAC9B,MAAO,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,EAAG,EAAK,CAAC,CAC1C,CAGA,QAAoD,CAChD,MAAO,CAAC,KAAK,GAAI,KAAK,GAAI,KAAK,GAAI,KAAK,EAAE,CAC9C,CAQA,QAAoD,CAChD,MAAO,CAAC,KAAK,GAAI,KAAK,GAAI,KAAK,MAAO,KAAK,MAAM,CACrD,CAGA,WAAuD,CACnD,MAAO,CAAC,KAAK,MAAM,KAAK,EAAE,EAAG,KAAK,MAAM,KAAK,EAAE,EAAG,KAAK,MAAM,KAAK,EAAE,EAAG,KAAK,MAAM,KAAK,EAAE,CAAC,CAC9F,CACJ,EAyEa,EAAb,KAAkB,CAEM,KACA,MACA,OAHpB,YACI,EACA,EACA,EACF,CACE,GAJgB,KAAA,KAAA,EACA,KAAA,MAAA,EACA,KAAA,OAAA,EAEZ,EAAK,SAAW,EAAQ,EACxB,MAAM,IAAI,EAAA,eACN,oBAAoB,EAAK,OAAO,mCAC5B,EAAQ,EACX,EACL,CAER,CACJ"}
+{"version":3,"file":"types.cjs","names":[],"sources":["../../src/vision/types.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Public output types returned by the SDK's vision tasks.\n *\n * These types form the contract between the SDK and its callers. They mirror\n * the Python `ort-vision-sdk` output dataclasses 1-to-1.\n *\n * Naming is intentionally compatible with the Ultralytics / torchvision idiom\n * (`cls`, `conf`, `box`, `xyxy`, `xywh`, normalized variants) so code ported\n * from those projects keeps working with minimal edits. The original verbose\n * names (`classId`, `className`, `confidence`, `bbox`) are still populated for\n * backwards compatibility.\n */\n\nimport { ImageLoadError } from \"./core/exceptions\";\n\n/**\n * HWC RGB uint8 image — the canonical image format used across the SDK.\n *\n * `data.length` must equal `width * height * 3`. The buffer is laid out row\n * by row, top-to-bottom, with each pixel as `[R, G, B]`.\n */\nexport class RGBImage {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height * 3) {\n            throw new ImageLoadError(\n                `RGBImage data length ${data.length} does not match width * height * 3 = ${\n                    width * height * 3\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Axis-aligned bounding box in absolute pixel coordinates (xyxy format).\n *\n * Coordinates refer to the original input image (before any internal resize),\n * so callers can map detections back onto their source image without any\n * additional bookkeeping.\n */\nexport class BoundingBox {\n    constructor(\n        public readonly x1: number,\n        public readonly y1: number,\n        public readonly x2: number,\n        public readonly y2: number,\n    ) {}\n\n    /** Box width in pixels (clamped to non-negative). */\n    get width(): number {\n        return Math.max(0, this.x2 - this.x1);\n    }\n\n    /** Box height in pixels (clamped to non-negative). */\n    get height(): number {\n        return Math.max(0, this.y2 - this.y1);\n    }\n\n    /** Box area in pixels squared. */\n    get area(): number {\n        return this.width * this.height;\n    }\n\n    /** The box as `[x1, y1, x2, y2]` in absolute pixels (Ultralytics-style). */\n    get xyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` with `(cx, cy)` at the center.\n     *\n     * Matches Ultralytics' `boxes.xywh` and YOLO's native head format. For the\n     * top-left `[x, y, w, h]` convention, use {@link asXywh}.\n     */\n    get xywh(): readonly [number, number, number, number] {\n        return [(this.x1 + this.x2) / 2, (this.y1 + this.y2) / 2, this.width, this.height];\n    }\n\n    /**\n     * The box as `[x1, y1, x2, y2]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xyxyn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        return [this.x1 / w, this.y1 / h, this.x2 / w, this.y2 / h];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xywhn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        const [cx, cy, bw, bh] = this.xywh;\n        return [cx / w, cy / h, bw / w, bh / h];\n    }\n\n    /** Returns `[x1, y1, x2, y2]`. */\n    asXyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * Returns `[x, y, width, height]` with `(x, y)` at the **top-left**.\n     *\n     * Note: this is the top-left convention. Ultralytics' `xywh` getter uses\n     * **center** coordinates — for that, read {@link xywh}.\n     */\n    asXywh(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.width, this.height];\n    }\n\n    /** Returns `[x1, y1, x2, y2]` truncated to integers, useful for slicing arrays. */\n    asIntXyxy(): readonly [number, number, number, number] {\n        return [Math.trunc(this.x1), Math.trunc(this.y1), Math.trunc(this.x2), Math.trunc(this.y2)];\n    }\n}\n\n/**\n * Probability assigned to a single class for a classification prediction.\n *\n * `cls` / `name` / `conf` are Ultralytics-style aliases populated alongside\n * the verbose `classId` / `className` / `probability` fields.\n */\nexport interface ClassProbability {\n    readonly classId: number;\n    readonly className: string;\n    readonly probability: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `probability` (Ultralytics-style). */\n    readonly conf: number;\n}\n\n/**\n * Output of an image classification inference.\n */\nexport interface ClassificationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** The original input image as an HWC RGB uint8 array. */\n    readonly image: RGBImage;\n    /**\n     * Probabilities per class, sorted in descending order. The first entry\n     * mirrors `classId`, `className`, and `confidence`. When `topK` was passed\n     * to `predict`, the array is truncated to that length.\n     */\n    readonly probabilities: readonly ClassProbability[];\n}\n\n/**\n * Single detected object produced by an object-detection model.\n */\nexport interface DetectionResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * The original image cropped to `bbox`, HWC RGB uint8. Empty boxes\n     * (zero area) yield a zero-sized `RGBImage`.\n     */\n    readonly croppedImage: RGBImage;\n    /**\n     * What a second, classification stage predicted **for this crop** —\n     * populated only by {@link DetectClassify}, and `null` for a plain detector.\n     *\n     * Kept as its own field rather than folded into `classId`/`className`\n     * because the two answers are different questions: the detector says *what\n     * kind of object this is*, the classifier says *which sub-category the object\n     * belongs to*, and collapsing them would lose one of the two.\n     */\n    readonly classification?: ClassificationResult | null;\n}\n\n/**\n * Single-channel binary or grayscale mask, laid out row-major.\n *\n * `data.length` must equal `width * height`. For binary masks, values are\n * `0` (background) or `255` (foreground); soft masks may use the full\n * `[0, 255]` range.\n */\nexport class Mask {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height) {\n            throw new ImageLoadError(\n                `Mask data length ${data.length} does not match width * height = ${\n                    width * height\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Single segmented instance produced by an instance-segmentation model.\n *\n * Mirrors {@link DetectionResult} and adds the per-instance binary mask\n * plus a \"ready-to-display\" background-removed crop.\n */\nexport interface SegmentationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * Binary mask cropped to `bbox`. Values are `0` (background) or `255`\n     * (foreground). Empty boxes yield a zero-sized `Mask`.\n     */\n    readonly mask: Mask;\n    /**\n     * The original image cropped to `bbox` with background pixels (where\n     * `mask.data[i] === 0`) zeroed out. Empty boxes yield a zero-sized\n     * `RGBImage`.\n     */\n    readonly segmentedImage: RGBImage;\n}\n"],"mappings":"yCAsBA,IAAa,EAAb,KAAsB,CAEE,KACA,MACA,OAHpB,YACI,EACA,EACA,EACF,CACE,GAJgB,KAAA,KAAA,EACA,KAAA,MAAA,EACA,KAAA,OAAA,EAEZ,EAAK,SAAW,EAAQ,EAAS,EACjC,MAAM,IAAI,EAAA,eACN,wBAAwB,EAAK,OAAO,uCAChC,EAAQ,EAAS,EACpB,EACL,CAER,CACJ,EASa,EAAb,KAAyB,CAED,GACA,GACA,GACA,GAJpB,YACI,EACA,EACA,EACA,EACF,CAJkB,KAAA,GAAA,EACA,KAAA,GAAA,EACA,KAAA,GAAA,EACA,KAAA,GAAA,CACjB,CAGH,IAAI,OAAgB,CAChB,OAAO,KAAK,IAAI,EAAG,KAAK,GAAK,KAAK,EAAE,CACxC,CAGA,IAAI,QAAiB,CACjB,OAAO,KAAK,IAAI,EAAG,KAAK,GAAK,KAAK,EAAE,CACxC,CAGA,IAAI,MAAe,CACf,OAAO,KAAK,MAAQ,KAAK,MAC7B,CAGA,IAAI,MAAkD,CAClD,MAAO,CAAC,KAAK,GAAI,KAAK,GAAI,KAAK,GAAI,KAAK,EAAE,CAC9C,CAQA,IAAI,MAAkD,CAClD,MAAO,EAAE,KAAK,GAAK,KAAK,IAAM,GAAI,KAAK,GAAK,KAAK,IAAM,EAAG,KAAK,MAAO,KAAK,MAAM,CACrF,CAOA,MAAM,EAAiF,CACnF,GAAM,CAAC,EAAG,GAAK,EAEf,OADI,GAAK,GAAK,GAAK,EAAU,CAAC,EAAG,EAAG,EAAG,CAAC,EACjC,CAAC,KAAK,GAAK,EAAG,KAAK,GAAK,EAAG,KAAK,GAAK,EAAG,KAAK,GAAK,CAAC,CAC9D,CAOA,MAAM,EAAiF,CACnF,GAAM,CAAC,EAAG,GAAK,EACf,GAAI,GAAK,GAAK,GAAK,EAAG,MAAO,CAAC,EAAG,EAAG,EAAG,CAAC,EACxC,GAAM,CAAC,EAAI,EAAI,EAAI,GAAM,KAAK,KAC9B,MAAO,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,EAAG,EAAK,CAAC,CAC1C,CAGA,QAAoD,CAChD,MAAO,CAAC,KAAK,GAAI,KAAK,GAAI,KAAK,GAAI,KAAK,EAAE,CAC9C,CAQA,QAAoD,CAChD,MAAO,CAAC,KAAK,GAAI,KAAK,GAAI,KAAK,MAAO,KAAK,MAAM,CACrD,CAGA,WAAuD,CACnD,MAAO,CAAC,KAAK,MAAM,KAAK,EAAE,EAAG,KAAK,MAAM,KAAK,EAAE,EAAG,KAAK,MAAM,KAAK,EAAE,EAAG,KAAK,MAAM,KAAK,EAAE,CAAC,CAC9F,CACJ,EAmFa,EAAb,KAAkB,CAEM,KACA,MACA,OAHpB,YACI,EACA,EACA,EACF,CACE,GAJgB,KAAA,KAAA,EACA,KAAA,MAAA,EACA,KAAA,OAAA,EAEZ,EAAK,SAAW,EAAQ,EACxB,MAAM,IAAI,EAAA,eACN,oBAAoB,EAAK,OAAO,mCAC5B,EAAQ,EACX,EACL,CAER,CACJ"}

package/dist/vision/types.js.map

@@ -1 +1 @@
-{"version":3,"file":"types.js","names":[],"sources":["../../src/vision/types.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Public output types returned by the SDK's vision tasks.\n *\n * These types form the contract between the SDK and its callers. They mirror\n * the Python `ort-vision-sdk` output dataclasses 1-to-1.\n *\n * Naming is intentionally compatible with the Ultralytics / torchvision idiom\n * (`cls`, `conf`, `box`, `xyxy`, `xywh`, normalized variants) so code ported\n * from those projects keeps working with minimal edits. The original verbose\n * names (`classId`, `className`, `confidence`, `bbox`) are still populated for\n * backwards compatibility.\n */\n\nimport { ImageLoadError } from \"./core/exceptions\";\n\n/**\n * HWC RGB uint8 image — the canonical image format used across the SDK.\n *\n * `data.length` must equal `width * height * 3`. The buffer is laid out row\n * by row, top-to-bottom, with each pixel as `[R, G, B]`.\n */\nexport class RGBImage {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height * 3) {\n            throw new ImageLoadError(\n                `RGBImage data length ${data.length} does not match width * height * 3 = ${\n                    width * height * 3\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Axis-aligned bounding box in absolute pixel coordinates (xyxy format).\n *\n * Coordinates refer to the original input image (before any internal resize),\n * so callers can map detections back onto their source image without any\n * additional bookkeeping.\n */\nexport class BoundingBox {\n    constructor(\n        public readonly x1: number,\n        public readonly y1: number,\n        public readonly x2: number,\n        public readonly y2: number,\n    ) {}\n\n    /** Box width in pixels (clamped to non-negative). */\n    get width(): number {\n        return Math.max(0, this.x2 - this.x1);\n    }\n\n    /** Box height in pixels (clamped to non-negative). */\n    get height(): number {\n        return Math.max(0, this.y2 - this.y1);\n    }\n\n    /** Box area in pixels squared. */\n    get area(): number {\n        return this.width * this.height;\n    }\n\n    /** The box as `[x1, y1, x2, y2]` in absolute pixels (Ultralytics-style). */\n    get xyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` with `(cx, cy)` at the center.\n     *\n     * Matches Ultralytics' `boxes.xywh` and YOLO's native head format. For the\n     * top-left `[x, y, w, h]` convention, use {@link asXywh}.\n     */\n    get xywh(): readonly [number, number, number, number] {\n        return [(this.x1 + this.x2) / 2, (this.y1 + this.y2) / 2, this.width, this.height];\n    }\n\n    /**\n     * The box as `[x1, y1, x2, y2]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xyxyn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        return [this.x1 / w, this.y1 / h, this.x2 / w, this.y2 / h];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xywhn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        const [cx, cy, bw, bh] = this.xywh;\n        return [cx / w, cy / h, bw / w, bh / h];\n    }\n\n    /** Returns `[x1, y1, x2, y2]`. */\n    asXyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * Returns `[x, y, width, height]` with `(x, y)` at the **top-left**.\n     *\n     * Note: this is the top-left convention. Ultralytics' `xywh` getter uses\n     * **center** coordinates — for that, read {@link xywh}.\n     */\n    asXywh(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.width, this.height];\n    }\n\n    /** Returns `[x1, y1, x2, y2]` truncated to integers, useful for slicing arrays. */\n    asIntXyxy(): readonly [number, number, number, number] {\n        return [Math.trunc(this.x1), Math.trunc(this.y1), Math.trunc(this.x2), Math.trunc(this.y2)];\n    }\n}\n\n/**\n * Probability assigned to a single class for a classification prediction.\n *\n * `cls` / `name` / `conf` are Ultralytics-style aliases populated alongside\n * the verbose `classId` / `className` / `probability` fields.\n */\nexport interface ClassProbability {\n    readonly classId: number;\n    readonly className: string;\n    readonly probability: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `probability` (Ultralytics-style). */\n    readonly conf: number;\n}\n\n/**\n * Output of an image classification inference.\n */\nexport interface ClassificationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** The original input image as an HWC RGB uint8 array. */\n    readonly image: RGBImage;\n    /**\n     * Probabilities per class, sorted in descending order. The first entry\n     * mirrors `classId`, `className`, and `confidence`. When `topK` was passed\n     * to `predict`, the array is truncated to that length.\n     */\n    readonly probabilities: readonly ClassProbability[];\n}\n\n/**\n * Single detected object produced by an object-detection model.\n */\nexport interface DetectionResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * The original image cropped to `bbox`, HWC RGB uint8. Empty boxes\n     * (zero area) yield a zero-sized `RGBImage`.\n     */\n    readonly croppedImage: RGBImage;\n}\n\n/**\n * Single-channel binary or grayscale mask, laid out row-major.\n *\n * `data.length` must equal `width * height`. For binary masks, values are\n * `0` (background) or `255` (foreground); soft masks may use the full\n * `[0, 255]` range.\n */\nexport class Mask {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height) {\n            throw new ImageLoadError(\n                `Mask data length ${data.length} does not match width * height = ${\n                    width * height\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Single segmented instance produced by an instance-segmentation model.\n *\n * Mirrors {@link DetectionResult} and adds the per-instance binary mask\n * plus a \"ready-to-display\" background-removed crop.\n */\nexport interface SegmentationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * Binary mask cropped to `bbox`. Values are `0` (background) or `255`\n     * (foreground). Empty boxes yield a zero-sized `Mask`.\n     */\n    readonly mask: Mask;\n    /**\n     * The original image cropped to `bbox` with background pixels (where\n     * `mask.data[i] === 0`) zeroed out. Empty boxes yield a zero-sized\n     * `RGBImage`.\n     */\n    readonly segmentedImage: RGBImage;\n}\n"],"mappings":";;AAsBA,IAAa,IAAb,MAAsB;CAEE;CACA;CACA;CAHpB,YACI,GACA,GACA,GACF;EACE,IAJgB,KAAA,OAAA,GACA,KAAA,QAAA,GACA,KAAA,SAAA,GAEZ,EAAK,WAAW,IAAQ,IAAS,GACjC,MAAM,IAAI,EACN,wBAAwB,EAAK,OAAO,uCAChC,IAAQ,IAAS,EACpB,EACL;CAER;AACJ,GASa,IAAb,MAAyB;CAED;CACA;CACA;CACA;CAJpB,YACI,GACA,GACA,GACA,GACF;EADkB,AAHA,KAAA,KAAA,GACA,KAAA,KAAA,GACA,KAAA,KAAA,GACA,KAAA,KAAA;CACjB;CAGH,IAAI,QAAgB;EAChB,OAAO,KAAK,IAAI,GAAG,KAAK,KAAK,KAAK,EAAE;CACxC;CAGA,IAAI,SAAiB;EACjB,OAAO,KAAK,IAAI,GAAG,KAAK,KAAK,KAAK,EAAE;CACxC;CAGA,IAAI,OAAe;EACf,OAAO,KAAK,QAAQ,KAAK;CAC7B;CAGA,IAAI,OAAkD;EAClD,OAAO;GAAC,KAAK;GAAI,KAAK;GAAI,KAAK;GAAI,KAAK;EAAE;CAC9C;CAQA,IAAI,OAAkD;EAClD,OAAO;IAAE,KAAK,KAAK,KAAK,MAAM;IAAI,KAAK,KAAK,KAAK,MAAM;GAAG,KAAK;GAAO,KAAK;EAAM;CACrF;CAOA,MAAM,GAAiF;EACnF,IAAM,CAAC,GAAG,KAAK;EAEf,OADI,KAAK,KAAK,KAAK,IAAU;GAAC;GAAG;GAAG;GAAG;EAAC,IACjC;GAAC,KAAK,KAAK;GAAG,KAAK,KAAK;GAAG,KAAK,KAAK;GAAG,KAAK,KAAK;EAAC;CAC9D;CAOA,MAAM,GAAiF;EACnF,IAAM,CAAC,GAAG,KAAK;EACf,IAAI,KAAK,KAAK,KAAK,GAAG,OAAO;GAAC;GAAG;GAAG;GAAG;EAAC;EACxC,IAAM,CAAC,GAAI,GAAI,GAAI,KAAM,KAAK;EAC9B,OAAO;GAAC,IAAK;GAAG,IAAK;GAAG,IAAK;GAAG,IAAK;EAAC;CAC1C;CAGA,SAAoD;EAChD,OAAO;GAAC,KAAK;GAAI,KAAK;GAAI,KAAK;GAAI,KAAK;EAAE;CAC9C;CAQA,SAAoD;EAChD,OAAO;GAAC,KAAK;GAAI,KAAK;GAAI,KAAK;GAAO,KAAK;EAAM;CACrD;CAGA,YAAuD;EACnD,OAAO;GAAC,KAAK,MAAM,KAAK,EAAE;GAAG,KAAK,MAAM,KAAK,EAAE;GAAG,KAAK,MAAM,KAAK,EAAE;GAAG,KAAK,MAAM,KAAK,EAAE;EAAC;CAC9F;AACJ,GAyEa,IAAb,MAAkB;CAEM;CACA;CACA;CAHpB,YACI,GACA,GACA,GACF;EACE,IAJgB,KAAA,OAAA,GACA,KAAA,QAAA,GACA,KAAA,SAAA,GAEZ,EAAK,WAAW,IAAQ,GACxB,MAAM,IAAI,EACN,oBAAoB,EAAK,OAAO,mCAC5B,IAAQ,EACX,EACL;CAER;AACJ"}
+{"version":3,"file":"types.js","names":[],"sources":["../../src/vision/types.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Public output types returned by the SDK's vision tasks.\n *\n * These types form the contract between the SDK and its callers. They mirror\n * the Python `ort-vision-sdk` output dataclasses 1-to-1.\n *\n * Naming is intentionally compatible with the Ultralytics / torchvision idiom\n * (`cls`, `conf`, `box`, `xyxy`, `xywh`, normalized variants) so code ported\n * from those projects keeps working with minimal edits. The original verbose\n * names (`classId`, `className`, `confidence`, `bbox`) are still populated for\n * backwards compatibility.\n */\n\nimport { ImageLoadError } from \"./core/exceptions\";\n\n/**\n * HWC RGB uint8 image — the canonical image format used across the SDK.\n *\n * `data.length` must equal `width * height * 3`. The buffer is laid out row\n * by row, top-to-bottom, with each pixel as `[R, G, B]`.\n */\nexport class RGBImage {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height * 3) {\n            throw new ImageLoadError(\n                `RGBImage data length ${data.length} does not match width * height * 3 = ${\n                    width * height * 3\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Axis-aligned bounding box in absolute pixel coordinates (xyxy format).\n *\n * Coordinates refer to the original input image (before any internal resize),\n * so callers can map detections back onto their source image without any\n * additional bookkeeping.\n */\nexport class BoundingBox {\n    constructor(\n        public readonly x1: number,\n        public readonly y1: number,\n        public readonly x2: number,\n        public readonly y2: number,\n    ) {}\n\n    /** Box width in pixels (clamped to non-negative). */\n    get width(): number {\n        return Math.max(0, this.x2 - this.x1);\n    }\n\n    /** Box height in pixels (clamped to non-negative). */\n    get height(): number {\n        return Math.max(0, this.y2 - this.y1);\n    }\n\n    /** Box area in pixels squared. */\n    get area(): number {\n        return this.width * this.height;\n    }\n\n    /** The box as `[x1, y1, x2, y2]` in absolute pixels (Ultralytics-style). */\n    get xyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` with `(cx, cy)` at the center.\n     *\n     * Matches Ultralytics' `boxes.xywh` and YOLO's native head format. For the\n     * top-left `[x, y, w, h]` convention, use {@link asXywh}.\n     */\n    get xywh(): readonly [number, number, number, number] {\n        return [(this.x1 + this.x2) / 2, (this.y1 + this.y2) / 2, this.width, this.height];\n    }\n\n    /**\n     * The box as `[x1, y1, x2, y2]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xyxyn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        return [this.x1 / w, this.y1 / h, this.x2 / w, this.y2 / h];\n    }\n\n    /**\n     * The box as `[cx, cy, w, h]` normalized to `[0, 1]`.\n     *\n     * @param origShape `[height, width]` of the source image, in pixels.\n     */\n    xywhn(origShape: readonly [number, number]): readonly [number, number, number, number] {\n        const [h, w] = origShape;\n        if (w <= 0 || h <= 0) return [0, 0, 0, 0];\n        const [cx, cy, bw, bh] = this.xywh;\n        return [cx / w, cy / h, bw / w, bh / h];\n    }\n\n    /** Returns `[x1, y1, x2, y2]`. */\n    asXyxy(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.x2, this.y2];\n    }\n\n    /**\n     * Returns `[x, y, width, height]` with `(x, y)` at the **top-left**.\n     *\n     * Note: this is the top-left convention. Ultralytics' `xywh` getter uses\n     * **center** coordinates — for that, read {@link xywh}.\n     */\n    asXywh(): readonly [number, number, number, number] {\n        return [this.x1, this.y1, this.width, this.height];\n    }\n\n    /** Returns `[x1, y1, x2, y2]` truncated to integers, useful for slicing arrays. */\n    asIntXyxy(): readonly [number, number, number, number] {\n        return [Math.trunc(this.x1), Math.trunc(this.y1), Math.trunc(this.x2), Math.trunc(this.y2)];\n    }\n}\n\n/**\n * Probability assigned to a single class for a classification prediction.\n *\n * `cls` / `name` / `conf` are Ultralytics-style aliases populated alongside\n * the verbose `classId` / `className` / `probability` fields.\n */\nexport interface ClassProbability {\n    readonly classId: number;\n    readonly className: string;\n    readonly probability: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `probability` (Ultralytics-style). */\n    readonly conf: number;\n}\n\n/**\n * Output of an image classification inference.\n */\nexport interface ClassificationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** The original input image as an HWC RGB uint8 array. */\n    readonly image: RGBImage;\n    /**\n     * Probabilities per class, sorted in descending order. The first entry\n     * mirrors `classId`, `className`, and `confidence`. When `topK` was passed\n     * to `predict`, the array is truncated to that length.\n     */\n    readonly probabilities: readonly ClassProbability[];\n}\n\n/**\n * Single detected object produced by an object-detection model.\n */\nexport interface DetectionResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * The original image cropped to `bbox`, HWC RGB uint8. Empty boxes\n     * (zero area) yield a zero-sized `RGBImage`.\n     */\n    readonly croppedImage: RGBImage;\n    /**\n     * What a second, classification stage predicted **for this crop** —\n     * populated only by {@link DetectClassify}, and `null` for a plain detector.\n     *\n     * Kept as its own field rather than folded into `classId`/`className`\n     * because the two answers are different questions: the detector says *what\n     * kind of object this is*, the classifier says *which sub-category the object\n     * belongs to*, and collapsing them would lose one of the two.\n     */\n    readonly classification?: ClassificationResult | null;\n}\n\n/**\n * Single-channel binary or grayscale mask, laid out row-major.\n *\n * `data.length` must equal `width * height`. For binary masks, values are\n * `0` (background) or `255` (foreground); soft masks may use the full\n * `[0, 255]` range.\n */\nexport class Mask {\n    constructor(\n        public readonly data: Uint8Array,\n        public readonly width: number,\n        public readonly height: number,\n    ) {\n        if (data.length !== width * height) {\n            throw new ImageLoadError(\n                `Mask data length ${data.length} does not match width * height = ${\n                    width * height\n                }.`,\n            );\n        }\n    }\n}\n\n/**\n * Single segmented instance produced by an instance-segmentation model.\n *\n * Mirrors {@link DetectionResult} and adds the per-instance binary mask\n * plus a \"ready-to-display\" background-removed crop.\n */\nexport interface SegmentationResult {\n    readonly classId: number;\n    readonly className: string;\n    readonly confidence: number;\n    readonly bbox: BoundingBox;\n    /** Alias for `classId` (Ultralytics-style). */\n    readonly cls: number;\n    /** Alias for `className`. */\n    readonly name: string;\n    /** Alias for `confidence` (Ultralytics-style). */\n    readonly conf: number;\n    /** Alias for `bbox` (Ultralytics-style). */\n    readonly box: BoundingBox;\n    /**\n     * Binary mask cropped to `bbox`. Values are `0` (background) or `255`\n     * (foreground). Empty boxes yield a zero-sized `Mask`.\n     */\n    readonly mask: Mask;\n    /**\n     * The original image cropped to `bbox` with background pixels (where\n     * `mask.data[i] === 0`) zeroed out. Empty boxes yield a zero-sized\n     * `RGBImage`.\n     */\n    readonly segmentedImage: RGBImage;\n}\n"],"mappings":";;AAsBA,IAAa,IAAb,MAAsB;CAEE;CACA;CACA;CAHpB,YACI,GACA,GACA,GACF;EACE,IAJgB,KAAA,OAAA,GACA,KAAA,QAAA,GACA,KAAA,SAAA,GAEZ,EAAK,WAAW,IAAQ,IAAS,GACjC,MAAM,IAAI,EACN,wBAAwB,EAAK,OAAO,uCAChC,IAAQ,IAAS,EACpB,EACL;CAER;AACJ,GASa,IAAb,MAAyB;CAED;CACA;CACA;CACA;CAJpB,YACI,GACA,GACA,GACA,GACF;EADkB,AAHA,KAAA,KAAA,GACA,KAAA,KAAA,GACA,KAAA,KAAA,GACA,KAAA,KAAA;CACjB;CAGH,IAAI,QAAgB;EAChB,OAAO,KAAK,IAAI,GAAG,KAAK,KAAK,KAAK,EAAE;CACxC;CAGA,IAAI,SAAiB;EACjB,OAAO,KAAK,IAAI,GAAG,KAAK,KAAK,KAAK,EAAE;CACxC;CAGA,IAAI,OAAe;EACf,OAAO,KAAK,QAAQ,KAAK;CAC7B;CAGA,IAAI,OAAkD;EAClD,OAAO;GAAC,KAAK;GAAI,KAAK;GAAI,KAAK;GAAI,KAAK;EAAE;CAC9C;CAQA,IAAI,OAAkD;EAClD,OAAO;IAAE,KAAK,KAAK,KAAK,MAAM;IAAI,KAAK,KAAK,KAAK,MAAM;GAAG,KAAK;GAAO,KAAK;EAAM;CACrF;CAOA,MAAM,GAAiF;EACnF,IAAM,CAAC,GAAG,KAAK;EAEf,OADI,KAAK,KAAK,KAAK,IAAU;GAAC;GAAG;GAAG;GAAG;EAAC,IACjC;GAAC,KAAK,KAAK;GAAG,KAAK,KAAK;GAAG,KAAK,KAAK;GAAG,KAAK,KAAK;EAAC;CAC9D;CAOA,MAAM,GAAiF;EACnF,IAAM,CAAC,GAAG,KAAK;EACf,IAAI,KAAK,KAAK,KAAK,GAAG,OAAO;GAAC;GAAG;GAAG;GAAG;EAAC;EACxC,IAAM,CAAC,GAAI,GAAI,GAAI,KAAM,KAAK;EAC9B,OAAO;GAAC,IAAK;GAAG,IAAK;GAAG,IAAK;GAAG,IAAK;EAAC;CAC1C;CAGA,SAAoD;EAChD,OAAO;GAAC,KAAK;GAAI,KAAK;GAAI,KAAK;GAAI,KAAK;EAAE;CAC9C;CAQA,SAAoD;EAChD,OAAO;GAAC,KAAK;GAAI,KAAK;GAAI,KAAK;GAAO,KAAK;EAAM;CACrD;CAGA,YAAuD;EACnD,OAAO;GAAC,KAAK,MAAM,KAAK,EAAE;GAAG,KAAK,MAAM,KAAK,EAAE;GAAG,KAAK,MAAM,KAAK,EAAE;GAAG,KAAK,MAAM,KAAK,EAAE;EAAC;CAC9F;AACJ,GAmFa,IAAb,MAAkB;CAEM;CACA;CACA;CAHpB,YACI,GACA,GACA,GACF;EACE,IAJgB,KAAA,OAAA,GACA,KAAA,QAAA,GACA,KAAA,SAAA,GAEZ,EAAK,WAAW,IAAQ,GACxB,MAAM,IAAI,EACN,oBAAoB,EAAK,OAAO,mCAC5B,IAAQ,EACX,EACL;CAER;AACJ"}

package/dist/vision/use-camera-stream.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"use-camera-stream.cjs","names":[],"sources":["../../src/vision/use-camera-stream.ts"],"sourcesContent":["import { useEffect, useRef, useState, type RefObject } from \"react\";\n\nimport {\n    classifyMediaError,\n    missingCaptureApiError,\n    type MediaAccessError,\n} from \"@/audio/media-access\";\n\n/** Lifecycle status of the camera stream. */\nexport type CameraStreamStatus = \"idle\" | \"loading\" | \"ready\" | \"error\";\n\n/** Classified reason a camera stream could not be acquired. */\nexport type CameraStreamErrorKind =\n    \"unsupported\" | \"permission-denied\" | \"no-camera\" | \"in-use\" | \"insecure\" | \"unknown\";\n\n/** A classified camera error with a human-readable, English message. */\nexport interface CameraStreamError {\n    kind: CameraStreamErrorKind;\n    message: string;\n}\n\n/** Options for {@link useCameraStream}. */\nexport interface UseCameraStreamOptions {\n    /**\n     * Constraints passed to `getUserMedia`. Defaults to the rear\n     * (\"environment\") camera at Full-HD ideal resolution with audio off.\n     * Read when the stream (re)starts — change it and call `retry()` to apply.\n     */\n    constraints?: MediaStreamConstraints;\n    /**\n     * Hold off acquiring the camera until this is `true`. Default `true`.\n     *\n     * The point is to be able to *not* prompt. A permission prompt costs the user a\n     * decision and, if they refuse, costs the app the feature permanently — so a\n     * surface that already knows it cannot do its job (a barcode scanner in a browser\n     * with no decoder) must not open the camera to then say so. Flipping this to `false`\n     * also releases a stream that is already live.\n     */\n    enabled?: boolean;\n}\n\n/** Value returned by {@link useCameraStream}. */\nexport interface UseCameraStreamApi {\n    /** Current lifecycle status. */\n    status: CameraStreamStatus;\n    /** The classified error, or `null` while not in the `error` status. */\n    error: CameraStreamError | null;\n    /** Attach to a `<video ref={…} />`. The stream is wired to it once ready. */\n    videoRef: RefObject<HTMLVideoElement | null>;\n    /**\n     * The live stream, or `null`.\n     *\n     * Exposed for the things that need the **track** rather than the picture — the LED\n     * torch (`useTorch`), the real frame size from `getSettings()`, recording it with\n     * `useVideoRecorder`. Do not stop it yourself: the hook owns its lifetime and\n     * releases it on unmount and on `retry()`.\n     */\n    stream: MediaStream | null;\n    /** Manually re-attempt after an error (e.g. the user changed permissions). */\n    retry: () => void;\n}\n\n/** Rear-camera Full-HD defaults used when no `constraints` are supplied. */\nconst DEFAULT_CONSTRAINTS: MediaStreamConstraints = {\n    video: {\n        facingMode: { ideal: \"environment\" },\n        width: { ideal: 1920 },\n        height: { ideal: 1080 },\n    },\n    audio: false,\n};\n\n/**\n * Re-label a {@link MediaAccessError} as a {@link CameraStreamError}.\n *\n * The classification itself lives in one place for the whole SDK\n * (`classifyMediaError`), so a microphone and a camera failure are never explained\n * two different ways. Only the name of one kind differs: this surface shipped\n * `\"no-camera\"` where the shared taxonomy says `\"not-found\"`, and renaming a\n * published union member would break every consumer switching on it.\n *\n * @param error - The shared classification.\n * @returns The same error under this module's kind names.\n */\nfunction toCameraError({ kind, message }: MediaAccessError): CameraStreamError {\n    return { kind: kind === \"not-found\" ? \"no-camera\" : kind, message };\n}\n\n/**\n * Map an unknown `getUserMedia` failure into a {@link CameraStreamError}. Secure-context\n * and environment checks run first (they are the reason `getUserMedia` is missing or\n * rejects), then the `DOMException.name` is mapped to a stable `kind`.\n */\nfunction classifyError(err: unknown): CameraStreamError {\n    return toCameraError(classifyMediaError(err, \"camera\"));\n}\n\n/**\n * Acquire a `MediaStream` via `getUserMedia`, attach it to a `<video>` element,\n * and expose status/error so the page can render permission and error states.\n * The stream is automatically released on unmount or retry.\n *\n * Defaults to the rear (\"environment\") camera; desktops fall back to whatever\n * single camera they expose. Pass `options.constraints` to override, or\n * `options.enabled: false` to render the surface without prompting for the camera\n * at all.\n *\n * Implementation notes:\n * - Cleanup detaches the stream from a *snapshotted* video node, so it releases\n *   the same element it attached to even if the page remounts the `<video>`.\n * - When `getUserMedia` is missing, an insecure context is the usual cause, so\n *   the hook prefers that (actionable) error; otherwise it reports `unsupported`.\n * - `video.play()` rejections are swallowed: autoplay may be blocked, but the\n *   user gesture that opened the camera usually counts and playback resumes on\n *   the next interaction.\n *\n * @param options - optional configuration (see {@link UseCameraStreamOptions}).\n * @returns The stream status, classified error, a `videoRef` to attach, the live\n *   `stream` for whatever needs the track itself, and a `retry()` to re-attempt\n *   acquisition.\n */\nexport function useCameraStream(options: UseCameraStreamOptions = {}): UseCameraStreamApi {\n    const [status, setStatus] = useState<CameraStreamStatus>(\"loading\");\n    const [error, setError] = useState<CameraStreamError | null>(null);\n    const [live, setLive] = useState<MediaStream | null>(null);\n    const [retryToken, setRetryToken] = useState(0);\n    const videoRef = useRef<HTMLVideoElement | null>(null);\n    const constraintsRef = useRef<MediaStreamConstraints>(\n        options.constraints ?? DEFAULT_CONSTRAINTS,\n    );\n    useEffect(() => {\n        constraintsRef.current = options.constraints ?? DEFAULT_CONSTRAINTS;\n    }, [options.constraints]);\n\n    const enabled = options.enabled ?? true;\n\n    useEffect(() => {\n        let cancelled = false;\n        let stream: MediaStream | null = null;\n        let attachedVideo: HTMLVideoElement | null = null;\n\n        async function start(): Promise<void> {\n            if (!enabled) {\n                setStatus(\"idle\");\n                setError(null);\n                return;\n            }\n            setStatus(\"loading\");\n            setError(null);\n\n            if (\n                typeof navigator === \"undefined\" ||\n                !navigator.mediaDevices ||\n                typeof navigator.mediaDevices.getUserMedia !== \"function\"\n            ) {\n                if (!cancelled) {\n                    setError(toCameraError(missingCaptureApiError(\"camera\")));\n                    setStatus(\"error\");\n                }\n                return;\n            }\n\n            try {\n                stream = await navigator.mediaDevices.getUserMedia(constraintsRef.current);\n                if (cancelled) {\n                    stream.getTracks().forEach((track) => track.stop());\n                    return;\n                }\n                const video = videoRef.current;\n                if (!video) {\n                    stream.getTracks().forEach((track) => track.stop());\n                    return;\n                }\n                attachedVideo = video;\n                video.srcObject = stream;\n                setLive(stream);\n                await video.play().catch(() => undefined);\n                if (!cancelled) setStatus(\"ready\");\n            } catch (err) {\n                if (!cancelled) {\n                    setError(classifyError(err));\n                    setStatus(\"error\");\n                }\n            }\n        }\n\n        void start();\n\n        return () => {\n            cancelled = true;\n            if (stream) {\n                stream.getTracks().forEach((track) => track.stop());\n            }\n            if (attachedVideo) {\n                attachedVideo.srcObject = null;\n            }\n            setLive(null);\n        };\n    }, [retryToken, enabled]);\n\n    return {\n        status,\n        error,\n        videoRef,\n        stream: live,\n        retry: () => setRetryToken((n) => n + 1),\n    };\n}\n"],"mappings":"oEA+DA,IAAM,EAA8C,CAChD,MAAO,CACH,WAAY,CAAE,MAAO,aAAc,EACnC,MAAO,CAAE,MAAO,IAAK,EACrB,OAAQ,CAAE,MAAO,IAAK,CAC1B,EACA,MAAO,EACX,EAcA,SAAS,EAAc,CAAE,OAAM,WAAgD,CAC3E,MAAO,CAAE,KAAM,IAAS,YAAc,YAAc,EAAM,SAAQ,CACtE,CAOA,SAAS,EAAc,EAAiC,CACpD,OAAO,EAAc,EAAA,mBAAmB,EAAK,QAAQ,CAAC,CAC1D,CA0BA,SAAgB,EAAgB,EAAkC,CAAC,EAAuB,CACtF,GAAM,CAAC,EAAQ,IAAA,EAAA,EAAA,SAAA,CAA0C,SAAS,EAC5D,CAAC,EAAO,IAAA,EAAA,EAAA,SAAA,CAA+C,IAAI,EAC3D,CAAC,EAAM,IAAA,EAAA,EAAA,SAAA,CAAwC,IAAI,EACnD,CAAC,EAAY,IAAA,EAAA,EAAA,SAAA,CAA0B,CAAC,EACxC,GAAA,EAAA,EAAA,OAAA,CAA2C,IAAI,EAC/C,GAAA,EAAA,EAAA,OAAA,CACF,EAAQ,aAAe,CAC3B,GACA,EAAA,EAAA,UAAA,KAAgB,CACZ,EAAe,QAAU,EAAQ,aAAe,CACpD,EAAG,CAAC,EAAQ,WAAW,CAAC,EAExB,IAAM,EAAU,EAAQ,SAAW,GAkEnC,OAhEA,EAAA,EAAA,UAAA,KAAgB,CACZ,IAAI,EAAY,GACZ,EAA6B,KAC7B,EAAyC,KAE7C,eAAe,GAAuB,CAClC,GAAI,CAAC,EAAS,CACV,EAAU,MAAM,EAChB,EAAS,IAAI,EACb,MACJ,CAIA,GAHA,EAAU,SAAS,EACnB,EAAS,IAAI,EAGT,OAAO,UAAc,KACrB,CAAC,UAAU,cACX,OAAO,UAAU,aAAa,cAAiB,WACjD,CACO,IACD,EAAS,EAAc,EAAA,uBAAuB,QAAQ,CAAC,CAAC,EACxD,EAAU,OAAO,GAErB,MACJ,CAEA,GAAI,CAEA,GADA,EAAS,MAAM,UAAU,aAAa,aAAa,EAAe,OAAO,EACrE,EAAW,CACX,EAAO,UAAU,CAAC,CAAC,QAAS,GAAU,EAAM,KAAK,CAAC,EAClD,MACJ,CACA,IAAM,EAAQ,EAAS,QACvB,GAAI,CAAC,EAAO,CACR,EAAO,UAAU,CAAC,CAAC,QAAS,GAAU,EAAM,KAAK,CAAC,EAClD,MACJ,CACA,EAAgB,EAChB,EAAM,UAAY,EAClB,EAAQ,CAAM,EACd,MAAM,EAAM,KAAK,CAAC,CAAC,UAAY,IAAA,EAAS,EACnC,GAAW,EAAU,OAAO,CACrC,OAAS,EAAK,CACL,IACD,EAAS,EAAc,CAAG,CAAC,EAC3B,EAAU,OAAO,EAEzB,CACJ,CAIA,OAFA,EAAW,MAEE,CACT,EAAY,GACR,GACA,EAAO,UAAU,CAAC,CAAC,QAAS,GAAU,EAAM,KAAK,CAAC,EAElD,IACA,EAAc,UAAY,MAE9B,EAAQ,IAAI,CAChB,CACJ,EAAG,CAAC,EAAY,CAAO,CAAC,EAEjB,CACH,SACA,QACA,WACA,OAAQ,EACR,UAAa,EAAe,GAAM,EAAI,CAAC,CAC3C,CACJ"}
+{"version":3,"file":"use-camera-stream.cjs","names":[],"sources":["../../src/vision/use-camera-stream.ts"],"sourcesContent":["import { useEffect, useRef, useState, type RefObject } from \"react\";\n\nimport {\n    classifyMediaError,\n    missingCaptureApiError,\n    type MediaAccessError,\n} from \"@/audio/media-access\";\n\n/** Lifecycle status of the camera stream. */\nexport type CameraStreamStatus = \"idle\" | \"loading\" | \"ready\" | \"error\";\n\n/** Classified reason a camera stream could not be acquired. */\nexport type CameraStreamErrorKind =\n    \"unsupported\" | \"permission-denied\" | \"no-camera\" | \"in-use\" | \"insecure\" | \"unknown\";\n\n/** A classified camera error with a human-readable, English message. */\nexport interface CameraStreamError {\n    kind: CameraStreamErrorKind;\n    message: string;\n}\n\n/** Options for {@link useCameraStream}. */\nexport interface UseCameraStreamOptions {\n    /**\n     * Constraints passed to `getUserMedia`. Defaults to the rear\n     * (\"environment\") camera at Full-HD ideal resolution with audio off.\n     * Read when the stream (re)starts — change it and call `retry()` to apply.\n     */\n    constraints?: MediaStreamConstraints;\n    /**\n     * Hold off acquiring the camera until this is `true`. Default `true`.\n     *\n     * The point is to be able to *not* prompt. A permission prompt costs the user a\n     * decision and, if they refuse, costs the app the feature permanently — so a\n     * surface that already knows it cannot do its job (a barcode scanner in a browser\n     * with no decoder) must not open the camera to then say so. Flipping this to `false`\n     * also releases a stream that is already live.\n     */\n    enabled?: boolean;\n}\n\n/** Value returned by {@link useCameraStream}. */\nexport interface UseCameraStreamApi {\n    /** Current lifecycle status. */\n    status: CameraStreamStatus;\n    /** The classified error, or `null` while not in the `error` status. */\n    error: CameraStreamError | null;\n    /** Attach to a `<video ref={…} />`. The stream is wired to it once ready. */\n    videoRef: RefObject<HTMLVideoElement | null>;\n    /**\n     * The live stream, or `null`.\n     *\n     * Exposed for the things that need the **track** rather than the picture — the LED\n     * torch (`useTorch`), the real frame size from `getSettings()`, recording it with\n     * `useVideoRecorder`. Do not stop it yourself: the hook owns its lifetime and\n     * releases it on unmount and on `retry()`.\n     */\n    stream: MediaStream | null;\n    /** Manually re-attempt after an error (e.g. the user changed permissions). */\n    retry: () => void;\n}\n\n/** Rear-camera Full-HD defaults used when no `constraints` are supplied. */\nconst DEFAULT_CONSTRAINTS: MediaStreamConstraints = {\n    video: {\n        facingMode: { ideal: \"environment\" },\n        width: { ideal: 1920 },\n        height: { ideal: 1080 },\n    },\n    audio: false,\n};\n\n/**\n * Re-label a {@link MediaAccessError} as a {@link CameraStreamError}.\n *\n * The classification itself lives in one place for the whole SDK\n * (`classifyMediaError`), so a microphone and a camera failure are never explained\n * two different ways. Only the name of one kind differs: this surface shipped\n * `\"no-camera\"` where the shared taxonomy says `\"not-found\"`, and renaming a\n * published union member would break every consumer switching on it.\n *\n * @param error - The shared classification.\n * @returns The same error under this module's kind names.\n */\nfunction toCameraError({ kind, message }: MediaAccessError): CameraStreamError {\n    return { kind: kind === \"not-found\" ? \"no-camera\" : kind, message };\n}\n\n/**\n * Map an unknown `getUserMedia` failure into a {@link CameraStreamError}. Secure-context\n * and environment checks run first (they are the reason `getUserMedia` is missing or\n * rejects), then the `DOMException.name` is mapped to a stable `kind`.\n */\nfunction classifyError(err: unknown): CameraStreamError {\n    return toCameraError(classifyMediaError(err, \"camera\"));\n}\n\n/**\n * Acquire a `MediaStream` via `getUserMedia`, attach it to a `<video>` element,\n * and expose status/error so the page can render permission and error states.\n * The stream is automatically released on unmount or retry.\n *\n * Defaults to the rear (\"environment\") camera; desktops fall back to whatever\n * single camera they expose. Pass `options.constraints` to override, or\n * `options.enabled: false` to render the surface without prompting for the camera\n * at all.\n *\n * Implementation notes:\n * - Cleanup detaches the stream from a *snapshotted* video node, so it releases\n *   the same element it attached to even if the page remounts the `<video>`.\n * - When `getUserMedia` is missing, an insecure context is the usual cause, so\n *   the hook prefers that (actionable) error; otherwise it reports `unsupported`.\n * - `video.play()` rejections are swallowed: autoplay may be blocked, but the\n *   user gesture that opened the camera usually counts and playback resumes on\n *   the next interaction.\n *\n * @param options - optional configuration (see {@link UseCameraStreamOptions}).\n * @returns The stream status, classified error, a `videoRef` to attach, the live\n *   `stream` for whatever needs the track itself, and a `retry()` to re-attempt\n *   acquisition.\n */\nexport function useCameraStream(options: UseCameraStreamOptions = {}): UseCameraStreamApi {\n    const [status, setStatus] = useState<CameraStreamStatus>(\"loading\");\n    const [error, setError] = useState<CameraStreamError | null>(null);\n    const [live, setLive] = useState<MediaStream | null>(null);\n    const [retryToken, setRetryToken] = useState(0);\n    const videoRef = useRef<HTMLVideoElement | null>(null);\n    const constraintsRef = useRef<MediaStreamConstraints>(\n        options.constraints ?? DEFAULT_CONSTRAINTS,\n    );\n    useEffect(() => {\n        constraintsRef.current = options.constraints ?? DEFAULT_CONSTRAINTS;\n    }, [options.constraints]);\n\n    const enabled = options.enabled ?? true;\n\n    useEffect(() => {\n        let cancelled = false;\n        let stream: MediaStream | null = null;\n        let attachedVideo: HTMLVideoElement | null = null;\n\n        async function start(): Promise<void> {\n            if (!enabled) {\n                setStatus(\"idle\");\n                setError(null);\n                return;\n            }\n            setStatus(\"loading\");\n            setError(null);\n\n            if (\n                typeof navigator === \"undefined\" ||\n                !navigator.mediaDevices ||\n                typeof navigator.mediaDevices.getUserMedia !== \"function\"\n            ) {\n                if (!cancelled) {\n                    setError(toCameraError(missingCaptureApiError(\"camera\")));\n                    setStatus(\"error\");\n                }\n                return;\n            }\n\n            try {\n                stream = await navigator.mediaDevices.getUserMedia(constraintsRef.current);\n                if (cancelled) {\n                    stream.getTracks().forEach((track) => track.stop());\n                    return;\n                }\n                const video = videoRef.current;\n                if (!video) {\n                    stream.getTracks().forEach((track) => track.stop());\n                    return;\n                }\n                attachedVideo = video;\n                video.srcObject = stream;\n                setLive(stream);\n                await video.play().catch(() => undefined);\n                if (!cancelled) setStatus(\"ready\");\n            } catch (err) {\n                if (!cancelled) {\n                    setError(classifyError(err));\n                    setStatus(\"error\");\n                }\n            }\n        }\n\n        void start();\n\n        return () => {\n            cancelled = true;\n            if (stream) {\n                stream.getTracks().forEach((track) => track.stop());\n            }\n            if (attachedVideo) {\n                attachedVideo.srcObject = null;\n            }\n            setLive(null);\n        };\n    }, [retryToken, enabled]);\n\n    return {\n        status,\n        error,\n        videoRef,\n        stream: live,\n        retry: () => setRetryToken((n) => n + 1),\n    };\n}\n"],"mappings":"oEA+DA,IAAM,EAA8C,CAChD,MAAO,CACH,WAAY,CAAE,MAAO,aAAc,EACnC,MAAO,CAAE,MAAO,IAAK,EACrB,OAAQ,CAAE,MAAO,IAAK,CAC1B,EACA,MAAO,EACX,EAcA,SAAS,EAAc,CAAE,OAAM,WAAgD,CAC3E,MAAO,CAAE,KAAM,IAAS,YAAc,YAAc,EAAM,SAAQ,CACtE,CAOA,SAAS,EAAc,EAAiC,CACpD,OAAO,EAAc,EAAA,mBAAmB,EAAK,QAAQ,CAAC,CAC1D,CA0BA,SAAgB,EAAgB,EAAkC,CAAC,EAAuB,CACtF,GAAM,CAAC,EAAQ,IAAA,EAAa,EAAA,SAAA,CAA6B,SAAS,EAC5D,CAAC,EAAO,IAAA,EAAY,EAAA,SAAA,CAAmC,IAAI,EAC3D,CAAC,EAAM,IAAA,EAAW,EAAA,SAAA,CAA6B,IAAI,EACnD,CAAC,EAAY,IAAA,EAAiB,EAAA,SAAA,CAAS,CAAC,EACxC,GAAA,EAAW,EAAA,OAAA,CAAgC,IAAI,EAC/C,GAAA,EAAiB,EAAA,OAAA,CACnB,EAAQ,aAAe,CAC3B,GACA,EAAA,EAAA,UAAA,KAAgB,CACZ,EAAe,QAAU,EAAQ,aAAe,CACpD,EAAG,CAAC,EAAQ,WAAW,CAAC,EAExB,IAAM,EAAU,EAAQ,SAAW,GAkEnC,OAhEA,EAAA,EAAA,UAAA,KAAgB,CACZ,IAAI,EAAY,GACZ,EAA6B,KAC7B,EAAyC,KAE7C,eAAe,GAAuB,CAClC,GAAI,CAAC,EAAS,CACV,EAAU,MAAM,EAChB,EAAS,IAAI,EACb,MACJ,CAIA,GAHA,EAAU,SAAS,EACnB,EAAS,IAAI,EAGT,OAAO,UAAc,KACrB,CAAC,UAAU,cACX,OAAO,UAAU,aAAa,cAAiB,WACjD,CACO,IACD,EAAS,EAAc,EAAA,uBAAuB,QAAQ,CAAC,CAAC,EACxD,EAAU,OAAO,GAErB,MACJ,CAEA,GAAI,CAEA,GADA,EAAS,MAAM,UAAU,aAAa,aAAa,EAAe,OAAO,EACrE,EAAW,CACX,EAAO,UAAU,CAAC,CAAC,QAAS,GAAU,EAAM,KAAK,CAAC,EAClD,MACJ,CACA,IAAM,EAAQ,EAAS,QACvB,GAAI,CAAC,EAAO,CACR,EAAO,UAAU,CAAC,CAAC,QAAS,GAAU,EAAM,KAAK,CAAC,EAClD,MACJ,CACA,EAAgB,EAChB,EAAM,UAAY,EAClB,EAAQ,CAAM,EACd,MAAM,EAAM,KAAK,CAAC,CAAC,UAAY,IAAA,EAAS,EACnC,GAAW,EAAU,OAAO,CACrC,OAAS,EAAK,CACL,IACD,EAAS,EAAc,CAAG,CAAC,EAC3B,EAAU,OAAO,EAEzB,CACJ,CAIA,OAFA,EAAW,MAEE,CACT,EAAY,GACR,GACA,EAAO,UAAU,CAAC,CAAC,QAAS,GAAU,EAAM,KAAK,CAAC,EAElD,IACA,EAAc,UAAY,MAE9B,EAAQ,IAAI,CAChB,CACJ,EAAG,CAAC,EAAY,CAAO,CAAC,EAEjB,CACH,SACA,QACA,WACA,OAAQ,EACR,UAAa,EAAe,GAAM,EAAI,CAAC,CAC3C,CACJ"}

package/dist/vision/use-live-luminance.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"use-live-luminance.cjs","names":[],"sources":["../../src/vision/use-live-luminance.ts"],"sourcesContent":["import { useEffect, useRef, useState, type RefObject } from \"react\";\nimport { computeImageLuminance } from \"./luminance\";\n\n/** Options for {@link useLiveLuminance}. */\nexport interface UseLiveLuminanceOptions {\n    /** When `false` the loop is paused (e.g. while a capture is in flight). Default: `true`. */\n    enabled?: boolean;\n    /** Throttle measurements in milliseconds. Default: `160` (~6 fps), plenty for UX. */\n    intervalMs?: number;\n}\n\n/**\n * Sample mean luminance from a `<video>` source on a `requestAnimationFrame`\n * loop and expose the rolling value. Sampling is throttled by `intervalMs` and\n * paused whenever `enabled` is `false` or the video is not ready yet\n * (`readyState < 2` or `videoWidth === 0`).\n *\n * One offscreen canvas is reused across frames to avoid GC pressure. Designed\n * to feed a live brightness bar / border color on a camera page.\n *\n * @param videoRef - ref to the `<video>` element to sample.\n * @param options - optional configuration (see {@link UseLiveLuminanceOptions}).\n * @returns The rolling mean luminance in `0..255` (`0` until the first sample).\n */\nexport function useLiveLuminance(\n    videoRef: RefObject<HTMLVideoElement | null>,\n    { enabled = true, intervalMs = 160 }: UseLiveLuminanceOptions = {},\n): number {\n    const [luminance, setLuminance] = useState(0);\n    const canvasRef = useRef<HTMLCanvasElement | null>(null);\n\n    useEffect(() => {\n        if (!enabled) return;\n        if (typeof window === \"undefined\") return;\n        if (!canvasRef.current) canvasRef.current = document.createElement(\"canvas\");\n\n        let rafId = 0;\n        let lastSampledAt = 0;\n\n        const tick = (timestamp: number): void => {\n            const video = videoRef.current;\n            if (!video || video.readyState < 2 || video.videoWidth === 0) {\n                rafId = window.requestAnimationFrame(tick);\n                return;\n            }\n            if (timestamp - lastSampledAt >= intervalMs) {\n                lastSampledAt = timestamp;\n                setLuminance(computeImageLuminance(video, canvasRef.current ?? undefined));\n            }\n            rafId = window.requestAnimationFrame(tick);\n        };\n\n        rafId = window.requestAnimationFrame(tick);\n        return () => window.cancelAnimationFrame(rafId);\n    }, [videoRef, enabled, intervalMs]);\n\n    return luminance;\n}\n"],"mappings":"0DAwBA,SAAgB,EACZ,EACA,CAAE,UAAU,GAAM,aAAa,KAAiC,CAAC,EAC3D,CACN,GAAM,CAAC,EAAW,IAAA,EAAA,EAAA,SAAA,CAAyB,CAAC,EACtC,GAAA,EAAA,EAAA,OAAA,CAA6C,IAAI,EA2BvD,OAzBA,EAAA,EAAA,UAAA,KAAgB,CAEZ,GADI,CAAC,GACD,OAAO,OAAW,IAAa,OACnC,AAAwB,EAAU,UAAU,SAAS,cAAc,QAAQ,EAE3E,IAAI,EAAQ,EACR,EAAgB,EAEd,EAAQ,GAA4B,CACtC,IAAM,EAAQ,EAAS,QACvB,GAAI,CAAC,GAAS,EAAM,WAAa,GAAK,EAAM,aAAe,EAAG,CAC1D,EAAQ,OAAO,sBAAsB,CAAI,EACzC,MACJ,CACI,EAAY,GAAiB,IAC7B,EAAgB,EAChB,EAAa,EAAA,sBAAsB,EAAO,EAAU,SAAW,IAAA,EAAS,CAAC,GAE7E,EAAQ,OAAO,sBAAsB,CAAI,CAC7C,EAGA,MADA,GAAQ,OAAO,sBAAsB,CAAI,MAC5B,OAAO,qBAAqB,CAAK,CAClD,EAAG,CAAC,EAAU,EAAS,CAAU,CAAC,EAE3B,CACX"}
+{"version":3,"file":"use-live-luminance.cjs","names":[],"sources":["../../src/vision/use-live-luminance.ts"],"sourcesContent":["import { useEffect, useRef, useState, type RefObject } from \"react\";\nimport { computeImageLuminance } from \"./luminance\";\n\n/** Options for {@link useLiveLuminance}. */\nexport interface UseLiveLuminanceOptions {\n    /** When `false` the loop is paused (e.g. while a capture is in flight). Default: `true`. */\n    enabled?: boolean;\n    /** Throttle measurements in milliseconds. Default: `160` (~6 fps), plenty for UX. */\n    intervalMs?: number;\n}\n\n/**\n * Sample mean luminance from a `<video>` source on a `requestAnimationFrame`\n * loop and expose the rolling value. Sampling is throttled by `intervalMs` and\n * paused whenever `enabled` is `false` or the video is not ready yet\n * (`readyState < 2` or `videoWidth === 0`).\n *\n * One offscreen canvas is reused across frames to avoid GC pressure. Designed\n * to feed a live brightness bar / border color on a camera page.\n *\n * @param videoRef - ref to the `<video>` element to sample.\n * @param options - optional configuration (see {@link UseLiveLuminanceOptions}).\n * @returns The rolling mean luminance in `0..255` (`0` until the first sample).\n */\nexport function useLiveLuminance(\n    videoRef: RefObject<HTMLVideoElement | null>,\n    { enabled = true, intervalMs = 160 }: UseLiveLuminanceOptions = {},\n): number {\n    const [luminance, setLuminance] = useState(0);\n    const canvasRef = useRef<HTMLCanvasElement | null>(null);\n\n    useEffect(() => {\n        if (!enabled) return;\n        if (typeof window === \"undefined\") return;\n        if (!canvasRef.current) canvasRef.current = document.createElement(\"canvas\");\n\n        let rafId = 0;\n        let lastSampledAt = 0;\n\n        const tick = (timestamp: number): void => {\n            const video = videoRef.current;\n            if (!video || video.readyState < 2 || video.videoWidth === 0) {\n                rafId = window.requestAnimationFrame(tick);\n                return;\n            }\n            if (timestamp - lastSampledAt >= intervalMs) {\n                lastSampledAt = timestamp;\n                setLuminance(computeImageLuminance(video, canvasRef.current ?? undefined));\n            }\n            rafId = window.requestAnimationFrame(tick);\n        };\n\n        rafId = window.requestAnimationFrame(tick);\n        return () => window.cancelAnimationFrame(rafId);\n    }, [videoRef, enabled, intervalMs]);\n\n    return luminance;\n}\n"],"mappings":"0DAwBA,SAAgB,EACZ,EACA,CAAE,UAAU,GAAM,aAAa,KAAiC,CAAC,EAC3D,CACN,GAAM,CAAC,EAAW,IAAA,EAAgB,EAAA,SAAA,CAAS,CAAC,EACtC,GAAA,EAAY,EAAA,OAAA,CAAiC,IAAI,EA2BvD,OAzBA,EAAA,EAAA,UAAA,KAAgB,CAEZ,GADI,CAAC,GACD,OAAO,OAAW,IAAa,OACnC,AAAwB,EAAU,UAAU,SAAS,cAAc,QAAQ,EAE3E,IAAI,EAAQ,EACR,EAAgB,EAEd,EAAQ,GAA4B,CACtC,IAAM,EAAQ,EAAS,QACvB,GAAI,CAAC,GAAS,EAAM,WAAa,GAAK,EAAM,aAAe,EAAG,CAC1D,EAAQ,OAAO,sBAAsB,CAAI,EACzC,MACJ,CACI,EAAY,GAAiB,IAC7B,EAAgB,EAChB,EAAa,EAAA,sBAAsB,EAAO,EAAU,SAAW,IAAA,EAAS,CAAC,GAE7E,EAAQ,OAAO,sBAAsB,CAAI,CAC7C,EAGA,MADA,GAAQ,OAAO,sBAAsB,CAAI,MAC5B,OAAO,qBAAqB,CAAK,CAClD,EAAG,CAAC,EAAU,EAAS,CAAU,CAAC,EAE3B,CACX"}

package/dist/vision.cjs

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