tempest-react-sdk 0.23.0 → 0.25.0

package/dist/vision/tasks/detector.js

@@ -1,147 +1,112 @@
-import { OrtSession as g } from "../core/session.js";
-import { loadImage as T } from "../io/image.js";
-import { resolveLabels as D } from "../labels.js";
-import { decodeYolo as S } from "../postprocess/detection.js";
-import { letterbox as A, toFloat32 as I, toCHW as v, toFloat32Tensor as z } from "../preprocess/image.js";
-import { DetectionResults as B, Boxes as C } from "../results.js";
-import { VisionTask as F } from "./base.js";
-import { RGBImage as y } from "../types.js";
-class b extends F {
-  constructor(o, e, r, t, n, a, s, i) {
-    super(o), this._head = e, this._labels = r, this._names = t, this._inputSize = n, this._confThreshold = a, this._iouThreshold = s, this._maxDetections = i;
-  }
-  _head;
-  _labels;
-  _names;
-  _inputSize;
-  _confThreshold;
-  _iouThreshold;
-  _maxDetections;
-  /** Load the model and resolve labels. */
-  static async create(o, e = {}) {
-    const r = e.head ?? "yolo";
-    if (r !== "yolo")
-      throw new Error(`Unsupported detector head '${r}'. Supported: 'yolo'.`);
-    const t = await g.create(o, e), n = D(e.labels ?? "coco", {
-      numClasses: e.numClasses
-    }), a = {};
-    for (let s = 0; s < n.length; s++)
-      a[s] = n[s];
-    return new b(
-      t,
-      r,
-      n,
-      a,
-      e.inputSize ?? [640, 640],
-      e.confThreshold ?? 0.25,
-      e.iouThreshold ?? 0.45,
-      e.maxDetections ?? 300
-    );
-  }
-  /** The decoder family used to interpret the model's output. */
-  get head() {
-    return this._head;
-  }
-  /** Class labels indexed by class id. */
-  get labels() {
-    return this._labels;
-  }
-  /** Class id → class name dict (matches Ultralytics' `model.names`). */
-  get names() {
-    return this._names;
-  }
-  /** Number of classes the model predicts. */
-  get numClasses() {
-    return this._labels.length;
-  }
-  /**
-   * Alias for {@link predict} — call the detector like a torch `nn.Module`.
-   *
-   * Use as `det.call(img)` since JavaScript class instances are not callable;
-   * for direct invocation, prefer `det.predict(img)`. The full
-   * {@link DetectorPredictOptions} (including `classes`) is supported.
-   */
-  async call(o, e = {}) {
-    return this.predict(o, e);
-  }
-  /** Run detection on a single image. */
-  async predict(o, e = {}) {
-    const r = typeof o == "string" ? o : null, t = await T(o), { tensor: n, scale: a, padLeft: s, padTop: i } = this._preprocess(t), m = await this._session.run({ [this._session.inputName]: n }), h = this._session.outputNames[0];
-    if (h === void 0)
-      throw new Error("Detector model has no outputs.");
-    const d = m[h];
-    if (d === void 0)
-      throw new Error(`Detector model output ${h} missing from run() result.`);
-    const u = S(d.data, d.dims, {
-      originalWidth: t.width,
-      originalHeight: t.height,
-      padLeft: s,
-      padTop: i,
-      scale: a,
-      confThreshold: e.confThreshold ?? this._confThreshold,
-      iouThreshold: e.iouThreshold ?? this._iouThreshold,
-      maxDetections: this._maxDetections
-    }), p = (e.classes !== void 0 ? (() => {
-      const c = new Set(e.classes);
-      return u.filter((_) => c.has(_.classId));
-    })() : u).map(
-      (c) => this._buildResult(t, c.bbox, c.classId, c.confidence)
-    ), l = [t.height, t.width];
-    return [
-      new B(
-        this._buildBoxes(p, l),
-        p,
-        this._names,
-        t,
-        l,
-        r
-      )
-    ];
-  }
-  _preprocess(o) {
-    const [e, r] = this._inputSize, t = A(o, e, r), n = I(t.image), a = v(n, t.image.width, t.image.height, 3);
-    return {
-      tensor: z(a, [1, 3, t.image.height, t.image.width]),
-      scale: t.scale,
-      padLeft: t.padLeft,
-      padTop: t.padTop
-    };
-  }
-  _buildResult(o, e, r, t) {
-    const [n, a, s, i] = e.asIntXyxy(), m = Math.max(0, n), h = Math.max(0, a), d = Math.min(o.width, s), u = Math.min(o.height, i);
-    let f;
-    if (d > m && u > h) {
-      const l = d - m, c = u - h, _ = new Uint8Array(l * c * 3);
-      for (let w = 0; w < c; w++) {
-        const x = ((h + w) * o.width + m) * 3;
-        _.set(o.data.subarray(x, x + l * 3), w * l * 3);
-      }
-      f = new y(_, l, c);
-    } else
-      f = new y(new Uint8Array(0), 0, 0);
-    const p = this._names[r] ?? `class_${r}`;
-    return {
-      classId: r,
-      className: p,
-      confidence: t,
-      bbox: e,
-      cls: r,
-      name: p,
-      conf: t,
-      box: e,
-      croppedImage: f
-    };
-  }
-  _buildBoxes(o, e) {
-    const r = o.length, t = new Float32Array(r * 4), n = new Int32Array(r), a = new Float32Array(r);
-    for (let s = 0; s < r; s++) {
-      const i = o[s];
-      t[s * 4] = i.bbox.x1, t[s * 4 + 1] = i.bbox.y1, t[s * 4 + 2] = i.bbox.x2, t[s * 4 + 3] = i.bbox.y2, n[s] = i.classId, a[s] = i.confidence;
-    }
-    return new C(t, n, a, e);
-  }
-}
-export {
-  b as Detector
+import { RGBImage as e } from "../types.js";
+import { Boxes as t, DetectionResults as n } from "../results.js";
+import { resolveLabels as r } from "../labels.js";
+import { OrtSession as i } from "../core/session.js";
+import { loadImage as a } from "../io/image.js";
+import { letterbox as o, toCHW as s, toFloat32 as c, toFloat32Tensor as l } from "../preprocess/image.js";
+import { decodeYolo as u } from "../postprocess/detection.js";
+import { VisionTask as d } from "./base.js";
+//#region src/vision/tasks/detector.ts
+var f = class f extends d {
+	_head;
+	_labels;
+	_names;
+	_inputSize;
+	_confThreshold;
+	_iouThreshold;
+	_maxDetections;
+	constructor(e, t, n, r, i, a, o, s) {
+		super(e), this._head = t, this._labels = n, this._names = r, this._inputSize = i, this._confThreshold = a, this._iouThreshold = o, this._maxDetections = s;
+	}
+	static async create(e, t = {}) {
+		let n = t.head ?? "yolo";
+		if (n !== "yolo") throw Error(`Unsupported detector head '${n}'. Supported: 'yolo'.`);
+		let a = await i.create(e, t), o = r(t.labels ?? "coco", { numClasses: t.numClasses }), s = {};
+		for (let e = 0; e < o.length; e++) s[e] = o[e];
+		return new f(a, n, o, s, t.inputSize ?? [640, 640], t.confThreshold ?? .25, t.iouThreshold ?? .45, t.maxDetections ?? 300);
+	}
+	get head() {
+		return this._head;
+	}
+	get labels() {
+		return this._labels;
+	}
+	get names() {
+		return this._names;
+	}
+	get numClasses() {
+		return this._labels.length;
+	}
+	async call(e, t = {}) {
+		return this.predict(e, t);
+	}
+	async predict(e, t = {}) {
+		let r = typeof e == "string" ? e : null, i = await a(e), { tensor: o, scale: s, padLeft: c, padTop: l } = this._preprocess(i), d = await this._session.run({ [this._session.inputName]: o }), f = this._session.outputNames[0];
+		if (f === void 0) throw Error("Detector model has no outputs.");
+		let p = d[f];
+		if (p === void 0) throw Error(`Detector model output ${f} missing from run() result.`);
+		let m = u(p.data, p.dims, {
+			originalWidth: i.width,
+			originalHeight: i.height,
+			padLeft: c,
+			padTop: l,
+			scale: s,
+			confThreshold: t.confThreshold ?? this._confThreshold,
+			iouThreshold: t.iouThreshold ?? this._iouThreshold,
+			maxDetections: this._maxDetections
+		}), h = (t.classes === void 0 ? m : (() => {
+			let e = new Set(t.classes);
+			return m.filter((t) => e.has(t.classId));
+		})()).map((e) => this._buildResult(i, e.bbox, e.classId, e.confidence)), g = [i.height, i.width];
+		return [new n(this._buildBoxes(h, g), h, this._names, i, g, r)];
+	}
+	_preprocess(e) {
+		let [t, n] = this._inputSize, r = o(e, t, n);
+		return {
+			tensor: l(s(c(r.image), r.image.width, r.image.height, 3), [
+				1,
+				3,
+				r.image.height,
+				r.image.width
+			]),
+			scale: r.scale,
+			padLeft: r.padLeft,
+			padTop: r.padTop
+		};
+	}
+	_buildResult(t, n, r, i) {
+		let [a, o, s, c] = n.asIntXyxy(), l = Math.max(0, a), u = Math.max(0, o), d = Math.min(t.width, s), f = Math.min(t.height, c), p;
+		if (d > l && f > u) {
+			let n = d - l, r = f - u, i = new Uint8Array(n * r * 3);
+			for (let e = 0; e < r; e++) {
+				let r = ((u + e) * t.width + l) * 3;
+				i.set(t.data.subarray(r, r + n * 3), e * n * 3);
+			}
+			p = new e(i, n, r);
+		} else p = new e(/* @__PURE__ */ new Uint8Array(), 0, 0);
+		let m = this._names[r] ?? `class_${r}`;
+		return {
+			classId: r,
+			className: m,
+			confidence: i,
+			bbox: n,
+			cls: r,
+			name: m,
+			conf: i,
+			box: n,
+			croppedImage: p
+		};
+	}
+	_buildBoxes(e, n) {
+		let r = e.length, i = new Float32Array(r * 4), a = new Int32Array(r), o = new Float32Array(r);
+		for (let t = 0; t < r; t++) {
+			let n = e[t];
+			i[t * 4] = n.bbox.x1, i[t * 4 + 1] = n.bbox.y1, i[t * 4 + 2] = n.bbox.x2, i[t * 4 + 3] = n.bbox.y2, a[t] = n.classId, o[t] = n.confidence;
+		}
+		return new t(i, a, o, n);
+	}
 };
-//# sourceMappingURL=detector.js.map
+//#endregion
+export { f as Detector };
+
+//# sourceMappingURL=detector.js.map

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

@@ -1 +1 @@
-{"version":3,"file":"detector.js","sources":["../../../src/vision/tasks/detector.ts"],"sourcesContent":["/**\n * Object detection task using anchor-free YOLO ONNX models (v8/v9/v10/v11/v12).\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { decodeYolo } from \"../postprocess/detection\";\nimport { letterbox, toCHW, toFloat32, toFloat32Tensor } from \"../preprocess/image\";\nimport { Boxes, DetectionResults } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type BoundingBox, type DetectionResult, RGBImage } from \"../types\";\n\n/**\n * Decoder family for the model's detection head.\n *\n * - `\"yolo\"`: anchor-free YOLO head with output shape `[1, 4 + nc, N]` —\n *   covers YOLOv8, v9, v10, v11, v12, v26 detect exports.\n *\n * The SDK does **not** auto-detect the head from the model — the caller is\n * responsible for picking a head that matches their export. Future families\n * (v5/v6/v7 with `[1, N, 5+nc]`) will be added as new literal members.\n */\nexport type DetectorHead = \"yolo\";\n\nexport interface DetectorOptions extends OrtSessionOptions {\n    /**\n     * Decoder family for the detection head. Default `\"yolo\"` covers\n     * YOLOv8/v9/v10/v11/v12/v26.\n     */\n    readonly head?: DetectorHead;\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    /** Model input `[width, height]` for letterboxing. Defaults to `[640, 640]`. */\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 detections per image. */\n    readonly maxDetections?: number;\n}\n\nexport interface DetectorPredictOptions {\n    /** Override the default confidence threshold. */\n    readonly confThreshold?: number;\n    /** Override the default IoU threshold. */\n    readonly iouThreshold?: number;\n    /**\n     * If set, keep only detections 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 * Object detector for anchor-free YOLO ONNX models (v8/v9/v10/v11/v12).\n *\n * `predict()` returns `Promise<DetectionResults[]>` (length 1 for a single\n * image), mirroring Ultralytics' `YOLO(\"img.jpg\")`. Iterate the envelope for\n * per-instance dataclasses, or use the bulk `boxes` view (`.xyxy`, `.xywh`,\n * `.xyxyn`, `.xywhn`, `.cls`, `.conf`).\n *\n * @example\n * ```typescript\n * const det = await Detector.create(\"/models/yolov8n.onnx\");\n * const results = await det.predict(\"/images/street.jpg\");\n * const r = results[0];\n * console.log(r.boxes.xyxy, r.boxes.cls, r.boxes.conf, r.names);\n * for (const d of r) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n */\nexport class Detector extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _head: DetectorHead,\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    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: DetectorOptions = {}): Promise<Detector> {\n        const head: DetectorHead = options.head ?? \"yolo\";\n        if (head !== \"yolo\") {\n            throw new Error(`Unsupported detector head '${head}'. Supported: 'yolo'.`);\n        }\n        const session = await OrtSession.create(model, options);\n        const labels = resolveLabels(options.labels ?? \"coco\", {\n            numClasses: options.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 Detector(\n            session,\n            head,\n            labels,\n            names,\n            options.inputSize ?? [640, 640],\n            options.confThreshold ?? 0.25,\n            options.iouThreshold ?? 0.45,\n            options.maxDetections ?? 300,\n        );\n    }\n\n    /** The decoder family used to interpret the model's output. */\n    get head(): DetectorHead {\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    /** Number of classes the model predicts. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /**\n     * Alias for {@link predict} — call the detector like a torch `nn.Module`.\n     *\n     * Use as `det.call(img)` since JavaScript class instances are not callable;\n     * for direct invocation, prefer `det.predict(img)`. The full\n     * {@link DetectorPredictOptions} (including `classes`) is supported.\n     */\n    async call(\n        image: ImageInput,\n        options: DetectorPredictOptions = {},\n    ): Promise<DetectionResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run detection on a single image. */\n    async predict(\n        image: ImageInput,\n        options: DetectorPredictOptions = {},\n    ): Promise<DetectionResults[]> {\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        const { tensor, scale, padLeft, padTop } = this._preprocess(original);\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Detector model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(`Detector model output ${firstOutputName} missing from run() result.`);\n        }\n\n        const decodedAll = decodeYolo(raw.data as Float32Array, raw.dims, {\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        });\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),\n        );\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        return [\n            new DetectionResults(\n                this._buildBoxes(detections, orig),\n                detections,\n                this._names,\n                original,\n                orig,\n                path,\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 _buildResult(\n        original: RGBImage,\n        bbox: BoundingBox,\n        classId: number,\n        confidence: number,\n    ): DetectionResult {\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 cropped: RGBImage;\n        if (cx2 > cx1 && cy2 > cy1) {\n            const cw = cx2 - cx1;\n            const ch = cy2 - cy1;\n            const out = new Uint8Array(cw * ch * 3);\n            for (let row = 0; row < ch; row++) {\n                const srcOffset = ((cy1 + row) * original.width + cx1) * 3;\n                out.set(original.data.subarray(srcOffset, srcOffset + cw * 3), row * cw * 3);\n            }\n            cropped = new RGBImage(out, cw, ch);\n        } else {\n            cropped = 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            croppedImage: cropped,\n        };\n    }\n\n    private _buildBoxes(\n        detections: readonly DetectionResult[],\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 DetectionResult;\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"],"names":["Detector","VisionTask","session","_head","_labels","_names","_inputSize","_confThreshold","_iouThreshold","_maxDetections","model","options","head","OrtSession","labels","resolveLabels","names","i","image","path","original","loadImage","tensor","scale","padLeft","padTop","outputs","firstOutputName","raw","decodedAll","decodeYolo","detections","allowed","d","orig","DetectionResults","tw","th","lb","letterbox","f32","toFloat32","chw","toCHW","toFloat32Tensor","bbox","classId","confidence","x1","y1","x2","y2","cx1","cy1","cx2","cy2","cropped","cw","ch","out","row","srcOffset","RGBImage","className","origShape","n","xyxy","cls","conf","Boxes"],"mappings":";;;;;;;;AA8EO,MAAMA,UAAiBC,EAAW;AAAA,EAC7B,YACJC,GACiBC,GACAC,GACAC,GACAC,GACAC,GACAC,GACAC,GACnB;AACE,UAAMP,CAAO,GARI,KAAA,QAAAC,GACA,KAAA,UAAAC,GACA,KAAA,SAAAC,GACA,KAAA,aAAAC,GACA,KAAA,iBAAAC,GACA,KAAA,gBAAAC,GACA,KAAA,iBAAAC;AAAA,EAGrB;AAAA,EATqB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AAAA,EAMrB,aAAa,OAAOC,GAAoBC,IAA2B,IAAuB;AACtF,UAAMC,IAAqBD,EAAQ,QAAQ;AAC3C,QAAIC,MAAS;AACT,YAAM,IAAI,MAAM,8BAA8BA,CAAI,uBAAuB;AAE7E,UAAMV,IAAU,MAAMW,EAAW,OAAOH,GAAOC,CAAO,GAChDG,IAASC,EAAcJ,EAAQ,UAAU,QAAQ;AAAA,MACnD,YAAYA,EAAQ;AAAA,IAAA,CACvB,GACKK,IAAgC,CAAA;AACtC,aAASC,IAAI,GAAGA,IAAIH,EAAO,QAAQG;AAC/B,MAAAD,EAAMC,CAAC,IAAIH,EAAOG,CAAC;AAEvB,WAAO,IAAIjB;AAAA,MACPE;AAAA,MACAU;AAAA,MACAE;AAAA,MACAE;AAAA,MACAL,EAAQ,aAAa,CAAC,KAAK,GAAG;AAAA,MAC9BA,EAAQ,iBAAiB;AAAA,MACzBA,EAAQ,gBAAgB;AAAA,MACxBA,EAAQ,iBAAiB;AAAA,IAAA;AAAA,EAEjC;AAAA;AAAA,EAGA,IAAI,OAAqB;AACrB,WAAO,KAAK;AAAA,EAChB;AAAA;AAAA,EAGA,IAAI,SAA4B;AAC5B,WAAO,KAAK;AAAA,EAChB;AAAA;AAAA,EAGA,IAAI,QAA0C;AAC1C,WAAO,KAAK;AAAA,EAChB;AAAA;AAAA,EAGA,IAAI,aAAqB;AACrB,WAAO,KAAK,QAAQ;AAAA,EACxB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,KACFO,GACAP,IAAkC,IACP;AAC3B,WAAO,KAAK,QAAQO,GAAOP,CAAO;AAAA,EACtC;AAAA;AAAA,EAGA,MAAM,QACFO,GACAP,IAAkC,IACP;AAC3B,UAAMQ,IAAO,OAAOD,KAAU,WAAWA,IAAQ,MAC3CE,IAAW,MAAMC,EAAUH,CAAK,GAChC,EAAE,QAAAI,GAAQ,OAAAC,GAAO,SAAAC,GAAS,QAAAC,MAAW,KAAK,YAAYL,CAAQ,GAC9DM,IAAU,MAAM,KAAK,SAAS,IAAI,EAAE,CAAC,KAAK,SAAS,SAAS,GAAGJ,GAAQ,GAEvEK,IAAkB,KAAK,SAAS,YAAY,CAAC;AACnD,QAAIA,MAAoB;AACpB,YAAM,IAAI,MAAM,gCAAgC;AAEpD,UAAMC,IAAMF,EAAQC,CAAe;AACnC,QAAIC,MAAQ;AACR,YAAM,IAAI,MAAM,yBAAyBD,CAAe,6BAA6B;AAGzF,UAAME,IAAaC,EAAWF,EAAI,MAAsBA,EAAI,MAAM;AAAA,MAC9D,eAAeR,EAAS;AAAA,MACxB,gBAAgBA,EAAS;AAAA,MACzB,SAAAI;AAAA,MACA,QAAAC;AAAA,MACA,OAAAF;AAAA,MACA,eAAeZ,EAAQ,iBAAiB,KAAK;AAAA,MAC7C,cAAcA,EAAQ,gBAAgB,KAAK;AAAA,MAC3C,eAAe,KAAK;AAAA,IAAA,CACvB,GAUKoB,KAPFpB,EAAQ,YAAY,UACb,MAAM;AACH,YAAMqB,IAAU,IAAI,IAAIrB,EAAQ,OAAO;AACvC,aAAOkB,EAAW,OAAO,CAACI,MAAMD,EAAQ,IAAIC,EAAE,OAAO,CAAC;AAAA,IAC1D,OACAJ,GAEiB;AAAA,MAAI,CAACI,MAC5B,KAAK,aAAab,GAAUa,EAAE,MAAMA,EAAE,SAASA,EAAE,UAAU;AAAA,IAAA,GAGzDC,IAAkC,CAACd,EAAS,QAAQA,EAAS,KAAK;AACxE,WAAO;AAAA,MACH,IAAIe;AAAA,QACA,KAAK,YAAYJ,GAAYG,CAAI;AAAA,QACjCH;AAAA,QACA,KAAK;AAAA,QACLX;AAAA,QACAc;AAAA,QACAf;AAAA,MAAA;AAAA,IACJ;AAAA,EAER;AAAA,EAEQ,YAAYD,GAKlB;AACE,UAAM,CAACkB,GAAIC,CAAE,IAAI,KAAK,YAChBC,IAAKC,EAAUrB,GAAOkB,GAAIC,CAAE,GAC5BG,IAAMC,EAAUH,EAAG,KAAK,GACxBI,IAAMC,EAAMH,GAAKF,EAAG,MAAM,OAAOA,EAAG,MAAM,QAAQ,CAAC;AACzD,WAAO;AAAA,MACH,QAAQM,EAAgBF,GAAK,CAAC,GAAG,GAAGJ,EAAG,MAAM,QAAQA,EAAG,MAAM,KAAK,CAAC;AAAA,MACpE,OAAOA,EAAG;AAAA,MACV,SAASA,EAAG;AAAA,MACZ,QAAQA,EAAG;AAAA,IAAA;AAAA,EAEnB;AAAA,EAEQ,aACJlB,GACAyB,GACAC,GACAC,GACe;AACf,UAAM,CAACC,GAAIC,GAAIC,GAAIC,CAAE,IAAIN,EAAK,UAAA,GACxBO,IAAM,KAAK,IAAI,GAAGJ,CAAE,GACpBK,IAAM,KAAK,IAAI,GAAGJ,CAAE,GACpBK,IAAM,KAAK,IAAIlC,EAAS,OAAO8B,CAAE,GACjCK,IAAM,KAAK,IAAInC,EAAS,QAAQ+B,CAAE;AAExC,QAAIK;AACJ,QAAIF,IAAMF,KAAOG,IAAMF,GAAK;AACxB,YAAMI,IAAKH,IAAMF,GACXM,IAAKH,IAAMF,GACXM,IAAM,IAAI,WAAWF,IAAKC,IAAK,CAAC;AACtC,eAASE,IAAM,GAAGA,IAAMF,GAAIE,KAAO;AAC/B,cAAMC,MAAcR,IAAMO,KAAOxC,EAAS,QAAQgC,KAAO;AACzD,QAAAO,EAAI,IAAIvC,EAAS,KAAK,SAASyC,GAAWA,IAAYJ,IAAK,CAAC,GAAGG,IAAMH,IAAK,CAAC;AAAA,MAC/E;AACA,MAAAD,IAAU,IAAIM,EAASH,GAAKF,GAAIC,CAAE;AAAA,IACtC;AACI,MAAAF,IAAU,IAAIM,EAAS,IAAI,WAAW,CAAC,GAAG,GAAG,CAAC;AAGlD,UAAMC,IAAY,KAAK,OAAOjB,CAAO,KAAK,SAASA,CAAO;AAE1D,WAAO;AAAA,MACH,SAAAA;AAAA,MACA,WAAAiB;AAAA,MACA,YAAAhB;AAAA,MACA,MAAAF;AAAA,MACA,KAAKC;AAAA,MACL,MAAMiB;AAAA,MACN,MAAMhB;AAAA,MACN,KAAKF;AAAA,MACL,cAAcW;AAAA,IAAA;AAAA,EAEtB;AAAA,EAEQ,YACJzB,GACAiC,GACK;AACL,UAAMC,IAAIlC,EAAW,QACfmC,IAAO,IAAI,aAAaD,IAAI,CAAC,GAC7BE,IAAM,IAAI,WAAWF,CAAC,GACtBG,IAAO,IAAI,aAAaH,CAAC;AAC/B,aAAShD,IAAI,GAAGA,IAAIgD,GAAGhD,KAAK;AACxB,YAAMgB,IAAIF,EAAWd,CAAC;AACtB,MAAAiD,EAAKjD,IAAI,CAAC,IAAIgB,EAAE,KAAK,IACrBiC,EAAKjD,IAAI,IAAI,CAAC,IAAIgB,EAAE,KAAK,IACzBiC,EAAKjD,IAAI,IAAI,CAAC,IAAIgB,EAAE,KAAK,IACzBiC,EAAKjD,IAAI,IAAI,CAAC,IAAIgB,EAAE,KAAK,IACzBkC,EAAIlD,CAAC,IAAIgB,EAAE,SACXmC,EAAKnD,CAAC,IAAIgB,EAAE;AAAA,IAChB;AACA,WAAO,IAAIoC,EAAMH,GAAMC,GAAKC,GAAMJ,CAAS;AAAA,EAC/C;AACJ;"}
+{"version":3,"file":"detector.js","names":[],"sources":["../../../src/vision/tasks/detector.ts"],"sourcesContent":["/**\n * Object detection task using anchor-free YOLO ONNX models (v8/v9/v10/v11/v12).\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { decodeYolo } from \"../postprocess/detection\";\nimport { letterbox, toCHW, toFloat32, toFloat32Tensor } from \"../preprocess/image\";\nimport { Boxes, DetectionResults } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type BoundingBox, type DetectionResult, RGBImage } from \"../types\";\n\n/**\n * Decoder family for the model's detection head.\n *\n * - `\"yolo\"`: anchor-free YOLO head with output shape `[1, 4 + nc, N]` —\n *   covers YOLOv8, v9, v10, v11, v12, v26 detect exports.\n *\n * The SDK does **not** auto-detect the head from the model — the caller is\n * responsible for picking a head that matches their export. Future families\n * (v5/v6/v7 with `[1, N, 5+nc]`) will be added as new literal members.\n */\nexport type DetectorHead = \"yolo\";\n\nexport interface DetectorOptions extends OrtSessionOptions {\n    /**\n     * Decoder family for the detection head. Default `\"yolo\"` covers\n     * YOLOv8/v9/v10/v11/v12/v26.\n     */\n    readonly head?: DetectorHead;\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    /** Model input `[width, height]` for letterboxing. Defaults to `[640, 640]`. */\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 detections per image. */\n    readonly maxDetections?: number;\n}\n\nexport interface DetectorPredictOptions {\n    /** Override the default confidence threshold. */\n    readonly confThreshold?: number;\n    /** Override the default IoU threshold. */\n    readonly iouThreshold?: number;\n    /**\n     * If set, keep only detections 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 * Object detector for anchor-free YOLO ONNX models (v8/v9/v10/v11/v12).\n *\n * `predict()` returns `Promise<DetectionResults[]>` (length 1 for a single\n * image), mirroring Ultralytics' `YOLO(\"img.jpg\")`. Iterate the envelope for\n * per-instance dataclasses, or use the bulk `boxes` view (`.xyxy`, `.xywh`,\n * `.xyxyn`, `.xywhn`, `.cls`, `.conf`).\n *\n * @example\n * ```typescript\n * const det = await Detector.create(\"/models/yolov8n.onnx\");\n * const results = await det.predict(\"/images/street.jpg\");\n * const r = results[0];\n * console.log(r.boxes.xyxy, r.boxes.cls, r.boxes.conf, r.names);\n * for (const d of r) {\n *   console.log(d.cls, d.conf, d.box.xyxy);\n * }\n * ```\n */\nexport class Detector extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _head: DetectorHead,\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    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: DetectorOptions = {}): Promise<Detector> {\n        const head: DetectorHead = options.head ?? \"yolo\";\n        if (head !== \"yolo\") {\n            throw new Error(`Unsupported detector head '${head}'. Supported: 'yolo'.`);\n        }\n        const session = await OrtSession.create(model, options);\n        const labels = resolveLabels(options.labels ?? \"coco\", {\n            numClasses: options.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 Detector(\n            session,\n            head,\n            labels,\n            names,\n            options.inputSize ?? [640, 640],\n            options.confThreshold ?? 0.25,\n            options.iouThreshold ?? 0.45,\n            options.maxDetections ?? 300,\n        );\n    }\n\n    /** The decoder family used to interpret the model's output. */\n    get head(): DetectorHead {\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    /** Number of classes the model predicts. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /**\n     * Alias for {@link predict} — call the detector like a torch `nn.Module`.\n     *\n     * Use as `det.call(img)` since JavaScript class instances are not callable;\n     * for direct invocation, prefer `det.predict(img)`. The full\n     * {@link DetectorPredictOptions} (including `classes`) is supported.\n     */\n    async call(\n        image: ImageInput,\n        options: DetectorPredictOptions = {},\n    ): Promise<DetectionResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run detection on a single image. */\n    async predict(\n        image: ImageInput,\n        options: DetectorPredictOptions = {},\n    ): Promise<DetectionResults[]> {\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        const { tensor, scale, padLeft, padTop } = this._preprocess(original);\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Detector model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(`Detector model output ${firstOutputName} missing from run() result.`);\n        }\n\n        const decodedAll = decodeYolo(raw.data as Float32Array, raw.dims, {\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        });\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),\n        );\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        return [\n            new DetectionResults(\n                this._buildBoxes(detections, orig),\n                detections,\n                this._names,\n                original,\n                orig,\n                path,\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 _buildResult(\n        original: RGBImage,\n        bbox: BoundingBox,\n        classId: number,\n        confidence: number,\n    ): DetectionResult {\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 cropped: RGBImage;\n        if (cx2 > cx1 && cy2 > cy1) {\n            const cw = cx2 - cx1;\n            const ch = cy2 - cy1;\n            const out = new Uint8Array(cw * ch * 3);\n            for (let row = 0; row < ch; row++) {\n                const srcOffset = ((cy1 + row) * original.width + cx1) * 3;\n                out.set(original.data.subarray(srcOffset, srcOffset + cw * 3), row * cw * 3);\n            }\n            cropped = new RGBImage(out, cw, ch);\n        } else {\n            cropped = 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            croppedImage: cropped,\n        };\n    }\n\n    private _buildBoxes(\n        detections: readonly DetectionResult[],\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 DetectionResult;\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"],"mappings":";;;;;;;;;AA8EA,IAAa,IAAb,MAAa,UAAiB,EAAW;CAGhB;CACA;CACA;CACA;CACA;CACA;CACA;CARrB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,GACA,GACF;EADmB,AAEjB,MAAM,CAAO,GARI,KAAA,QAAA,GACA,KAAA,UAAA,GACA,KAAA,SAAA,GACA,KAAA,aAAA,GACA,KAAA,iBAAA,GACA,KAAA,gBAAA,GACA,KAAA,iBAAA;CAGrB;CAGA,aAAa,OAAO,GAAoB,IAA2B,CAAC,GAAsB;EACtF,IAAM,IAAqB,EAAQ,QAAQ;EAC3C,IAAI,MAAS,QACT,MAAU,MAAM,8BAA8B,EAAK,sBAAsB;EAE7E,IAAM,IAAU,MAAM,EAAW,OAAO,GAAO,CAAO,GAChD,IAAS,EAAc,EAAQ,UAAU,QAAQ,EACnD,YAAY,EAAQ,WACxB,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,EAAQ,aAAa,CAAC,KAAK,GAAG,GAC9B,EAAQ,iBAAiB,KACzB,EAAQ,gBAAgB,KACxB,EAAQ,iBAAiB,GAC7B;CACJ;CAGA,IAAI,OAAqB;EACrB,OAAO,KAAK;CAChB;CAGA,IAAI,SAA4B;EAC5B,OAAO,KAAK;CAChB;CAGA,IAAI,QAA0C;EAC1C,OAAO,KAAK;CAChB;CAGA,IAAI,aAAqB;EACrB,OAAO,KAAK,QAAQ;CACxB;CASA,MAAM,KACF,GACA,IAAkC,CAAC,GACR;EAC3B,OAAO,KAAK,QAAQ,GAAO,CAAO;CACtC;CAGA,MAAM,QACF,GACA,IAAkC,CAAC,GACR;EAC3B,IAAM,IAAO,OAAO,KAAU,WAAW,IAAQ,MAC3C,IAAW,MAAM,EAAU,CAAK,GAChC,EAAE,WAAQ,UAAO,YAAS,cAAW,KAAK,YAAY,CAAQ,GAC9D,IAAU,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC,GAEvE,IAAkB,KAAK,SAAS,YAAY;EAClD,IAAI,MAAoB,KAAA,GACpB,MAAU,MAAM,gCAAgC;EAEpD,IAAM,IAAM,EAAQ;EACpB,IAAI,MAAQ,KAAA,GACR,MAAU,MAAM,yBAAyB,EAAgB,4BAA4B;EAGzF,IAAM,IAAa,EAAW,EAAI,MAAsB,EAAI,MAAM;GAC9D,eAAe,EAAS;GACxB,gBAAgB,EAAS;GACzB;GACA;GACA;GACA,eAAe,EAAQ,iBAAiB,KAAK;GAC7C,cAAc,EAAQ,gBAAgB,KAAK;GAC3C,eAAe,KAAK;EACxB,CAAC,GAUK,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,UAAU,CAC/D,GAEM,IAAkC,CAAC,EAAS,QAAQ,EAAS,KAAK;EACxE,OAAO,CACH,IAAI,EACA,KAAK,YAAY,GAAY,CAAI,GACjC,GACA,KAAK,QACL,GACA,GACA,CACJ,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,aACI,GACA,GACA,GACA,GACe;EACf,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;EACJ,IAAI,IAAM,KAAO,IAAM,GAAK;GACxB,IAAM,IAAK,IAAM,GACX,IAAK,IAAM,GACX,IAAM,IAAI,WAAW,IAAK,IAAK,CAAC;GACtC,KAAK,IAAI,IAAM,GAAG,IAAM,GAAI,KAAO;IAC/B,IAAM,MAAc,IAAM,KAAO,EAAS,QAAQ,KAAO;IACzD,EAAI,IAAI,EAAS,KAAK,SAAS,GAAW,IAAY,IAAK,CAAC,GAAG,IAAM,IAAK,CAAC;GAC/E;GACA,IAAU,IAAI,EAAS,GAAK,GAAI,CAAE;EACtC,OACI,IAAU,IAAI,kBAAS,IAAI,WAAY,GAAG,GAAG,CAAC;EAGlD,IAAM,IAAY,KAAK,OAAO,MAAY,SAAS;EAEnD,OAAO;GACH;GACA;GACA;GACA;GACA,KAAK;GACL,MAAM;GACN,MAAM;GACN,KAAK;GACL,cAAc;EAClB;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;AACJ"}

package/dist/vision/tasks/segmenter.cjs

@@ -1,2 +1,2 @@
-"use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});const z=require("../core/session.cjs"),I=require("../io/image.cjs"),$=require("../labels.cjs"),B=require("../postprocess/segmentation.cjs"),x=require("../preprocess/image.cjs"),v=require("../results.cjs"),C=require("./base.cjs"),T=require("../types.cjs");class D extends C.VisionTask{constructor(n,s,o,e,t,a,i,r,p){super(n),this._head=s,this._labels=o,this._names=e,this._inputSize=t,this._confThreshold=a,this._iouThreshold=i,this._maxDetections=r,this._maskThreshold=p}_head;_labels;_names;_inputSize;_confThreshold;_iouThreshold;_maxDetections;_maskThreshold;static async create(n,s={}){const o=s.head??"yolo-seg";if(o!=="yolo-seg")throw new Error(`Unsupported segmenter head '${o}'. Supported: 'yolo-seg'.`);const e=await z.OrtSession.create(n,s),t=$.resolveLabels(s.labels??"coco",{numClasses:s.numClasses}),a={};for(let i=0;i<t.length;i++)a[i]=t[i];return new D(e,o,t,a,s.inputSize??[640,640],s.confThreshold??.25,s.iouThreshold??.45,s.maxDetections??300,s.maskThreshold??.5)}get head(){return this._head}get labels(){return this._labels}get names(){return this._names}get numClasses(){return this._labels.length}async call(n,s={}){return this.predict(n,s)}async predict(n,s={}){const o=typeof n=="string"?n:null,e=await I.loadImage(n),{tensor:t,scale:a,padLeft:i,padTop:r}=this._preprocess(e),p=await this._session.run({[this._session.inputName]:t}),{perAnchor:w,prototypes:_}=this._splitOutputs(p),f=B.decodeYoloSeg(w.data,w.dims,_.data,_.dims,{numClasses:this._labels.length,inputWidth:this._inputSize[0],inputHeight:this._inputSize[1],originalWidth:e.width,originalHeight:e.height,padLeft:i,padTop:r,scale:a,confThreshold:s.confThreshold??this._confThreshold,iouThreshold:s.iouThreshold??this._iouThreshold,maxDetections:this._maxDetections,maskThreshold:this._maskThreshold}),d=(s.classes!==void 0?(()=>{const h=new Set(s.classes);return f.filter(M=>h.has(M.classId))})():f).map(h=>this._buildResult(e,h.bbox,h.classId,h.confidence,h.mask)),u=[e.height,e.width];return[new v.SegmentationResults(this._buildBoxes(d,u),this._buildMasks(d,u),d,this._names,e,u,o)]}_preprocess(n){const[s,o]=this._inputSize,e=x.letterbox(n,s,o),t=x.toFloat32(e.image),a=x.toCHW(t,e.image.width,e.image.height,3);return{tensor:x.toFloat32Tensor(a,[1,3,e.image.height,e.image.width]),scale:e.scale,padLeft:e.padLeft,padTop:e.padTop}}_splitOutputs(n){let s,o;for(const e of this._session.outputNames){const t=n[e];t!==void 0&&(t.dims.length===3&&s===void 0?s=t:t.dims.length===4&&o===void 0&&(o=t))}if(s===void 0||o===void 0){const e=this._session.outputNames.map(t=>`${t}: ${JSON.stringify(n[t]?.dims??[])}`);throw new Error(`Segmenter expected one 3-D and one 4-D output, got [${e.join(", ")}].`)}return{perAnchor:s,prototypes:o}}_buildResult(n,s,o,e,t){const[a,i,r,p]=s.asIntXyxy(),w=Math.max(0,a),_=Math.max(0,i),f=Math.min(n.width,r),S=Math.min(n.height,p);let d,u=t;if(f>w&&S>_&&t.data.length>0){const M=f-w,O=S-_,c=Math.min(t.width,M),m=Math.min(t.height,O),y=new Uint8Array(c*m*3);for(let l=0;l<m;l++){const g=((_+l)*n.width+w)*3,R=l*c*3,k=l*t.width;for(let b=0;b<c;b++)if(t.data[k+b]!==0){const A=g+b*3,q=R+b*3;y[q]=n.data[A],y[q+1]=n.data[A+1],y[q+2]=n.data[A+2]}}if(d=new T.RGBImage(y,c,m),c!==t.width||m!==t.height){const l=new Uint8Array(c*m);for(let g=0;g<m;g++)l.set(t.data.subarray(g*t.width,g*t.width+c),g*c);u=new T.Mask(l,c,m)}}else u=new T.Mask(new Uint8Array(0),0,0),d=new T.RGBImage(new Uint8Array(0),0,0);const h=this._names[o]??`class_${o}`;return{classId:o,className:h,confidence:e,bbox:s,cls:o,name:h,conf:e,box:s,mask:u,segmentedImage:d}}_buildBoxes(n,s){const o=n.length,e=new Float32Array(o*4),t=new Int32Array(o),a=new Float32Array(o);for(let i=0;i<o;i++){const r=n[i];e[i*4]=r.bbox.x1,e[i*4+1]=r.bbox.y1,e[i*4+2]=r.bbox.x2,e[i*4+3]=r.bbox.y2,t[i]=r.classId,a[i]=r.confidence}return new v.Boxes(e,t,a,s)}_buildMasks(n,s){const o=new Float32Array(n.length*4);for(let e=0;e<n.length;e++){const t=n[e];o[e*4]=t.bbox.x1,o[e*4+1]=t.bbox.y1,o[e*4+2]=t.bbox.x2,o[e*4+3]=t.bbox.y2}return new v.Masks(n.map(e=>e.mask),o,s)}}exports.Segmenter=D;
-//# sourceMappingURL=segmenter.cjs.map
+const e=require("../types.cjs"),t=require("../results.cjs"),n=require("../labels.cjs"),r=require("../core/session.cjs"),i=require("../io/image.cjs"),a=require("../preprocess/image.cjs"),o=require("../postprocess/segmentation.cjs"),s=require("./base.cjs");var c=class c extends s.VisionTask{_head;_labels;_names;_inputSize;_confThreshold;_iouThreshold;_maxDetections;_maskThreshold;constructor(e,t,n,r,i,a,o,s,c){super(e),this._head=t,this._labels=n,this._names=r,this._inputSize=i,this._confThreshold=a,this._iouThreshold=o,this._maxDetections=s,this._maskThreshold=c}static async create(e,t={}){let i=t.head??`yolo-seg`;if(i!==`yolo-seg`)throw Error(`Unsupported segmenter head '${i}'. Supported: 'yolo-seg'.`);let a=await r.OrtSession.create(e,t),o=n.resolveLabels(t.labels??`coco`,{numClasses:t.numClasses}),s={};for(let e=0;e<o.length;e++)s[e]=o[e];return new c(a,i,o,s,t.inputSize??[640,640],t.confThreshold??.25,t.iouThreshold??.45,t.maxDetections??300,t.maskThreshold??.5)}get head(){return this._head}get labels(){return this._labels}get names(){return this._names}get numClasses(){return this._labels.length}async call(e,t={}){return this.predict(e,t)}async predict(e,n={}){let r=typeof e==`string`?e:null,a=await i.loadImage(e),{tensor:s,scale:c,padLeft:l,padTop:u}=this._preprocess(a),d=await this._session.run({[this._session.inputName]:s}),{perAnchor:f,prototypes:p}=this._splitOutputs(d),m=o.decodeYoloSeg(f.data,f.dims,p.data,p.dims,{numClasses:this._labels.length,inputWidth:this._inputSize[0],inputHeight:this._inputSize[1],originalWidth:a.width,originalHeight:a.height,padLeft:l,padTop:u,scale:c,confThreshold:n.confThreshold??this._confThreshold,iouThreshold:n.iouThreshold??this._iouThreshold,maxDetections:this._maxDetections,maskThreshold:this._maskThreshold}),h=(n.classes===void 0?m:(()=>{let e=new Set(n.classes);return m.filter(t=>e.has(t.classId))})()).map(e=>this._buildResult(a,e.bbox,e.classId,e.confidence,e.mask)),g=[a.height,a.width];return[new t.SegmentationResults(this._buildBoxes(h,g),this._buildMasks(h,g),h,this._names,a,g,r)]}_preprocess(e){let[t,n]=this._inputSize,r=a.letterbox(e,t,n);return{tensor:a.toFloat32Tensor(a.toCHW(a.toFloat32(r.image),r.image.width,r.image.height,3),[1,3,r.image.height,r.image.width]),scale:r.scale,padLeft:r.padLeft,padTop:r.padTop}}_splitOutputs(e){let t,n;for(let r of this._session.outputNames){let i=e[r];i!==void 0&&(i.dims.length===3&&t===void 0?t=i:i.dims.length===4&&n===void 0&&(n=i))}if(t===void 0||n===void 0){let t=this._session.outputNames.map(t=>`${t}: ${JSON.stringify(e[t]?.dims??[])}`);throw Error(`Segmenter expected one 3-D and one 4-D output, got [${t.join(`, `)}].`)}return{perAnchor:t,prototypes:n}}_buildResult(t,n,r,i,a){let[o,s,c,l]=n.asIntXyxy(),u=Math.max(0,o),d=Math.max(0,s),f=Math.min(t.width,c),p=Math.min(t.height,l),m,h=a;if(f>u&&p>d&&a.data.length>0){let n=f-u,r=p-d,i=Math.min(a.width,n),o=Math.min(a.height,r),s=new Uint8Array(i*o*3);for(let e=0;e<o;e++){let n=((d+e)*t.width+u)*3,r=e*i*3,o=e*a.width;for(let e=0;e<i;e++)if(a.data[o+e]!==0){let i=n+e*3,a=r+e*3;s[a]=t.data[i],s[a+1]=t.data[i+1],s[a+2]=t.data[i+2]}}if(m=new e.RGBImage(s,i,o),i!==a.width||o!==a.height){let t=new Uint8Array(i*o);for(let e=0;e<o;e++)t.set(a.data.subarray(e*a.width,e*a.width+i),e*i);h=new e.Mask(t,i,o)}}else h=new e.Mask(new Uint8Array,0,0),m=new e.RGBImage(new Uint8Array,0,0);let g=this._names[r]??`class_${r}`;return{classId:r,className:g,confidence:i,bbox:n,cls:r,name:g,conf:i,box:n,mask:h,segmentedImage:m}}_buildBoxes(e,n){let r=e.length,i=new Float32Array(r*4),a=new Int32Array(r),o=new Float32Array(r);for(let t=0;t<r;t++){let n=e[t];i[t*4]=n.bbox.x1,i[t*4+1]=n.bbox.y1,i[t*4+2]=n.bbox.x2,i[t*4+3]=n.bbox.y2,a[t]=n.classId,o[t]=n.confidence}return new t.Boxes(i,a,o,n)}_buildMasks(e,n){let r=new Float32Array(e.length*4);for(let t=0;t<e.length;t++){let n=e[t];r[t*4]=n.bbox.x1,r[t*4+1]=n.bbox.y1,r[t*4+2]=n.bbox.x2,r[t*4+3]=n.bbox.y2}return new t.Masks(e.map(e=>e.mask),r,n)}};exports.Segmenter=c;
+//# sourceMappingURL=segmenter.cjs.map

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

@@ -1 +1 @@
-{"version":3,"file":"segmenter.cjs","sources":["../../../src/vision/tasks/segmenter.ts"],"sourcesContent":["/**\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 { type ImageInput, loadImage } from \"../io/image\";\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    /** Model input `[width, height]` for letterboxing. Defaults to `[640, 640]`. */\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 ?? \"coco\", {\n            numClasses: options.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            options.inputSize ?? [640, 640],\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    /** 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 path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        const { tensor, scale, padLeft, padTop } = this._preprocess(original);\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\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        return [\n            new SegmentationResults(\n                this._buildBoxes(detections, orig),\n                this._buildMasks(detections, orig),\n                detections,\n                this._names,\n                original,\n                orig,\n                path,\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"],"names":["Segmenter","VisionTask","session","_head","_labels","_names","_inputSize","_confThreshold","_iouThreshold","_maxDetections","_maskThreshold","model","options","head","OrtSession","labels","resolveLabels","names","image","path","original","loadImage","tensor","scale","padLeft","padTop","outputs","perAnchor","prototypes","decodedAll","decodeYoloSeg","detections","allowed","d","orig","SegmentationResults","tw","th","lb","letterbox","f32","toFloat32","chw","toCHW","toFloat32Tensor","name","shapes","n","bbox","classId","confidence","mask","x1","y1","x2","y2","cx1","cy1","cx2","cy2","segmentedImage","finalMask","cropW","cropH","mw","mh","segData","row","srcRowOffset","dstRowOffset","maskRowOffset","col","s","RGBImage","trimmed","Mask","className","origShape","xyxy","cls","conf","Boxes","i","Masks"],"mappings":"+UAoFO,MAAMA,UAAkBC,EAAAA,UAAW,CAC9B,YACJC,EACiBC,EACAC,EACAC,EACAC,EACAC,EACAC,EACAC,EACAC,EACnB,CACE,MAAMR,CAAO,EATI,KAAA,MAAAC,EACA,KAAA,QAAAC,EACA,KAAA,OAAAC,EACA,KAAA,WAAAC,EACA,KAAA,eAAAC,EACA,KAAA,cAAAC,EACA,KAAA,eAAAC,EACA,KAAA,eAAAC,CAGrB,CAVqB,MACA,QACA,OACA,WACA,eACA,cACA,eACA,eAMrB,aAAa,OAAOC,EAAoBC,EAA4B,GAAwB,CACxF,MAAMC,EAAsBD,EAAQ,MAAQ,WAC5C,GAAIC,IAAS,WACT,MAAM,IAAI,MAAM,+BAA+BA,CAAI,2BAA2B,EAElF,MAAMX,EAAU,MAAMY,EAAAA,WAAW,OAAOH,EAAOC,CAAO,EAChDG,EAASC,EAAAA,cAAcJ,EAAQ,QAAU,OAAQ,CACnD,WAAYA,EAAQ,UAAA,CACvB,EACKK,EAAgC,CAAA,EACtC,QAAS,EAAI,EAAG,EAAIF,EAAO,OAAQ,IAC/BE,EAAM,CAAC,EAAIF,EAAO,CAAC,EAEvB,OAAO,IAAIf,EACPE,EACAW,EACAE,EACAE,EACAL,EAAQ,WAAa,CAAC,IAAK,GAAG,EAC9BA,EAAQ,eAAiB,IACzBA,EAAQ,cAAgB,IACxBA,EAAQ,eAAiB,IACzBA,EAAQ,eAAiB,EAAA,CAEjC,CAGA,IAAI,MAAsB,CACtB,OAAO,KAAK,KAChB,CAGA,IAAI,QAA4B,CAC5B,OAAO,KAAK,OAChB,CAGA,IAAI,OAA0C,CAC1C,OAAO,KAAK,MAChB,CAGA,IAAI,YAAqB,CACrB,OAAO,KAAK,QAAQ,MACxB,CAGA,MAAM,KACFM,EACAN,EAAmC,GACL,CAC9B,OAAO,KAAK,QAAQM,EAAON,CAAO,CACtC,CAGA,MAAM,QACFM,EACAN,EAAmC,GACL,CAC9B,MAAMO,EAAO,OAAOD,GAAU,SAAWA,EAAQ,KAC3CE,EAAW,MAAMC,EAAAA,UAAUH,CAAK,EAChC,CAAE,OAAAI,EAAQ,MAAAC,EAAO,QAAAC,EAAS,OAAAC,GAAW,KAAK,YAAYL,CAAQ,EAC9DM,EAAU,MAAM,KAAK,SAAS,IAAI,CAAE,CAAC,KAAK,SAAS,SAAS,EAAGJ,EAAQ,EAEvE,CAAE,UAAAK,EAAW,WAAAC,CAAA,EAAe,KAAK,cAAcF,CAAO,EAEtDG,EAAaC,EAAAA,cACfH,EAAU,KACVA,EAAU,KACVC,EAAW,KACXA,EAAW,KACX,CACI,WAAY,KAAK,QAAQ,OACzB,WAAY,KAAK,WAAW,CAAC,EAC7B,YAAa,KAAK,WAAW,CAAC,EAC9B,cAAeR,EAAS,MACxB,eAAgBA,EAAS,OACzB,QAAAI,EACA,OAAAC,EACA,MAAAF,EACA,cAAeX,EAAQ,eAAiB,KAAK,eAC7C,aAAcA,EAAQ,cAAgB,KAAK,cAC3C,cAAe,KAAK,eACpB,cAAe,KAAK,cAAA,CACxB,EAWEmB,GAPFnB,EAAQ,UAAY,QACb,IAAM,CACH,MAAMoB,EAAU,IAAI,IAAIpB,EAAQ,OAAO,EACvC,OAAOiB,EAAW,OAAQI,GAAMD,EAAQ,IAAIC,EAAE,OAAO,CAAC,CAC1D,KACAJ,GAEiB,IAAKI,GAC5B,KAAK,aAAab,EAAUa,EAAE,KAAMA,EAAE,QAASA,EAAE,WAAYA,EAAE,IAAI,CAAA,EAGjEC,EAAkC,CAACd,EAAS,OAAQA,EAAS,KAAK,EACxE,MAAO,CACH,IAAIe,EAAAA,oBACA,KAAK,YAAYJ,EAAYG,CAAI,EACjC,KAAK,YAAYH,EAAYG,CAAI,EACjCH,EACA,KAAK,OACLX,EACAc,EACAf,CAAA,CACJ,CAER,CAEQ,YAAYD,EAKlB,CACE,KAAM,CAACkB,EAAIC,CAAE,EAAI,KAAK,WAChBC,EAAKC,EAAAA,UAAUrB,EAAOkB,EAAIC,CAAE,EAC5BG,EAAMC,EAAAA,UAAUH,EAAG,KAAK,EACxBI,EAAMC,EAAAA,MAAMH,EAAKF,EAAG,MAAM,MAAOA,EAAG,MAAM,OAAQ,CAAC,EACzD,MAAO,CACH,OAAQM,EAAAA,gBAAgBF,EAAK,CAAC,EAAG,EAAGJ,EAAG,MAAM,OAAQA,EAAG,MAAM,KAAK,CAAC,EACpE,MAAOA,EAAG,MACV,QAASA,EAAG,QACZ,OAAQA,EAAG,MAAA,CAEnB,CAEQ,cAAcZ,EAGpB,CACE,IAAIC,EACAC,EACJ,UAAWiB,KAAQ,KAAK,SAAS,YAAa,CAC1C,MAAM,EAAInB,EAAQmB,CAAI,EAClB,IAAM,SACN,EAAE,KAAK,SAAW,GAAKlB,IAAc,OACrCA,EAAY,EACL,EAAE,KAAK,SAAW,GAAKC,IAAe,SAC7CA,EAAa,GAErB,CACA,GAAID,IAAc,QAAaC,IAAe,OAAW,CACrD,MAAMkB,EAAS,KAAK,SAAS,YAAY,IACpCC,GAAM,GAAGA,CAAC,KAAK,KAAK,UAAUrB,EAAQqB,CAAC,GAAG,MAAQ,CAAA,CAAE,CAAC,EAAA,EAE1D,MAAM,IAAI,MACN,uDAAuDD,EAAO,KAAK,IAAI,CAAC,IAAA,CAEhF,CACA,MAAO,CAAE,UAAAnB,EAAW,WAAAC,CAAA,CACxB,CAEQ,aACJR,EACA4B,EACAC,EACAC,EACAC,EACkB,CAClB,KAAM,CAACC,EAAIC,EAAIC,EAAIC,CAAE,EAAIP,EAAK,UAAA,EACxBQ,EAAM,KAAK,IAAI,EAAGJ,CAAE,EACpBK,EAAM,KAAK,IAAI,EAAGJ,CAAE,EACpBK,EAAM,KAAK,IAAItC,EAAS,MAAOkC,CAAE,EACjCK,EAAM,KAAK,IAAIvC,EAAS,OAAQmC,CAAE,EAExC,IAAIK,EACAC,EAAYV,EAChB,GAAIO,EAAMF,GAAOG,EAAMF,GAAON,EAAK,KAAK,OAAS,EAAG,CAChD,MAAMW,EAAQJ,EAAMF,EACdO,EAAQJ,EAAMF,EACdO,EAAK,KAAK,IAAIb,EAAK,MAAOW,CAAK,EAC/BG,EAAK,KAAK,IAAId,EAAK,OAAQY,CAAK,EAChCG,EAAU,IAAI,WAAWF,EAAKC,EAAK,CAAC,EAC1C,QAASE,EAAM,EAAGA,EAAMF,EAAIE,IAAO,CAC/B,MAAMC,IAAiBX,EAAMU,GAAO/C,EAAS,MAAQoC,GAAO,EACtDa,EAAeF,EAAMH,EAAK,EAC1BM,EAAgBH,EAAMhB,EAAK,MACjC,QAASoB,EAAM,EAAGA,EAAMP,EAAIO,IAExB,GADUpB,EAAK,KAAKmB,EAAgBC,CAAG,IAC7B,EAAG,CACT,MAAMC,EAAIJ,EAAeG,EAAM,EACzBtC,EAAIoC,EAAeE,EAAM,EAC/BL,EAAQjC,CAAC,EAAIb,EAAS,KAAKoD,CAAC,EAC5BN,EAAQjC,EAAI,CAAC,EAAIb,EAAS,KAAKoD,EAAI,CAAC,EACpCN,EAAQjC,EAAI,CAAC,EAAIb,EAAS,KAAKoD,EAAI,CAAC,CACxC,CAER,CAEA,GADAZ,EAAiB,IAAIa,EAAAA,SAASP,EAASF,EAAIC,CAAE,EACzCD,IAAOb,EAAK,OAASc,IAAOd,EAAK,OAAQ,CACzC,MAAMuB,EAAU,IAAI,WAAWV,EAAKC,CAAE,EACtC,QAASE,EAAM,EAAGA,EAAMF,EAAIE,IACxBO,EAAQ,IACJvB,EAAK,KAAK,SAASgB,EAAMhB,EAAK,MAAOgB,EAAMhB,EAAK,MAAQa,CAAE,EAC1DG,EAAMH,CAAA,EAGdH,EAAY,IAAIc,EAAAA,KAAKD,EAASV,EAAIC,CAAE,CACxC,CACJ,MACIJ,EAAY,IAAIc,EAAAA,KAAK,IAAI,WAAW,CAAC,EAAG,EAAG,CAAC,EAC5Cf,EAAiB,IAAIa,EAAAA,SAAS,IAAI,WAAW,CAAC,EAAG,EAAG,CAAC,EAGzD,MAAMG,EAAY,KAAK,OAAO3B,CAAO,GAAK,SAASA,CAAO,GAE1D,MAAO,CACH,QAAAA,EACA,UAAA2B,EACA,WAAA1B,EACA,KAAAF,EACA,IAAKC,EACL,KAAM2B,EACN,KAAM1B,EACN,IAAKF,EACL,KAAMa,EACN,eAAAD,CAAA,CAER,CAEQ,YACJ7B,EACA8C,EACK,CACL,MAAM9B,EAAIhB,EAAW,OACf+C,EAAO,IAAI,aAAa/B,EAAI,CAAC,EAC7BgC,EAAM,IAAI,WAAWhC,CAAC,EACtBiC,EAAO,IAAI,aAAajC,CAAC,EAC/B,QAAS,EAAI,EAAG,EAAIA,EAAG,IAAK,CACxB,MAAMd,EAAIF,EAAW,CAAC,EACtB+C,EAAK,EAAI,CAAC,EAAI7C,EAAE,KAAK,GACrB6C,EAAK,EAAI,EAAI,CAAC,EAAI7C,EAAE,KAAK,GACzB6C,EAAK,EAAI,EAAI,CAAC,EAAI7C,EAAE,KAAK,GACzB6C,EAAK,EAAI,EAAI,CAAC,EAAI7C,EAAE,KAAK,GACzB8C,EAAI,CAAC,EAAI9C,EAAE,QACX+C,EAAK,CAAC,EAAI/C,EAAE,UAChB,CACA,OAAO,IAAIgD,EAAAA,MAAMH,EAAMC,EAAKC,EAAMH,CAAS,CAC/C,CAEQ,YACJ9C,EACA8C,EACK,CACL,MAAMC,EAAO,IAAI,aAAa/C,EAAW,OAAS,CAAC,EACnD,QAASmD,EAAI,EAAGA,EAAInD,EAAW,OAAQmD,IAAK,CACxC,MAAMjD,EAAIF,EAAWmD,CAAC,EACtBJ,EAAKI,EAAI,CAAC,EAAIjD,EAAE,KAAK,GACrB6C,EAAKI,EAAI,EAAI,CAAC,EAAIjD,EAAE,KAAK,GACzB6C,EAAKI,EAAI,EAAI,CAAC,EAAIjD,EAAE,KAAK,GACzB6C,EAAKI,EAAI,EAAI,CAAC,EAAIjD,EAAE,KAAK,EAC7B,CACA,OAAO,IAAIkD,EAAAA,MACPpD,EAAW,IAAKE,GAAMA,EAAE,IAAI,EAC5B6C,EACAD,CAAA,CAER,CACJ"}
+{"version":3,"file":"segmenter.cjs","names":[],"sources":["../../../src/vision/tasks/segmenter.ts"],"sourcesContent":["/**\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 { type ImageInput, loadImage } from \"../io/image\";\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    /** Model input `[width, height]` for letterboxing. Defaults to `[640, 640]`. */\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 ?? \"coco\", {\n            numClasses: options.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            options.inputSize ?? [640, 640],\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    /** 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 path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        const { tensor, scale, padLeft, padTop } = this._preprocess(original);\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\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        return [\n            new SegmentationResults(\n                this._buildBoxes(detections, orig),\n                this._buildMasks(detections, orig),\n                detections,\n                this._names,\n                original,\n                orig,\n                path,\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":"+PAoFA,IAAa,EAAb,MAAa,UAAkB,EAAA,UAAW,CAGjB,MACA,QACA,OACA,WACA,eACA,cACA,eACA,eATrB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EACA,EACA,EACF,CACE,MAAM,CAAO,EATI,KAAA,MAAA,EACA,KAAA,QAAA,EACA,KAAA,OAAA,EACA,KAAA,WAAA,EACA,KAAA,eAAA,EACA,KAAA,cAAA,EACA,KAAA,eAAA,EACA,KAAA,eAAA,CAGrB,CAGA,aAAa,OAAO,EAAoB,EAA4B,CAAC,EAAuB,CACxF,IAAM,EAAsB,EAAQ,MAAQ,WAC5C,GAAI,IAAS,WACT,MAAU,MAAM,+BAA+B,EAAK,0BAA0B,EAElF,IAAM,EAAU,MAAM,EAAA,WAAW,OAAO,EAAO,CAAO,EAChD,EAAS,EAAA,cAAc,EAAQ,QAAU,OAAQ,CACnD,WAAY,EAAQ,UACxB,CAAC,EACK,EAAgC,CAAC,EACvC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAO,OAAQ,IAC/B,EAAM,GAAK,EAAO,GAEtB,OAAO,IAAI,EACP,EACA,EACA,EACA,EACA,EAAQ,WAAa,CAAC,IAAK,GAAG,EAC9B,EAAQ,eAAiB,IACzB,EAAQ,cAAgB,IACxB,EAAQ,eAAiB,IACzB,EAAQ,eAAiB,EAC7B,CACJ,CAGA,IAAI,MAAsB,CACtB,OAAO,KAAK,KAChB,CAGA,IAAI,QAA4B,CAC5B,OAAO,KAAK,OAChB,CAGA,IAAI,OAA0C,CAC1C,OAAO,KAAK,MAChB,CAGA,IAAI,YAAqB,CACrB,OAAO,KAAK,QAAQ,MACxB,CAGA,MAAM,KACF,EACA,EAAmC,CAAC,EACN,CAC9B,OAAO,KAAK,QAAQ,EAAO,CAAO,CACtC,CAGA,MAAM,QACF,EACA,EAAmC,CAAC,EACN,CAC9B,IAAM,EAAO,OAAO,GAAU,SAAW,EAAQ,KAC3C,EAAW,MAAM,EAAA,UAAU,CAAK,EAChC,CAAE,SAAQ,QAAO,UAAS,UAAW,KAAK,YAAY,CAAQ,EAC9D,EAAU,MAAM,KAAK,SAAS,IAAI,EAAG,KAAK,SAAS,WAAY,CAAO,CAAC,EAEvE,CAAE,YAAW,cAAe,KAAK,cAAc,CAAO,EAEtD,EAAa,EAAA,cACf,EAAU,KACV,EAAU,KACV,EAAW,KACX,EAAW,KACX,CACI,WAAY,KAAK,QAAQ,OACzB,WAAY,KAAK,WAAW,GAC5B,YAAa,KAAK,WAAW,GAC7B,cAAe,EAAS,MACxB,eAAgB,EAAS,OACzB,UACA,SACA,QACA,cAAe,EAAQ,eAAiB,KAAK,eAC7C,aAAc,EAAQ,cAAgB,KAAK,cAC3C,cAAe,KAAK,eACpB,cAAe,KAAK,cACxB,CACJ,EAUM,GAPF,EAAQ,UAAY,IAAA,GAKd,OAJO,CACH,IAAM,EAAU,IAAI,IAAI,EAAQ,OAAO,EACvC,OAAO,EAAW,OAAQ,GAAM,EAAQ,IAAI,EAAE,OAAO,CAAC,CAC1D,EAAA,CAAG,EACH,CAEiB,IAAK,GAC5B,KAAK,aAAa,EAAU,EAAE,KAAM,EAAE,QAAS,EAAE,WAAY,EAAE,IAAI,CACvE,EAEM,EAAkC,CAAC,EAAS,OAAQ,EAAS,KAAK,EACxE,MAAO,CACH,IAAI,EAAA,oBACA,KAAK,YAAY,EAAY,CAAI,EACjC,KAAK,YAAY,EAAY,CAAI,EACjC,EACA,KAAK,OACL,EACA,EACA,CACJ,CACJ,CACJ,CAEA,YAAoB,EAKlB,CACE,GAAM,CAAC,EAAI,GAAM,KAAK,WAChB,EAAK,EAAA,UAAU,EAAO,EAAI,CAAE,EAGlC,MAAO,CACH,OAAQ,EAAA,gBAFA,EAAA,MADA,EAAA,UAAU,EAAG,KACP,EAAK,EAAG,MAAM,MAAO,EAAG,MAAM,OAAQ,CAE5B,EAAK,CAAC,EAAG,EAAG,EAAG,MAAM,OAAQ,EAAG,MAAM,KAAK,CAAC,EACpE,MAAO,EAAG,MACV,QAAS,EAAG,QACZ,OAAQ,EAAG,MACf,CACJ,CAEA,cAAsB,EAGpB,CACE,IAAI,EACA,EACJ,IAAK,IAAM,KAAQ,KAAK,SAAS,YAAa,CAC1C,IAAM,EAAI,EAAQ,GACd,IAAM,IAAA,KACN,EAAE,KAAK,SAAW,GAAK,IAAc,IAAA,GACrC,EAAY,EACL,EAAE,KAAK,SAAW,GAAK,IAAe,IAAA,KAC7C,EAAa,GAErB,CACA,GAAI,IAAc,IAAA,IAAa,IAAe,IAAA,GAAW,CACrD,IAAM,EAAS,KAAK,SAAS,YAAY,IACpC,GAAM,GAAG,EAAE,IAAI,KAAK,UAAU,EAAQ,EAAE,EAAE,MAAQ,CAAC,CAAC,GACzD,EACA,MAAU,MACN,uDAAuD,EAAO,KAAK,IAAI,EAAE,GAC7E,CACJ,CACA,MAAO,CAAE,YAAW,YAAW,CACnC,CAEA,aACI,EACA,EACA,EACA,EACA,EACkB,CAClB,GAAM,CAAC,EAAI,EAAI,EAAI,GAAM,EAAK,UAAU,EAClC,EAAM,KAAK,IAAI,EAAG,CAAE,EACpB,EAAM,KAAK,IAAI,EAAG,CAAE,EACpB,EAAM,KAAK,IAAI,EAAS,MAAO,CAAE,EACjC,EAAM,KAAK,IAAI,EAAS,OAAQ,CAAE,EAEpC,EACA,EAAY,EAChB,GAAI,EAAM,GAAO,EAAM,GAAO,EAAK,KAAK,OAAS,EAAG,CAChD,IAAM,EAAQ,EAAM,EACd,EAAQ,EAAM,EACd,EAAK,KAAK,IAAI,EAAK,MAAO,CAAK,EAC/B,EAAK,KAAK,IAAI,EAAK,OAAQ,CAAK,EAChC,EAAU,IAAI,WAAW,EAAK,EAAK,CAAC,EAC1C,IAAK,IAAI,EAAM,EAAG,EAAM,EAAI,IAAO,CAC/B,IAAM,IAAiB,EAAM,GAAO,EAAS,MAAQ,GAAO,EACtD,EAAe,EAAM,EAAK,EAC1B,EAAgB,EAAM,EAAK,MACjC,IAAK,IAAI,EAAM,EAAG,EAAM,EAAI,IAExB,GADU,EAAK,KAAK,EAAgB,KAC1B,EAAG,CACT,IAAM,EAAI,EAAe,EAAM,EACzB,EAAI,EAAe,EAAM,EAC/B,EAAQ,GAAK,EAAS,KAAK,GAC3B,EAAQ,EAAI,GAAK,EAAS,KAAK,EAAI,GACnC,EAAQ,EAAI,GAAK,EAAS,KAAK,EAAI,EACvC,CAER,CAEA,GADA,EAAiB,IAAI,EAAA,SAAS,EAAS,EAAI,CAAE,EACzC,IAAO,EAAK,OAAS,IAAO,EAAK,OAAQ,CACzC,IAAM,EAAU,IAAI,WAAW,EAAK,CAAE,EACtC,IAAK,IAAI,EAAM,EAAG,EAAM,EAAI,IACxB,EAAQ,IACJ,EAAK,KAAK,SAAS,EAAM,EAAK,MAAO,EAAM,EAAK,MAAQ,CAAE,EAC1D,EAAM,CACV,EAEJ,EAAY,IAAI,EAAA,KAAK,EAAS,EAAI,CAAE,CACxC,CACJ,KACI,GAAY,IAAI,EAAA,KAAK,IAAI,WAAe,EAAG,CAAC,EAC5C,EAAiB,IAAI,EAAA,SAAS,IAAI,WAAe,EAAG,CAAC,EAGzD,IAAM,EAAY,KAAK,OAAO,IAAY,SAAS,IAEnD,MAAO,CACH,UACA,YACA,aACA,OACA,IAAK,EACL,KAAM,EACN,KAAM,EACN,IAAK,EACL,KAAM,EACN,gBACJ,CACJ,CAEA,YACI,EACA,EACK,CACL,IAAM,EAAI,EAAW,OACf,EAAO,IAAI,aAAa,EAAI,CAAC,EAC7B,EAAM,IAAI,WAAW,CAAC,EACtB,EAAO,IAAI,aAAa,CAAC,EAC/B,IAAK,IAAI,EAAI,EAAG,EAAI,EAAG,IAAK,CACxB,IAAM,EAAI,EAAW,GACrB,EAAK,EAAI,GAAK,EAAE,KAAK,GACrB,EAAK,EAAI,EAAI,GAAK,EAAE,KAAK,GACzB,EAAK,EAAI,EAAI,GAAK,EAAE,KAAK,GACzB,EAAK,EAAI,EAAI,GAAK,EAAE,KAAK,GACzB,EAAI,GAAK,EAAE,QACX,EAAK,GAAK,EAAE,UAChB,CACA,OAAO,IAAI,EAAA,MAAM,EAAM,EAAK,EAAM,CAAS,CAC/C,CAEA,YACI,EACA,EACK,CACL,IAAM,EAAO,IAAI,aAAa,EAAW,OAAS,CAAC,EACnD,IAAK,IAAI,EAAI,EAAG,EAAI,EAAW,OAAQ,IAAK,CACxC,IAAM,EAAI,EAAW,GACrB,EAAK,EAAI,GAAK,EAAE,KAAK,GACrB,EAAK,EAAI,EAAI,GAAK,EAAE,KAAK,GACzB,EAAK,EAAI,EAAI,GAAK,EAAE,KAAK,GACzB,EAAK,EAAI,EAAI,GAAK,EAAE,KAAK,EAC7B,CACA,OAAO,IAAI,EAAA,MACP,EAAW,IAAK,GAAM,EAAE,IAAI,EAC5B,EACA,CACJ,CACJ,CACJ"}