tempest-react-sdk 0.21.0 → 0.23.0

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

@@ -0,0 +1 @@
+{"version":3,"file":"detector.cjs","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","xyxy","cls","conf","Boxes"],"mappings":"4UA8EO,MAAMA,UAAiBC,EAAAA,UAAW,CAC7B,YACJC,EACiBC,EACAC,EACAC,EACAC,EACAC,EACAC,EACAC,EACnB,CACE,MAAMP,CAAO,EARI,KAAA,MAAAC,EACA,KAAA,QAAAC,EACA,KAAA,OAAAC,EACA,KAAA,WAAAC,EACA,KAAA,eAAAC,EACA,KAAA,cAAAC,EACA,KAAA,eAAAC,CAGrB,CATqB,MACA,QACA,OACA,WACA,eACA,cACA,eAMrB,aAAa,OAAOC,EAAoBC,EAA2B,GAAuB,CACtF,MAAMC,EAAqBD,EAAQ,MAAQ,OAC3C,GAAIC,IAAS,OACT,MAAM,IAAI,MAAM,8BAA8BA,CAAI,uBAAuB,EAE7E,MAAMV,EAAU,MAAMW,EAAAA,WAAW,OAAOH,EAAOC,CAAO,EAChDG,EAASC,EAAAA,cAAcJ,EAAQ,QAAU,OAAQ,CACnD,WAAYA,EAAQ,UAAA,CACvB,EACKK,EAAgC,CAAA,EACtC,QAASC,EAAI,EAAGA,EAAIH,EAAO,OAAQG,IAC/BD,EAAMC,CAAC,EAAIH,EAAOG,CAAC,EAEvB,OAAO,IAAIjB,EACPE,EACAU,EACAE,EACAE,EACAL,EAAQ,WAAa,CAAC,IAAK,GAAG,EAC9BA,EAAQ,eAAiB,IACzBA,EAAQ,cAAgB,IACxBA,EAAQ,eAAiB,GAAA,CAEjC,CAGA,IAAI,MAAqB,CACrB,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,CASA,MAAM,KACFO,EACAP,EAAkC,GACP,CAC3B,OAAO,KAAK,QAAQO,EAAOP,CAAO,CACtC,CAGA,MAAM,QACFO,EACAP,EAAkC,GACP,CAC3B,MAAMQ,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,EAEvEK,EAAkB,KAAK,SAAS,YAAY,CAAC,EACnD,GAAIA,IAAoB,OACpB,MAAM,IAAI,MAAM,gCAAgC,EAEpD,MAAMC,EAAMF,EAAQC,CAAe,EACnC,GAAIC,IAAQ,OACR,MAAM,IAAI,MAAM,yBAAyBD,CAAe,6BAA6B,EAGzF,MAAME,EAAaC,EAAAA,WAAWF,EAAI,KAAsBA,EAAI,KAAM,CAC9D,cAAeR,EAAS,MACxB,eAAgBA,EAAS,OACzB,QAAAI,EACA,OAAAC,EACA,MAAAF,EACA,cAAeZ,EAAQ,eAAiB,KAAK,eAC7C,aAAcA,EAAQ,cAAgB,KAAK,cAC3C,cAAe,KAAK,cAAA,CACvB,EAUKoB,GAPFpB,EAAQ,UAAY,QACb,IAAM,CACH,MAAMqB,EAAU,IAAI,IAAIrB,EAAQ,OAAO,EACvC,OAAOkB,EAAW,OAAQI,GAAMD,EAAQ,IAAIC,EAAE,OAAO,CAAC,CAC1D,KACAJ,GAEiB,IAAKI,GAC5B,KAAK,aAAab,EAAUa,EAAE,KAAMA,EAAE,QAASA,EAAE,UAAU,CAAA,EAGzDC,EAAkC,CAACd,EAAS,OAAQA,EAAS,KAAK,EACxE,MAAO,CACH,IAAIe,EAAAA,iBACA,KAAK,YAAYJ,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,aACJlB,EACAyB,EACAC,EACAC,EACe,CACf,KAAM,CAACC,EAAIC,EAAIC,EAAIC,CAAE,EAAIN,EAAK,UAAA,EACxBO,EAAM,KAAK,IAAI,EAAGJ,CAAE,EACpBK,EAAM,KAAK,IAAI,EAAGJ,CAAE,EACpBK,EAAM,KAAK,IAAIlC,EAAS,MAAO8B,CAAE,EACjCK,EAAM,KAAK,IAAInC,EAAS,OAAQ+B,CAAE,EAExC,IAAIK,EACJ,GAAIF,EAAMF,GAAOG,EAAMF,EAAK,CACxB,MAAMI,EAAKH,EAAMF,EACXM,EAAKH,EAAMF,EACXM,EAAM,IAAI,WAAWF,EAAKC,EAAK,CAAC,EACtC,QAASE,EAAM,EAAGA,EAAMF,EAAIE,IAAO,CAC/B,MAAMC,IAAcR,EAAMO,GAAOxC,EAAS,MAAQgC,GAAO,EACzDO,EAAI,IAAIvC,EAAS,KAAK,SAASyC,EAAWA,EAAYJ,EAAK,CAAC,EAAGG,EAAMH,EAAK,CAAC,CAC/E,CACAD,EAAU,IAAIM,EAAAA,SAASH,EAAKF,EAAIC,CAAE,CACtC,MACIF,EAAU,IAAIM,EAAAA,SAAS,IAAI,WAAW,CAAC,EAAG,EAAG,CAAC,EAGlD,MAAMC,EAAY,KAAK,OAAOjB,CAAO,GAAK,SAASA,CAAO,GAE1D,MAAO,CACH,QAAAA,EACA,UAAAiB,EACA,WAAAhB,EACA,KAAAF,EACA,IAAKC,EACL,KAAMiB,EACN,KAAMhB,EACN,IAAKF,EACL,aAAcW,CAAA,CAEtB,CAEQ,YACJzB,EACAiC,EACK,CACL,MAAM,EAAIjC,EAAW,OACfkC,EAAO,IAAI,aAAa,EAAI,CAAC,EAC7BC,EAAM,IAAI,WAAW,CAAC,EACtBC,EAAO,IAAI,aAAa,CAAC,EAC/B,QAASlD,EAAI,EAAGA,EAAI,EAAGA,IAAK,CACxB,MAAMgB,EAAIF,EAAWd,CAAC,EACtBgD,EAAKhD,EAAI,CAAC,EAAIgB,EAAE,KAAK,GACrBgC,EAAKhD,EAAI,EAAI,CAAC,EAAIgB,EAAE,KAAK,GACzBgC,EAAKhD,EAAI,EAAI,CAAC,EAAIgB,EAAE,KAAK,GACzBgC,EAAKhD,EAAI,EAAI,CAAC,EAAIgB,EAAE,KAAK,GACzBiC,EAAIjD,CAAC,EAAIgB,EAAE,QACXkC,EAAKlD,CAAC,EAAIgB,EAAE,UAChB,CACA,OAAO,IAAImC,EAAAA,MAAMH,EAAMC,EAAKC,EAAMH,CAAS,CAC/C,CACJ"}

package/dist/vision/tasks/detector.js

@@ -0,0 +1,147 @@
+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
+};
+//# sourceMappingURL=detector.js.map

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

@@ -0,0 +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;"}

package/dist/vision/tasks/segmenter.cjs

@@ -0,0 +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

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

@@ -0,0 +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"}

package/dist/vision/tasks/segmenter.js

@@ -0,0 +1,189 @@
+import { OrtSession as k } from "../core/session.js";
+import { loadImage as C } from "../io/image.js";
+import { resolveLabels as F } from "../labels.js";
+import { decodeYoloSeg as I } from "../postprocess/segmentation.js";
+import { letterbox as N, toFloat32 as U, toCHW as $, toFloat32Tensor as B } from "../preprocess/image.js";
+import { SegmentationResults as H, Boxes as L, Masks as W } from "../results.js";
+import { VisionTask as E } from "./base.js";
+import { RGBImage as M, Mask as D } from "../types.js";
+class v extends E {
+  constructor(n, s, o, t, e, r, i, a, _) {
+    super(n), this._head = s, this._labels = o, this._names = t, this._inputSize = e, this._confThreshold = r, this._iouThreshold = i, this._maxDetections = a, this._maskThreshold = _;
+  }
+  _head;
+  _labels;
+  _names;
+  _inputSize;
+  _confThreshold;
+  _iouThreshold;
+  _maxDetections;
+  _maskThreshold;
+  /** Load the model and resolve labels. */
+  static async create(n, s = {}) {
+    const o = s.head ?? "yolo-seg";
+    if (o !== "yolo-seg")
+      throw new Error(`Unsupported segmenter head '${o}'. Supported: 'yolo-seg'.`);
+    const t = await k.create(n, s), e = F(s.labels ?? "coco", {
+      numClasses: s.numClasses
+    }), r = {};
+    for (let i = 0; i < e.length; i++)
+      r[i] = e[i];
+    return new v(
+      t,
+      o,
+      e,
+      r,
+      s.inputSize ?? [640, 640],
+      s.confThreshold ?? 0.25,
+      s.iouThreshold ?? 0.45,
+      s.maxDetections ?? 300,
+      s.maskThreshold ?? 0.5
+    );
+  }
+  /** 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} (parity with PyTorch `nn.Module.__call__`). */
+  async call(n, s = {}) {
+    return this.predict(n, s);
+  }
+  /** Run instance segmentation on a single image. */
+  async predict(n, s = {}) {
+    const o = typeof n == "string" ? n : null, t = await C(n), { tensor: e, scale: r, padLeft: i, padTop: a } = this._preprocess(t), _ = await this._session.run({ [this._session.inputName]: e }), { perAnchor: f, prototypes: w } = this._splitOutputs(_), g = I(
+      f.data,
+      f.dims,
+      w.data,
+      w.dims,
+      {
+        numClasses: this._labels.length,
+        inputWidth: this._inputSize[0],
+        inputHeight: this._inputSize[1],
+        originalWidth: t.width,
+        originalHeight: t.height,
+        padLeft: i,
+        padTop: a,
+        scale: r,
+        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 g.filter((T) => h.has(T.classId));
+    })() : g).map(
+      (h) => this._buildResult(t, h.bbox, h.classId, h.confidence, h.mask)
+    ), m = [t.height, t.width];
+    return [
+      new H(
+        this._buildBoxes(d, m),
+        this._buildMasks(d, m),
+        d,
+        this._names,
+        t,
+        m,
+        o
+      )
+    ];
+  }
+  _preprocess(n) {
+    const [s, o] = this._inputSize, t = N(n, s, o), e = U(t.image), r = $(e, t.image.width, t.image.height, 3);
+    return {
+      tensor: B(r, [1, 3, t.image.height, t.image.width]),
+      scale: t.scale,
+      padLeft: t.padLeft,
+      padTop: t.padTop
+    };
+  }
+  _splitOutputs(n) {
+    let s, o;
+    for (const t of this._session.outputNames) {
+      const e = n[t];
+      e !== void 0 && (e.dims.length === 3 && s === void 0 ? s = e : e.dims.length === 4 && o === void 0 && (o = e));
+    }
+    if (s === void 0 || o === void 0) {
+      const t = this._session.outputNames.map(
+        (e) => `${e}: ${JSON.stringify(n[e]?.dims ?? [])}`
+      );
+      throw new Error(
+        `Segmenter expected one 3-D and one 4-D output, got [${t.join(", ")}].`
+      );
+    }
+    return { perAnchor: s, prototypes: o };
+  }
+  _buildResult(n, s, o, t, e) {
+    const [r, i, a, _] = s.asIntXyxy(), f = Math.max(0, r), w = Math.max(0, i), g = Math.min(n.width, a), y = Math.min(n.height, _);
+    let d, m = e;
+    if (g > f && y > w && e.data.length > 0) {
+      const T = g - f, O = y - w, l = Math.min(e.width, T), u = Math.min(e.height, O), b = new Uint8Array(l * u * 3);
+      for (let c = 0; c < u; c++) {
+        const p = ((w + c) * n.width + f) * 3, R = c * l * 3, z = c * e.width;
+        for (let x = 0; x < l; x++)
+          if (e.data[z + x] !== 0) {
+            const S = p + x * 3, A = R + x * 3;
+            b[A] = n.data[S], b[A + 1] = n.data[S + 1], b[A + 2] = n.data[S + 2];
+          }
+      }
+      if (d = new M(b, l, u), l !== e.width || u !== e.height) {
+        const c = new Uint8Array(l * u);
+        for (let p = 0; p < u; p++)
+          c.set(
+            e.data.subarray(p * e.width, p * e.width + l),
+            p * l
+          );
+        m = new D(c, l, u);
+      }
+    } else
+      m = new D(new Uint8Array(0), 0, 0), d = new M(new Uint8Array(0), 0, 0);
+    const h = this._names[o] ?? `class_${o}`;
+    return {
+      classId: o,
+      className: h,
+      confidence: t,
+      bbox: s,
+      cls: o,
+      name: h,
+      conf: t,
+      box: s,
+      mask: m,
+      segmentedImage: d
+    };
+  }
+  _buildBoxes(n, s) {
+    const o = n.length, t = new Float32Array(o * 4), e = new Int32Array(o), r = new Float32Array(o);
+    for (let i = 0; i < o; i++) {
+      const a = n[i];
+      t[i * 4] = a.bbox.x1, t[i * 4 + 1] = a.bbox.y1, t[i * 4 + 2] = a.bbox.x2, t[i * 4 + 3] = a.bbox.y2, e[i] = a.classId, r[i] = a.confidence;
+    }
+    return new L(t, e, r, s);
+  }
+  _buildMasks(n, s) {
+    const o = new Float32Array(n.length * 4);
+    for (let t = 0; t < n.length; t++) {
+      const e = n[t];
+      o[t * 4] = e.bbox.x1, o[t * 4 + 1] = e.bbox.y1, o[t * 4 + 2] = e.bbox.x2, o[t * 4 + 3] = e.bbox.y2;
+    }
+    return new W(
+      n.map((t) => t.mask),
+      o,
+      s
+    );
+  }
+}
+export {
+  v as Segmenter
+};
+//# sourceMappingURL=segmenter.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"segmenter.js","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","t","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":";;;;;;;;AAoFO,MAAMA,UAAkBC,EAAW;AAAA,EAC9B,YACJC,GACiBC,GACAC,GACAC,GACAC,GACAC,GACAC,GACAC,GACAC,GACnB;AACE,UAAMR,CAAO,GATI,KAAA,QAAAC,GACA,KAAA,UAAAC,GACA,KAAA,SAAAC,GACA,KAAA,aAAAC,GACA,KAAA,iBAAAC,GACA,KAAA,gBAAAC,GACA,KAAA,iBAAAC,GACA,KAAA,iBAAAC;AAAA,EAGrB;AAAA,EAVqB;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AAAA,EAMrB,aAAa,OAAOC,GAAoBC,IAA4B,IAAwB;AACxF,UAAMC,IAAsBD,EAAQ,QAAQ;AAC5C,QAAIC,MAAS;AACT,YAAM,IAAI,MAAM,+BAA+BA,CAAI,2BAA2B;AAElF,UAAMX,IAAU,MAAMY,EAAW,OAAOH,GAAOC,CAAO,GAChDG,IAASC,EAAcJ,EAAQ,UAAU,QAAQ;AAAA,MACnD,YAAYA,EAAQ;AAAA,IAAA,CACvB,GACKK,IAAgC,CAAA;AACtC,aAAS,IAAI,GAAG,IAAIF,EAAO,QAAQ;AAC/B,MAAAE,EAAM,CAAC,IAAIF,EAAO,CAAC;AAEvB,WAAO,IAAIf;AAAA,MACPE;AAAA,MACAW;AAAA,MACAE;AAAA,MACAE;AAAA,MACAL,EAAQ,aAAa,CAAC,KAAK,GAAG;AAAA,MAC9BA,EAAQ,iBAAiB;AAAA,MACzBA,EAAQ,gBAAgB;AAAA,MACxBA,EAAQ,iBAAiB;AAAA,MACzBA,EAAQ,iBAAiB;AAAA,IAAA;AAAA,EAEjC;AAAA;AAAA,EAGA,IAAI,OAAsB;AACtB,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,EAGA,MAAM,KACFM,GACAN,IAAmC,IACL;AAC9B,WAAO,KAAK,QAAQM,GAAON,CAAO;AAAA,EACtC;AAAA;AAAA,EAGA,MAAM,QACFM,GACAN,IAAmC,IACL;AAC9B,UAAMO,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,GAEvE,EAAE,WAAAK,GAAW,YAAAC,EAAA,IAAe,KAAK,cAAcF,CAAO,GAEtDG,IAAaC;AAAA,MACfH,EAAU;AAAA,MACVA,EAAU;AAAA,MACVC,EAAW;AAAA,MACXA,EAAW;AAAA,MACX;AAAA,QACI,YAAY,KAAK,QAAQ;AAAA,QACzB,YAAY,KAAK,WAAW,CAAC;AAAA,QAC7B,aAAa,KAAK,WAAW,CAAC;AAAA,QAC9B,eAAeR,EAAS;AAAA,QACxB,gBAAgBA,EAAS;AAAA,QACzB,SAAAI;AAAA,QACA,QAAAC;AAAA,QACA,OAAAF;AAAA,QACA,eAAeX,EAAQ,iBAAiB,KAAK;AAAA,QAC7C,cAAcA,EAAQ,gBAAgB,KAAK;AAAA,QAC3C,eAAe,KAAK;AAAA,QACpB,eAAe,KAAK;AAAA,MAAA;AAAA,IACxB,GAWEmB,KAPFnB,EAAQ,YAAY,UACb,MAAM;AACH,YAAMoB,IAAU,IAAI,IAAIpB,EAAQ,OAAO;AACvC,aAAOiB,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,YAAYA,EAAE,IAAI;AAAA,IAAA,GAGjEC,IAAkC,CAACd,EAAS,QAAQA,EAAS,KAAK;AACxE,WAAO;AAAA,MACH,IAAIe;AAAA,QACA,KAAK,YAAYJ,GAAYG,CAAI;AAAA,QACjC,KAAK,YAAYH,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,cAAcZ,GAGpB;AACE,QAAIC,GACAC;AACJ,eAAWiB,KAAQ,KAAK,SAAS,aAAa;AAC1C,YAAMC,IAAIpB,EAAQmB,CAAI;AACtB,MAAIC,MAAM,WACNA,EAAE,KAAK,WAAW,KAAKnB,MAAc,SACrCA,IAAYmB,IACLA,EAAE,KAAK,WAAW,KAAKlB,MAAe,WAC7CA,IAAakB;AAAA,IAErB;AACA,QAAInB,MAAc,UAAaC,MAAe,QAAW;AACrD,YAAMmB,IAAS,KAAK,SAAS,YAAY;AAAA,QACrC,CAACC,MAAM,GAAGA,CAAC,KAAK,KAAK,UAAUtB,EAAQsB,CAAC,GAAG,QAAQ,CAAA,CAAE,CAAC;AAAA,MAAA;AAE1D,YAAM,IAAI;AAAA,QACN,uDAAuDD,EAAO,KAAK,IAAI,CAAC;AAAA,MAAA;AAAA,IAEhF;AACA,WAAO,EAAE,WAAApB,GAAW,YAAAC,EAAA;AAAA,EACxB;AAAA,EAEQ,aACJR,GACA6B,GACAC,GACAC,GACAC,GACkB;AAClB,UAAM,CAACC,GAAIC,GAAIC,GAAIC,CAAE,IAAIP,EAAK,UAAA,GACxBQ,IAAM,KAAK,IAAI,GAAGJ,CAAE,GACpBK,IAAM,KAAK,IAAI,GAAGJ,CAAE,GACpBK,IAAM,KAAK,IAAIvC,EAAS,OAAOmC,CAAE,GACjCK,IAAM,KAAK,IAAIxC,EAAS,QAAQoC,CAAE;AAExC,QAAIK,GACAC,IAAYV;AAChB,QAAIO,IAAMF,KAAOG,IAAMF,KAAON,EAAK,KAAK,SAAS,GAAG;AAChD,YAAMW,IAAQJ,IAAMF,GACdO,IAAQJ,IAAMF,GACdO,IAAK,KAAK,IAAIb,EAAK,OAAOW,CAAK,GAC/BG,IAAK,KAAK,IAAId,EAAK,QAAQY,CAAK,GAChCG,IAAU,IAAI,WAAWF,IAAKC,IAAK,CAAC;AAC1C,eAASE,IAAM,GAAGA,IAAMF,GAAIE,KAAO;AAC/B,cAAMC,MAAiBX,IAAMU,KAAOhD,EAAS,QAAQqC,KAAO,GACtDa,IAAeF,IAAMH,IAAK,GAC1BM,IAAgBH,IAAMhB,EAAK;AACjC,iBAASoB,IAAM,GAAGA,IAAMP,GAAIO;AAExB,cADUpB,EAAK,KAAKmB,IAAgBC,CAAG,MAC7B,GAAG;AACT,kBAAMC,IAAIJ,IAAeG,IAAM,GACzBvC,IAAIqC,IAAeE,IAAM;AAC/B,YAAAL,EAAQlC,CAAC,IAAIb,EAAS,KAAKqD,CAAC,GAC5BN,EAAQlC,IAAI,CAAC,IAAIb,EAAS,KAAKqD,IAAI,CAAC,GACpCN,EAAQlC,IAAI,CAAC,IAAIb,EAAS,KAAKqD,IAAI,CAAC;AAAA,UACxC;AAAA,MAER;AAEA,UADAZ,IAAiB,IAAIa,EAASP,GAASF,GAAIC,CAAE,GACzCD,MAAOb,EAAK,SAASc,MAAOd,EAAK,QAAQ;AACzC,cAAMuB,IAAU,IAAI,WAAWV,IAAKC,CAAE;AACtC,iBAASE,IAAM,GAAGA,IAAMF,GAAIE;AACxB,UAAAO,EAAQ;AAAA,YACJvB,EAAK,KAAK,SAASgB,IAAMhB,EAAK,OAAOgB,IAAMhB,EAAK,QAAQa,CAAE;AAAA,YAC1DG,IAAMH;AAAA,UAAA;AAGd,QAAAH,IAAY,IAAIc,EAAKD,GAASV,GAAIC,CAAE;AAAA,MACxC;AAAA,IACJ;AACI,MAAAJ,IAAY,IAAIc,EAAK,IAAI,WAAW,CAAC,GAAG,GAAG,CAAC,GAC5Cf,IAAiB,IAAIa,EAAS,IAAI,WAAW,CAAC,GAAG,GAAG,CAAC;AAGzD,UAAMG,IAAY,KAAK,OAAO3B,CAAO,KAAK,SAASA,CAAO;AAE1D,WAAO;AAAA,MACH,SAAAA;AAAA,MACA,WAAA2B;AAAA,MACA,YAAA1B;AAAA,MACA,MAAAF;AAAA,MACA,KAAKC;AAAA,MACL,MAAM2B;AAAA,MACN,MAAM1B;AAAA,MACN,KAAKF;AAAA,MACL,MAAMa;AAAA,MACN,gBAAAD;AAAA,IAAA;AAAA,EAER;AAAA,EAEQ,YACJ9B,GACA+C,GACK;AACL,UAAM9B,IAAIjB,EAAW,QACfgD,IAAO,IAAI,aAAa/B,IAAI,CAAC,GAC7BgC,IAAM,IAAI,WAAWhC,CAAC,GACtBiC,IAAO,IAAI,aAAajC,CAAC;AAC/B,aAAS,IAAI,GAAG,IAAIA,GAAG,KAAK;AACxB,YAAMf,IAAIF,EAAW,CAAC;AACtB,MAAAgD,EAAK,IAAI,CAAC,IAAI9C,EAAE,KAAK,IACrB8C,EAAK,IAAI,IAAI,CAAC,IAAI9C,EAAE,KAAK,IACzB8C,EAAK,IAAI,IAAI,CAAC,IAAI9C,EAAE,KAAK,IACzB8C,EAAK,IAAI,IAAI,CAAC,IAAI9C,EAAE,KAAK,IACzB+C,EAAI,CAAC,IAAI/C,EAAE,SACXgD,EAAK,CAAC,IAAIhD,EAAE;AAAA,IAChB;AACA,WAAO,IAAIiD,EAAMH,GAAMC,GAAKC,GAAMH,CAAS;AAAA,EAC/C;AAAA,EAEQ,YACJ/C,GACA+C,GACK;AACL,UAAMC,IAAO,IAAI,aAAahD,EAAW,SAAS,CAAC;AACnD,aAASoD,IAAI,GAAGA,IAAIpD,EAAW,QAAQoD,KAAK;AACxC,YAAMlD,IAAIF,EAAWoD,CAAC;AACtB,MAAAJ,EAAKI,IAAI,CAAC,IAAIlD,EAAE,KAAK,IACrB8C,EAAKI,IAAI,IAAI,CAAC,IAAIlD,EAAE,KAAK,IACzB8C,EAAKI,IAAI,IAAI,CAAC,IAAIlD,EAAE,KAAK,IACzB8C,EAAKI,IAAI,IAAI,CAAC,IAAIlD,EAAE,KAAK;AAAA,IAC7B;AACA,WAAO,IAAImD;AAAA,MACPrD,EAAW,IAAI,CAACE,MAAMA,EAAE,IAAI;AAAA,MAC5B8C;AAAA,MACAD;AAAA,IAAA;AAAA,EAER;AACJ;"}

package/dist/vision/types.cjs

@@ -0,0 +1,2 @@
+"use strict";Object.defineProperty(exports,Symbol.toStringTag,{value:"Module"});const r=require("./core/exceptions.cjs");class y{constructor(s,t,h){if(this.data=s,this.width=t,this.height=h,s.length!==t*h*3)throw new r.ImageLoadError(`RGBImage data length ${s.length} does not match width * height * 3 = ${t*h*3}.`)}data;width;height}class o{constructor(s,t,h,i){this.x1=s,this.y1=t,this.x2=h,this.y2=i}x1;y1;x2;y2;get width(){return Math.max(0,this.x2-this.x1)}get height(){return Math.max(0,this.y2-this.y1)}get area(){return this.width*this.height}get xyxy(){return[this.x1,this.y1,this.x2,this.y2]}get xywh(){return[(this.x1+this.x2)/2,(this.y1+this.y2)/2,this.width,this.height]}xyxyn(s){const[t,h]=s;return h<=0||t<=0?[0,0,0,0]:[this.x1/h,this.y1/t,this.x2/h,this.y2/t]}xywhn(s){const[t,h]=s;if(h<=0||t<=0)return[0,0,0,0];const[i,n,a,x]=this.xywh;return[i/h,n/t,a/h,x/t]}asXyxy(){return[this.x1,this.y1,this.x2,this.y2]}asXywh(){return[this.x1,this.y1,this.width,this.height]}asIntXyxy(){return[Math.trunc(this.x1),Math.trunc(this.y1),Math.trunc(this.x2),Math.trunc(this.y2)]}}class g{constructor(s,t,h){if(this.data=s,this.width=t,this.height=h,s.length!==t*h)throw new r.ImageLoadError(`Mask data length ${s.length} does not match width * height = ${t*h}.`)}data;width;height}exports.BoundingBox=o;exports.Mask=g;exports.RGBImage=y;
+//# sourceMappingURL=types.cjs.map

package/dist/vision/types.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"types.cjs","sources":["../../src/vision/types.ts"],"sourcesContent":["/**\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"],"names":["RGBImage","data","width","height","ImageLoadError","BoundingBox","x1","y1","x2","y2","origShape","h","w","cx","cy","bw","bh","Mask"],"mappings":"yHAqBO,MAAMA,CAAS,CAClB,YACoBC,EACAC,EACAC,EAClB,CACE,GAJgB,KAAA,KAAAF,EACA,KAAA,MAAAC,EACA,KAAA,OAAAC,EAEZF,EAAK,SAAWC,EAAQC,EAAS,EACjC,MAAM,IAAIC,EAAAA,eACN,wBAAwBH,EAAK,MAAM,wCAC/BC,EAAQC,EAAS,CACrB,GAAA,CAGZ,CAXoB,KACA,MACA,MAUxB,CASO,MAAME,CAAY,CACrB,YACoBC,EACAC,EACAC,EACAC,EAClB,CAJkB,KAAA,GAAAH,EACA,KAAA,GAAAC,EACA,KAAA,GAAAC,EACA,KAAA,GAAAC,CACjB,CAJiB,GACA,GACA,GACA,GAIpB,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,MAAMC,EAAiF,CACnF,KAAM,CAACC,EAAGC,CAAC,EAAIF,EACf,OAAIE,GAAK,GAAKD,GAAK,EAAU,CAAC,EAAG,EAAG,EAAG,CAAC,EACjC,CAAC,KAAK,GAAKC,EAAG,KAAK,GAAKD,EAAG,KAAK,GAAKC,EAAG,KAAK,GAAKD,CAAC,CAC9D,CAOA,MAAMD,EAAiF,CACnF,KAAM,CAACC,EAAGC,CAAC,EAAIF,EACf,GAAIE,GAAK,GAAKD,GAAK,QAAU,CAAC,EAAG,EAAG,EAAG,CAAC,EACxC,KAAM,CAACE,EAAIC,EAAIC,EAAIC,CAAE,EAAI,KAAK,KAC9B,MAAO,CAACH,EAAKD,EAAGE,EAAKH,EAAGI,EAAKH,EAAGI,EAAKL,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,CAyEO,MAAMM,CAAK,CACd,YACoBhB,EACAC,EACAC,EAClB,CACE,GAJgB,KAAA,KAAAF,EACA,KAAA,MAAAC,EACA,KAAA,OAAAC,EAEZF,EAAK,SAAWC,EAAQC,EACxB,MAAM,IAAIC,EAAAA,eACN,oBAAoBH,EAAK,MAAM,oCAC3BC,EAAQC,CACZ,GAAA,CAGZ,CAXoB,KACA,MACA,MAUxB"}