@camstack/addon-vision 0.1.2 → 0.1.4

package/dist/chunk-2YMA6QOV.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/shared/postprocess/scrfd.ts","../src/catalogs/face-detection-models.ts"],"sourcesContent":["import type { SpatialDetection, BoundingBox, Landmark } from '@camstack/types'\nimport { iou, nms } from './yolo.js'\n\nexport interface ScrfdRawOutputs {\n  readonly [key: string]: Float32Array\n}\n\nconst STRIDES = [8, 16, 32] as const\nconst NUM_ANCHORS_PER_STRIDE = 2\n\n/** Generate anchor points for a given stride and input size */\nfunction generateAnchors(stride: number, inputSize: number): Array<{ cx: number; cy: number }> {\n  const featureSize = Math.ceil(inputSize / stride)\n  const anchors: Array<{ cx: number; cy: number }> = []\n  for (let y = 0; y < featureSize; y++) {\n    for (let x = 0; x < featureSize; x++) {\n      for (let k = 0; k < NUM_ANCHORS_PER_STRIDE; k++) {\n        anchors.push({\n          cx: (x + 0.5) * stride,\n          cy: (y + 0.5) * stride,\n        })\n      }\n    }\n  }\n  return anchors\n}\n\nexport function scrfdPostprocess(\n  outputs: ScrfdRawOutputs,\n  confidence: number,\n  inputSize: number,\n  originalWidth: number,\n  originalHeight: number,\n): SpatialDetection[] {\n  // Scale factor from letterbox (assume square crop, so same scale both axes)\n  const scaleX = originalWidth / inputSize\n  const scaleY = originalHeight / inputSize\n\n  interface Candidate {\n    readonly bbox: BoundingBox\n    readonly score: number\n    readonly landmarks?: readonly Landmark[]\n  }\n\n  const candidates: Candidate[] = []\n\n  for (const stride of STRIDES) {\n    const scoreKey = Object.keys(outputs).find((k) => k.includes(`score_${stride}`) || k.includes(`_${stride}_score`))\n    const bboxKey = Object.keys(outputs).find((k) => k.includes(`bbox_${stride}`) || k.includes(`_${stride}_bbox`))\n    const kpsKey = Object.keys(outputs).find((k) => k.includes(`kps_${stride}`) || k.includes(`_${stride}_kps`))\n\n    if (!scoreKey || !bboxKey) continue\n\n    const scores = outputs[scoreKey]!\n    const bboxes = outputs[bboxKey]!\n    const kps = kpsKey ? outputs[kpsKey] : undefined\n    const anchors = generateAnchors(stride, inputSize)\n\n    const n = anchors.length\n\n    for (let i = 0; i < n; i++) {\n      const score = scores[i]!\n      if (score < confidence) continue\n\n      const anchor = anchors[i]!\n\n      // Bboxes are relative to the anchor center in stride units, scaled by stride\n      const x1 = anchor.cx - bboxes[i * 4]! * stride\n      const y1 = anchor.cy - bboxes[i * 4 + 1]! * stride\n      const x2 = anchor.cx + bboxes[i * 4 + 2]! * stride\n      const y2 = anchor.cy + bboxes[i * 4 + 3]! * stride\n\n      const bbox: BoundingBox = {\n        x: x1 * scaleX,\n        y: y1 * scaleY,\n        w: (x2 - x1) * scaleX,\n        h: (y2 - y1) * scaleY,\n      }\n\n      let landmarks: readonly Landmark[] | undefined\n      if (kps) {\n        const pts: Landmark[] = []\n        for (let p = 0; p < 5; p++) {\n          pts.push({\n            x: (anchor.cx + kps[i * 10 + p * 2]! * stride) * scaleX,\n            y: (anchor.cy + kps[i * 10 + p * 2 + 1]! * stride) * scaleY,\n          })\n        }\n        landmarks = pts\n      }\n\n      candidates.push({ bbox, score, landmarks })\n    }\n  }\n\n  if (candidates.length === 0) return []\n\n  const keptIndices = nms(candidates, 0.45)\n\n  return keptIndices.map((idx) => {\n    const { bbox, score, landmarks } = candidates[idx]!\n    return {\n      class: 'face',\n      originalClass: 'face',\n      score,\n      bbox,\n      ...(landmarks ? { landmarks } : {}),\n    } satisfies SpatialDetection\n  })\n}\n","import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst FACE_LABELS: readonly LabelDefinition[] = [\n  { id: 'face', name: 'Face' },\n] as const\n\nexport const FACE_DETECTION_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'scrfd-500m',\n    name: 'SCRFD 500M',\n    description: 'SCRFD 500M — ultra-lightweight face detector',\n    inputSize: { width: 640, height: 640 },\n    labels: FACE_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/onnx/camstack-scrfd-500m.onnx'),\n        sizeMB: 2.2,\n      },\n      coreml: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/coreml/camstack-scrfd-500m.mlpackage'),\n        sizeMB: 1.2,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/openvino/camstack-scrfd-500m.xml'),\n        sizeMB: 1.3,\n        runtimes: ['python'],\n      },\n    },\n  },\n  {\n    id: 'scrfd-2.5g',\n    name: 'SCRFD 2.5G',\n    description: 'SCRFD 2.5G — balanced face detection model',\n    inputSize: { width: 640, height: 640 },\n    labels: FACE_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/onnx/camstack-scrfd-2.5g.onnx'),\n        sizeMB: 3.1,\n      },\n      coreml: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/coreml/camstack-scrfd-2.5g.mlpackage'),\n        sizeMB: 1.7,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/openvino/camstack-scrfd-2.5g.xml'),\n        sizeMB: 1.8,\n        runtimes: ['python'],\n      },\n    },\n  },\n  {\n    id: 'scrfd-10g',\n    name: 'SCRFD 10G',\n    description: 'SCRFD 10G — high-accuracy face detector',\n    inputSize: { width: 640, height: 640 },\n    labels: FACE_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/onnx/camstack-scrfd-10g.onnx'),\n        sizeMB: 16,\n      },\n      coreml: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/coreml/camstack-scrfd-10g.mlpackage'),\n        sizeMB: 8.2,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'faceDetection/scrfd/openvino/camstack-scrfd-10g.xml'),\n        sizeMB: 8.3,\n        runtimes: ['python'],\n      },\n    },\n  },\n] as const\n"],"mappings":";;;;;;;;;;;;;;;;AA2BA,YAAA,mBAAA;AA1BA,QAAA,YAAA;AAMA,QAAM,UAAU,CAAC,GAAG,IAAI,EAAE;AAC1B,QAAM,yBAAyB;AAG/B,aAAS,gBAAgB,QAAgB,WAAiB;AACxD,YAAM,cAAc,KAAK,KAAK,YAAY,MAAM;AAChD,YAAM,UAA6C,CAAA;AACnD,eAAS,IAAI,GAAG,IAAI,aAAa,KAAK;AACpC,iBAAS,IAAI,GAAG,IAAI,aAAa,KAAK;AACpC,mBAAS,IAAI,GAAG,IAAI,wBAAwB,KAAK;AAC/C,oBAAQ,KAAK;cACX,KAAK,IAAI,OAAO;cAChB,KAAK,IAAI,OAAO;aACjB;UACH;QACF;MACF;AACA,aAAO;IACT;AAEA,aAAgB,iBACd,SACA,YACA,WACA,eACA,gBAAsB;AAGtB,YAAM,SAAS,gBAAgB;AAC/B,YAAM,SAAS,iBAAiB;AAQhC,YAAM,aAA0B,CAAA;AAEhC,iBAAW,UAAU,SAAS;AAC5B,cAAM,WAAW,OAAO,KAAK,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,SAAS,SAAS,MAAM,EAAE,KAAK,EAAE,SAAS,IAAI,MAAM,QAAQ,CAAC;AACjH,cAAM,UAAU,OAAO,KAAK,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,SAAS,QAAQ,MAAM,EAAE,KAAK,EAAE,SAAS,IAAI,MAAM,OAAO,CAAC;AAC9G,cAAM,SAAS,OAAO,KAAK,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,SAAS,OAAO,MAAM,EAAE,KAAK,EAAE,SAAS,IAAI,MAAM,MAAM,CAAC;AAE3G,YAAI,CAAC,YAAY,CAAC;AAAS;AAE3B,cAAM,SAAS,QAAQ,QAAQ;AAC/B,cAAM,SAAS,QAAQ,OAAO;AAC9B,cAAM,MAAM,SAAS,QAAQ,MAAM,IAAI;AACvC,cAAM,UAAU,gBAAgB,QAAQ,SAAS;AAEjD,cAAM,IAAI,QAAQ;AAElB,iBAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,gBAAM,QAAQ,OAAO,CAAC;AACtB,cAAI,QAAQ;AAAY;AAExB,gBAAM,SAAS,QAAQ,CAAC;AAGxB,gBAAM,KAAK,OAAO,KAAK,OAAO,IAAI,CAAC,IAAK;AACxC,gBAAM,KAAK,OAAO,KAAK,OAAO,IAAI,IAAI,CAAC,IAAK;AAC5C,gBAAM,KAAK,OAAO,KAAK,OAAO,IAAI,IAAI,CAAC,IAAK;AAC5C,gBAAM,KAAK,OAAO,KAAK,OAAO,IAAI,IAAI,CAAC,IAAK;AAE5C,gBAAM,OAAoB;YACxB,GAAG,KAAK;YACR,GAAG,KAAK;YACR,IAAI,KAAK,MAAM;YACf,IAAI,KAAK,MAAM;;AAGjB,cAAI;AACJ,cAAI,KAAK;AACP,kBAAM,MAAkB,CAAA;AACxB,qBAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,kBAAI,KAAK;gBACP,IAAI,OAAO,KAAK,IAAI,IAAI,KAAK,IAAI,CAAC,IAAK,UAAU;gBACjD,IAAI,OAAO,KAAK,IAAI,IAAI,KAAK,IAAI,IAAI,CAAC,IAAK,UAAU;eACtD;YACH;AACA,wBAAY;UACd;AAEA,qBAAW,KAAK,EAAE,MAAM,OAAO,UAAS,CAAE;QAC5C;MACF;AAEA,UAAI,WAAW,WAAW;AAAG,eAAO,CAAA;AAEpC,YAAM,eAAc,GAAA,UAAA,KAAI,YAAY,IAAI;AAExC,aAAO,YAAY,IAAI,CAAC,QAAO;AAC7B,cAAM,EAAE,MAAM,OAAO,UAAS,IAAK,WAAW,GAAG;AACjD,eAAO;UACL,OAAO;UACP,eAAe;UACf;UACA;UACA,GAAI,YAAY,EAAE,UAAS,IAAK,CAAA;;MAEpC,CAAC;IACH;;;;;;;;;;AC5GA,QAAA,UAAA,UAAA,iBAAA;AACA,QAAA,+BAAA;AAEA,QAAM,UAAU;AAEhB,QAAM,cAA0C;MAC9C,EAAE,IAAI,QAAQ,MAAM,OAAM;;AAGf,YAAA,wBAAsD;MACjE;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,mDAAmD;YAC5E,QAAQ;;UAEV,QAAQ;YACN,MAAK,GAAA,QAAA,YAAW,SAAS,0DAA0D;YACnF,QAAQ;YACR,aAAa;YACb,OAAO,6BAAA;YACP,UAAU,CAAC,QAAQ;;UAErB,UAAU;YACR,MAAK,GAAA,QAAA,YAAW,SAAS,sDAAsD;YAC/E,QAAQ;YACR,UAAU,CAAC,QAAQ;;;;MAIzB;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,mDAAmD;YAC5E,QAAQ;;UAEV,QAAQ;YACN,MAAK,GAAA,QAAA,YAAW,SAAS,0DAA0D;YACnF,QAAQ;YACR,aAAa;YACb,OAAO,6BAAA;YACP,UAAU,CAAC,QAAQ;;UAErB,UAAU;YACR,MAAK,GAAA,QAAA,YAAW,SAAS,sDAAsD;YAC/E,QAAQ;YACR,UAAU,CAAC,QAAQ;;;;MAIzB;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,kDAAkD;YAC3E,QAAQ;;UAEV,QAAQ;YACN,MAAK,GAAA,QAAA,YAAW,SAAS,yDAAyD;YAClF,QAAQ;YACR,aAAa;YACb,OAAO,6BAAA;YACP,UAAU,CAAC,QAAQ;;UAErB,UAAU;YACR,MAAK,GAAA,QAAA,YAAW,SAAS,qDAAqD;YAC9E,QAAQ;YACR,UAAU,CAAC,QAAQ;;;;;;;","names":[]}

package/dist/chunk-3IIFBJCD.mjs

@@ -0,0 +1,45 @@
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __require = /* @__PURE__ */ ((x) => typeof require !== "undefined" ? require : typeof Proxy !== "undefined" ? new Proxy(x, {
+  get: (a, b) => (typeof require !== "undefined" ? require : a)[b]
+}) : x)(function(x) {
+  if (typeof require !== "undefined") return require.apply(this, arguments);
+  throw Error('Dynamic require of "' + x + '" is not supported');
+});
+var __commonJS = (cb, mod) => function __require2() {
+  return mod || (0, cb[__getOwnPropNames(cb)[0]])((mod = { exports: {} }).exports, mod), mod.exports;
+};
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __reExport = (target, mod, secondTarget) => (__copyProps(target, mod, "default"), secondTarget && __copyProps(secondTarget, mod, "default"));
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
+  mod
+));
+
+export {
+  __require,
+  __commonJS,
+  __export,
+  __reExport,
+  __toESM
+};
+//# sourceMappingURL=chunk-3IIFBJCD.mjs.map

package/dist/chunk-BS4DKYGN.mjs

@@ -0,0 +1,48 @@
+import {
+  require_object_detection_models
+} from "./chunk-MGT6RUVX.mjs";
+import {
+  __commonJS,
+  __require
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/catalogs/segmentation-refiner-models.js
+var require_segmentation_refiner_models = __commonJS({
+  "src/catalogs/segmentation-refiner-models.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.SEGMENTATION_REFINER_MODELS = void 0;
+    var types_1 = __require("@camstack/types");
+    var object_detection_models_js_1 = require_object_detection_models();
+    var HF_REPO = "camstack/camstack-models";
+    var hf = (path) => (0, types_1.hfModelUrl)(HF_REPO, path);
+    var MASK_LABELS = [
+      { id: "mask", name: "Segmentation Mask" }
+    ];
+    exports.SEGMENTATION_REFINER_MODELS = [
+      {
+        id: "u2netp",
+        name: "U2-Net Portable",
+        description: "U2-Net-P \u2014 ultra-lightweight salient object segmentation (4.7 MB), no prompt needed",
+        inputSize: { width: 320, height: 320 },
+        labels: MASK_LABELS,
+        formats: {
+          onnx: { url: hf("segmentationRefiner/u2netp/onnx/camstack-u2netp.onnx"), sizeMB: 5 },
+          coreml: {
+            url: hf("segmentationRefiner/u2netp/coreml/camstack-u2netp.mlpackage"),
+            sizeMB: 3,
+            isDirectory: true,
+            files: object_detection_models_js_1.MLPACKAGE_FILES,
+            runtimes: ["python"]
+          }
+          // OpenVINO: not yet converted
+        }
+      }
+    ];
+  }
+});
+
+export {
+  require_segmentation_refiner_models
+};
+//# sourceMappingURL=chunk-BS4DKYGN.mjs.map

package/dist/{chunk-7DYHXUPZ.mjs.map → chunk-BS4DKYGN.mjs.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/catalogs/segmentation-refiner-models.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst hf = (path: string) => hfModelUrl(HF_REPO, path)\n\nconst MASK_LABELS: readonly LabelDefinition[] = [\n  { id: 'mask', name: 'Segmentation Mask' },\n]\n\nexport const SEGMENTATION_REFINER_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'u2netp',\n    name: 'U2-Net Portable',\n    description: 'U2-Net-P — ultra-lightweight salient object segmentation (4.7 MB), no prompt needed',\n    inputSize: { width: 320, height: 320 },\n    labels: MASK_LABELS,\n    formats: {\n      onnx: { url: hf('segmentationRefiner/u2netp/onnx/camstack-u2netp.onnx'), sizeMB: 5 },\n      coreml: {\n        url: hf('segmentationRefiner/u2netp/coreml/camstack-u2netp.mlpackage'),\n        sizeMB: 3,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      // OpenVINO: not yet converted\n    },\n  },\n]\n"],"mappings":";;;;;AACA,SAAS,kBAAkB;AAG3B,IAAM,UAAU;AAEhB,IAAM,KAAK,CAAC,SAAiB,WAAW,SAAS,IAAI;AAErD,IAAM,cAA0C;AAAA,EAC9C,EAAE,IAAI,QAAQ,MAAM,oBAAoB;AAC1C;AAEO,IAAM,8BAA4D;AAAA,EACvE;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAI;AAAA,IACrC,QAAQ;AAAA,IACR,SAAS;AAAA,MACP,MAAM,EAAE,KAAK,GAAG,sDAAsD,GAAG,QAAQ,EAAE;AAAA,MACnF,QAAQ;AAAA,QACN,KAAK,GAAG,6DAA6D;AAAA,QACrE,QAAQ;AAAA,QACR,aAAa;AAAA,QACb,OAAO;AAAA,QACP,UAAU,CAAC,QAAQ;AAAA,MACrB;AAAA;AAAA,IAEF;AAAA,EACF;AACF;","names":[]}
+{"version":3,"sources":["../src/catalogs/segmentation-refiner-models.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst hf = (path: string) => hfModelUrl(HF_REPO, path)\n\nconst MASK_LABELS: readonly LabelDefinition[] = [\n  { id: 'mask', name: 'Segmentation Mask' },\n]\n\nexport const SEGMENTATION_REFINER_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'u2netp',\n    name: 'U2-Net Portable',\n    description: 'U2-Net-P — ultra-lightweight salient object segmentation (4.7 MB), no prompt needed',\n    inputSize: { width: 320, height: 320 },\n    labels: MASK_LABELS,\n    formats: {\n      onnx: { url: hf('segmentationRefiner/u2netp/onnx/camstack-u2netp.onnx'), sizeMB: 5 },\n      coreml: {\n        url: hf('segmentationRefiner/u2netp/coreml/camstack-u2netp.mlpackage'),\n        sizeMB: 3,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      // OpenVINO: not yet converted\n    },\n  },\n]\n"],"mappings":";;;;;;;;;;;;;;AACA,QAAA,UAAA,UAAA,iBAAA;AACA,QAAA,+BAAA;AAEA,QAAM,UAAU;AAEhB,QAAM,KAAK,CAAC,UAAiB,GAAA,QAAA,YAAW,SAAS,IAAI;AAErD,QAAM,cAA0C;MAC9C,EAAE,IAAI,QAAQ,MAAM,oBAAmB;;AAG5B,YAAA,8BAA4D;MACvE;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,QAAQ;QACR,SAAS;UACP,MAAM,EAAE,KAAK,GAAG,sDAAsD,GAAG,QAAQ,EAAC;UAClF,QAAQ;YACN,KAAK,GAAG,6DAA6D;YACrE,QAAQ;YACR,aAAa;YACb,OAAO,6BAAA;YACP,UAAU,CAAC,QAAQ;;;;;;;;","names":[]}

package/dist/chunk-DE7I3VHO.mjs

@@ -0,0 +1,106 @@
+import {
+  __commonJS
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/shared/postprocess/yolo.js
+var require_yolo = __commonJS({
+  "src/shared/postprocess/yolo.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.iou = iou;
+    exports.nms = nms;
+    exports.yoloPostprocess = yoloPostprocess;
+    function iou(a, b) {
+      const ax1 = a.x;
+      const ay1 = a.y;
+      const ax2 = a.x + a.w;
+      const ay2 = a.y + a.h;
+      const bx1 = b.x;
+      const by1 = b.y;
+      const bx2 = b.x + b.w;
+      const by2 = b.y + b.h;
+      const interX1 = Math.max(ax1, bx1);
+      const interY1 = Math.max(ay1, by1);
+      const interX2 = Math.min(ax2, bx2);
+      const interY2 = Math.min(ay2, by2);
+      const interW = Math.max(0, interX2 - interX1);
+      const interH = Math.max(0, interY2 - interY1);
+      const interArea = interW * interH;
+      if (interArea === 0)
+        return 0;
+      const areaA = a.w * a.h;
+      const areaB = b.w * b.h;
+      const unionArea = areaA + areaB - interArea;
+      return unionArea === 0 ? 0 : interArea / unionArea;
+    }
+    function nms(boxes, iouThreshold) {
+      const indices = boxes.map((_, i) => i).sort((a, b) => boxes[b].score - boxes[a].score);
+      const kept = [];
+      const suppressed = /* @__PURE__ */ new Set();
+      for (const idx of indices) {
+        if (suppressed.has(idx))
+          continue;
+        kept.push(idx);
+        for (const other of indices) {
+          if (other === idx || suppressed.has(other))
+            continue;
+          if (iou(boxes[idx].bbox, boxes[other].bbox) > iouThreshold) {
+            suppressed.add(other);
+          }
+        }
+      }
+      return kept;
+    }
+    function yoloPostprocess(output, numClasses, numBoxes, options) {
+      const { confidence, iouThreshold, labels, scale, padX, padY, originalWidth, originalHeight } = options;
+      const candidates = [];
+      for (let i = 0; i < numBoxes; i++) {
+        const cx = output[0 * numBoxes + i];
+        const cy = output[1 * numBoxes + i];
+        const w = output[2 * numBoxes + i];
+        const h = output[3 * numBoxes + i];
+        let bestScore = -Infinity;
+        let bestClass = 0;
+        for (let j = 0; j < numClasses; j++) {
+          const score = output[(4 + j) * numBoxes + i];
+          if (score > bestScore) {
+            bestScore = score;
+            bestClass = j;
+          }
+        }
+        if (bestScore < confidence)
+          continue;
+        const bbox = {
+          x: cx - w / 2,
+          y: cy - h / 2,
+          w,
+          h
+        };
+        candidates.push({ bbox, score: bestScore, classIdx: bestClass });
+      }
+      if (candidates.length === 0)
+        return [];
+      const keptIndices = nms(candidates, iouThreshold);
+      return keptIndices.map((idx) => {
+        const { bbox, score, classIdx } = candidates[idx];
+        const label = labels[classIdx] ?? String(classIdx);
+        const x = Math.max(0, Math.min(originalWidth, (bbox.x - padX) / scale));
+        const y = Math.max(0, Math.min(originalHeight, (bbox.y - padY) / scale));
+        const x2 = Math.max(0, Math.min(originalWidth, (bbox.x + bbox.w - padX) / scale));
+        const y2 = Math.max(0, Math.min(originalHeight, (bbox.y + bbox.h - padY) / scale));
+        const finalBbox = { x, y, w: x2 - x, h: y2 - y };
+        return {
+          class: label,
+          originalClass: label,
+          score,
+          bbox: finalBbox
+        };
+      });
+    }
+  }
+});
+
+export {
+  require_yolo
+};
+//# sourceMappingURL=chunk-DE7I3VHO.mjs.map

package/dist/{chunk-KUO2BVFY.mjs.map → chunk-DE7I3VHO.mjs.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/shared/postprocess/yolo.ts"],"sourcesContent":["import type { SpatialDetection, BoundingBox } from '@camstack/types'\n\nexport interface YoloPostprocessOptions {\n  readonly confidence: number\n  readonly iouThreshold: number\n  readonly labels: readonly string[]\n  readonly scale: number\n  readonly padX: number\n  readonly padY: number\n  readonly originalWidth: number\n  readonly originalHeight: number\n}\n\n/** Calculate IoU between two bounding boxes */\nexport function iou(a: BoundingBox, b: BoundingBox): number {\n  const ax1 = a.x\n  const ay1 = a.y\n  const ax2 = a.x + a.w\n  const ay2 = a.y + a.h\n\n  const bx1 = b.x\n  const by1 = b.y\n  const bx2 = b.x + b.w\n  const by2 = b.y + b.h\n\n  const interX1 = Math.max(ax1, bx1)\n  const interY1 = Math.max(ay1, by1)\n  const interX2 = Math.min(ax2, bx2)\n  const interY2 = Math.min(ay2, by2)\n\n  const interW = Math.max(0, interX2 - interX1)\n  const interH = Math.max(0, interY2 - interY1)\n  const interArea = interW * interH\n\n  if (interArea === 0) return 0\n\n  const areaA = a.w * a.h\n  const areaB = b.w * b.h\n  const unionArea = areaA + areaB - interArea\n\n  return unionArea === 0 ? 0 : interArea / unionArea\n}\n\n/** Non-maximum suppression — returns indices of kept boxes (sorted by score desc) */\nexport function nms(\n  boxes: ReadonlyArray<{ readonly bbox: BoundingBox; readonly score: number }>,\n  iouThreshold: number,\n): number[] {\n  const indices = boxes\n    .map((_, i) => i)\n    .sort((a, b) => (boxes[b]!.score) - (boxes[a]!.score))\n\n  const kept: number[] = []\n  const suppressed = new Set<number>()\n\n  for (const idx of indices) {\n    if (suppressed.has(idx)) continue\n    kept.push(idx)\n    for (const other of indices) {\n      if (other === idx || suppressed.has(other)) continue\n      if (iou(boxes[idx]!.bbox, boxes[other]!.bbox) > iouThreshold) {\n        suppressed.add(other)\n      }\n    }\n  }\n\n  return kept\n}\n\n/** Full YOLO v8/v9 postprocessing: filter → NMS → scale back to original coords */\nexport function yoloPostprocess(\n  output: Float32Array,\n  numClasses: number,\n  numBoxes: number,\n  options: YoloPostprocessOptions,\n): SpatialDetection[] {\n  const { confidence, iouThreshold, labels, scale, padX, padY, originalWidth, originalHeight } = options\n\n  interface Candidate {\n    readonly bbox: BoundingBox\n    readonly score: number\n    readonly classIdx: number\n  }\n\n  const candidates: Candidate[] = []\n\n  for (let i = 0; i < numBoxes; i++) {\n    // YOLO v8/v9 output layout: [1, 4+numClasses, numBoxes] stored row-major\n    const cx = output[0 * numBoxes + i]!\n    const cy = output[1 * numBoxes + i]!\n    const w = output[2 * numBoxes + i]!\n    const h = output[3 * numBoxes + i]!\n\n    let bestScore = -Infinity\n    let bestClass = 0\n\n    for (let j = 0; j < numClasses; j++) {\n      const score = output[(4 + j) * numBoxes + i]!\n      if (score > bestScore) {\n        bestScore = score\n        bestClass = j\n      }\n    }\n\n    if (bestScore < confidence) continue\n\n    // Convert cx,cy,w,h to x,y,w,h (top-left origin)\n    const bbox: BoundingBox = {\n      x: cx - w / 2,\n      y: cy - h / 2,\n      w,\n      h,\n    }\n\n    candidates.push({ bbox, score: bestScore, classIdx: bestClass })\n  }\n\n  if (candidates.length === 0) return []\n\n  const keptIndices = nms(candidates, iouThreshold)\n\n  return keptIndices.map((idx) => {\n    const { bbox, score, classIdx } = candidates[idx]!\n    const label = labels[classIdx] ?? String(classIdx)\n\n    // Transform from letterbox coords back to original image coords\n    const x = Math.max(0, Math.min(originalWidth, (bbox.x - padX) / scale))\n    const y = Math.max(0, Math.min(originalHeight, (bbox.y - padY) / scale))\n    const x2 = Math.max(0, Math.min(originalWidth, (bbox.x + bbox.w - padX) / scale))\n    const y2 = Math.max(0, Math.min(originalHeight, (bbox.y + bbox.h - padY) / scale))\n\n    const finalBbox: BoundingBox = { x, y, w: x2 - x, h: y2 - y }\n\n    return {\n      class: label,\n      originalClass: label,\n      score,\n      bbox: finalBbox,\n    } satisfies SpatialDetection\n  })\n}\n"],"mappings":";AAcO,SAAS,IAAI,GAAgB,GAAwB;AAC1D,QAAM,MAAM,EAAE;AACd,QAAM,MAAM,EAAE;AACd,QAAM,MAAM,EAAE,IAAI,EAAE;AACpB,QAAM,MAAM,EAAE,IAAI,EAAE;AAEpB,QAAM,MAAM,EAAE;AACd,QAAM,MAAM,EAAE;AACd,QAAM,MAAM,EAAE,IAAI,EAAE;AACpB,QAAM,MAAM,EAAE,IAAI,EAAE;AAEpB,QAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AACjC,QAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AACjC,QAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AACjC,QAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AAEjC,QAAM,SAAS,KAAK,IAAI,GAAG,UAAU,OAAO;AAC5C,QAAM,SAAS,KAAK,IAAI,GAAG,UAAU,OAAO;AAC5C,QAAM,YAAY,SAAS;AAE3B,MAAI,cAAc,EAAG,QAAO;AAE5B,QAAM,QAAQ,EAAE,IAAI,EAAE;AACtB,QAAM,QAAQ,EAAE,IAAI,EAAE;AACtB,QAAM,YAAY,QAAQ,QAAQ;AAElC,SAAO,cAAc,IAAI,IAAI,YAAY;AAC3C;AAGO,SAAS,IACd,OACA,cACU;AACV,QAAM,UAAU,MACb,IAAI,CAAC,GAAG,MAAM,CAAC,EACf,KAAK,CAAC,GAAG,MAAO,MAAM,CAAC,EAAG,QAAU,MAAM,CAAC,EAAG,KAAM;AAEvD,QAAM,OAAiB,CAAC;AACxB,QAAM,aAAa,oBAAI,IAAY;AAEnC,aAAW,OAAO,SAAS;AACzB,QAAI,WAAW,IAAI,GAAG,EAAG;AACzB,SAAK,KAAK,GAAG;AACb,eAAW,SAAS,SAAS;AAC3B,UAAI,UAAU,OAAO,WAAW,IAAI,KAAK,EAAG;AAC5C,UAAI,IAAI,MAAM,GAAG,EAAG,MAAM,MAAM,KAAK,EAAG,IAAI,IAAI,cAAc;AAC5D,mBAAW,IAAI,KAAK;AAAA,MACtB;AAAA,IACF;AAAA,EACF;AAEA,SAAO;AACT;AAGO,SAAS,gBACd,QACA,YACA,UACA,SACoB;AACpB,QAAM,EAAE,YAAY,cAAc,QAAQ,OAAO,MAAM,MAAM,eAAe,eAAe,IAAI;AAQ/F,QAAM,aAA0B,CAAC;AAEjC,WAAS,IAAI,GAAG,IAAI,UAAU,KAAK;AAEjC,UAAM,KAAK,OAAO,IAAI,WAAW,CAAC;AAClC,UAAM,KAAK,OAAO,IAAI,WAAW,CAAC;AAClC,UAAM,IAAI,OAAO,IAAI,WAAW,CAAC;AACjC,UAAM,IAAI,OAAO,IAAI,WAAW,CAAC;AAEjC,QAAI,YAAY;AAChB,QAAI,YAAY;AAEhB,aAAS,IAAI,GAAG,IAAI,YAAY,KAAK;AACnC,YAAM,QAAQ,QAAQ,IAAI,KAAK,WAAW,CAAC;AAC3C,UAAI,QAAQ,WAAW;AACrB,oBAAY;AACZ,oBAAY;AAAA,MACd;AAAA,IACF;AAEA,QAAI,YAAY,WAAY;AAG5B,UAAM,OAAoB;AAAA,MACxB,GAAG,KAAK,IAAI;AAAA,MACZ,GAAG,KAAK,IAAI;AAAA,MACZ;AAAA,MACA;AAAA,IACF;AAEA,eAAW,KAAK,EAAE,MAAM,OAAO,WAAW,UAAU,UAAU,CAAC;AAAA,EACjE;AAEA,MAAI,WAAW,WAAW,EAAG,QAAO,CAAC;AAErC,QAAM,cAAc,IAAI,YAAY,YAAY;AAEhD,SAAO,YAAY,IAAI,CAAC,QAAQ;AAC9B,UAAM,EAAE,MAAM,OAAO,SAAS,IAAI,WAAW,GAAG;AAChD,UAAM,QAAQ,OAAO,QAAQ,KAAK,OAAO,QAAQ;AAGjD,UAAM,IAAI,KAAK,IAAI,GAAG,KAAK,IAAI,gBAAgB,KAAK,IAAI,QAAQ,KAAK,CAAC;AACtE,UAAM,IAAI,KAAK,IAAI,GAAG,KAAK,IAAI,iBAAiB,KAAK,IAAI,QAAQ,KAAK,CAAC;AACvE,UAAM,KAAK,KAAK,IAAI,GAAG,KAAK,IAAI,gBAAgB,KAAK,IAAI,KAAK,IAAI,QAAQ,KAAK,CAAC;AAChF,UAAM,KAAK,KAAK,IAAI,GAAG,KAAK,IAAI,iBAAiB,KAAK,IAAI,KAAK,IAAI,QAAQ,KAAK,CAAC;AAEjF,UAAM,YAAyB,EAAE,GAAG,GAAG,GAAG,KAAK,GAAG,GAAG,KAAK,EAAE;AAE5D,WAAO;AAAA,MACL,OAAO;AAAA,MACP,eAAe;AAAA,MACf;AAAA,MACA,MAAM;AAAA,IACR;AAAA,EACF,CAAC;AACH;","names":[]}
+{"version":3,"sources":["../src/shared/postprocess/yolo.ts"],"sourcesContent":["import type { SpatialDetection, BoundingBox } from '@camstack/types'\n\nexport interface YoloPostprocessOptions {\n  readonly confidence: number\n  readonly iouThreshold: number\n  readonly labels: readonly string[]\n  readonly scale: number\n  readonly padX: number\n  readonly padY: number\n  readonly originalWidth: number\n  readonly originalHeight: number\n}\n\n/** Calculate IoU between two bounding boxes */\nexport function iou(a: BoundingBox, b: BoundingBox): number {\n  const ax1 = a.x\n  const ay1 = a.y\n  const ax2 = a.x + a.w\n  const ay2 = a.y + a.h\n\n  const bx1 = b.x\n  const by1 = b.y\n  const bx2 = b.x + b.w\n  const by2 = b.y + b.h\n\n  const interX1 = Math.max(ax1, bx1)\n  const interY1 = Math.max(ay1, by1)\n  const interX2 = Math.min(ax2, bx2)\n  const interY2 = Math.min(ay2, by2)\n\n  const interW = Math.max(0, interX2 - interX1)\n  const interH = Math.max(0, interY2 - interY1)\n  const interArea = interW * interH\n\n  if (interArea === 0) return 0\n\n  const areaA = a.w * a.h\n  const areaB = b.w * b.h\n  const unionArea = areaA + areaB - interArea\n\n  return unionArea === 0 ? 0 : interArea / unionArea\n}\n\n/** Non-maximum suppression — returns indices of kept boxes (sorted by score desc) */\nexport function nms(\n  boxes: ReadonlyArray<{ readonly bbox: BoundingBox; readonly score: number }>,\n  iouThreshold: number,\n): number[] {\n  const indices = boxes\n    .map((_, i) => i)\n    .sort((a, b) => (boxes[b]!.score) - (boxes[a]!.score))\n\n  const kept: number[] = []\n  const suppressed = new Set<number>()\n\n  for (const idx of indices) {\n    if (suppressed.has(idx)) continue\n    kept.push(idx)\n    for (const other of indices) {\n      if (other === idx || suppressed.has(other)) continue\n      if (iou(boxes[idx]!.bbox, boxes[other]!.bbox) > iouThreshold) {\n        suppressed.add(other)\n      }\n    }\n  }\n\n  return kept\n}\n\n/** Full YOLO v8/v9 postprocessing: filter → NMS → scale back to original coords */\nexport function yoloPostprocess(\n  output: Float32Array,\n  numClasses: number,\n  numBoxes: number,\n  options: YoloPostprocessOptions,\n): SpatialDetection[] {\n  const { confidence, iouThreshold, labels, scale, padX, padY, originalWidth, originalHeight } = options\n\n  interface Candidate {\n    readonly bbox: BoundingBox\n    readonly score: number\n    readonly classIdx: number\n  }\n\n  const candidates: Candidate[] = []\n\n  for (let i = 0; i < numBoxes; i++) {\n    // YOLO v8/v9 output layout: [1, 4+numClasses, numBoxes] stored row-major\n    const cx = output[0 * numBoxes + i]!\n    const cy = output[1 * numBoxes + i]!\n    const w = output[2 * numBoxes + i]!\n    const h = output[3 * numBoxes + i]!\n\n    let bestScore = -Infinity\n    let bestClass = 0\n\n    for (let j = 0; j < numClasses; j++) {\n      const score = output[(4 + j) * numBoxes + i]!\n      if (score > bestScore) {\n        bestScore = score\n        bestClass = j\n      }\n    }\n\n    if (bestScore < confidence) continue\n\n    // Convert cx,cy,w,h to x,y,w,h (top-left origin)\n    const bbox: BoundingBox = {\n      x: cx - w / 2,\n      y: cy - h / 2,\n      w,\n      h,\n    }\n\n    candidates.push({ bbox, score: bestScore, classIdx: bestClass })\n  }\n\n  if (candidates.length === 0) return []\n\n  const keptIndices = nms(candidates, iouThreshold)\n\n  return keptIndices.map((idx) => {\n    const { bbox, score, classIdx } = candidates[idx]!\n    const label = labels[classIdx] ?? String(classIdx)\n\n    // Transform from letterbox coords back to original image coords\n    const x = Math.max(0, Math.min(originalWidth, (bbox.x - padX) / scale))\n    const y = Math.max(0, Math.min(originalHeight, (bbox.y - padY) / scale))\n    const x2 = Math.max(0, Math.min(originalWidth, (bbox.x + bbox.w - padX) / scale))\n    const y2 = Math.max(0, Math.min(originalHeight, (bbox.y + bbox.h - padY) / scale))\n\n    const finalBbox: BoundingBox = { x, y, w: x2 - x, h: y2 - y }\n\n    return {\n      class: label,\n      originalClass: label,\n      score,\n      bbox: finalBbox,\n    } satisfies SpatialDetection\n  })\n}\n"],"mappings":";;;;;;;;;AAcA,YAAA,MAAA;AA8BA,YAAA,MAAA;AA0BA,YAAA,kBAAA;AAxDA,aAAgB,IAAI,GAAgB,GAAc;AAChD,YAAM,MAAM,EAAE;AACd,YAAM,MAAM,EAAE;AACd,YAAM,MAAM,EAAE,IAAI,EAAE;AACpB,YAAM,MAAM,EAAE,IAAI,EAAE;AAEpB,YAAM,MAAM,EAAE;AACd,YAAM,MAAM,EAAE;AACd,YAAM,MAAM,EAAE,IAAI,EAAE;AACpB,YAAM,MAAM,EAAE,IAAI,EAAE;AAEpB,YAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AACjC,YAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AACjC,YAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AACjC,YAAM,UAAU,KAAK,IAAI,KAAK,GAAG;AAEjC,YAAM,SAAS,KAAK,IAAI,GAAG,UAAU,OAAO;AAC5C,YAAM,SAAS,KAAK,IAAI,GAAG,UAAU,OAAO;AAC5C,YAAM,YAAY,SAAS;AAE3B,UAAI,cAAc;AAAG,eAAO;AAE5B,YAAM,QAAQ,EAAE,IAAI,EAAE;AACtB,YAAM,QAAQ,EAAE,IAAI,EAAE;AACtB,YAAM,YAAY,QAAQ,QAAQ;AAElC,aAAO,cAAc,IAAI,IAAI,YAAY;IAC3C;AAGA,aAAgB,IACd,OACA,cAAoB;AAEpB,YAAM,UAAU,MACb,IAAI,CAAC,GAAG,MAAM,CAAC,EACf,KAAK,CAAC,GAAG,MAAO,MAAM,CAAC,EAAG,QAAU,MAAM,CAAC,EAAG,KAAM;AAEvD,YAAM,OAAiB,CAAA;AACvB,YAAM,aAAa,oBAAI,IAAG;AAE1B,iBAAW,OAAO,SAAS;AACzB,YAAI,WAAW,IAAI,GAAG;AAAG;AACzB,aAAK,KAAK,GAAG;AACb,mBAAW,SAAS,SAAS;AAC3B,cAAI,UAAU,OAAO,WAAW,IAAI,KAAK;AAAG;AAC5C,cAAI,IAAI,MAAM,GAAG,EAAG,MAAM,MAAM,KAAK,EAAG,IAAI,IAAI,cAAc;AAC5D,uBAAW,IAAI,KAAK;UACtB;QACF;MACF;AAEA,aAAO;IACT;AAGA,aAAgB,gBACd,QACA,YACA,UACA,SAA+B;AAE/B,YAAM,EAAE,YAAY,cAAc,QAAQ,OAAO,MAAM,MAAM,eAAe,eAAc,IAAK;AAQ/F,YAAM,aAA0B,CAAA;AAEhC,eAAS,IAAI,GAAG,IAAI,UAAU,KAAK;AAEjC,cAAM,KAAK,OAAO,IAAI,WAAW,CAAC;AAClC,cAAM,KAAK,OAAO,IAAI,WAAW,CAAC;AAClC,cAAM,IAAI,OAAO,IAAI,WAAW,CAAC;AACjC,cAAM,IAAI,OAAO,IAAI,WAAW,CAAC;AAEjC,YAAI,YAAY;AAChB,YAAI,YAAY;AAEhB,iBAAS,IAAI,GAAG,IAAI,YAAY,KAAK;AACnC,gBAAM,QAAQ,QAAQ,IAAI,KAAK,WAAW,CAAC;AAC3C,cAAI,QAAQ,WAAW;AACrB,wBAAY;AACZ,wBAAY;UACd;QACF;AAEA,YAAI,YAAY;AAAY;AAG5B,cAAM,OAAoB;UACxB,GAAG,KAAK,IAAI;UACZ,GAAG,KAAK,IAAI;UACZ;UACA;;AAGF,mBAAW,KAAK,EAAE,MAAM,OAAO,WAAW,UAAU,UAAS,CAAE;MACjE;AAEA,UAAI,WAAW,WAAW;AAAG,eAAO,CAAA;AAEpC,YAAM,cAAc,IAAI,YAAY,YAAY;AAEhD,aAAO,YAAY,IAAI,CAAC,QAAO;AAC7B,cAAM,EAAE,MAAM,OAAO,SAAQ,IAAK,WAAW,GAAG;AAChD,cAAM,QAAQ,OAAO,QAAQ,KAAK,OAAO,QAAQ;AAGjD,cAAM,IAAI,KAAK,IAAI,GAAG,KAAK,IAAI,gBAAgB,KAAK,IAAI,QAAQ,KAAK,CAAC;AACtE,cAAM,IAAI,KAAK,IAAI,GAAG,KAAK,IAAI,iBAAiB,KAAK,IAAI,QAAQ,KAAK,CAAC;AACvE,cAAM,KAAK,KAAK,IAAI,GAAG,KAAK,IAAI,gBAAgB,KAAK,IAAI,KAAK,IAAI,QAAQ,KAAK,CAAC;AAChF,cAAM,KAAK,KAAK,IAAI,GAAG,KAAK,IAAI,iBAAiB,KAAK,IAAI,KAAK,IAAI,QAAQ,KAAK,CAAC;AAEjF,cAAM,YAAyB,EAAE,GAAG,GAAG,GAAG,KAAK,GAAG,GAAG,KAAK,EAAC;AAE3D,eAAO;UACL,OAAO;UACP,eAAe;UACf;UACA,MAAM;;MAEV,CAAC;IACH;;;","names":[]}

package/dist/chunk-F6D2OZ36.mjs

@@ -0,0 +1,89 @@
+import {
+  require_object_detection_models
+} from "./chunk-MGT6RUVX.mjs";
+import {
+  __commonJS,
+  __require
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/shared/postprocess/arcface.js
+var require_arcface = __commonJS({
+  "src/shared/postprocess/arcface.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.l2Normalize = l2Normalize;
+    exports.cosineSimilarity = cosineSimilarity;
+    function l2Normalize(vec) {
+      let sumSq = 0;
+      for (let i = 0; i < vec.length; i++) {
+        sumSq += vec[i] * vec[i];
+      }
+      const norm = Math.sqrt(sumSq);
+      if (norm === 0)
+        return new Float32Array(vec.length);
+      const out = new Float32Array(vec.length);
+      for (let i = 0; i < vec.length; i++) {
+        out[i] = vec[i] / norm;
+      }
+      return out;
+    }
+    function cosineSimilarity(a, b) {
+      if (a.length !== b.length)
+        throw new Error("Embedding length mismatch");
+      let dot = 0;
+      for (let i = 0; i < a.length; i++) {
+        dot += a[i] * b[i];
+      }
+      return dot;
+    }
+  }
+});
+
+// src/catalogs/face-recognition-models.js
+var require_face_recognition_models = __commonJS({
+  "src/catalogs/face-recognition-models.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.FACE_RECOGNITION_MODELS = void 0;
+    var types_1 = __require("@camstack/types");
+    var object_detection_models_js_1 = require_object_detection_models();
+    var HF_REPO = "camstack/camstack-models";
+    var FACE_EMBEDDING_LABELS = [
+      { id: "embedding", name: "Face Embedding" }
+    ];
+    exports.FACE_RECOGNITION_MODELS = [
+      {
+        id: "arcface-r100",
+        name: "ArcFace R100",
+        description: "ArcFace ResNet-100 \u2014 high-accuracy face recognition embeddings",
+        inputSize: { width: 112, height: 112 },
+        inputLayout: "nhwc",
+        labels: FACE_EMBEDDING_LABELS,
+        formats: {
+          onnx: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "faceRecognition/arcface/onnx/camstack-arcface-arcface.onnx"),
+            sizeMB: 130
+          },
+          coreml: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "faceRecognition/arcface/coreml/camstack-arcface-r100.mlpackage"),
+            sizeMB: 65,
+            isDirectory: true,
+            files: object_detection_models_js_1.MLPACKAGE_FILES,
+            runtimes: ["python"]
+          },
+          openvino: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "faceRecognition/arcface/openvino/camstack-arcface-r100.xml"),
+            sizeMB: 65,
+            runtimes: ["python"]
+          }
+        }
+      }
+    ];
+  }
+});
+
+export {
+  require_arcface,
+  require_face_recognition_models
+};
+//# sourceMappingURL=chunk-F6D2OZ36.mjs.map

package/dist/chunk-F6D2OZ36.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/shared/postprocess/arcface.ts","../src/catalogs/face-recognition-models.ts"],"sourcesContent":["/** L2 normalize a vector in-place, returning a new Float32Array */\nexport function l2Normalize(vec: Float32Array): Float32Array {\n  let sumSq = 0\n  for (let i = 0; i < vec.length; i++) {\n    sumSq += vec[i]! * vec[i]!\n  }\n  const norm = Math.sqrt(sumSq)\n  if (norm === 0) return new Float32Array(vec.length)\n\n  const out = new Float32Array(vec.length)\n  for (let i = 0; i < vec.length; i++) {\n    out[i] = vec[i]! / norm\n  }\n  return out\n}\n\n/** Cosine similarity between two embeddings (assumes they are already L2-normalized) */\nexport function cosineSimilarity(a: Float32Array, b: Float32Array): number {\n  if (a.length !== b.length) throw new Error('Embedding length mismatch')\n  let dot = 0\n  for (let i = 0; i < a.length; i++) {\n    dot += a[i]! * b[i]!\n  }\n  return dot\n}\n","import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst FACE_EMBEDDING_LABELS: readonly LabelDefinition[] = [\n  { id: 'embedding', name: 'Face Embedding' },\n] as const\n\nexport const FACE_RECOGNITION_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'arcface-r100',\n    name: 'ArcFace R100',\n    description: 'ArcFace ResNet-100 — high-accuracy face recognition embeddings',\n    inputSize: { width: 112, height: 112 },\n    inputLayout: 'nhwc',\n    labels: FACE_EMBEDDING_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'faceRecognition/arcface/onnx/camstack-arcface-arcface.onnx'),\n        sizeMB: 130,\n      },\n      coreml: {\n        url: hfModelUrl(HF_REPO, 'faceRecognition/arcface/coreml/camstack-arcface-r100.mlpackage'),\n        sizeMB: 65,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'faceRecognition/arcface/openvino/camstack-arcface-r100.xml'),\n        sizeMB: 65,\n        runtimes: ['python'],\n      },\n    },\n  },\n] as const\n"],"mappings":";;;;;;;;;;;;;AACA,YAAA,cAAA;AAgBA,YAAA,mBAAA;AAhBA,aAAgB,YAAY,KAAiB;AAC3C,UAAI,QAAQ;AACZ,eAAS,IAAI,GAAG,IAAI,IAAI,QAAQ,KAAK;AACnC,iBAAS,IAAI,CAAC,IAAK,IAAI,CAAC;MAC1B;AACA,YAAM,OAAO,KAAK,KAAK,KAAK;AAC5B,UAAI,SAAS;AAAG,eAAO,IAAI,aAAa,IAAI,MAAM;AAElD,YAAM,MAAM,IAAI,aAAa,IAAI,MAAM;AACvC,eAAS,IAAI,GAAG,IAAI,IAAI,QAAQ,KAAK;AACnC,YAAI,CAAC,IAAI,IAAI,CAAC,IAAK;MACrB;AACA,aAAO;IACT;AAGA,aAAgB,iBAAiB,GAAiB,GAAe;AAC/D,UAAI,EAAE,WAAW,EAAE;AAAQ,cAAM,IAAI,MAAM,2BAA2B;AACtE,UAAI,MAAM;AACV,eAAS,IAAI,GAAG,IAAI,EAAE,QAAQ,KAAK;AACjC,eAAO,EAAE,CAAC,IAAK,EAAE,CAAC;MACpB;AACA,aAAO;IACT;;;;;;;;;;ACvBA,QAAA,UAAA,UAAA,iBAAA;AACA,QAAA,+BAAA;AAEA,QAAM,UAAU;AAEhB,QAAM,wBAAoD;MACxD,EAAE,IAAI,aAAa,MAAM,iBAAgB;;AAG9B,YAAA,0BAAwD;MACnE;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,aAAa;QACb,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,4DAA4D;YACrF,QAAQ;;UAEV,QAAQ;YACN,MAAK,GAAA,QAAA,YAAW,SAAS,gEAAgE;YACzF,QAAQ;YACR,aAAa;YACb,OAAO,6BAAA;YACP,UAAU,CAAC,QAAQ;;UAErB,UAAU;YACR,MAAK,GAAA,QAAA,YAAW,SAAS,4DAA4D;YACrF,QAAQ;YACR,UAAU,CAAC,QAAQ;;;;;;;","names":[]}

package/dist/chunk-GAOIFQDX.mjs

@@ -0,0 +1,59 @@
+import {
+  require_object_detection_models
+} from "./chunk-MGT6RUVX.mjs";
+import {
+  __commonJS,
+  __require
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/catalogs/plate-detection-models.js
+var require_plate_detection_models = __commonJS({
+  "src/catalogs/plate-detection-models.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.PLATE_DETECTION_MODELS = void 0;
+    var types_1 = __require("@camstack/types");
+    var object_detection_models_js_1 = require_object_detection_models();
+    var HF_REPO = "camstack/camstack-models";
+    var PLATE_LABELS = [
+      { id: "plate", name: "License Plate" }
+    ];
+    exports.PLATE_DETECTION_MODELS = [
+      {
+        id: "yolov8n-plate",
+        name: "YOLOv8 Nano \u2014 License Plate",
+        description: "YOLOv8 Nano fine-tuned for license plate detection",
+        inputSize: { width: 640, height: 640 },
+        labels: PLATE_LABELS,
+        formats: {
+          onnx: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateDetection/yolov8-plate/onnx/camstack-yolov8n-plate.onnx"),
+            sizeMB: 12
+          },
+          coreml: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateDetection/yolov8-plate/coreml/camstack-yolov8n-plate.mlpackage"),
+            sizeMB: 5.9,
+            isDirectory: true,
+            files: object_detection_models_js_1.MLPACKAGE_FILES,
+            runtimes: ["python"]
+          },
+          openvino: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateDetection/yolov8-plate/openvino/camstack-yolov8n-plate.xml"),
+            sizeMB: 6.1,
+            runtimes: ["python"]
+          },
+          tflite: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateDetection/yolov8-plate/tflite/camstack-yolov8n-plate_float32.tflite"),
+            sizeMB: 12,
+            runtimes: ["python"]
+          }
+        }
+      }
+    ];
+  }
+});
+
+export {
+  require_plate_detection_models
+};
+//# sourceMappingURL=chunk-GAOIFQDX.mjs.map

package/dist/chunk-GAOIFQDX.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/catalogs/plate-detection-models.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst PLATE_LABELS: readonly LabelDefinition[] = [\n  { id: 'plate', name: 'License Plate' },\n] as const\n\nexport const PLATE_DETECTION_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'yolov8n-plate',\n    name: 'YOLOv8 Nano — License Plate',\n    description: 'YOLOv8 Nano fine-tuned for license plate detection',\n    inputSize: { width: 640, height: 640 },\n    labels: PLATE_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/onnx/camstack-yolov8n-plate.onnx'),\n        sizeMB: 12,\n      },\n      coreml: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/coreml/camstack-yolov8n-plate.mlpackage'),\n        sizeMB: 5.9,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/openvino/camstack-yolov8n-plate.xml'),\n        sizeMB: 6.1,\n        runtimes: ['python'],\n      },\n      tflite: {\n        url: hfModelUrl(HF_REPO, 'plateDetection/yolov8-plate/tflite/camstack-yolov8n-plate_float32.tflite'),\n        sizeMB: 12,\n        runtimes: ['python'],\n      },\n    },\n  },\n] as const\n"],"mappings":";;;;;;;;;;;;;;AACA,QAAA,UAAA,UAAA,iBAAA;AACA,QAAA,+BAAA;AAEA,QAAM,UAAU;AAEhB,QAAM,eAA2C;MAC/C,EAAE,IAAI,SAAS,MAAM,gBAAe;;AAGzB,YAAA,yBAAuD;MAClE;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAG;QACpC,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,8DAA8D;YACvF,QAAQ;;UAEV,QAAQ;YACN,MAAK,GAAA,QAAA,YAAW,SAAS,qEAAqE;YAC9F,QAAQ;YACR,aAAa;YACb,OAAO,6BAAA;YACP,UAAU,CAAC,QAAQ;;UAErB,UAAU;YACR,MAAK,GAAA,QAAA,YAAW,SAAS,iEAAiE;YAC1F,QAAQ;YACR,UAAU,CAAC,QAAQ;;UAErB,QAAQ;YACN,MAAK,GAAA,QAAA,YAAW,SAAS,0EAA0E;YACnG,QAAQ;YACR,UAAU,CAAC,QAAQ;;;;;;;","names":[]}

package/dist/chunk-HUIX2XVR.mjs

@@ -0,0 +1,159 @@
+import {
+  __commonJS,
+  __require
+} from "./chunk-3IIFBJCD.mjs";
+
+// src/shared/postprocess/paddleocr.js
+var require_paddleocr = __commonJS({
+  "src/shared/postprocess/paddleocr.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.ctcDecode = ctcDecode;
+    function ctcDecode(output, seqLen, numChars, charset) {
+      let totalLogScore = 0;
+      const rawIndices = [];
+      for (let t = 0; t < seqLen; t++) {
+        const offset = t * numChars;
+        let bestIdx = 0;
+        let bestVal = output[offset];
+        for (let c = 1; c < numChars; c++) {
+          const val = output[offset + c];
+          if (val > bestVal) {
+            bestVal = val;
+            bestIdx = c;
+          }
+        }
+        rawIndices.push(bestIdx);
+        totalLogScore += bestVal;
+      }
+      const collapsed = [];
+      for (let i = 0; i < rawIndices.length; i++) {
+        const cur = rawIndices[i];
+        if (i === 0 || cur !== rawIndices[i - 1]) {
+          collapsed.push(cur);
+        }
+      }
+      const filtered = collapsed.filter((idx) => idx !== 0);
+      const text = filtered.map((idx) => charset[idx] ?? "").join("");
+      const confidence = seqLen > 0 ? totalLogScore / seqLen : 0;
+      return { text, confidence };
+    }
+  }
+});
+
+// src/catalogs/plate-recognition-models.js
+var require_plate_recognition_models = __commonJS({
+  "src/catalogs/plate-recognition-models.js"(exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.PLATE_RECOGNITION_MODELS = void 0;
+    var types_1 = __require("@camstack/types");
+    var HF_REPO = "camstack/camstack-models";
+    var PLATE_TEXT_LABELS = [
+      { id: "text", name: "Plate Text" }
+    ];
+    exports.PLATE_RECOGNITION_MODELS = [
+      // ── PaddleOCR PP-OCRv5 ────────────────────────────────────────
+      {
+        id: "paddleocr-latin",
+        name: "PaddleOCR Latin",
+        description: "PaddleOCR PP-OCRv5 recognition model for Latin-script license plates",
+        inputSize: { width: 320, height: 48 },
+        labels: PLATE_TEXT_LABELS,
+        formats: {
+          // ONNX only — PaddleOCR has dynamic dimensions incompatible with CoreML native conversion.
+          // On Apple Silicon, ONNX Runtime uses CoreML EP automatically for acceleration.
+          onnx: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/paddleocr/onnx/camstack-paddleocr-latin-rec.onnx"),
+            sizeMB: 7.5
+          },
+          openvino: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/paddleocr/openvino/camstack-paddleocr-latin.xml"),
+            sizeMB: 4,
+            runtimes: ["python"]
+          }
+        },
+        extraFiles: [
+          {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/paddleocr/onnx/camstack-paddleocr-latin-dict.txt"),
+            filename: "camstack-paddleocr-latin-dict.txt",
+            sizeMB: 0.01
+          }
+        ]
+      },
+      {
+        id: "paddleocr-en",
+        name: "PaddleOCR English",
+        description: "PaddleOCR PP-OCRv5 recognition model optimized for English license plates",
+        inputSize: { width: 320, height: 48 },
+        labels: PLATE_TEXT_LABELS,
+        formats: {
+          onnx: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/paddleocr/onnx/camstack-paddleocr-en-rec.onnx"),
+            sizeMB: 7.5
+          },
+          openvino: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/paddleocr/openvino/camstack-paddleocr-en.xml"),
+            sizeMB: 4,
+            runtimes: ["python"]
+          }
+        },
+        extraFiles: [
+          {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/paddleocr/onnx/camstack-paddleocr-en-dict.txt"),
+            filename: "camstack-paddleocr-en-dict.txt",
+            sizeMB: 0.01
+          }
+        ]
+      },
+      // ── CRNN-MobileNetV3 (via OnnxTR/docTR) ─────────────────────────
+      // Simple CNN+LSTM+CTC architecture — good CoreML compatibility (no dynamic ops)
+      {
+        id: "crnn-mobilenet-v3-small",
+        name: "CRNN MobileNet V3 Small",
+        description: "CRNN MobileNetV3-Small \u2014 lightweight text recognition, CoreML compatible via OnnxTR",
+        inputSize: { width: 128, height: 32 },
+        labels: PLATE_TEXT_LABELS,
+        formats: {
+          onnx: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/crnn-mobilenet/onnx/camstack-crnn-mobilenet-v3-small.onnx"),
+            sizeMB: 8
+          }
+        },
+        extraFiles: [
+          {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/crnn-mobilenet/camstack-crnn-mobilenet-charset.txt"),
+            filename: "camstack-crnn-mobilenet-charset.txt",
+            sizeMB: 0.01
+          }
+        ]
+      },
+      {
+        id: "crnn-mobilenet-v3-large",
+        name: "CRNN MobileNet V3 Large",
+        description: "CRNN MobileNetV3-Large \u2014 higher accuracy text recognition, CoreML compatible",
+        inputSize: { width: 128, height: 32 },
+        labels: PLATE_TEXT_LABELS,
+        formats: {
+          onnx: {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/crnn-mobilenet/onnx/camstack-crnn-mobilenet-v3-large.onnx"),
+            sizeMB: 17
+          }
+        },
+        extraFiles: [
+          {
+            url: (0, types_1.hfModelUrl)(HF_REPO, "plateRecognition/crnn-mobilenet/camstack-crnn-mobilenet-charset.txt"),
+            filename: "camstack-crnn-mobilenet-charset.txt",
+            sizeMB: 0.01
+          }
+        ]
+      }
+    ];
+  }
+});
+
+export {
+  require_paddleocr,
+  require_plate_recognition_models
+};
+//# sourceMappingURL=chunk-HUIX2XVR.mjs.map

package/dist/chunk-HUIX2XVR.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/shared/postprocess/paddleocr.ts","../src/catalogs/plate-recognition-models.ts"],"sourcesContent":["/** Decode CTC output to text.\n *\n * Output shape: [1, seqLen, numChars]\n * Algorithm: argmax per timestep → collapse consecutive duplicates → remove blank (index 0) → join\n */\nexport function ctcDecode(\n  output: Float32Array,\n  seqLen: number,\n  numChars: number,\n  charset: readonly string[], // index 0 = blank token\n): { text: string; confidence: number } {\n  // Step 1: argmax per timestep + track confidence as mean of selected scores\n  let totalLogScore = 0\n  const rawIndices: number[] = []\n\n  for (let t = 0; t < seqLen; t++) {\n    const offset = t * numChars\n    let bestIdx = 0\n    let bestVal = output[offset]!\n\n    for (let c = 1; c < numChars; c++) {\n      const val = output[offset + c]!\n      if (val > bestVal) {\n        bestVal = val\n        bestIdx = c\n      }\n    }\n\n    rawIndices.push(bestIdx)\n    totalLogScore += bestVal\n  }\n\n  // Step 2: collapse consecutive duplicates\n  const collapsed: number[] = []\n  for (let i = 0; i < rawIndices.length; i++) {\n    const cur = rawIndices[i]!\n    if (i === 0 || cur !== rawIndices[i - 1]) {\n      collapsed.push(cur)\n    }\n  }\n\n  // Step 3: remove blank (index 0)\n  const filtered = collapsed.filter((idx) => idx !== 0)\n\n  // Step 4: join characters\n  const text = filtered.map((idx) => charset[idx] ?? '').join('')\n\n  const confidence = seqLen > 0 ? totalLogScore / seqLen : 0\n\n  return { text, confidence }\n}\n","import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst PLATE_TEXT_LABELS: readonly LabelDefinition[] = [\n  { id: 'text', name: 'Plate Text' },\n] as const\n\nexport const PLATE_RECOGNITION_MODELS: readonly ModelCatalogEntry[] = [\n  // ── PaddleOCR PP-OCRv5 ────────────────────────────────────────\n  {\n    id: 'paddleocr-latin',\n    name: 'PaddleOCR Latin',\n    description: 'PaddleOCR PP-OCRv5 recognition model for Latin-script license plates',\n    inputSize: { width: 320, height: 48 },\n    labels: PLATE_TEXT_LABELS,\n    formats: {\n      // ONNX only — PaddleOCR has dynamic dimensions incompatible with CoreML native conversion.\n      // On Apple Silicon, ONNX Runtime uses CoreML EP automatically for acceleration.\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/paddleocr/onnx/camstack-paddleocr-latin-rec.onnx'),\n        sizeMB: 7.5,\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/paddleocr/openvino/camstack-paddleocr-latin.xml'),\n        sizeMB: 4,\n        runtimes: ['python'],\n      },\n    },\n    extraFiles: [\n      {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/paddleocr/onnx/camstack-paddleocr-latin-dict.txt'),\n        filename: 'camstack-paddleocr-latin-dict.txt',\n        sizeMB: 0.01,\n      },\n    ],\n  },\n  {\n    id: 'paddleocr-en',\n    name: 'PaddleOCR English',\n    description: 'PaddleOCR PP-OCRv5 recognition model optimized for English license plates',\n    inputSize: { width: 320, height: 48 },\n    labels: PLATE_TEXT_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/paddleocr/onnx/camstack-paddleocr-en-rec.onnx'),\n        sizeMB: 7.5,\n      },\n      openvino: {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/paddleocr/openvino/camstack-paddleocr-en.xml'),\n        sizeMB: 4,\n        runtimes: ['python'],\n      },\n    },\n    extraFiles: [\n      {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/paddleocr/onnx/camstack-paddleocr-en-dict.txt'),\n        filename: 'camstack-paddleocr-en-dict.txt',\n        sizeMB: 0.01,\n      },\n    ],\n  },\n\n  // ── CRNN-MobileNetV3 (via OnnxTR/docTR) ─────────────────────────\n  // Simple CNN+LSTM+CTC architecture — good CoreML compatibility (no dynamic ops)\n  {\n    id: 'crnn-mobilenet-v3-small',\n    name: 'CRNN MobileNet V3 Small',\n    description: 'CRNN MobileNetV3-Small — lightweight text recognition, CoreML compatible via OnnxTR',\n    inputSize: { width: 128, height: 32 },\n    labels: PLATE_TEXT_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/crnn-mobilenet/onnx/camstack-crnn-mobilenet-v3-small.onnx'),\n        sizeMB: 8,\n      },\n    },\n    extraFiles: [\n      {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/crnn-mobilenet/camstack-crnn-mobilenet-charset.txt'),\n        filename: 'camstack-crnn-mobilenet-charset.txt',\n        sizeMB: 0.01,\n      },\n    ],\n  },\n  {\n    id: 'crnn-mobilenet-v3-large',\n    name: 'CRNN MobileNet V3 Large',\n    description: 'CRNN MobileNetV3-Large — higher accuracy text recognition, CoreML compatible',\n    inputSize: { width: 128, height: 32 },\n    labels: PLATE_TEXT_LABELS,\n    formats: {\n      onnx: {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/crnn-mobilenet/onnx/camstack-crnn-mobilenet-v3-large.onnx'),\n        sizeMB: 17,\n      },\n    },\n    extraFiles: [\n      {\n        url: hfModelUrl(HF_REPO, 'plateRecognition/crnn-mobilenet/camstack-crnn-mobilenet-charset.txt'),\n        filename: 'camstack-crnn-mobilenet-charset.txt',\n        sizeMB: 0.01,\n      },\n    ],\n  },\n] as const\n"],"mappings":";;;;;;;;;;AAKA,YAAA,YAAA;AAAA,aAAgB,UACd,QACA,QACA,UACA,SAA0B;AAG1B,UAAI,gBAAgB;AACpB,YAAM,aAAuB,CAAA;AAE7B,eAAS,IAAI,GAAG,IAAI,QAAQ,KAAK;AAC/B,cAAM,SAAS,IAAI;AACnB,YAAI,UAAU;AACd,YAAI,UAAU,OAAO,MAAM;AAE3B,iBAAS,IAAI,GAAG,IAAI,UAAU,KAAK;AACjC,gBAAM,MAAM,OAAO,SAAS,CAAC;AAC7B,cAAI,MAAM,SAAS;AACjB,sBAAU;AACV,sBAAU;UACZ;QACF;AAEA,mBAAW,KAAK,OAAO;AACvB,yBAAiB;MACnB;AAGA,YAAM,YAAsB,CAAA;AAC5B,eAAS,IAAI,GAAG,IAAI,WAAW,QAAQ,KAAK;AAC1C,cAAM,MAAM,WAAW,CAAC;AACxB,YAAI,MAAM,KAAK,QAAQ,WAAW,IAAI,CAAC,GAAG;AACxC,oBAAU,KAAK,GAAG;QACpB;MACF;AAGA,YAAM,WAAW,UAAU,OAAO,CAAC,QAAQ,QAAQ,CAAC;AAGpD,YAAM,OAAO,SAAS,IAAI,CAAC,QAAQ,QAAQ,GAAG,KAAK,EAAE,EAAE,KAAK,EAAE;AAE9D,YAAM,aAAa,SAAS,IAAI,gBAAgB,SAAS;AAEzD,aAAO,EAAE,MAAM,WAAU;IAC3B;;;;;;;;;;ACjDA,QAAA,UAAA,UAAA,iBAAA;AAEA,QAAM,UAAU;AAEhB,QAAM,oBAAgD;MACpD,EAAE,IAAI,QAAQ,MAAM,aAAY;;AAGrB,YAAA,2BAAyD;;MAEpE;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,GAAE;QACnC,QAAQ;QACR,SAAS;;;UAGP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,mEAAmE;YAC5F,QAAQ;;UAEV,UAAU;YACR,MAAK,GAAA,QAAA,YAAW,SAAS,kEAAkE;YAC3F,QAAQ;YACR,UAAU,CAAC,QAAQ;;;QAGvB,YAAY;UACV;YACE,MAAK,GAAA,QAAA,YAAW,SAAS,mEAAmE;YAC5F,UAAU;YACV,QAAQ;;;;MAId;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,GAAE;QACnC,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,gEAAgE;YACzF,QAAQ;;UAEV,UAAU;YACR,MAAK,GAAA,QAAA,YAAW,SAAS,+DAA+D;YACxF,QAAQ;YACR,UAAU,CAAC,QAAQ;;;QAGvB,YAAY;UACV;YACE,MAAK,GAAA,QAAA,YAAW,SAAS,gEAAgE;YACzF,UAAU;YACV,QAAQ;;;;;;MAOd;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,GAAE;QACnC,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,4EAA4E;YACrG,QAAQ;;;QAGZ,YAAY;UACV;YACE,MAAK,GAAA,QAAA,YAAW,SAAS,qEAAqE;YAC9F,UAAU;YACV,QAAQ;;;;MAId;QACE,IAAI;QACJ,MAAM;QACN,aAAa;QACb,WAAW,EAAE,OAAO,KAAK,QAAQ,GAAE;QACnC,QAAQ;QACR,SAAS;UACP,MAAM;YACJ,MAAK,GAAA,QAAA,YAAW,SAAS,4EAA4E;YACrG,QAAQ;;;QAGZ,YAAY;UACV;YACE,MAAK,GAAA,QAAA,YAAW,SAAS,qEAAqE;YAC9F,UAAU;YACV,QAAQ;;;;;;;","names":[]}