tempest-react-sdk 0.39.0 → 0.40.0

package/dist/vision/io/image.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"image.cjs","names":[],"sources":["../../../src/vision/io/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image loading utilities — convert any supported source into the canonical\n * {@link RGBImage} format.\n *\n * Browser-only: uses `fetch`, `createImageBitmap`, and a Canvas 2D context to\n * decode arbitrary inputs into a tightly-packed `Uint8Array` of HWC RGB pixels.\n */\n\nimport { createCanvas, get2DContext, imageDataToRGB } from \"../core/canvas\";\nimport { ImageLoadError } from \"../core/exceptions\";\nimport { RGBImage } from \"../types\";\n\n/** Anything {@link loadImage} accepts as an image input. */\nexport type ImageInput =\n    | string\n    | Blob\n    | HTMLImageElement\n    | HTMLCanvasElement\n    | OffscreenCanvas\n    | ImageBitmap\n    | ImageData\n    | RGBImage;\n\n/**\n * Load an image from any supported source into a HWC uint8 RGB array.\n *\n * @throws {@link ImageLoadError} if the source cannot be decoded or has an unsupported shape.\n */\nexport async function loadImage(source: ImageInput): Promise<RGBImage> {\n    if (source instanceof RGBImage) {\n        return source;\n    }\n\n    if (typeof ImageData !== \"undefined\" && source instanceof ImageData) {\n        return imageDataToRGB(source);\n    }\n\n    if (typeof source === \"string\") {\n        return loadFromUrl(source);\n    }\n\n    if (typeof Blob !== \"undefined\" && source instanceof Blob) {\n        return loadFromBlob(source);\n    }\n\n    if (typeof HTMLImageElement !== \"undefined\" && source instanceof HTMLImageElement) {\n        await waitForImageElement(source);\n        return drawableToRGB(source, source.naturalWidth, source.naturalHeight);\n    }\n\n    if (typeof HTMLCanvasElement !== \"undefined\" && source instanceof HTMLCanvasElement) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof OffscreenCanvas !== \"undefined\" && source instanceof OffscreenCanvas) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof ImageBitmap !== \"undefined\" && source instanceof ImageBitmap) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    throw new ImageLoadError(\n        `Unsupported image source type: ${Object.prototype.toString.call(source)}`,\n    );\n}\n\nasync function loadFromUrl(url: string): Promise<RGBImage> {\n    let response: Response;\n    try {\n        response = await fetch(url);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to fetch image from ${url}: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    if (!response.ok) {\n        throw new ImageLoadError(\n            `Failed to fetch image from ${url}: HTTP ${response.status} ${response.statusText}`,\n        );\n    }\n    const blob = await response.blob();\n    return loadFromBlob(blob);\n}\n\nasync function loadFromBlob(blob: Blob): Promise<RGBImage> {\n    let bitmap: ImageBitmap;\n    try {\n        bitmap = await createImageBitmap(blob);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to decode image blob: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    try {\n        return drawableToRGB(bitmap, bitmap.width, bitmap.height);\n    } finally {\n        bitmap.close();\n    }\n}\n\nfunction waitForImageElement(img: HTMLImageElement): Promise<void> {\n    if (img.complete && img.naturalWidth > 0) {\n        return Promise.resolve();\n    }\n    return new Promise<void>((resolve, reject) => {\n        const onLoad = (): void => {\n            cleanup();\n            resolve();\n        };\n        const onError = (): void => {\n            cleanup();\n            reject(new ImageLoadError(\"Failed to load HTMLImageElement (load event errored)\"));\n        };\n        const cleanup = (): void => {\n            img.removeEventListener(\"load\", onLoad);\n            img.removeEventListener(\"error\", onError);\n        };\n        img.addEventListener(\"load\", onLoad, { once: true });\n        img.addEventListener(\"error\", onError, { once: true });\n    });\n}\n\nfunction drawableToRGB(drawable: CanvasImageSource, width: number, height: number): RGBImage {\n    if (width === 0 || height === 0) {\n        throw new ImageLoadError(`Cannot load image with zero dimension (${width}x${height}).`);\n    }\n    const canvas = createCanvas(width, height);\n    const ctx = get2DContext(canvas);\n    ctx.drawImage(drawable, 0, 0);\n    const imageData = ctx.getImageData(0, 0, width, height);\n    return imageDataToRGB(imageData);\n}\n"],"mappings":"oGA6BA,eAAsB,EAAU,EAAuC,CACnE,GAAI,aAAkB,EAAA,SAClB,OAAO,EAGX,GAAI,OAAO,UAAc,KAAe,aAAkB,UACtD,OAAO,EAAA,eAAe,CAAM,EAGhC,GAAI,OAAO,GAAW,SAClB,OAAO,EAAY,CAAM,EAG7B,GAAI,OAAO,KAAS,KAAe,aAAkB,KACjD,OAAO,EAAa,CAAM,EAG9B,GAAI,OAAO,iBAAqB,KAAe,aAAkB,iBAE7D,OADA,MAAM,EAAoB,CAAM,EACzB,EAAc,EAAQ,EAAO,aAAc,EAAO,aAAa,EAW1E,GARI,OAAO,kBAAsB,KAAe,aAAkB,mBAI9D,OAAO,gBAAoB,KAAe,aAAkB,iBAI5D,OAAO,YAAgB,KAAe,aAAkB,YACxD,OAAO,EAAc,EAAQ,EAAO,MAAO,EAAO,MAAM,EAG5D,MAAM,IAAI,EAAA,eACN,kCAAkC,OAAO,UAAU,SAAS,KAAK,CAAM,GAC3E,CACJ,CAEA,eAAe,EAAY,EAAgC,CACvD,IAAI,EACJ,GAAI,CACA,EAAW,MAAM,MAAM,CAAG,CAC9B,OAAS,EAAK,CACV,MAAM,IAAI,EAAA,eAAe,8BAA8B,EAAI,IAAK,EAAc,UAAW,CACrF,MAAO,CACX,CAAC,CACL,CACA,GAAI,CAAC,EAAS,GACV,MAAM,IAAI,EAAA,eACN,8BAA8B,EAAI,SAAS,EAAS,OAAO,GAAG,EAAS,YAC3E,EAGJ,OAAO,EAAa,MADD,EAAS,KAAK,CACT,CAC5B,CAEA,eAAe,EAAa,EAA+B,CACvD,IAAI,EACJ,GAAI,CACA,EAAS,MAAM,kBAAkB,CAAI,CACzC,OAAS,EAAK,CACV,MAAM,IAAI,EAAA,eAAe,gCAAiC,EAAc,UAAW,CAC/E,MAAO,CACX,CAAC,CACL,CACA,GAAI,CACA,OAAO,EAAc,EAAQ,EAAO,MAAO,EAAO,MAAM,CAC5D,QAAU,CACN,EAAO,MAAM,CACjB,CACJ,CAEA,SAAS,EAAoB,EAAsC,CAI/D,OAHI,EAAI,UAAY,EAAI,aAAe,EAC5B,QAAQ,QAAQ,EAEpB,IAAI,SAAe,EAAS,IAAW,CAC1C,IAAM,MAAqB,CACvB,EAAQ,EACR,EAAQ,CACZ,EACM,MAAsB,CACxB,EAAQ,EACR,EAAO,IAAI,EAAA,eAAe,sDAAsD,CAAC,CACrF,EACM,MAAsB,CACxB,EAAI,oBAAoB,OAAQ,CAAM,EACtC,EAAI,oBAAoB,QAAS,CAAO,CAC5C,EACA,EAAI,iBAAiB,OAAQ,EAAQ,CAAE,KAAM,EAAK,CAAC,EACnD,EAAI,iBAAiB,QAAS,EAAS,CAAE,KAAM,EAAK,CAAC,CACzD,CAAC,CACL,CAEA,SAAS,EAAc,EAA6B,EAAe,EAA0B,CACzF,GAAI,IAAU,GAAK,IAAW,EAC1B,MAAM,IAAI,EAAA,eAAe,0CAA0C,EAAM,GAAG,EAAO,GAAG,EAG1F,IAAM,EAAM,EAAA,aADG,EAAA,aAAa,EAAO,CACV,CAAM,EAG/B,OAFA,EAAI,UAAU,EAAU,EAAG,CAAC,EAErB,EAAA,eADW,EAAI,aAAa,EAAG,EAAG,EAAO,CAC1B,CAAS,CACnC"}
+{"version":3,"file":"image.cjs","names":[],"sources":["../../../src/vision/io/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image loading utilities — convert any supported source into the canonical\n * {@link RGBImage} format.\n *\n * Browser-only: uses `fetch`, `createImageBitmap`, and a Canvas 2D context to\n * decode arbitrary inputs into a tightly-packed `Uint8Array` of HWC RGB pixels.\n */\n\nimport { createCanvas, get2DContext, imageDataToRGB } from \"../core/canvas\";\nimport { ImageLoadError } from \"../core/exceptions\";\nimport { RGBImage } from \"../types\";\n\n/** Anything {@link loadImage} accepts as an image input. */\nexport type ImageInput =\n    | string\n    | Blob\n    | HTMLImageElement\n    | HTMLCanvasElement\n    | OffscreenCanvas\n    | ImageBitmap\n    | ImageData\n    | RGBImage;\n\n/**\n * Load an image from any supported source into a HWC uint8 RGB array.\n *\n * @throws {@link ImageLoadError} if the source cannot be decoded or has an unsupported shape.\n */\nexport async function loadImage(source: ImageInput): Promise<RGBImage> {\n    if (source instanceof RGBImage) {\n        return source;\n    }\n\n    if (typeof ImageData !== \"undefined\" && source instanceof ImageData) {\n        return imageDataToRGB(source);\n    }\n\n    if (typeof source === \"string\") {\n        return loadFromUrl(source);\n    }\n\n    if (typeof Blob !== \"undefined\" && source instanceof Blob) {\n        return loadFromBlob(source);\n    }\n\n    if (typeof HTMLImageElement !== \"undefined\" && source instanceof HTMLImageElement) {\n        await waitForImageElement(source);\n        return drawableToRGB(source, source.naturalWidth, source.naturalHeight);\n    }\n\n    if (typeof HTMLCanvasElement !== \"undefined\" && source instanceof HTMLCanvasElement) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof OffscreenCanvas !== \"undefined\" && source instanceof OffscreenCanvas) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof ImageBitmap !== \"undefined\" && source instanceof ImageBitmap) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    throw new ImageLoadError(\n        `Unsupported image source type: ${Object.prototype.toString.call(source)}`,\n    );\n}\n\nasync function loadFromUrl(url: string): Promise<RGBImage> {\n    let response: Response;\n    try {\n        response = await fetch(url);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to fetch image from ${url}: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    if (!response.ok) {\n        throw new ImageLoadError(\n            `Failed to fetch image from ${url}: HTTP ${response.status} ${response.statusText}`,\n        );\n    }\n    const blob = await response.blob();\n    return loadFromBlob(blob);\n}\n\nasync function loadFromBlob(blob: Blob): Promise<RGBImage> {\n    let bitmap: ImageBitmap;\n    try {\n        bitmap = await createImageBitmap(blob);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to decode image blob: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    try {\n        return drawableToRGB(bitmap, bitmap.width, bitmap.height);\n    } finally {\n        bitmap.close();\n    }\n}\n\nfunction waitForImageElement(img: HTMLImageElement): Promise<void> {\n    if (img.complete && img.naturalWidth > 0) {\n        return Promise.resolve();\n    }\n    return new Promise<void>((resolve, reject) => {\n        const onLoad = (): void => {\n            cleanup();\n            resolve();\n        };\n        const onError = (): void => {\n            cleanup();\n            reject(new ImageLoadError(\"Failed to load HTMLImageElement (load event errored)\"));\n        };\n        const cleanup = (): void => {\n            img.removeEventListener(\"load\", onLoad);\n            img.removeEventListener(\"error\", onError);\n        };\n        img.addEventListener(\"load\", onLoad, { once: true });\n        img.addEventListener(\"error\", onError, { once: true });\n    });\n}\n\nfunction drawableToRGB(drawable: CanvasImageSource, width: number, height: number): RGBImage {\n    if (width === 0 || height === 0) {\n        throw new ImageLoadError(`Cannot load image with zero dimension (${width}x${height}).`);\n    }\n    const canvas = createCanvas(width, height);\n    const ctx = get2DContext(canvas);\n    ctx.drawImage(drawable, 0, 0);\n    const imageData = ctx.getImageData(0, 0, width, height);\n    return imageDataToRGB(imageData);\n}\n"],"mappings":"oGA6BA,eAAsB,EAAU,EAAuC,CACnE,GAAI,aAAkB,EAAA,SAClB,OAAO,EAGX,GAAI,OAAO,UAAc,KAAe,aAAkB,UACtD,OAAO,EAAA,eAAe,CAAM,EAGhC,GAAI,OAAO,GAAW,SAClB,OAAO,EAAY,CAAM,EAG7B,GAAI,OAAO,KAAS,KAAe,aAAkB,KACjD,OAAO,EAAa,CAAM,EAG9B,GAAI,OAAO,iBAAqB,KAAe,aAAkB,iBAE7D,OADA,MAAM,EAAoB,CAAM,EACzB,EAAc,EAAQ,EAAO,aAAc,EAAO,aAAa,EAW1E,GARI,OAAO,kBAAsB,KAAe,aAAkB,mBAI9D,OAAO,gBAAoB,KAAe,aAAkB,iBAI5D,OAAO,YAAgB,KAAe,aAAkB,YACxD,OAAO,EAAc,EAAQ,EAAO,MAAO,EAAO,MAAM,EAG5D,MAAM,IAAI,EAAA,eACN,kCAAkC,OAAO,UAAU,SAAS,KAAK,CAAM,GAC3E,CACJ,CAEA,eAAe,EAAY,EAAgC,CACvD,IAAI,EACJ,GAAI,CACA,EAAW,MAAM,MAAM,CAAG,CAC9B,OAAS,EAAK,CACV,MAAM,IAAI,EAAA,eAAe,8BAA8B,EAAI,IAAK,EAAc,UAAW,CACrF,MAAO,CACX,CAAC,CACL,CACA,GAAI,CAAC,EAAS,GACV,MAAM,IAAI,EAAA,eACN,8BAA8B,EAAI,SAAS,EAAS,OAAO,GAAG,EAAS,YAC3E,EAGJ,OAAO,EAAa,MADD,EAAS,KAAK,CACT,CAC5B,CAEA,eAAe,EAAa,EAA+B,CACvD,IAAI,EACJ,GAAI,CACA,EAAS,MAAM,kBAAkB,CAAI,CACzC,OAAS,EAAK,CACV,MAAM,IAAI,EAAA,eAAe,gCAAiC,EAAc,UAAW,CAC/E,MAAO,CACX,CAAC,CACL,CACA,GAAI,CACA,OAAO,EAAc,EAAQ,EAAO,MAAO,EAAO,MAAM,CAC5D,QAAU,CACN,EAAO,MAAM,CACjB,CACJ,CAEA,SAAS,EAAoB,EAAsC,CAI/D,OAHI,EAAI,UAAY,EAAI,aAAe,EAC5B,QAAQ,QAAQ,EAEpB,IAAI,SAAe,EAAS,IAAW,CAC1C,IAAM,MAAqB,CACvB,EAAQ,EACR,EAAQ,CACZ,EACM,MAAsB,CACxB,EAAQ,EACR,EAAO,IAAI,EAAA,eAAe,sDAAsD,CAAC,CACrF,EACM,MAAsB,CACxB,EAAI,oBAAoB,OAAQ,CAAM,EACtC,EAAI,oBAAoB,QAAS,CAAO,CAC5C,EACA,EAAI,iBAAiB,OAAQ,EAAQ,CAAE,KAAM,EAAK,CAAC,EACnD,EAAI,iBAAiB,QAAS,EAAS,CAAE,KAAM,EAAK,CAAC,CACzD,CAAC,CACL,CAEA,SAAS,EAAc,EAA6B,EAAe,EAA0B,CACzF,GAAI,IAAU,GAAK,IAAW,EAC1B,MAAM,IAAI,EAAA,eAAe,0CAA0C,EAAM,GAAG,EAAO,GAAG,EAE1F,IAAM,EAAS,EAAA,aAAa,EAAO,CAAM,EACnC,EAAM,EAAA,aAAa,CAAM,EAC/B,EAAI,UAAU,EAAU,EAAG,CAAC,EAC5B,IAAM,EAAY,EAAI,aAAa,EAAG,EAAG,EAAO,CAAM,EACtD,OAAO,EAAA,eAAe,CAAS,CACnC"}

package/dist/vision/io/image.js

@@ -48,8 +48,10 @@ function c(t) {
 }
 function l(t, a, o) {
 	if (a === 0 || o === 0) throw new e(`Cannot load image with zero dimension (${a}x${o}).`);
-	let s = r(n(a, o));
-	return s.drawImage(t, 0, 0), i(s.getImageData(0, 0, a, o));
+	let s = n(a, o), c = r(s);
+	c.drawImage(t, 0, 0);
+	let l = c.getImageData(0, 0, a, o);
+	return i(l);
 }
 //#endregion
 export { a as loadImage };

package/dist/vision/io/image.js.map

@@ -1 +1 @@
-{"version":3,"file":"image.js","names":[],"sources":["../../../src/vision/io/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image loading utilities — convert any supported source into the canonical\n * {@link RGBImage} format.\n *\n * Browser-only: uses `fetch`, `createImageBitmap`, and a Canvas 2D context to\n * decode arbitrary inputs into a tightly-packed `Uint8Array` of HWC RGB pixels.\n */\n\nimport { createCanvas, get2DContext, imageDataToRGB } from \"../core/canvas\";\nimport { ImageLoadError } from \"../core/exceptions\";\nimport { RGBImage } from \"../types\";\n\n/** Anything {@link loadImage} accepts as an image input. */\nexport type ImageInput =\n    | string\n    | Blob\n    | HTMLImageElement\n    | HTMLCanvasElement\n    | OffscreenCanvas\n    | ImageBitmap\n    | ImageData\n    | RGBImage;\n\n/**\n * Load an image from any supported source into a HWC uint8 RGB array.\n *\n * @throws {@link ImageLoadError} if the source cannot be decoded or has an unsupported shape.\n */\nexport async function loadImage(source: ImageInput): Promise<RGBImage> {\n    if (source instanceof RGBImage) {\n        return source;\n    }\n\n    if (typeof ImageData !== \"undefined\" && source instanceof ImageData) {\n        return imageDataToRGB(source);\n    }\n\n    if (typeof source === \"string\") {\n        return loadFromUrl(source);\n    }\n\n    if (typeof Blob !== \"undefined\" && source instanceof Blob) {\n        return loadFromBlob(source);\n    }\n\n    if (typeof HTMLImageElement !== \"undefined\" && source instanceof HTMLImageElement) {\n        await waitForImageElement(source);\n        return drawableToRGB(source, source.naturalWidth, source.naturalHeight);\n    }\n\n    if (typeof HTMLCanvasElement !== \"undefined\" && source instanceof HTMLCanvasElement) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof OffscreenCanvas !== \"undefined\" && source instanceof OffscreenCanvas) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof ImageBitmap !== \"undefined\" && source instanceof ImageBitmap) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    throw new ImageLoadError(\n        `Unsupported image source type: ${Object.prototype.toString.call(source)}`,\n    );\n}\n\nasync function loadFromUrl(url: string): Promise<RGBImage> {\n    let response: Response;\n    try {\n        response = await fetch(url);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to fetch image from ${url}: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    if (!response.ok) {\n        throw new ImageLoadError(\n            `Failed to fetch image from ${url}: HTTP ${response.status} ${response.statusText}`,\n        );\n    }\n    const blob = await response.blob();\n    return loadFromBlob(blob);\n}\n\nasync function loadFromBlob(blob: Blob): Promise<RGBImage> {\n    let bitmap: ImageBitmap;\n    try {\n        bitmap = await createImageBitmap(blob);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to decode image blob: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    try {\n        return drawableToRGB(bitmap, bitmap.width, bitmap.height);\n    } finally {\n        bitmap.close();\n    }\n}\n\nfunction waitForImageElement(img: HTMLImageElement): Promise<void> {\n    if (img.complete && img.naturalWidth > 0) {\n        return Promise.resolve();\n    }\n    return new Promise<void>((resolve, reject) => {\n        const onLoad = (): void => {\n            cleanup();\n            resolve();\n        };\n        const onError = (): void => {\n            cleanup();\n            reject(new ImageLoadError(\"Failed to load HTMLImageElement (load event errored)\"));\n        };\n        const cleanup = (): void => {\n            img.removeEventListener(\"load\", onLoad);\n            img.removeEventListener(\"error\", onError);\n        };\n        img.addEventListener(\"load\", onLoad, { once: true });\n        img.addEventListener(\"error\", onError, { once: true });\n    });\n}\n\nfunction drawableToRGB(drawable: CanvasImageSource, width: number, height: number): RGBImage {\n    if (width === 0 || height === 0) {\n        throw new ImageLoadError(`Cannot load image with zero dimension (${width}x${height}).`);\n    }\n    const canvas = createCanvas(width, height);\n    const ctx = get2DContext(canvas);\n    ctx.drawImage(drawable, 0, 0);\n    const imageData = ctx.getImageData(0, 0, width, height);\n    return imageDataToRGB(imageData);\n}\n"],"mappings":";;;;AA6BA,eAAsB,EAAU,GAAuC;CACnE,IAAI,aAAkB,GAClB,OAAO;CAGX,IAAI,OAAO,YAAc,OAAe,aAAkB,WACtD,OAAO,EAAe,CAAM;CAGhC,IAAI,OAAO,KAAW,UAClB,OAAO,EAAY,CAAM;CAG7B,IAAI,OAAO,OAAS,OAAe,aAAkB,MACjD,OAAO,EAAa,CAAM;CAG9B,IAAI,OAAO,mBAAqB,OAAe,aAAkB,kBAE7D,OADA,MAAM,EAAoB,CAAM,GACzB,EAAc,GAAQ,EAAO,cAAc,EAAO,aAAa;CAW1E,IARI,OAAO,oBAAsB,OAAe,aAAkB,qBAI9D,OAAO,kBAAoB,OAAe,aAAkB,mBAI5D,OAAO,cAAgB,OAAe,aAAkB,aACxD,OAAO,EAAc,GAAQ,EAAO,OAAO,EAAO,MAAM;CAG5D,MAAM,IAAI,EACN,kCAAkC,OAAO,UAAU,SAAS,KAAK,CAAM,GAC3E;AACJ;AAEA,eAAe,EAAY,GAAgC;CACvD,IAAI;CACJ,IAAI;EACA,IAAW,MAAM,MAAM,CAAG;CAC9B,SAAS,GAAK;EACV,MAAM,IAAI,EAAe,8BAA8B,EAAI,IAAK,EAAc,WAAW,EACrF,OAAO,EACX,CAAC;CACL;CACA,IAAI,CAAC,EAAS,IACV,MAAM,IAAI,EACN,8BAA8B,EAAI,SAAS,EAAS,OAAO,GAAG,EAAS,YAC3E;CAGJ,OAAO,EAAa,MADD,EAAS,KAAK,CACT;AAC5B;AAEA,eAAe,EAAa,GAA+B;CACvD,IAAI;CACJ,IAAI;EACA,IAAS,MAAM,kBAAkB,CAAI;CACzC,SAAS,GAAK;EACV,MAAM,IAAI,EAAe,gCAAiC,EAAc,WAAW,EAC/E,OAAO,EACX,CAAC;CACL;CACA,IAAI;EACA,OAAO,EAAc,GAAQ,EAAO,OAAO,EAAO,MAAM;CAC5D,UAAU;EACN,EAAO,MAAM;CACjB;AACJ;AAEA,SAAS,EAAoB,GAAsC;CAI/D,OAHI,EAAI,YAAY,EAAI,eAAe,IAC5B,QAAQ,QAAQ,IAEpB,IAAI,SAAe,GAAS,MAAW;EAC1C,IAAM,UAAqB;GAEvB,AADA,EAAQ,GACR,EAAQ;EACZ,GACM,UAAsB;GAExB,AADA,EAAQ,GACR,EAAO,IAAI,EAAe,sDAAsD,CAAC;EACrF,GACM,UAAsB;GAExB,AADA,EAAI,oBAAoB,QAAQ,CAAM,GACtC,EAAI,oBAAoB,SAAS,CAAO;EAC5C;EAEA,AADA,EAAI,iBAAiB,QAAQ,GAAQ,EAAE,MAAM,GAAK,CAAC,GACnD,EAAI,iBAAiB,SAAS,GAAS,EAAE,MAAM,GAAK,CAAC;CACzD,CAAC;AACL;AAEA,SAAS,EAAc,GAA6B,GAAe,GAA0B;CACzF,IAAI,MAAU,KAAK,MAAW,GAC1B,MAAM,IAAI,EAAe,0CAA0C,EAAM,GAAG,EAAO,GAAG;CAG1F,IAAM,IAAM,EADG,EAAa,GAAO,CACV,CAAM;CAG/B,OAFA,EAAI,UAAU,GAAU,GAAG,CAAC,GAErB,EADW,EAAI,aAAa,GAAG,GAAG,GAAO,CAC1B,CAAS;AACnC"}
+{"version":3,"file":"image.js","names":[],"sources":["../../../src/vision/io/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image loading utilities — convert any supported source into the canonical\n * {@link RGBImage} format.\n *\n * Browser-only: uses `fetch`, `createImageBitmap`, and a Canvas 2D context to\n * decode arbitrary inputs into a tightly-packed `Uint8Array` of HWC RGB pixels.\n */\n\nimport { createCanvas, get2DContext, imageDataToRGB } from \"../core/canvas\";\nimport { ImageLoadError } from \"../core/exceptions\";\nimport { RGBImage } from \"../types\";\n\n/** Anything {@link loadImage} accepts as an image input. */\nexport type ImageInput =\n    | string\n    | Blob\n    | HTMLImageElement\n    | HTMLCanvasElement\n    | OffscreenCanvas\n    | ImageBitmap\n    | ImageData\n    | RGBImage;\n\n/**\n * Load an image from any supported source into a HWC uint8 RGB array.\n *\n * @throws {@link ImageLoadError} if the source cannot be decoded or has an unsupported shape.\n */\nexport async function loadImage(source: ImageInput): Promise<RGBImage> {\n    if (source instanceof RGBImage) {\n        return source;\n    }\n\n    if (typeof ImageData !== \"undefined\" && source instanceof ImageData) {\n        return imageDataToRGB(source);\n    }\n\n    if (typeof source === \"string\") {\n        return loadFromUrl(source);\n    }\n\n    if (typeof Blob !== \"undefined\" && source instanceof Blob) {\n        return loadFromBlob(source);\n    }\n\n    if (typeof HTMLImageElement !== \"undefined\" && source instanceof HTMLImageElement) {\n        await waitForImageElement(source);\n        return drawableToRGB(source, source.naturalWidth, source.naturalHeight);\n    }\n\n    if (typeof HTMLCanvasElement !== \"undefined\" && source instanceof HTMLCanvasElement) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof OffscreenCanvas !== \"undefined\" && source instanceof OffscreenCanvas) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    if (typeof ImageBitmap !== \"undefined\" && source instanceof ImageBitmap) {\n        return drawableToRGB(source, source.width, source.height);\n    }\n\n    throw new ImageLoadError(\n        `Unsupported image source type: ${Object.prototype.toString.call(source)}`,\n    );\n}\n\nasync function loadFromUrl(url: string): Promise<RGBImage> {\n    let response: Response;\n    try {\n        response = await fetch(url);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to fetch image from ${url}: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    if (!response.ok) {\n        throw new ImageLoadError(\n            `Failed to fetch image from ${url}: HTTP ${response.status} ${response.statusText}`,\n        );\n    }\n    const blob = await response.blob();\n    return loadFromBlob(blob);\n}\n\nasync function loadFromBlob(blob: Blob): Promise<RGBImage> {\n    let bitmap: ImageBitmap;\n    try {\n        bitmap = await createImageBitmap(blob);\n    } catch (err) {\n        throw new ImageLoadError(`Failed to decode image blob: ${(err as Error).message}`, {\n            cause: err,\n        });\n    }\n    try {\n        return drawableToRGB(bitmap, bitmap.width, bitmap.height);\n    } finally {\n        bitmap.close();\n    }\n}\n\nfunction waitForImageElement(img: HTMLImageElement): Promise<void> {\n    if (img.complete && img.naturalWidth > 0) {\n        return Promise.resolve();\n    }\n    return new Promise<void>((resolve, reject) => {\n        const onLoad = (): void => {\n            cleanup();\n            resolve();\n        };\n        const onError = (): void => {\n            cleanup();\n            reject(new ImageLoadError(\"Failed to load HTMLImageElement (load event errored)\"));\n        };\n        const cleanup = (): void => {\n            img.removeEventListener(\"load\", onLoad);\n            img.removeEventListener(\"error\", onError);\n        };\n        img.addEventListener(\"load\", onLoad, { once: true });\n        img.addEventListener(\"error\", onError, { once: true });\n    });\n}\n\nfunction drawableToRGB(drawable: CanvasImageSource, width: number, height: number): RGBImage {\n    if (width === 0 || height === 0) {\n        throw new ImageLoadError(`Cannot load image with zero dimension (${width}x${height}).`);\n    }\n    const canvas = createCanvas(width, height);\n    const ctx = get2DContext(canvas);\n    ctx.drawImage(drawable, 0, 0);\n    const imageData = ctx.getImageData(0, 0, width, height);\n    return imageDataToRGB(imageData);\n}\n"],"mappings":";;;;AA6BA,eAAsB,EAAU,GAAuC;CACnE,IAAI,aAAkB,GAClB,OAAO;CAGX,IAAI,OAAO,YAAc,OAAe,aAAkB,WACtD,OAAO,EAAe,CAAM;CAGhC,IAAI,OAAO,KAAW,UAClB,OAAO,EAAY,CAAM;CAG7B,IAAI,OAAO,OAAS,OAAe,aAAkB,MACjD,OAAO,EAAa,CAAM;CAG9B,IAAI,OAAO,mBAAqB,OAAe,aAAkB,kBAE7D,OADA,MAAM,EAAoB,CAAM,GACzB,EAAc,GAAQ,EAAO,cAAc,EAAO,aAAa;CAW1E,IARI,OAAO,oBAAsB,OAAe,aAAkB,qBAI9D,OAAO,kBAAoB,OAAe,aAAkB,mBAI5D,OAAO,cAAgB,OAAe,aAAkB,aACxD,OAAO,EAAc,GAAQ,EAAO,OAAO,EAAO,MAAM;CAG5D,MAAM,IAAI,EACN,kCAAkC,OAAO,UAAU,SAAS,KAAK,CAAM,GAC3E;AACJ;AAEA,eAAe,EAAY,GAAgC;CACvD,IAAI;CACJ,IAAI;EACA,IAAW,MAAM,MAAM,CAAG;CAC9B,SAAS,GAAK;EACV,MAAM,IAAI,EAAe,8BAA8B,EAAI,IAAK,EAAc,WAAW,EACrF,OAAO,EACX,CAAC;CACL;CACA,IAAI,CAAC,EAAS,IACV,MAAM,IAAI,EACN,8BAA8B,EAAI,SAAS,EAAS,OAAO,GAAG,EAAS,YAC3E;CAGJ,OAAO,EAAa,MADD,EAAS,KAAK,CACT;AAC5B;AAEA,eAAe,EAAa,GAA+B;CACvD,IAAI;CACJ,IAAI;EACA,IAAS,MAAM,kBAAkB,CAAI;CACzC,SAAS,GAAK;EACV,MAAM,IAAI,EAAe,gCAAiC,EAAc,WAAW,EAC/E,OAAO,EACX,CAAC;CACL;CACA,IAAI;EACA,OAAO,EAAc,GAAQ,EAAO,OAAO,EAAO,MAAM;CAC5D,UAAU;EACN,EAAO,MAAM;CACjB;AACJ;AAEA,SAAS,EAAoB,GAAsC;CAI/D,OAHI,EAAI,YAAY,EAAI,eAAe,IAC5B,QAAQ,QAAQ,IAEpB,IAAI,SAAe,GAAS,MAAW;EAC1C,IAAM,UAAqB;GAEvB,AADA,EAAQ,GACR,EAAQ;EACZ,GACM,UAAsB;GAExB,AADA,EAAQ,GACR,EAAO,IAAI,EAAe,sDAAsD,CAAC;EACrF,GACM,UAAsB;GAExB,AADA,EAAI,oBAAoB,QAAQ,CAAM,GACtC,EAAI,oBAAoB,SAAS,CAAO;EAC5C;EAEA,AADA,EAAI,iBAAiB,QAAQ,GAAQ,EAAE,MAAM,GAAK,CAAC,GACnD,EAAI,iBAAiB,SAAS,GAAS,EAAE,MAAM,GAAK,CAAC;CACzD,CAAC;AACL;AAEA,SAAS,EAAc,GAA6B,GAAe,GAA0B;CACzF,IAAI,MAAU,KAAK,MAAW,GAC1B,MAAM,IAAI,EAAe,0CAA0C,EAAM,GAAG,EAAO,GAAG;CAE1F,IAAM,IAAS,EAAa,GAAO,CAAM,GACnC,IAAM,EAAa,CAAM;CAC/B,EAAI,UAAU,GAAU,GAAG,CAAC;CAC5B,IAAM,IAAY,EAAI,aAAa,GAAG,GAAG,GAAO,CAAM;CACtD,OAAO,EAAe,CAAS;AACnC"}

package/dist/vision/preprocess/image.cjs

@@ -1,2 +1,2 @@
-const e=require("../../_virtual/_rolldown/runtime.cjs"),t=require("../types.cjs"),n=require("../core/canvas.cjs");let r=require("onnxruntime-web");r=e.__toESM(r,1);function i(e,t,r){if(t<=0||r<=0)throw Error(`Invalid resize target ${t}x${r}.`);if(t===e.width&&r===e.height)return e;let i=n.createCanvas(e.width,e.height);n.get2DContext(i).putImageData(n.rgbToImageData(e),0,0);let a=n.get2DContext(n.createCanvas(t,r));return a.imageSmoothingEnabled=!0,a.imageSmoothingQuality=`high`,a.drawImage(i,0,0,t,r),n.imageDataToRGB(a.getImageData(0,0,t,r))}function a(e,t,n,r=1/255){let i=new Float32Array(e.data.length),a=e.data,o=t[0],s=t[1],c=t[2],l=n[0],u=n[1],d=n[2];for(let e=0;e<a.length;e+=3)i[e]=(a[e]*r-o)/l,i[e+1]=(a[e+1]*r-s)/u,i[e+2]=(a[e+2]*r-c)/d;return i}function o(e,t=1/255){let n=new Float32Array(e.data.length),r=e.data;for(let e=0;e<r.length;e++)n[e]=r[e]*t;return n}function s(e,t,n,r=3){let i=t*n*r;if(e.length!==i)throw Error(`toCHW: expected length ${i} for ${t}x${n}x${r}, got ${e.length}.`);let a=new Float32Array(i),o=t*n;for(let i=0;i<n;i++)for(let n=0;n<t;n++){let s=(i*t+n)*r,c=i*t+n;for(let t=0;t<r;t++)a[t*o+c]=e[s+t]}return a}function c(e,t){return new r.Tensor(`float32`,e,t)}function l(e){return s(o(e),e.width,e.height,3)}function u(e,n,r){if(e.length!==n*r*3)throw Error(`fromCv2: data length ${e.length} does not match width * height * 3 = ${n*r*3}.`);let i=new Uint8Array(e.length);for(let t=0;t<e.length;t+=3)i[t]=e[t+2],i[t+1]=e[t+1],i[t+2]=e[t];return new t.RGBImage(i,n,r)}function d(e){let t=e.data,n=new Uint8Array(t.length);for(let e=0;e<t.length;e+=3)n[e]=t[e+2],n[e+1]=t[e+1],n[e+2]=t[e];return n}function f(e,n,r,a=[114,114,114]){let o=Math.min(n/e.width,r/e.height),s=Math.round(e.width*o),c=Math.round(e.height*o),l=i(e,s,c),u=new Uint8Array(n*r*3),d=a[0],f=a[1],p=a[2];for(let e=0;e<u.length;e+=3)u[e]=d,u[e+1]=f,u[e+2]=p;let m=Math.floor((n-s)/2),h=Math.floor((r-c)/2),g=s*3;for(let e=0;e<c;e++){let t=e*g,r=((h+e)*n+m)*3;u.set(l.data.subarray(t,t+g),r)}return{image:new t.RGBImage(u,n,r),scale:o,padLeft:m,padTop:h}}exports.fromCv2=u,exports.letterbox=f,exports.normalize=a,exports.resize=i,exports.toCHW=s,exports.toCv2=d,exports.toFloat32=o,exports.toFloat32Tensor=c,exports.toTensor=l;
+const e=require("../../_virtual/_rolldown/runtime.cjs"),t=require("../types.cjs"),n=require("../core/canvas.cjs");let r=require("onnxruntime-web");r=e.__toESM(r,1);function i(e,t,r){if(t<=0||r<=0)throw Error(`Invalid resize target ${t}x${r}.`);if(t===e.width&&r===e.height)return e;let i=n.createCanvas(e.width,e.height);n.get2DContext(i).putImageData(n.rgbToImageData(e),0,0);let a=n.createCanvas(t,r),o=n.get2DContext(a);o.imageSmoothingEnabled=!0,o.imageSmoothingQuality=`high`,o.drawImage(i,0,0,t,r);let s=o.getImageData(0,0,t,r);return n.imageDataToRGB(s)}function a(e,t,n,r=1/255){let i=new Float32Array(e.data.length),a=e.data,o=t[0],s=t[1],c=t[2],l=n[0],u=n[1],d=n[2];for(let e=0;e<a.length;e+=3)i[e]=(a[e]*r-o)/l,i[e+1]=(a[e+1]*r-s)/u,i[e+2]=(a[e+2]*r-c)/d;return i}function o(e,t=1/255){let n=new Float32Array(e.data.length),r=e.data;for(let e=0;e<r.length;e++)n[e]=r[e]*t;return n}function s(e,t,n,r=3){let i=t*n*r;if(e.length!==i)throw Error(`toCHW: expected length ${i} for ${t}x${n}x${r}, got ${e.length}.`);let a=new Float32Array(i),o=t*n;for(let i=0;i<n;i++)for(let n=0;n<t;n++){let s=(i*t+n)*r,c=i*t+n;for(let t=0;t<r;t++)a[t*o+c]=e[s+t]}return a}function c(e,t){return new r.Tensor(`float32`,e,t)}function l(e){return s(o(e),e.width,e.height,3)}function u(e,n,r){if(e.length!==n*r*3)throw Error(`fromCv2: data length ${e.length} does not match width * height * 3 = ${n*r*3}.`);let i=new Uint8Array(e.length);for(let t=0;t<e.length;t+=3)i[t]=e[t+2],i[t+1]=e[t+1],i[t+2]=e[t];return new t.RGBImage(i,n,r)}function d(e){let t=e.data,n=new Uint8Array(t.length);for(let e=0;e<t.length;e+=3)n[e]=t[e+2],n[e+1]=t[e+1],n[e+2]=t[e];return n}function f(e,n,r,a=[114,114,114]){let o=Math.min(n/e.width,r/e.height),s=Math.round(e.width*o),c=Math.round(e.height*o),l=i(e,s,c),u=new Uint8Array(n*r*3),d=a[0],f=a[1],p=a[2];for(let e=0;e<u.length;e+=3)u[e]=d,u[e+1]=f,u[e+2]=p;let m=Math.floor((n-s)/2),h=Math.floor((r-c)/2),g=s*3;for(let e=0;e<c;e++){let t=e*g,r=((h+e)*n+m)*3;u.set(l.data.subarray(t,t+g),r)}return{image:new t.RGBImage(u,n,r),scale:o,padLeft:m,padTop:h}}exports.fromCv2=u,exports.letterbox=f,exports.normalize=a,exports.resize=i,exports.toCHW=s,exports.toCv2=d,exports.toFloat32=o,exports.toFloat32Tensor=c,exports.toTensor=l;
 //# sourceMappingURL=image.cjs.map

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

@@ -1 +1 @@
-{"version":3,"file":"image.cjs","names":[],"sources":["../../../src/vision/preprocess/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Composable image preprocessing primitives (resize, normalize, letterbox, layout).\n *\n * Mirrors the Python `preprocess.image` module. Operates on the canonical\n * {@link RGBImage} (HWC RGB uint8) and produces uint8 or float32 buffers\n * depending on the operation.\n */\n\nimport * as ortRuntime from \"onnxruntime-web\";\nimport type * as ort from \"onnxruntime-web\";\n\nimport { createCanvas, get2DContext, imageDataToRGB, rgbToImageData } from \"../core/canvas\";\nimport { RGBImage } from \"../types\";\n\n/** Resize an image to `(targetWidth, targetHeight)` using high-quality canvas resampling. */\nexport function resize(image: RGBImage, targetWidth: number, targetHeight: number): RGBImage {\n    if (targetWidth <= 0 || targetHeight <= 0) {\n        throw new Error(`Invalid resize target ${targetWidth}x${targetHeight}.`);\n    }\n    if (targetWidth === image.width && targetHeight === image.height) {\n        return image;\n    }\n\n    const srcCanvas = createCanvas(image.width, image.height);\n    const srcCtx = get2DContext(srcCanvas);\n    srcCtx.putImageData(rgbToImageData(image), 0, 0);\n\n    const dstCanvas = createCanvas(targetWidth, targetHeight);\n    const dstCtx = get2DContext(dstCanvas);\n    dstCtx.imageSmoothingEnabled = true;\n    dstCtx.imageSmoothingQuality = \"high\";\n    dstCtx.drawImage(srcCanvas as CanvasImageSource, 0, 0, targetWidth, targetHeight);\n\n    const imageData = dstCtx.getImageData(0, 0, targetWidth, targetHeight);\n    return imageDataToRGB(imageData);\n}\n\n/**\n * Convert a uint8 image to a normalized float32 array (HWC layout preserved).\n *\n * Applies `(pixel * scale - mean) / std` channel-wise.\n */\nexport function normalize(\n    image: RGBImage,\n    mean: readonly [number, number, number],\n    std: readonly [number, number, number],\n    scale: number = 1 / 255,\n): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    const m0 = mean[0];\n    const m1 = mean[1];\n    const m2 = mean[2];\n    const s0 = std[0];\n    const s1 = std[1];\n    const s2 = std[2];\n    for (let i = 0; i < data.length; i += 3) {\n        out[i] = ((data[i] as number) * scale - m0) / s0;\n        out[i + 1] = ((data[i + 1] as number) * scale - m1) / s1;\n        out[i + 2] = ((data[i + 2] as number) * scale - m2) / s2;\n    }\n    return out;\n}\n\n/** Convert a uint8 image to a `Float32Array` in `[0, 1]` (HWC layout preserved). */\nexport function toFloat32(image: RGBImage, scale: number = 1 / 255): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    for (let i = 0; i < data.length; i++) {\n        out[i] = (data[i] as number) * scale;\n    }\n    return out;\n}\n\n/**\n * Transpose interleaved HWC data to planar CHW layout.\n *\n * @param hwc Source array of length `width * height * channels`.\n */\nexport function toCHW(\n    hwc: Float32Array,\n    width: number,\n    height: number,\n    channels: number = 3,\n): Float32Array {\n    const expected = width * height * channels;\n    if (hwc.length !== expected) {\n        throw new Error(\n            `toCHW: expected length ${expected} for ${width}x${height}x${channels}, got ${hwc.length}.`,\n        );\n    }\n    const chw = new Float32Array(expected);\n    const plane = width * height;\n    for (let y = 0; y < height; y++) {\n        for (let x = 0; x < width; x++) {\n            const hwcBase = (y * width + x) * channels;\n            const planeIdx = y * width + x;\n            for (let c = 0; c < channels; c++) {\n                chw[c * plane + planeIdx] = hwc[hwcBase + c] as number;\n            }\n        }\n    }\n    return chw;\n}\n\n/** Wrap a Float32 buffer into an `ort.Tensor`. */\nexport function toFloat32Tensor(data: Float32Array, dims: readonly number[]): ort.Tensor {\n    return new ortRuntime.Tensor(\"float32\", data, dims as number[]);\n}\n\n/**\n * Convert an HWC uint8 image to a CHW `Float32Array` scaled to `[0, 1]`.\n *\n * Mirrors `torchvision.transforms.ToTensor()` semantics: HWC → CHW,\n * `uint8 → float32 / 255`. Useful as input to YOLO-style detectors that\n * don't require ImageNet normalization.\n *\n * @returns CHW `Float32Array` of length `width * height * 3`.\n */\nexport function toTensor(image: RGBImage): Float32Array {\n    const f32 = toFloat32(image);\n    return toCHW(f32, image.width, image.height, 3);\n}\n\n/**\n * Convert an HWC BGR uint8 buffer (OpenCV layout) to the SDK's HWC RGB.\n *\n * Use when you receive image bytes from `cv2.imencode` over the wire and\n * want to feed them to the SDK without going through a canvas decode.\n *\n * @param bgr Flat BGR Uint8Array of length `width * height * 3`.\n */\nexport function fromCv2(bgr: Uint8Array, width: number, height: number): RGBImage {\n    if (bgr.length !== width * height * 3) {\n        throw new Error(\n            `fromCv2: data length ${bgr.length} does not match width * height * 3 = ${width * height * 3}.`,\n        );\n    }\n    const rgb = new Uint8Array(bgr.length);\n    for (let i = 0; i < bgr.length; i += 3) {\n        rgb[i] = bgr[i + 2] as number;\n        rgb[i + 1] = bgr[i + 1] as number;\n        rgb[i + 2] = bgr[i] as number;\n    }\n    return new RGBImage(rgb, width, height);\n}\n\n/**\n * Convert the SDK's HWC RGB image to an HWC BGR `Uint8Array` (OpenCV layout).\n *\n * Useful for round-tripping data to a Python OpenCV consumer.\n */\nexport function toCv2(image: RGBImage): Uint8Array {\n    const rgb = image.data;\n    const bgr = new Uint8Array(rgb.length);\n    for (let i = 0; i < rgb.length; i += 3) {\n        bgr[i] = rgb[i + 2] as number;\n        bgr[i + 1] = rgb[i + 1] as number;\n        bgr[i + 2] = rgb[i] as number;\n    }\n    return bgr;\n}\n\nexport interface LetterboxResult {\n    /** The padded image at the target size. */\n    readonly image: RGBImage;\n    /** The factor applied to the original image (`< 1` if downscaled). */\n    readonly scale: number;\n    /** Horizontal padding in pixels (left side; right side has the same or +1). */\n    readonly padLeft: number;\n    /** Vertical padding in pixels (top side). */\n    readonly padTop: number;\n}\n\n/**\n * Resize preserving aspect ratio, padding to `(targetWidth, targetHeight)`\n * with a constant fill color.\n *\n * Standard YOLO preprocessing — returning `scale` and `padLeft`/`padTop`\n * lets callers map detections back to the original image coordinates.\n */\nexport function letterbox(\n    image: RGBImage,\n    targetWidth: number,\n    targetHeight: number,\n    fill: readonly [number, number, number] = [114, 114, 114],\n): LetterboxResult {\n    const scale = Math.min(targetWidth / image.width, targetHeight / image.height);\n    const newW = Math.round(image.width * scale);\n    const newH = Math.round(image.height * scale);\n    const resized = resize(image, newW, newH);\n\n    const out = new Uint8Array(targetWidth * targetHeight * 3);\n    const f0 = fill[0];\n    const f1 = fill[1];\n    const f2 = fill[2];\n    for (let i = 0; i < out.length; i += 3) {\n        out[i] = f0;\n        out[i + 1] = f1;\n        out[i + 2] = f2;\n    }\n\n    const padLeft = Math.floor((targetWidth - newW) / 2);\n    const padTop = Math.floor((targetHeight - newH) / 2);\n    const rowBytes = newW * 3;\n    for (let y = 0; y < newH; y++) {\n        const srcOffset = y * rowBytes;\n        const dstOffset = ((padTop + y) * targetWidth + padLeft) * 3;\n        out.set(resized.data.subarray(srcOffset, srcOffset + rowBytes), dstOffset);\n    }\n\n    return {\n        image: new RGBImage(out, targetWidth, targetHeight),\n        scale,\n        padLeft,\n        padTop,\n    };\n}\n"],"mappings":"oKAgBA,SAAgB,EAAO,EAAiB,EAAqB,EAAgC,CACzF,GAAI,GAAe,GAAK,GAAgB,EACpC,MAAU,MAAM,yBAAyB,EAAY,GAAG,EAAa,EAAE,EAE3E,GAAI,IAAgB,EAAM,OAAS,IAAiB,EAAM,OACtD,OAAO,EAGX,IAAM,EAAY,EAAA,aAAa,EAAM,MAAO,EAAM,MAAM,EAExD,EADe,aAAa,CAC5B,CAAA,CAAO,aAAa,EAAA,eAAe,CAAK,EAAG,EAAG,CAAC,EAG/C,IAAM,EAAS,EAAA,aADG,EAAA,aAAa,EAAa,CAChB,CAAS,EAMrC,MALA,GAAO,sBAAwB,GAC/B,EAAO,sBAAwB,OAC/B,EAAO,UAAU,EAAgC,EAAG,EAAG,EAAa,CAAY,EAGzE,EAAA,eADW,EAAO,aAAa,EAAG,EAAG,EAAa,CACnC,CAAS,CACnC,CAOA,SAAgB,EACZ,EACA,EACA,EACA,EAAgB,EAAI,IACR,CACZ,IAAM,EAAM,IAAI,aAAa,EAAM,KAAK,MAAM,EACxC,EAAO,EAAM,KACb,EAAK,EAAK,GACV,EAAK,EAAK,GACV,EAAK,EAAK,GACV,EAAK,EAAI,GACT,EAAK,EAAI,GACT,EAAK,EAAI,GACf,IAAK,IAAI,EAAI,EAAG,EAAI,EAAK,OAAQ,GAAK,EAClC,EAAI,IAAO,EAAK,GAAgB,EAAQ,GAAM,EAC9C,EAAI,EAAI,IAAO,EAAK,EAAI,GAAgB,EAAQ,GAAM,EACtD,EAAI,EAAI,IAAO,EAAK,EAAI,GAAgB,EAAQ,GAAM,EAE1D,OAAO,CACX,CAGA,SAAgB,EAAU,EAAiB,EAAgB,EAAI,IAAmB,CAC9E,IAAM,EAAM,IAAI,aAAa,EAAM,KAAK,MAAM,EACxC,EAAO,EAAM,KACnB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAK,OAAQ,IAC7B,EAAI,GAAM,EAAK,GAAgB,EAEnC,OAAO,CACX,CAOA,SAAgB,EACZ,EACA,EACA,EACA,EAAmB,EACP,CACZ,IAAM,EAAW,EAAQ,EAAS,EAClC,GAAI,EAAI,SAAW,EACf,MAAU,MACN,0BAA0B,EAAS,OAAO,EAAM,GAAG,EAAO,GAAG,EAAS,QAAQ,EAAI,OAAO,EAC7F,EAEJ,IAAM,EAAM,IAAI,aAAa,CAAQ,EAC/B,EAAQ,EAAQ,EACtB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,IACxB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAO,IAAK,CAC5B,IAAM,GAAW,EAAI,EAAQ,GAAK,EAC5B,EAAW,EAAI,EAAQ,EAC7B,IAAK,IAAI,EAAI,EAAG,EAAI,EAAU,IAC1B,EAAI,EAAI,EAAQ,GAAY,EAAI,EAAU,EAElD,CAEJ,OAAO,CACX,CAGA,SAAgB,EAAgB,EAAoB,EAAqC,CACrF,OAAO,IAAI,EAAW,OAAO,UAAW,EAAM,CAAgB,CAClE,CAWA,SAAgB,EAAS,EAA+B,CAEpD,OAAO,EADK,EAAU,CACT,EAAK,EAAM,MAAO,EAAM,OAAQ,CAAC,CAClD,CAUA,SAAgB,EAAQ,EAAiB,EAAe,EAA0B,CAC9E,GAAI,EAAI,SAAW,EAAQ,EAAS,EAChC,MAAU,MACN,wBAAwB,EAAI,OAAO,uCAAuC,EAAQ,EAAS,EAAE,EACjG,EAEJ,IAAM,EAAM,IAAI,WAAW,EAAI,MAAM,EACrC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAI,OAAQ,GAAK,EACjC,EAAI,GAAK,EAAI,EAAI,GACjB,EAAI,EAAI,GAAK,EAAI,EAAI,GACrB,EAAI,EAAI,GAAK,EAAI,GAErB,OAAO,IAAI,EAAA,SAAS,EAAK,EAAO,CAAM,CAC1C,CAOA,SAAgB,EAAM,EAA6B,CAC/C,IAAM,EAAM,EAAM,KACZ,EAAM,IAAI,WAAW,EAAI,MAAM,EACrC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAI,OAAQ,GAAK,EACjC,EAAI,GAAK,EAAI,EAAI,GACjB,EAAI,EAAI,GAAK,EAAI,EAAI,GACrB,EAAI,EAAI,GAAK,EAAI,GAErB,OAAO,CACX,CAoBA,SAAgB,EACZ,EACA,EACA,EACA,EAA0C,CAAC,IAAK,IAAK,GAAG,EACzC,CACf,IAAM,EAAQ,KAAK,IAAI,EAAc,EAAM,MAAO,EAAe,EAAM,MAAM,EACvE,EAAO,KAAK,MAAM,EAAM,MAAQ,CAAK,EACrC,EAAO,KAAK,MAAM,EAAM,OAAS,CAAK,EACtC,EAAU,EAAO,EAAO,EAAM,CAAI,EAElC,EAAM,IAAI,WAAW,EAAc,EAAe,CAAC,EACnD,EAAK,EAAK,GACV,EAAK,EAAK,GACV,EAAK,EAAK,GAChB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAI,OAAQ,GAAK,EACjC,EAAI,GAAK,EACT,EAAI,EAAI,GAAK,EACb,EAAI,EAAI,GAAK,EAGjB,IAAM,EAAU,KAAK,OAAO,EAAc,GAAQ,CAAC,EAC7C,EAAS,KAAK,OAAO,EAAe,GAAQ,CAAC,EAC7C,EAAW,EAAO,EACxB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAM,IAAK,CAC3B,IAAM,EAAY,EAAI,EAChB,IAAc,EAAS,GAAK,EAAc,GAAW,EAC3D,EAAI,IAAI,EAAQ,KAAK,SAAS,EAAW,EAAY,CAAQ,EAAG,CAAS,CAC7E,CAEA,MAAO,CACH,MAAO,IAAI,EAAA,SAAS,EAAK,EAAa,CAAY,EAClD,QACA,UACA,QACJ,CACJ"}
+{"version":3,"file":"image.cjs","names":[],"sources":["../../../src/vision/preprocess/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Composable image preprocessing primitives (resize, normalize, letterbox, layout).\n *\n * Mirrors the Python `preprocess.image` module. Operates on the canonical\n * {@link RGBImage} (HWC RGB uint8) and produces uint8 or float32 buffers\n * depending on the operation.\n */\n\nimport * as ortRuntime from \"onnxruntime-web\";\nimport type * as ort from \"onnxruntime-web\";\n\nimport { createCanvas, get2DContext, imageDataToRGB, rgbToImageData } from \"../core/canvas\";\nimport { RGBImage } from \"../types\";\n\n/** Resize an image to `(targetWidth, targetHeight)` using high-quality canvas resampling. */\nexport function resize(image: RGBImage, targetWidth: number, targetHeight: number): RGBImage {\n    if (targetWidth <= 0 || targetHeight <= 0) {\n        throw new Error(`Invalid resize target ${targetWidth}x${targetHeight}.`);\n    }\n    if (targetWidth === image.width && targetHeight === image.height) {\n        return image;\n    }\n\n    const srcCanvas = createCanvas(image.width, image.height);\n    const srcCtx = get2DContext(srcCanvas);\n    srcCtx.putImageData(rgbToImageData(image), 0, 0);\n\n    const dstCanvas = createCanvas(targetWidth, targetHeight);\n    const dstCtx = get2DContext(dstCanvas);\n    dstCtx.imageSmoothingEnabled = true;\n    dstCtx.imageSmoothingQuality = \"high\";\n    dstCtx.drawImage(srcCanvas as CanvasImageSource, 0, 0, targetWidth, targetHeight);\n\n    const imageData = dstCtx.getImageData(0, 0, targetWidth, targetHeight);\n    return imageDataToRGB(imageData);\n}\n\n/**\n * Convert a uint8 image to a normalized float32 array (HWC layout preserved).\n *\n * Applies `(pixel * scale - mean) / std` channel-wise.\n */\nexport function normalize(\n    image: RGBImage,\n    mean: readonly [number, number, number],\n    std: readonly [number, number, number],\n    scale: number = 1 / 255,\n): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    const m0 = mean[0];\n    const m1 = mean[1];\n    const m2 = mean[2];\n    const s0 = std[0];\n    const s1 = std[1];\n    const s2 = std[2];\n    for (let i = 0; i < data.length; i += 3) {\n        out[i] = ((data[i] as number) * scale - m0) / s0;\n        out[i + 1] = ((data[i + 1] as number) * scale - m1) / s1;\n        out[i + 2] = ((data[i + 2] as number) * scale - m2) / s2;\n    }\n    return out;\n}\n\n/** Convert a uint8 image to a `Float32Array` in `[0, 1]` (HWC layout preserved). */\nexport function toFloat32(image: RGBImage, scale: number = 1 / 255): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    for (let i = 0; i < data.length; i++) {\n        out[i] = (data[i] as number) * scale;\n    }\n    return out;\n}\n\n/**\n * Transpose interleaved HWC data to planar CHW layout.\n *\n * @param hwc Source array of length `width * height * channels`.\n */\nexport function toCHW(\n    hwc: Float32Array,\n    width: number,\n    height: number,\n    channels: number = 3,\n): Float32Array {\n    const expected = width * height * channels;\n    if (hwc.length !== expected) {\n        throw new Error(\n            `toCHW: expected length ${expected} for ${width}x${height}x${channels}, got ${hwc.length}.`,\n        );\n    }\n    const chw = new Float32Array(expected);\n    const plane = width * height;\n    for (let y = 0; y < height; y++) {\n        for (let x = 0; x < width; x++) {\n            const hwcBase = (y * width + x) * channels;\n            const planeIdx = y * width + x;\n            for (let c = 0; c < channels; c++) {\n                chw[c * plane + planeIdx] = hwc[hwcBase + c] as number;\n            }\n        }\n    }\n    return chw;\n}\n\n/** Wrap a Float32 buffer into an `ort.Tensor`. */\nexport function toFloat32Tensor(data: Float32Array, dims: readonly number[]): ort.Tensor {\n    return new ortRuntime.Tensor(\"float32\", data, dims as number[]);\n}\n\n/**\n * Convert an HWC uint8 image to a CHW `Float32Array` scaled to `[0, 1]`.\n *\n * Mirrors `torchvision.transforms.ToTensor()` semantics: HWC → CHW,\n * `uint8 → float32 / 255`. Useful as input to YOLO-style detectors that\n * don't require ImageNet normalization.\n *\n * @returns CHW `Float32Array` of length `width * height * 3`.\n */\nexport function toTensor(image: RGBImage): Float32Array {\n    const f32 = toFloat32(image);\n    return toCHW(f32, image.width, image.height, 3);\n}\n\n/**\n * Convert an HWC BGR uint8 buffer (OpenCV layout) to the SDK's HWC RGB.\n *\n * Use when you receive image bytes from `cv2.imencode` over the wire and\n * want to feed them to the SDK without going through a canvas decode.\n *\n * @param bgr Flat BGR Uint8Array of length `width * height * 3`.\n */\nexport function fromCv2(bgr: Uint8Array, width: number, height: number): RGBImage {\n    if (bgr.length !== width * height * 3) {\n        throw new Error(\n            `fromCv2: data length ${bgr.length} does not match width * height * 3 = ${width * height * 3}.`,\n        );\n    }\n    const rgb = new Uint8Array(bgr.length);\n    for (let i = 0; i < bgr.length; i += 3) {\n        rgb[i] = bgr[i + 2] as number;\n        rgb[i + 1] = bgr[i + 1] as number;\n        rgb[i + 2] = bgr[i] as number;\n    }\n    return new RGBImage(rgb, width, height);\n}\n\n/**\n * Convert the SDK's HWC RGB image to an HWC BGR `Uint8Array` (OpenCV layout).\n *\n * Useful for round-tripping data to a Python OpenCV consumer.\n */\nexport function toCv2(image: RGBImage): Uint8Array {\n    const rgb = image.data;\n    const bgr = new Uint8Array(rgb.length);\n    for (let i = 0; i < rgb.length; i += 3) {\n        bgr[i] = rgb[i + 2] as number;\n        bgr[i + 1] = rgb[i + 1] as number;\n        bgr[i + 2] = rgb[i] as number;\n    }\n    return bgr;\n}\n\nexport interface LetterboxResult {\n    /** The padded image at the target size. */\n    readonly image: RGBImage;\n    /** The factor applied to the original image (`< 1` if downscaled). */\n    readonly scale: number;\n    /** Horizontal padding in pixels (left side; right side has the same or +1). */\n    readonly padLeft: number;\n    /** Vertical padding in pixels (top side). */\n    readonly padTop: number;\n}\n\n/**\n * Resize preserving aspect ratio, padding to `(targetWidth, targetHeight)`\n * with a constant fill color.\n *\n * Standard YOLO preprocessing — returning `scale` and `padLeft`/`padTop`\n * lets callers map detections back to the original image coordinates.\n */\nexport function letterbox(\n    image: RGBImage,\n    targetWidth: number,\n    targetHeight: number,\n    fill: readonly [number, number, number] = [114, 114, 114],\n): LetterboxResult {\n    const scale = Math.min(targetWidth / image.width, targetHeight / image.height);\n    const newW = Math.round(image.width * scale);\n    const newH = Math.round(image.height * scale);\n    const resized = resize(image, newW, newH);\n\n    const out = new Uint8Array(targetWidth * targetHeight * 3);\n    const f0 = fill[0];\n    const f1 = fill[1];\n    const f2 = fill[2];\n    for (let i = 0; i < out.length; i += 3) {\n        out[i] = f0;\n        out[i + 1] = f1;\n        out[i + 2] = f2;\n    }\n\n    const padLeft = Math.floor((targetWidth - newW) / 2);\n    const padTop = Math.floor((targetHeight - newH) / 2);\n    const rowBytes = newW * 3;\n    for (let y = 0; y < newH; y++) {\n        const srcOffset = y * rowBytes;\n        const dstOffset = ((padTop + y) * targetWidth + padLeft) * 3;\n        out.set(resized.data.subarray(srcOffset, srcOffset + rowBytes), dstOffset);\n    }\n\n    return {\n        image: new RGBImage(out, targetWidth, targetHeight),\n        scale,\n        padLeft,\n        padTop,\n    };\n}\n"],"mappings":"oKAgBA,SAAgB,EAAO,EAAiB,EAAqB,EAAgC,CACzF,GAAI,GAAe,GAAK,GAAgB,EACpC,MAAU,MAAM,yBAAyB,EAAY,GAAG,EAAa,EAAE,EAE3E,GAAI,IAAgB,EAAM,OAAS,IAAiB,EAAM,OACtD,OAAO,EAGX,IAAM,EAAY,EAAA,aAAa,EAAM,MAAO,EAAM,MAAM,EAExD,EADe,aAAa,CAC5B,CAAA,CAAO,aAAa,EAAA,eAAe,CAAK,EAAG,EAAG,CAAC,EAE/C,IAAM,EAAY,EAAA,aAAa,EAAa,CAAY,EAClD,EAAS,EAAA,aAAa,CAAS,EACrC,EAAO,sBAAwB,GAC/B,EAAO,sBAAwB,OAC/B,EAAO,UAAU,EAAgC,EAAG,EAAG,EAAa,CAAY,EAEhF,IAAM,EAAY,EAAO,aAAa,EAAG,EAAG,EAAa,CAAY,EACrE,OAAO,EAAA,eAAe,CAAS,CACnC,CAOA,SAAgB,EACZ,EACA,EACA,EACA,EAAgB,EAAI,IACR,CACZ,IAAM,EAAM,IAAI,aAAa,EAAM,KAAK,MAAM,EACxC,EAAO,EAAM,KACb,EAAK,EAAK,GACV,EAAK,EAAK,GACV,EAAK,EAAK,GACV,EAAK,EAAI,GACT,EAAK,EAAI,GACT,EAAK,EAAI,GACf,IAAK,IAAI,EAAI,EAAG,EAAI,EAAK,OAAQ,GAAK,EAClC,EAAI,IAAO,EAAK,GAAgB,EAAQ,GAAM,EAC9C,EAAI,EAAI,IAAO,EAAK,EAAI,GAAgB,EAAQ,GAAM,EACtD,EAAI,EAAI,IAAO,EAAK,EAAI,GAAgB,EAAQ,GAAM,EAE1D,OAAO,CACX,CAGA,SAAgB,EAAU,EAAiB,EAAgB,EAAI,IAAmB,CAC9E,IAAM,EAAM,IAAI,aAAa,EAAM,KAAK,MAAM,EACxC,EAAO,EAAM,KACnB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAK,OAAQ,IAC7B,EAAI,GAAM,EAAK,GAAgB,EAEnC,OAAO,CACX,CAOA,SAAgB,EACZ,EACA,EACA,EACA,EAAmB,EACP,CACZ,IAAM,EAAW,EAAQ,EAAS,EAClC,GAAI,EAAI,SAAW,EACf,MAAU,MACN,0BAA0B,EAAS,OAAO,EAAM,GAAG,EAAO,GAAG,EAAS,QAAQ,EAAI,OAAO,EAC7F,EAEJ,IAAM,EAAM,IAAI,aAAa,CAAQ,EAC/B,EAAQ,EAAQ,EACtB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,IACxB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAO,IAAK,CAC5B,IAAM,GAAW,EAAI,EAAQ,GAAK,EAC5B,EAAW,EAAI,EAAQ,EAC7B,IAAK,IAAI,EAAI,EAAG,EAAI,EAAU,IAC1B,EAAI,EAAI,EAAQ,GAAY,EAAI,EAAU,EAElD,CAEJ,OAAO,CACX,CAGA,SAAgB,EAAgB,EAAoB,EAAqC,CACrF,OAAO,IAAI,EAAW,OAAO,UAAW,EAAM,CAAgB,CAClE,CAWA,SAAgB,EAAS,EAA+B,CAEpD,OAAO,EADK,EAAU,CACT,EAAK,EAAM,MAAO,EAAM,OAAQ,CAAC,CAClD,CAUA,SAAgB,EAAQ,EAAiB,EAAe,EAA0B,CAC9E,GAAI,EAAI,SAAW,EAAQ,EAAS,EAChC,MAAU,MACN,wBAAwB,EAAI,OAAO,uCAAuC,EAAQ,EAAS,EAAE,EACjG,EAEJ,IAAM,EAAM,IAAI,WAAW,EAAI,MAAM,EACrC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAI,OAAQ,GAAK,EACjC,EAAI,GAAK,EAAI,EAAI,GACjB,EAAI,EAAI,GAAK,EAAI,EAAI,GACrB,EAAI,EAAI,GAAK,EAAI,GAErB,OAAO,IAAI,EAAA,SAAS,EAAK,EAAO,CAAM,CAC1C,CAOA,SAAgB,EAAM,EAA6B,CAC/C,IAAM,EAAM,EAAM,KACZ,EAAM,IAAI,WAAW,EAAI,MAAM,EACrC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAI,OAAQ,GAAK,EACjC,EAAI,GAAK,EAAI,EAAI,GACjB,EAAI,EAAI,GAAK,EAAI,EAAI,GACrB,EAAI,EAAI,GAAK,EAAI,GAErB,OAAO,CACX,CAoBA,SAAgB,EACZ,EACA,EACA,EACA,EAA0C,CAAC,IAAK,IAAK,GAAG,EACzC,CACf,IAAM,EAAQ,KAAK,IAAI,EAAc,EAAM,MAAO,EAAe,EAAM,MAAM,EACvE,EAAO,KAAK,MAAM,EAAM,MAAQ,CAAK,EACrC,EAAO,KAAK,MAAM,EAAM,OAAS,CAAK,EACtC,EAAU,EAAO,EAAO,EAAM,CAAI,EAElC,EAAM,IAAI,WAAW,EAAc,EAAe,CAAC,EACnD,EAAK,EAAK,GACV,EAAK,EAAK,GACV,EAAK,EAAK,GAChB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAI,OAAQ,GAAK,EACjC,EAAI,GAAK,EACT,EAAI,EAAI,GAAK,EACb,EAAI,EAAI,GAAK,EAGjB,IAAM,EAAU,KAAK,OAAO,EAAc,GAAQ,CAAC,EAC7C,EAAS,KAAK,OAAO,EAAe,GAAQ,CAAC,EAC7C,EAAW,EAAO,EACxB,IAAK,IAAI,EAAI,EAAG,EAAI,EAAM,IAAK,CAC3B,IAAM,EAAY,EAAI,EAChB,IAAc,EAAS,GAAK,EAAc,GAAW,EAC3D,EAAI,IAAI,EAAQ,KAAK,SAAS,EAAW,EAAY,CAAQ,EAAG,CAAS,CAC7E,CAEA,MAAO,CACH,MAAO,IAAI,EAAA,SAAS,EAAK,EAAa,CAAY,EAClD,QACA,UACA,QACJ,CACJ"}

package/dist/vision/preprocess/image.js

@@ -7,8 +7,10 @@ function o(e, a, o) {
 	if (a === e.width && o === e.height) return e;
 	let s = t(e.width, e.height);
 	n(s).putImageData(i(e), 0, 0);
-	let c = n(t(a, o));
-	return c.imageSmoothingEnabled = !0, c.imageSmoothingQuality = "high", c.drawImage(s, 0, 0, a, o), r(c.getImageData(0, 0, a, o));
+	let c = t(a, o), l = n(c);
+	l.imageSmoothingEnabled = !0, l.imageSmoothingQuality = "high", l.drawImage(s, 0, 0, a, o);
+	let u = l.getImageData(0, 0, a, o);
+	return r(u);
 }
 function s(e, t, n, r = 1 / 255) {
 	let i = new Float32Array(e.data.length), a = e.data, o = t[0], s = t[1], c = t[2], l = n[0], u = n[1], d = n[2];

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

@@ -1 +1 @@
-{"version":3,"file":"image.js","names":[],"sources":["../../../src/vision/preprocess/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Composable image preprocessing primitives (resize, normalize, letterbox, layout).\n *\n * Mirrors the Python `preprocess.image` module. Operates on the canonical\n * {@link RGBImage} (HWC RGB uint8) and produces uint8 or float32 buffers\n * depending on the operation.\n */\n\nimport * as ortRuntime from \"onnxruntime-web\";\nimport type * as ort from \"onnxruntime-web\";\n\nimport { createCanvas, get2DContext, imageDataToRGB, rgbToImageData } from \"../core/canvas\";\nimport { RGBImage } from \"../types\";\n\n/** Resize an image to `(targetWidth, targetHeight)` using high-quality canvas resampling. */\nexport function resize(image: RGBImage, targetWidth: number, targetHeight: number): RGBImage {\n    if (targetWidth <= 0 || targetHeight <= 0) {\n        throw new Error(`Invalid resize target ${targetWidth}x${targetHeight}.`);\n    }\n    if (targetWidth === image.width && targetHeight === image.height) {\n        return image;\n    }\n\n    const srcCanvas = createCanvas(image.width, image.height);\n    const srcCtx = get2DContext(srcCanvas);\n    srcCtx.putImageData(rgbToImageData(image), 0, 0);\n\n    const dstCanvas = createCanvas(targetWidth, targetHeight);\n    const dstCtx = get2DContext(dstCanvas);\n    dstCtx.imageSmoothingEnabled = true;\n    dstCtx.imageSmoothingQuality = \"high\";\n    dstCtx.drawImage(srcCanvas as CanvasImageSource, 0, 0, targetWidth, targetHeight);\n\n    const imageData = dstCtx.getImageData(0, 0, targetWidth, targetHeight);\n    return imageDataToRGB(imageData);\n}\n\n/**\n * Convert a uint8 image to a normalized float32 array (HWC layout preserved).\n *\n * Applies `(pixel * scale - mean) / std` channel-wise.\n */\nexport function normalize(\n    image: RGBImage,\n    mean: readonly [number, number, number],\n    std: readonly [number, number, number],\n    scale: number = 1 / 255,\n): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    const m0 = mean[0];\n    const m1 = mean[1];\n    const m2 = mean[2];\n    const s0 = std[0];\n    const s1 = std[1];\n    const s2 = std[2];\n    for (let i = 0; i < data.length; i += 3) {\n        out[i] = ((data[i] as number) * scale - m0) / s0;\n        out[i + 1] = ((data[i + 1] as number) * scale - m1) / s1;\n        out[i + 2] = ((data[i + 2] as number) * scale - m2) / s2;\n    }\n    return out;\n}\n\n/** Convert a uint8 image to a `Float32Array` in `[0, 1]` (HWC layout preserved). */\nexport function toFloat32(image: RGBImage, scale: number = 1 / 255): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    for (let i = 0; i < data.length; i++) {\n        out[i] = (data[i] as number) * scale;\n    }\n    return out;\n}\n\n/**\n * Transpose interleaved HWC data to planar CHW layout.\n *\n * @param hwc Source array of length `width * height * channels`.\n */\nexport function toCHW(\n    hwc: Float32Array,\n    width: number,\n    height: number,\n    channels: number = 3,\n): Float32Array {\n    const expected = width * height * channels;\n    if (hwc.length !== expected) {\n        throw new Error(\n            `toCHW: expected length ${expected} for ${width}x${height}x${channels}, got ${hwc.length}.`,\n        );\n    }\n    const chw = new Float32Array(expected);\n    const plane = width * height;\n    for (let y = 0; y < height; y++) {\n        for (let x = 0; x < width; x++) {\n            const hwcBase = (y * width + x) * channels;\n            const planeIdx = y * width + x;\n            for (let c = 0; c < channels; c++) {\n                chw[c * plane + planeIdx] = hwc[hwcBase + c] as number;\n            }\n        }\n    }\n    return chw;\n}\n\n/** Wrap a Float32 buffer into an `ort.Tensor`. */\nexport function toFloat32Tensor(data: Float32Array, dims: readonly number[]): ort.Tensor {\n    return new ortRuntime.Tensor(\"float32\", data, dims as number[]);\n}\n\n/**\n * Convert an HWC uint8 image to a CHW `Float32Array` scaled to `[0, 1]`.\n *\n * Mirrors `torchvision.transforms.ToTensor()` semantics: HWC → CHW,\n * `uint8 → float32 / 255`. Useful as input to YOLO-style detectors that\n * don't require ImageNet normalization.\n *\n * @returns CHW `Float32Array` of length `width * height * 3`.\n */\nexport function toTensor(image: RGBImage): Float32Array {\n    const f32 = toFloat32(image);\n    return toCHW(f32, image.width, image.height, 3);\n}\n\n/**\n * Convert an HWC BGR uint8 buffer (OpenCV layout) to the SDK's HWC RGB.\n *\n * Use when you receive image bytes from `cv2.imencode` over the wire and\n * want to feed them to the SDK without going through a canvas decode.\n *\n * @param bgr Flat BGR Uint8Array of length `width * height * 3`.\n */\nexport function fromCv2(bgr: Uint8Array, width: number, height: number): RGBImage {\n    if (bgr.length !== width * height * 3) {\n        throw new Error(\n            `fromCv2: data length ${bgr.length} does not match width * height * 3 = ${width * height * 3}.`,\n        );\n    }\n    const rgb = new Uint8Array(bgr.length);\n    for (let i = 0; i < bgr.length; i += 3) {\n        rgb[i] = bgr[i + 2] as number;\n        rgb[i + 1] = bgr[i + 1] as number;\n        rgb[i + 2] = bgr[i] as number;\n    }\n    return new RGBImage(rgb, width, height);\n}\n\n/**\n * Convert the SDK's HWC RGB image to an HWC BGR `Uint8Array` (OpenCV layout).\n *\n * Useful for round-tripping data to a Python OpenCV consumer.\n */\nexport function toCv2(image: RGBImage): Uint8Array {\n    const rgb = image.data;\n    const bgr = new Uint8Array(rgb.length);\n    for (let i = 0; i < rgb.length; i += 3) {\n        bgr[i] = rgb[i + 2] as number;\n        bgr[i + 1] = rgb[i + 1] as number;\n        bgr[i + 2] = rgb[i] as number;\n    }\n    return bgr;\n}\n\nexport interface LetterboxResult {\n    /** The padded image at the target size. */\n    readonly image: RGBImage;\n    /** The factor applied to the original image (`< 1` if downscaled). */\n    readonly scale: number;\n    /** Horizontal padding in pixels (left side; right side has the same or +1). */\n    readonly padLeft: number;\n    /** Vertical padding in pixels (top side). */\n    readonly padTop: number;\n}\n\n/**\n * Resize preserving aspect ratio, padding to `(targetWidth, targetHeight)`\n * with a constant fill color.\n *\n * Standard YOLO preprocessing — returning `scale` and `padLeft`/`padTop`\n * lets callers map detections back to the original image coordinates.\n */\nexport function letterbox(\n    image: RGBImage,\n    targetWidth: number,\n    targetHeight: number,\n    fill: readonly [number, number, number] = [114, 114, 114],\n): LetterboxResult {\n    const scale = Math.min(targetWidth / image.width, targetHeight / image.height);\n    const newW = Math.round(image.width * scale);\n    const newH = Math.round(image.height * scale);\n    const resized = resize(image, newW, newH);\n\n    const out = new Uint8Array(targetWidth * targetHeight * 3);\n    const f0 = fill[0];\n    const f1 = fill[1];\n    const f2 = fill[2];\n    for (let i = 0; i < out.length; i += 3) {\n        out[i] = f0;\n        out[i + 1] = f1;\n        out[i + 2] = f2;\n    }\n\n    const padLeft = Math.floor((targetWidth - newW) / 2);\n    const padTop = Math.floor((targetHeight - newH) / 2);\n    const rowBytes = newW * 3;\n    for (let y = 0; y < newH; y++) {\n        const srcOffset = y * rowBytes;\n        const dstOffset = ((padTop + y) * targetWidth + padLeft) * 3;\n        out.set(resized.data.subarray(srcOffset, srcOffset + rowBytes), dstOffset);\n    }\n\n    return {\n        image: new RGBImage(out, targetWidth, targetHeight),\n        scale,\n        padLeft,\n        padTop,\n    };\n}\n"],"mappings":";;;;AAgBA,SAAgB,EAAO,GAAiB,GAAqB,GAAgC;CACzF,IAAI,KAAe,KAAK,KAAgB,GACpC,MAAU,MAAM,yBAAyB,EAAY,GAAG,EAAa,EAAE;CAE3E,IAAI,MAAgB,EAAM,SAAS,MAAiB,EAAM,QACtD,OAAO;CAGX,IAAM,IAAY,EAAa,EAAM,OAAO,EAAM,MAAM;CAExD,EAD4B,CAC5B,CAAA,CAAO,aAAa,EAAe,CAAK,GAAG,GAAG,CAAC;CAG/C,IAAM,IAAS,EADG,EAAa,GAAa,CAChB,CAAS;CAMrC,OALA,EAAO,wBAAwB,IAC/B,EAAO,wBAAwB,QAC/B,EAAO,UAAU,GAAgC,GAAG,GAAG,GAAa,CAAY,GAGzE,EADW,EAAO,aAAa,GAAG,GAAG,GAAa,CACnC,CAAS;AACnC;AAOA,SAAgB,EACZ,GACA,GACA,GACA,IAAgB,IAAI,KACR;CACZ,IAAM,IAAM,IAAI,aAAa,EAAM,KAAK,MAAM,GACxC,IAAO,EAAM,MACb,IAAK,EAAK,IACV,IAAK,EAAK,IACV,IAAK,EAAK,IACV,IAAK,EAAI,IACT,IAAK,EAAI,IACT,IAAK,EAAI;CACf,KAAK,IAAI,IAAI,GAAG,IAAI,EAAK,QAAQ,KAAK,GAGlC,AAFA,EAAI,MAAO,EAAK,KAAgB,IAAQ,KAAM,GAC9C,EAAI,IAAI,MAAO,EAAK,IAAI,KAAgB,IAAQ,KAAM,GACtD,EAAI,IAAI,MAAO,EAAK,IAAI,KAAgB,IAAQ,KAAM;CAE1D,OAAO;AACX;AAGA,SAAgB,EAAU,GAAiB,IAAgB,IAAI,KAAmB;CAC9E,IAAM,IAAM,IAAI,aAAa,EAAM,KAAK,MAAM,GACxC,IAAO,EAAM;CACnB,KAAK,IAAI,IAAI,GAAG,IAAI,EAAK,QAAQ,KAC7B,EAAI,KAAM,EAAK,KAAgB;CAEnC,OAAO;AACX;AAOA,SAAgB,EACZ,GACA,GACA,GACA,IAAmB,GACP;CACZ,IAAM,IAAW,IAAQ,IAAS;CAClC,IAAI,EAAI,WAAW,GACf,MAAU,MACN,0BAA0B,EAAS,OAAO,EAAM,GAAG,EAAO,GAAG,EAAS,QAAQ,EAAI,OAAO,EAC7F;CAEJ,IAAM,IAAM,IAAI,aAAa,CAAQ,GAC/B,IAAQ,IAAQ;CACtB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAQ,KACxB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAO,KAAK;EAC5B,IAAM,KAAW,IAAI,IAAQ,KAAK,GAC5B,IAAW,IAAI,IAAQ;EAC7B,KAAK,IAAI,IAAI,GAAG,IAAI,GAAU,KAC1B,EAAI,IAAI,IAAQ,KAAY,EAAI,IAAU;CAElD;CAEJ,OAAO;AACX;AAGA,SAAgB,EAAgB,GAAoB,GAAqC;CACrF,OAAO,IAAI,EAAW,OAAO,WAAW,GAAM,CAAgB;AAClE;AAWA,SAAgB,EAAS,GAA+B;CAEpD,OAAO,EADK,EAAU,CACT,GAAK,EAAM,OAAO,EAAM,QAAQ,CAAC;AAClD;AAUA,SAAgB,EAAQ,GAAiB,GAAe,GAA0B;CAC9E,IAAI,EAAI,WAAW,IAAQ,IAAS,GAChC,MAAU,MACN,wBAAwB,EAAI,OAAO,uCAAuC,IAAQ,IAAS,EAAE,EACjG;CAEJ,IAAM,IAAM,IAAI,WAAW,EAAI,MAAM;CACrC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAI,QAAQ,KAAK,GAGjC,AAFA,EAAI,KAAK,EAAI,IAAI,IACjB,EAAI,IAAI,KAAK,EAAI,IAAI,IACrB,EAAI,IAAI,KAAK,EAAI;CAErB,OAAO,IAAI,EAAS,GAAK,GAAO,CAAM;AAC1C;AAOA,SAAgB,EAAM,GAA6B;CAC/C,IAAM,IAAM,EAAM,MACZ,IAAM,IAAI,WAAW,EAAI,MAAM;CACrC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAI,QAAQ,KAAK,GAGjC,AAFA,EAAI,KAAK,EAAI,IAAI,IACjB,EAAI,IAAI,KAAK,EAAI,IAAI,IACrB,EAAI,IAAI,KAAK,EAAI;CAErB,OAAO;AACX;AAoBA,SAAgB,EACZ,GACA,GACA,GACA,IAA0C;CAAC;CAAK;CAAK;AAAG,GACzC;CACf,IAAM,IAAQ,KAAK,IAAI,IAAc,EAAM,OAAO,IAAe,EAAM,MAAM,GACvE,IAAO,KAAK,MAAM,EAAM,QAAQ,CAAK,GACrC,IAAO,KAAK,MAAM,EAAM,SAAS,CAAK,GACtC,IAAU,EAAO,GAAO,GAAM,CAAI,GAElC,IAAM,IAAI,WAAW,IAAc,IAAe,CAAC,GACnD,IAAK,EAAK,IACV,IAAK,EAAK,IACV,IAAK,EAAK;CAChB,KAAK,IAAI,IAAI,GAAG,IAAI,EAAI,QAAQ,KAAK,GAGjC,AAFA,EAAI,KAAK,GACT,EAAI,IAAI,KAAK,GACb,EAAI,IAAI,KAAK;CAGjB,IAAM,IAAU,KAAK,OAAO,IAAc,KAAQ,CAAC,GAC7C,IAAS,KAAK,OAAO,IAAe,KAAQ,CAAC,GAC7C,IAAW,IAAO;CACxB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAM,KAAK;EAC3B,IAAM,IAAY,IAAI,GAChB,MAAc,IAAS,KAAK,IAAc,KAAW;EAC3D,EAAI,IAAI,EAAQ,KAAK,SAAS,GAAW,IAAY,CAAQ,GAAG,CAAS;CAC7E;CAEA,OAAO;EACH,OAAO,IAAI,EAAS,GAAK,GAAa,CAAY;EAClD;EACA;EACA;CACJ;AACJ"}
+{"version":3,"file":"image.js","names":[],"sources":["../../../src/vision/preprocess/image.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Composable image preprocessing primitives (resize, normalize, letterbox, layout).\n *\n * Mirrors the Python `preprocess.image` module. Operates on the canonical\n * {@link RGBImage} (HWC RGB uint8) and produces uint8 or float32 buffers\n * depending on the operation.\n */\n\nimport * as ortRuntime from \"onnxruntime-web\";\nimport type * as ort from \"onnxruntime-web\";\n\nimport { createCanvas, get2DContext, imageDataToRGB, rgbToImageData } from \"../core/canvas\";\nimport { RGBImage } from \"../types\";\n\n/** Resize an image to `(targetWidth, targetHeight)` using high-quality canvas resampling. */\nexport function resize(image: RGBImage, targetWidth: number, targetHeight: number): RGBImage {\n    if (targetWidth <= 0 || targetHeight <= 0) {\n        throw new Error(`Invalid resize target ${targetWidth}x${targetHeight}.`);\n    }\n    if (targetWidth === image.width && targetHeight === image.height) {\n        return image;\n    }\n\n    const srcCanvas = createCanvas(image.width, image.height);\n    const srcCtx = get2DContext(srcCanvas);\n    srcCtx.putImageData(rgbToImageData(image), 0, 0);\n\n    const dstCanvas = createCanvas(targetWidth, targetHeight);\n    const dstCtx = get2DContext(dstCanvas);\n    dstCtx.imageSmoothingEnabled = true;\n    dstCtx.imageSmoothingQuality = \"high\";\n    dstCtx.drawImage(srcCanvas as CanvasImageSource, 0, 0, targetWidth, targetHeight);\n\n    const imageData = dstCtx.getImageData(0, 0, targetWidth, targetHeight);\n    return imageDataToRGB(imageData);\n}\n\n/**\n * Convert a uint8 image to a normalized float32 array (HWC layout preserved).\n *\n * Applies `(pixel * scale - mean) / std` channel-wise.\n */\nexport function normalize(\n    image: RGBImage,\n    mean: readonly [number, number, number],\n    std: readonly [number, number, number],\n    scale: number = 1 / 255,\n): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    const m0 = mean[0];\n    const m1 = mean[1];\n    const m2 = mean[2];\n    const s0 = std[0];\n    const s1 = std[1];\n    const s2 = std[2];\n    for (let i = 0; i < data.length; i += 3) {\n        out[i] = ((data[i] as number) * scale - m0) / s0;\n        out[i + 1] = ((data[i + 1] as number) * scale - m1) / s1;\n        out[i + 2] = ((data[i + 2] as number) * scale - m2) / s2;\n    }\n    return out;\n}\n\n/** Convert a uint8 image to a `Float32Array` in `[0, 1]` (HWC layout preserved). */\nexport function toFloat32(image: RGBImage, scale: number = 1 / 255): Float32Array {\n    const out = new Float32Array(image.data.length);\n    const data = image.data;\n    for (let i = 0; i < data.length; i++) {\n        out[i] = (data[i] as number) * scale;\n    }\n    return out;\n}\n\n/**\n * Transpose interleaved HWC data to planar CHW layout.\n *\n * @param hwc Source array of length `width * height * channels`.\n */\nexport function toCHW(\n    hwc: Float32Array,\n    width: number,\n    height: number,\n    channels: number = 3,\n): Float32Array {\n    const expected = width * height * channels;\n    if (hwc.length !== expected) {\n        throw new Error(\n            `toCHW: expected length ${expected} for ${width}x${height}x${channels}, got ${hwc.length}.`,\n        );\n    }\n    const chw = new Float32Array(expected);\n    const plane = width * height;\n    for (let y = 0; y < height; y++) {\n        for (let x = 0; x < width; x++) {\n            const hwcBase = (y * width + x) * channels;\n            const planeIdx = y * width + x;\n            for (let c = 0; c < channels; c++) {\n                chw[c * plane + planeIdx] = hwc[hwcBase + c] as number;\n            }\n        }\n    }\n    return chw;\n}\n\n/** Wrap a Float32 buffer into an `ort.Tensor`. */\nexport function toFloat32Tensor(data: Float32Array, dims: readonly number[]): ort.Tensor {\n    return new ortRuntime.Tensor(\"float32\", data, dims as number[]);\n}\n\n/**\n * Convert an HWC uint8 image to a CHW `Float32Array` scaled to `[0, 1]`.\n *\n * Mirrors `torchvision.transforms.ToTensor()` semantics: HWC → CHW,\n * `uint8 → float32 / 255`. Useful as input to YOLO-style detectors that\n * don't require ImageNet normalization.\n *\n * @returns CHW `Float32Array` of length `width * height * 3`.\n */\nexport function toTensor(image: RGBImage): Float32Array {\n    const f32 = toFloat32(image);\n    return toCHW(f32, image.width, image.height, 3);\n}\n\n/**\n * Convert an HWC BGR uint8 buffer (OpenCV layout) to the SDK's HWC RGB.\n *\n * Use when you receive image bytes from `cv2.imencode` over the wire and\n * want to feed them to the SDK without going through a canvas decode.\n *\n * @param bgr Flat BGR Uint8Array of length `width * height * 3`.\n */\nexport function fromCv2(bgr: Uint8Array, width: number, height: number): RGBImage {\n    if (bgr.length !== width * height * 3) {\n        throw new Error(\n            `fromCv2: data length ${bgr.length} does not match width * height * 3 = ${width * height * 3}.`,\n        );\n    }\n    const rgb = new Uint8Array(bgr.length);\n    for (let i = 0; i < bgr.length; i += 3) {\n        rgb[i] = bgr[i + 2] as number;\n        rgb[i + 1] = bgr[i + 1] as number;\n        rgb[i + 2] = bgr[i] as number;\n    }\n    return new RGBImage(rgb, width, height);\n}\n\n/**\n * Convert the SDK's HWC RGB image to an HWC BGR `Uint8Array` (OpenCV layout).\n *\n * Useful for round-tripping data to a Python OpenCV consumer.\n */\nexport function toCv2(image: RGBImage): Uint8Array {\n    const rgb = image.data;\n    const bgr = new Uint8Array(rgb.length);\n    for (let i = 0; i < rgb.length; i += 3) {\n        bgr[i] = rgb[i + 2] as number;\n        bgr[i + 1] = rgb[i + 1] as number;\n        bgr[i + 2] = rgb[i] as number;\n    }\n    return bgr;\n}\n\nexport interface LetterboxResult {\n    /** The padded image at the target size. */\n    readonly image: RGBImage;\n    /** The factor applied to the original image (`< 1` if downscaled). */\n    readonly scale: number;\n    /** Horizontal padding in pixels (left side; right side has the same or +1). */\n    readonly padLeft: number;\n    /** Vertical padding in pixels (top side). */\n    readonly padTop: number;\n}\n\n/**\n * Resize preserving aspect ratio, padding to `(targetWidth, targetHeight)`\n * with a constant fill color.\n *\n * Standard YOLO preprocessing — returning `scale` and `padLeft`/`padTop`\n * lets callers map detections back to the original image coordinates.\n */\nexport function letterbox(\n    image: RGBImage,\n    targetWidth: number,\n    targetHeight: number,\n    fill: readonly [number, number, number] = [114, 114, 114],\n): LetterboxResult {\n    const scale = Math.min(targetWidth / image.width, targetHeight / image.height);\n    const newW = Math.round(image.width * scale);\n    const newH = Math.round(image.height * scale);\n    const resized = resize(image, newW, newH);\n\n    const out = new Uint8Array(targetWidth * targetHeight * 3);\n    const f0 = fill[0];\n    const f1 = fill[1];\n    const f2 = fill[2];\n    for (let i = 0; i < out.length; i += 3) {\n        out[i] = f0;\n        out[i + 1] = f1;\n        out[i + 2] = f2;\n    }\n\n    const padLeft = Math.floor((targetWidth - newW) / 2);\n    const padTop = Math.floor((targetHeight - newH) / 2);\n    const rowBytes = newW * 3;\n    for (let y = 0; y < newH; y++) {\n        const srcOffset = y * rowBytes;\n        const dstOffset = ((padTop + y) * targetWidth + padLeft) * 3;\n        out.set(resized.data.subarray(srcOffset, srcOffset + rowBytes), dstOffset);\n    }\n\n    return {\n        image: new RGBImage(out, targetWidth, targetHeight),\n        scale,\n        padLeft,\n        padTop,\n    };\n}\n"],"mappings":";;;;AAgBA,SAAgB,EAAO,GAAiB,GAAqB,GAAgC;CACzF,IAAI,KAAe,KAAK,KAAgB,GACpC,MAAU,MAAM,yBAAyB,EAAY,GAAG,EAAa,EAAE;CAE3E,IAAI,MAAgB,EAAM,SAAS,MAAiB,EAAM,QACtD,OAAO;CAGX,IAAM,IAAY,EAAa,EAAM,OAAO,EAAM,MAAM;CAExD,EAD4B,CAC5B,CAAA,CAAO,aAAa,EAAe,CAAK,GAAG,GAAG,CAAC;CAE/C,IAAM,IAAY,EAAa,GAAa,CAAY,GAClD,IAAS,EAAa,CAAS;CAGrC,AAFA,EAAO,wBAAwB,IAC/B,EAAO,wBAAwB,QAC/B,EAAO,UAAU,GAAgC,GAAG,GAAG,GAAa,CAAY;CAEhF,IAAM,IAAY,EAAO,aAAa,GAAG,GAAG,GAAa,CAAY;CACrE,OAAO,EAAe,CAAS;AACnC;AAOA,SAAgB,EACZ,GACA,GACA,GACA,IAAgB,IAAI,KACR;CACZ,IAAM,IAAM,IAAI,aAAa,EAAM,KAAK,MAAM,GACxC,IAAO,EAAM,MACb,IAAK,EAAK,IACV,IAAK,EAAK,IACV,IAAK,EAAK,IACV,IAAK,EAAI,IACT,IAAK,EAAI,IACT,IAAK,EAAI;CACf,KAAK,IAAI,IAAI,GAAG,IAAI,EAAK,QAAQ,KAAK,GAGlC,AAFA,EAAI,MAAO,EAAK,KAAgB,IAAQ,KAAM,GAC9C,EAAI,IAAI,MAAO,EAAK,IAAI,KAAgB,IAAQ,KAAM,GACtD,EAAI,IAAI,MAAO,EAAK,IAAI,KAAgB,IAAQ,KAAM;CAE1D,OAAO;AACX;AAGA,SAAgB,EAAU,GAAiB,IAAgB,IAAI,KAAmB;CAC9E,IAAM,IAAM,IAAI,aAAa,EAAM,KAAK,MAAM,GACxC,IAAO,EAAM;CACnB,KAAK,IAAI,IAAI,GAAG,IAAI,EAAK,QAAQ,KAC7B,EAAI,KAAM,EAAK,KAAgB;CAEnC,OAAO;AACX;AAOA,SAAgB,EACZ,GACA,GACA,GACA,IAAmB,GACP;CACZ,IAAM,IAAW,IAAQ,IAAS;CAClC,IAAI,EAAI,WAAW,GACf,MAAU,MACN,0BAA0B,EAAS,OAAO,EAAM,GAAG,EAAO,GAAG,EAAS,QAAQ,EAAI,OAAO,EAC7F;CAEJ,IAAM,IAAM,IAAI,aAAa,CAAQ,GAC/B,IAAQ,IAAQ;CACtB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAQ,KACxB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAO,KAAK;EAC5B,IAAM,KAAW,IAAI,IAAQ,KAAK,GAC5B,IAAW,IAAI,IAAQ;EAC7B,KAAK,IAAI,IAAI,GAAG,IAAI,GAAU,KAC1B,EAAI,IAAI,IAAQ,KAAY,EAAI,IAAU;CAElD;CAEJ,OAAO;AACX;AAGA,SAAgB,EAAgB,GAAoB,GAAqC;CACrF,OAAO,IAAI,EAAW,OAAO,WAAW,GAAM,CAAgB;AAClE;AAWA,SAAgB,EAAS,GAA+B;CAEpD,OAAO,EADK,EAAU,CACT,GAAK,EAAM,OAAO,EAAM,QAAQ,CAAC;AAClD;AAUA,SAAgB,EAAQ,GAAiB,GAAe,GAA0B;CAC9E,IAAI,EAAI,WAAW,IAAQ,IAAS,GAChC,MAAU,MACN,wBAAwB,EAAI,OAAO,uCAAuC,IAAQ,IAAS,EAAE,EACjG;CAEJ,IAAM,IAAM,IAAI,WAAW,EAAI,MAAM;CACrC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAI,QAAQ,KAAK,GAGjC,AAFA,EAAI,KAAK,EAAI,IAAI,IACjB,EAAI,IAAI,KAAK,EAAI,IAAI,IACrB,EAAI,IAAI,KAAK,EAAI;CAErB,OAAO,IAAI,EAAS,GAAK,GAAO,CAAM;AAC1C;AAOA,SAAgB,EAAM,GAA6B;CAC/C,IAAM,IAAM,EAAM,MACZ,IAAM,IAAI,WAAW,EAAI,MAAM;CACrC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAI,QAAQ,KAAK,GAGjC,AAFA,EAAI,KAAK,EAAI,IAAI,IACjB,EAAI,IAAI,KAAK,EAAI,IAAI,IACrB,EAAI,IAAI,KAAK,EAAI;CAErB,OAAO;AACX;AAoBA,SAAgB,EACZ,GACA,GACA,GACA,IAA0C;CAAC;CAAK;CAAK;AAAG,GACzC;CACf,IAAM,IAAQ,KAAK,IAAI,IAAc,EAAM,OAAO,IAAe,EAAM,MAAM,GACvE,IAAO,KAAK,MAAM,EAAM,QAAQ,CAAK,GACrC,IAAO,KAAK,MAAM,EAAM,SAAS,CAAK,GACtC,IAAU,EAAO,GAAO,GAAM,CAAI,GAElC,IAAM,IAAI,WAAW,IAAc,IAAe,CAAC,GACnD,IAAK,EAAK,IACV,IAAK,EAAK,IACV,IAAK,EAAK;CAChB,KAAK,IAAI,IAAI,GAAG,IAAI,EAAI,QAAQ,KAAK,GAGjC,AAFA,EAAI,KAAK,GACT,EAAI,IAAI,KAAK,GACb,EAAI,IAAI,KAAK;CAGjB,IAAM,IAAU,KAAK,OAAO,IAAc,KAAQ,CAAC,GAC7C,IAAS,KAAK,OAAO,IAAe,KAAQ,CAAC,GAC7C,IAAW,IAAO;CACxB,KAAK,IAAI,IAAI,GAAG,IAAI,GAAM,KAAK;EAC3B,IAAM,IAAY,IAAI,GAChB,MAAc,IAAS,KAAK,IAAc,KAAW;EAC3D,EAAI,IAAI,EAAQ,KAAK,SAAS,GAAW,IAAY,CAAQ,GAAG,CAAS;CAC7E;CAEA,OAAO;EACH,OAAO,IAAI,EAAS,GAAK,GAAa,CAAY;EAClD;EACA;EACA;CACJ;AACJ"}

package/dist/vision/tasks/base.cjs

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

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

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

package/dist/vision/tasks/base.js

@@ -13,7 +13,9 @@ function n(e) {
 	return e.toFixed(6).replace(/0+$/, "").replace(/\.$/, "");
 }
 function r(t, r) {
-	if (!(!r.raiseOnEmpty || t > 0)) throw new e(`No detections${r.path ? ` in ${r.path}` : ""}${r.classes === void 0 ? "" : ` among classes [${[...r.classes].sort((e, t) => e - t).join(", ")}]`}: nothing cleared confThreshold=${n(r.confThreshold)}.`);
+	if (!r.raiseOnEmpty || t > 0) return;
+	let i = r.path ? ` in ${r.path}` : "", a = r.classes === void 0 ? "" : ` among classes [${[...r.classes].sort((e, t) => e - t).join(", ")}]`;
+	throw new e(`No detections${i}${a}: nothing cleared confThreshold=${n(r.confThreshold)}.`);
 }
 //#endregion
 export { t as VisionTask, r as requireDetections };

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

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

package/dist/vision/tasks/classifier.cjs

@@ -1,2 +1,2 @@
-const e=require("../core/timing.cjs"),t=require("../results.cjs"),n=require("../labels.cjs"),r=require("../core/graph.cjs"),i=require("../core/metadata.cjs"),a=require("../core/session.cjs"),o=require("../io/image.cjs"),s=require("../preprocess/image.cjs"),c=require("../postprocess/classification.cjs"),l=require("./base.cjs");var u=[.485,.456,.406],d=[.229,.224,.225],f=class f extends l.VisionTask{_labels;_names;_inputSize;_mean;_std;_applySoftmax;constructor(e,t,n,r,i,a,o){super(e),this._labels=t,this._names=n,this._inputSize=r,this._mean=i,this._std=a,this._applySoftmax=o}static async create(e,t={}){let o=await a.OrtSession.create(e,t),s=t.numClasses??r.classificationNumClasses(o.outputShape)??void 0,c=n.resolveLabels(t.labels??i.modelNames(o.metadata),{numClasses:s}),l={};for(let e=0;e<c.length;e++)l[e]=c[e];return new f(o,c,l,r.resolveInputSize({graphShape:o.inputShape,requested:t.inputSize,fallback:[224,224]}),t.mean??u,t.std??d,t.applySoftmax??!0)}get labels(){return this._labels}get names(){return this._names}get inputSize(){return this._inputSize}get numClasses(){return this._labels.length}async call(e,t={}){return this.predict(e,t)}async predict(n,r={}){let i=new e.SpeedTimer,a=typeof n==`string`?n:null,s=await o.loadImage(n);i.stage(`load`);let l=this._preprocess(s);i.stage(`preprocess`);let u=await this._session.run({[this._session.inputName]:l});i.stage(`inference`);let d=this._session.outputNames[0];if(d===void 0)throw Error(`Classifier model has no outputs.`);let f=u[d];if(f===void 0)throw Error(`Classifier model output ${d} missing from run() result.`);let p=this._postprocess(f.data),{indices:m,values:h}=c.topK(p,r.topK??null),g=[];for(let e=0;e<m.length;e++){let t=m[e],n=this._labels[t]??`class_${t}`;g.push({classId:t,className:n,probability:h[e],cls:t,name:n,conf:h[e]})}if(g.length===0)throw Error(`Classifier produced no probabilities (empty output).`);let _=g[0],v={classId:_.classId,className:_.className,confidence:_.probability,cls:_.classId,name:_.className,conf:_.probability,image:s,probabilities:g},y=[s.height,s.width],b=new t.Probs(p);return i.stage(`postprocess`),[new t.ClassificationResults(b,v,this._names,s,y,a,i.speed())]}_preprocess(e){let[t,n]=this._inputSize,r=s.resize(e,t,n);return s.toFloat32Tensor(s.toCHW(s.normalize(r,this._mean,this._std),r.width,r.height,3),[1,3,r.height,r.width])}_postprocess(e){return this._applySoftmax?c.softmax(e):new Float32Array(e)}};exports.Classifier=f;
+const e=require("../core/timing.cjs"),t=require("../results.cjs"),n=require("../labels.cjs"),r=require("../core/graph.cjs"),i=require("../core/metadata.cjs"),a=require("../core/session.cjs"),o=require("../io/image.cjs"),s=require("../preprocess/image.cjs"),c=require("../postprocess/classification.cjs"),l=require("./base.cjs");var u=[.485,.456,.406],d=[.229,.224,.225],f=class f extends l.VisionTask{_labels;_names;_inputSize;_mean;_std;_applySoftmax;constructor(e,t,n,r,i,a,o){super(e),this._labels=t,this._names=n,this._inputSize=r,this._mean=i,this._std=a,this._applySoftmax=o}static async create(e,t={}){let o=await a.OrtSession.create(e,t),s=t.numClasses??r.classificationNumClasses(o.outputShape)??void 0,c=n.resolveLabels(t.labels??i.modelNames(o.metadata),{numClasses:s}),l={};for(let e=0;e<c.length;e++)l[e]=c[e];return new f(o,c,l,r.resolveInputSize({graphShape:o.inputShape,requested:t.inputSize,fallback:[224,224]}),t.mean??u,t.std??d,t.applySoftmax??!0)}get labels(){return this._labels}get names(){return this._names}get inputSize(){return this._inputSize}get numClasses(){return this._labels.length}async call(e,t={}){return this.predict(e,t)}async predict(n,r={}){let i=new e.SpeedTimer,a=typeof n==`string`?n:null,s=await o.loadImage(n);i.stage(`load`);let l=this._preprocess(s);i.stage(`preprocess`);let u=await this._session.run({[this._session.inputName]:l});i.stage(`inference`);let d=this._session.outputNames[0];if(d===void 0)throw Error(`Classifier model has no outputs.`);let f=u[d];if(f===void 0)throw Error(`Classifier model output ${d} missing from run() result.`);let p=this._postprocess(f.data),{indices:m,values:h}=c.topK(p,r.topK??null),g=[];for(let e=0;e<m.length;e++){let t=m[e],n=this._labels[t]??`class_${t}`;g.push({classId:t,className:n,probability:h[e],cls:t,name:n,conf:h[e]})}if(g.length===0)throw Error(`Classifier produced no probabilities (empty output).`);let _=g[0],v={classId:_.classId,className:_.className,confidence:_.probability,cls:_.classId,name:_.className,conf:_.probability,image:s,probabilities:g},y=[s.height,s.width],b=new t.Probs(p);return i.stage(`postprocess`),[new t.ClassificationResults(b,v,this._names,s,y,a,i.speed())]}_preprocess(e){let[t,n]=this._inputSize,r=s.resize(e,t,n),i=s.normalize(r,this._mean,this._std),a=s.toCHW(i,r.width,r.height,3);return s.toFloat32Tensor(a,[1,3,r.height,r.width])}_postprocess(e){return this._applySoftmax?c.softmax(e):new Float32Array(e)}};exports.Classifier=f;
 //# sourceMappingURL=classifier.cjs.map

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

@@ -1 +1 @@
-{"version":3,"file":"classifier.cjs","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":"wUAmBA,IAAM,EAAmD,CAAC,KAAO,KAAO,IAAK,EACvE,EAAkD,CAAC,KAAO,KAAO,IAAK,EAqE/D,EAAb,MAAa,UAAmB,EAAA,UAAW,CAGlB,QACA,OACA,WACA,MACA,KACA,cAPrB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EACF,CACE,MAAM,CAAO,EAPI,KAAA,QAAA,EACA,KAAA,OAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,KAAA,EACA,KAAA,cAAA,CAGrB,CAGA,aAAa,OAAO,EAAoB,EAA6B,CAAC,EAAwB,CAC1F,IAAM,EAAU,MAAM,EAAA,WAAW,OAAO,EAAO,CAAO,EAChD,EACF,EAAQ,YAAc,EAAA,yBAAyB,EAAQ,WAAW,GAAK,IAAA,GACrE,EAAS,EAAA,cAAc,EAAQ,QAAU,EAAA,WAAW,EAAQ,QAAQ,EAAG,CACzE,YACJ,CAAC,EACK,EAAgC,CAAC,EACvC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAO,OAAQ,IAC/B,EAAM,GAAK,EAAO,GAEtB,OAAO,IAAI,EACP,EACA,EACA,EACA,EAAA,iBAAiB,CACb,WAAY,EAAQ,WACpB,UAAW,EAAQ,UACnB,SAAU,CAAC,IAAK,GAAG,CACvB,CAAC,EACD,EAAQ,MAAQ,EAChB,EAAQ,KAAO,EACf,EAAQ,cAAgB,EAC5B,CACJ,CAGA,IAAI,QAA4B,CAC5B,OAAO,KAAK,OAChB,CAGA,IAAI,OAA0C,CAC1C,OAAO,KAAK,MAChB,CASA,IAAI,WAAuC,CACvC,OAAO,KAAK,UAChB,CAGA,IAAI,YAAqB,CACrB,OAAO,KAAK,QAAQ,MACxB,CAGA,MAAM,KACF,EACA,EAAoC,CAAC,EACL,CAChC,OAAO,KAAK,QAAQ,EAAO,CAAO,CACtC,CAGA,MAAM,QACF,EACA,EAAoC,CAAC,EACL,CAChC,IAAM,EAAQ,IAAI,EAAA,WACZ,EAAO,OAAO,GAAU,SAAW,EAAQ,KAC3C,EAAW,MAAM,EAAA,UAAU,CAAK,EACtC,EAAM,MAAM,MAAM,EAClB,IAAM,EAAS,KAAK,YAAY,CAAQ,EACxC,EAAM,MAAM,YAAY,EACxB,IAAM,EAAU,MAAM,KAAK,SAAS,IAAI,EAAG,KAAK,SAAS,WAAY,CAAO,CAAC,EAC7E,EAAM,MAAM,WAAW,EACvB,IAAM,EAAkB,KAAK,SAAS,YAAY,GAClD,GAAI,IAAoB,IAAA,GACpB,MAAU,MAAM,kCAAkC,EAEtD,IAAM,EAAM,EAAQ,GACpB,GAAI,IAAQ,IAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C,EAEJ,IAAM,EAAY,KAAK,aAAa,EAAI,IAAoB,EAEtD,CAAE,UAAS,UAAW,EAAA,KAAK,EAAW,EAAQ,MAAQ,IAAI,EAC1D,EAAoC,CAAC,EAC3C,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,OAAQ,IAAK,CACrC,IAAM,EAAK,EAAQ,GACb,EAAY,KAAK,QAAQ,IAAO,SAAS,IAC/C,EAAc,KAAK,CACf,QAAS,EACT,YACA,YAAa,EAAO,GACpB,IAAK,EACL,KAAM,EACN,KAAM,EAAO,EACjB,CAAC,CACL,CACA,GAAI,EAAc,SAAW,EACzB,MAAU,MAAM,sDAAsD,EAG1E,IAAM,EAAM,EAAc,GACpB,EAA+B,CACjC,QAAS,EAAI,QACb,UAAW,EAAI,UACf,WAAY,EAAI,YAChB,IAAK,EAAI,QACT,KAAM,EAAI,UACV,KAAM,EAAI,YACV,MAAO,EACP,eACJ,EAEM,EAAkC,CAAC,EAAS,OAAQ,EAAS,KAAK,EAClE,EAAQ,IAAI,EAAA,MAAM,CAAS,EAEjC,OADA,EAAM,MAAM,aAAa,EAClB,CACH,IAAI,EAAA,sBACA,EACA,EACA,KAAK,OACL,EACA,EACA,EACA,EAAM,MAAM,CAChB,CACJ,CACJ,CAEA,YAAoB,EAA6B,CAC7C,GAAM,CAAC,EAAI,GAAM,KAAK,WAChB,EAAU,EAAA,OAAO,EAAO,EAAI,CAAE,EAGpC,OAAO,EAAA,gBADK,EAAA,MADO,EAAA,UAAU,EAAS,KAAK,MAAO,KAAK,IACrC,EAAY,EAAQ,MAAO,EAAQ,OAAQ,CACtC,EAAK,CAAC,EAAG,EAAG,EAAQ,OAAQ,EAAQ,KAAK,CAAC,CACrE,CAEA,aAAqB,EAAiC,CAClD,OAAO,KAAK,cAAgB,EAAA,QAAQ,CAAG,EAAI,IAAI,aAAa,CAAG,CACnE,CACJ"}
+{"version":3,"file":"classifier.cjs","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":"wUAmBA,IAAM,EAAmD,CAAC,KAAO,KAAO,IAAK,EACvE,EAAkD,CAAC,KAAO,KAAO,IAAK,EAqE/D,EAAb,MAAa,UAAmB,EAAA,UAAW,CAGlB,QACA,OACA,WACA,MACA,KACA,cAPrB,YACI,EACA,EACA,EACA,EACA,EACA,EACA,EACF,CACE,MAAM,CAAO,EAPI,KAAA,QAAA,EACA,KAAA,OAAA,EACA,KAAA,WAAA,EACA,KAAA,MAAA,EACA,KAAA,KAAA,EACA,KAAA,cAAA,CAGrB,CAGA,aAAa,OAAO,EAAoB,EAA6B,CAAC,EAAwB,CAC1F,IAAM,EAAU,MAAM,EAAA,WAAW,OAAO,EAAO,CAAO,EAChD,EACF,EAAQ,YAAc,EAAA,yBAAyB,EAAQ,WAAW,GAAK,IAAA,GACrE,EAAS,EAAA,cAAc,EAAQ,QAAU,EAAA,WAAW,EAAQ,QAAQ,EAAG,CACzE,YACJ,CAAC,EACK,EAAgC,CAAC,EACvC,IAAK,IAAI,EAAI,EAAG,EAAI,EAAO,OAAQ,IAC/B,EAAM,GAAK,EAAO,GAEtB,OAAO,IAAI,EACP,EACA,EACA,EACA,EAAA,iBAAiB,CACb,WAAY,EAAQ,WACpB,UAAW,EAAQ,UACnB,SAAU,CAAC,IAAK,GAAG,CACvB,CAAC,EACD,EAAQ,MAAQ,EAChB,EAAQ,KAAO,EACf,EAAQ,cAAgB,EAC5B,CACJ,CAGA,IAAI,QAA4B,CAC5B,OAAO,KAAK,OAChB,CAGA,IAAI,OAA0C,CAC1C,OAAO,KAAK,MAChB,CASA,IAAI,WAAuC,CACvC,OAAO,KAAK,UAChB,CAGA,IAAI,YAAqB,CACrB,OAAO,KAAK,QAAQ,MACxB,CAGA,MAAM,KACF,EACA,EAAoC,CAAC,EACL,CAChC,OAAO,KAAK,QAAQ,EAAO,CAAO,CACtC,CAGA,MAAM,QACF,EACA,EAAoC,CAAC,EACL,CAChC,IAAM,EAAQ,IAAI,EAAA,WACZ,EAAO,OAAO,GAAU,SAAW,EAAQ,KAC3C,EAAW,MAAM,EAAA,UAAU,CAAK,EACtC,EAAM,MAAM,MAAM,EAClB,IAAM,EAAS,KAAK,YAAY,CAAQ,EACxC,EAAM,MAAM,YAAY,EACxB,IAAM,EAAU,MAAM,KAAK,SAAS,IAAI,EAAG,KAAK,SAAS,WAAY,CAAO,CAAC,EAC7E,EAAM,MAAM,WAAW,EACvB,IAAM,EAAkB,KAAK,SAAS,YAAY,GAClD,GAAI,IAAoB,IAAA,GACpB,MAAU,MAAM,kCAAkC,EAEtD,IAAM,EAAM,EAAQ,GACpB,GAAI,IAAQ,IAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C,EAEJ,IAAM,EAAY,KAAK,aAAa,EAAI,IAAoB,EAEtD,CAAE,UAAS,UAAW,EAAA,KAAK,EAAW,EAAQ,MAAQ,IAAI,EAC1D,EAAoC,CAAC,EAC3C,IAAK,IAAI,EAAI,EAAG,EAAI,EAAQ,OAAQ,IAAK,CACrC,IAAM,EAAK,EAAQ,GACb,EAAY,KAAK,QAAQ,IAAO,SAAS,IAC/C,EAAc,KAAK,CACf,QAAS,EACT,YACA,YAAa,EAAO,GACpB,IAAK,EACL,KAAM,EACN,KAAM,EAAO,EACjB,CAAC,CACL,CACA,GAAI,EAAc,SAAW,EACzB,MAAU,MAAM,sDAAsD,EAG1E,IAAM,EAAM,EAAc,GACpB,EAA+B,CACjC,QAAS,EAAI,QACb,UAAW,EAAI,UACf,WAAY,EAAI,YAChB,IAAK,EAAI,QACT,KAAM,EAAI,UACV,KAAM,EAAI,YACV,MAAO,EACP,eACJ,EAEM,EAAkC,CAAC,EAAS,OAAQ,EAAS,KAAK,EAClE,EAAQ,IAAI,EAAA,MAAM,CAAS,EAEjC,OADA,EAAM,MAAM,aAAa,EAClB,CACH,IAAI,EAAA,sBACA,EACA,EACA,KAAK,OACL,EACA,EACA,EACA,EAAM,MAAM,CAChB,CACJ,CACJ,CAEA,YAAoB,EAA6B,CAC7C,GAAM,CAAC,EAAI,GAAM,KAAK,WAChB,EAAU,EAAA,OAAO,EAAO,EAAI,CAAE,EAC9B,EAAa,EAAA,UAAU,EAAS,KAAK,MAAO,KAAK,IAAI,EACrD,EAAM,EAAA,MAAM,EAAY,EAAQ,MAAO,EAAQ,OAAQ,CAAC,EAC9D,OAAO,EAAA,gBAAgB,EAAK,CAAC,EAAG,EAAG,EAAQ,OAAQ,EAAQ,KAAK,CAAC,CACrE,CAEA,aAAqB,EAAiC,CAClD,OAAO,KAAK,cAAgB,EAAA,QAAQ,CAAG,EAAI,IAAI,aAAa,CAAG,CACnE,CACJ"}

package/dist/vision/tasks/classifier.js

@@ -88,8 +88,8 @@ var g = [
 		return a.stage("postprocess"), [new t(x, y, this._names, s, b, o, a.speed())];
 	}
 	_preprocess(e) {
-		let [t, n] = this._inputSize, r = u(e, t, n);
-		return f(d(l(r, this._mean, this._std), r.width, r.height, 3), [
+		let [t, n] = this._inputSize, r = u(e, t, n), i = l(r, this._mean, this._std), a = d(i, r.width, r.height, 3);
+		return f(a, [
 			1,
 			3,
 			r.height,

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

@@ -1 +1 @@
-{"version":3,"file":"classifier.js","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":";;;;;;;;;;;AAmBA,IAAM,IAAmD;CAAC;CAAO;CAAO;AAAK,GACvE,IAAkD;CAAC;CAAO;CAAO;AAAK,GAqE/D,IAAb,MAAa,UAAmB,EAAW;CAGlB;CACA;CACA;CACA;CACA;CACA;CAPrB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,GACF;EADmB,AAEjB,MAAM,CAAO,GAPI,KAAA,UAAA,GACA,KAAA,SAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,OAAA,GACA,KAAA,gBAAA;CAGrB;CAGA,aAAa,OAAO,GAAoB,IAA6B,CAAC,GAAwB;EAC1F,IAAM,IAAU,MAAM,EAAW,OAAO,GAAO,CAAO,GAChD,IACF,EAAQ,cAAc,EAAyB,EAAQ,WAAW,KAAK,KAAA,GACrE,IAAS,EAAc,EAAQ,UAAU,EAAW,EAAQ,QAAQ,GAAG,EACzE,cACJ,CAAC,GACK,IAAgC,CAAC;EACvC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAO,QAAQ,KAC/B,EAAM,KAAK,EAAO;EAEtB,OAAO,IAAI,EACP,GACA,GACA,GACA,EAAiB;GACb,YAAY,EAAQ;GACpB,WAAW,EAAQ;GACnB,UAAU,CAAC,KAAK,GAAG;EACvB,CAAC,GACD,EAAQ,QAAQ,GAChB,EAAQ,OAAO,GACf,EAAQ,gBAAgB,EAC5B;CACJ;CAGA,IAAI,SAA4B;EAC5B,OAAO,KAAK;CAChB;CAGA,IAAI,QAA0C;EAC1C,OAAO,KAAK;CAChB;CASA,IAAI,YAAuC;EACvC,OAAO,KAAK;CAChB;CAGA,IAAI,aAAqB;EACrB,OAAO,KAAK,QAAQ;CACxB;CAGA,MAAM,KACF,GACA,IAAoC,CAAC,GACL;EAChC,OAAO,KAAK,QAAQ,GAAO,CAAO;CACtC;CAGA,MAAM,QACF,GACA,IAAoC,CAAC,GACL;EAChC,IAAM,IAAQ,IAAI,EAAW,GACvB,IAAO,OAAO,KAAU,WAAW,IAAQ,MAC3C,IAAW,MAAM,EAAU,CAAK;EACtC,EAAM,MAAM,MAAM;EAClB,IAAM,IAAS,KAAK,YAAY,CAAQ;EACxC,EAAM,MAAM,YAAY;EACxB,IAAM,IAAU,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EAC7E,EAAM,MAAM,WAAW;EACvB,IAAM,IAAkB,KAAK,SAAS,YAAY;EAClD,IAAI,MAAoB,KAAA,GACpB,MAAU,MAAM,kCAAkC;EAEtD,IAAM,IAAM,EAAQ;EACpB,IAAI,MAAQ,KAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C;EAEJ,IAAM,IAAY,KAAK,aAAa,EAAI,IAAoB,GAEtD,EAAE,YAAS,cAAW,EAAK,GAAW,EAAQ,QAAQ,IAAI,GAC1D,IAAoC,CAAC;EAC3C,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,QAAQ,KAAK;GACrC,IAAM,IAAK,EAAQ,IACb,IAAY,KAAK,QAAQ,MAAO,SAAS;GAC/C,EAAc,KAAK;IACf,SAAS;IACT;IACA,aAAa,EAAO;IACpB,KAAK;IACL,MAAM;IACN,MAAM,EAAO;GACjB,CAAC;EACL;EACA,IAAI,EAAc,WAAW,GACzB,MAAU,MAAM,sDAAsD;EAG1E,IAAM,IAAM,EAAc,IACpB,IAA+B;GACjC,SAAS,EAAI;GACb,WAAW,EAAI;GACf,YAAY,EAAI;GAChB,KAAK,EAAI;GACT,MAAM,EAAI;GACV,MAAM,EAAI;GACV,OAAO;GACP;EACJ,GAEM,IAAkC,CAAC,EAAS,QAAQ,EAAS,KAAK,GAClE,IAAQ,IAAI,EAAM,CAAS;EAEjC,OADA,EAAM,MAAM,aAAa,GAClB,CACH,IAAI,EACA,GACA,GACA,KAAK,QACL,GACA,GACA,GACA,EAAM,MAAM,CAChB,CACJ;CACJ;CAEA,YAAoB,GAA6B;EAC7C,IAAM,CAAC,GAAI,KAAM,KAAK,YAChB,IAAU,EAAO,GAAO,GAAI,CAAE;EAGpC,OAAO,EADK,EADO,EAAU,GAAS,KAAK,OAAO,KAAK,IACrC,GAAY,EAAQ,OAAO,EAAQ,QAAQ,CACtC,GAAK;GAAC;GAAG;GAAG,EAAQ;GAAQ,EAAQ;EAAK,CAAC;CACrE;CAEA,aAAqB,GAAiC;EAClD,OAAO,KAAK,gBAAgB,EAAQ,CAAG,IAAI,IAAI,aAAa,CAAG;CACnE;AACJ"}
+{"version":3,"file":"classifier.js","names":[],"sources":["../../../src/vision/tasks/classifier.ts"],"sourcesContent":["/** @generated Vendored from @mauriciobenjamin700/ort-vision-sdk-web. Do not hand-edit — regenerate with `npm run vendor:vision`. */\n/**\n * Image classification task using ONNX Runtime Web.\n */\n\nimport type * as ort from \"onnxruntime-web\";\n\nimport { type ModelSource, type OrtSessionOptions, OrtSession } from \"../core/session\";\nimport { SpeedTimer } from \"../core/timing\";\nimport { type ImageInput, loadImage } from \"../io/image\";\nimport { classificationNumClasses, resolveInputSize } from \"../core/graph\";\nimport { modelNames } from \"../core/metadata\";\nimport { type LabelSpec, resolveLabels } from \"../labels\";\nimport { softmax, topK } from \"../postprocess/classification\";\nimport { normalize, resize, toCHW, toFloat32Tensor } from \"../preprocess/image\";\nimport { ClassificationResults, Probs } from \"../results\";\nimport { VisionTask } from \"./base\";\nimport { type ClassProbability, type ClassificationResult, type RGBImage } from \"../types\";\n\nconst IMAGENET_MEAN: readonly [number, number, number] = [0.485, 0.456, 0.406];\nconst IMAGENET_STD: readonly [number, number, number] = [0.229, 0.224, 0.225];\n\nexport interface ClassifierOptions extends OrtSessionOptions {\n    /**\n     * Class label spec — see {@link resolveLabels}.\n     *\n     * Optional: when omitted, the names the export baked into the model are used\n     * (Ultralytics writes them as `names` in the metadata map). Only when the\n     * model carries none does this fall back to generated `class_<id>` labels.\n     * Passing a spec always wins, for a model whose names are wrong or absent.\n     */\n    readonly labels?: LabelSpec;\n    /**\n     * Number of classes the model can predict.\n     *\n     * Optional: inferred from the classification head's declared output shape\n     * `(B, nc)`. Pass it to validate that the supplied labels match the model.\n     */\n    readonly numClasses?: number;\n    /**\n     * Model input `[width, height]` in pixels.\n     *\n     * Only used when the model's graph leaves its spatial axes dynamic: a graph\n     * that declares a static size always wins, since that is the only shape ONNX\n     * Runtime will accept. Defaults to `[224, 224]`.\n     */\n    readonly inputSize?: readonly [number, number];\n    /** Per-channel RGB mean used for normalization. Defaults to ImageNet. */\n    readonly mean?: readonly [number, number, number];\n    /** Per-channel RGB standard deviation. Defaults to ImageNet. */\n    readonly std?: readonly [number, number, number];\n    /**\n     * If `true` (default), apply softmax to the raw model output. Set to\n     * `false` for models whose final layer already produces a probability\n     * distribution.\n     */\n    readonly applySoftmax?: boolean;\n}\n\nexport interface ClassifierPredictOptions {\n    /**\n     * If set, the per-class probability list in `results[0].result.probabilities`\n     * is truncated to the top-K entries. The bulk `probs` view always exposes\n     * the full vector.\n     */\n    readonly topK?: number;\n}\n\n/**\n * Image classifier wrapping an ONNX model with ImageNet-style preprocessing.\n *\n * `predict()` returns `Promise<ClassificationResults[]>` (length 1 for a\n * single image), mirroring Ultralytics' API. The envelope exposes a `probs`\n * collection (`top1`, `top1conf`, `top5`, `top5conf`, `data`) plus the\n * legacy per-class probability list with names already resolved.\n *\n * Defaults: 224×224 RGB input, `float32` normalized with ImageNet mean/std,\n * NCHW layout, batch size 1, softmax applied to the raw output.\n *\n * @example\n * ```typescript\n * const clf = await Classifier.create(\"/models/resnet50.onnx\", {\n *   labels: [\"tench\", \"goldfish\", ...]  // 1000 ImageNet labels\n * });\n * const r = (await clf.predict(\"/images/dog.jpg\"))[0];\n * console.log(r.cls, r.conf, r.name);\n * console.log(r.probs.top5, r.probs.top5conf);\n * ```\n */\nexport class Classifier extends VisionTask {\n    private constructor(\n        session: OrtSession,\n        private readonly _labels: readonly string[],\n        private readonly _names: Readonly<Record<number, string>>,\n        private readonly _inputSize: readonly [number, number],\n        private readonly _mean: readonly [number, number, number],\n        private readonly _std: readonly [number, number, number],\n        private readonly _applySoftmax: boolean,\n    ) {\n        super(session);\n    }\n\n    /** Load the model and resolve labels. */\n    static async create(model: ModelSource, options: ClassifierOptions = {}): Promise<Classifier> {\n        const session = await OrtSession.create(model, options);\n        const numClasses =\n            options.numClasses ?? classificationNumClasses(session.outputShape) ?? undefined;\n        const labels = resolveLabels(options.labels ?? modelNames(session.metadata), {\n            numClasses,\n        });\n        const names: Record<number, string> = {};\n        for (let i = 0; i < labels.length; i++) {\n            names[i] = labels[i] as string;\n        }\n        return new Classifier(\n            session,\n            labels,\n            names,\n            resolveInputSize({\n                graphShape: session.inputShape,\n                requested: options.inputSize,\n                fallback: [224, 224],\n            }),\n            options.mean ?? IMAGENET_MEAN,\n            options.std ?? IMAGENET_STD,\n            options.applySoftmax ?? true,\n        );\n    }\n\n    /** Class labels indexed by class id. */\n    get labels(): readonly string[] {\n        return this._labels;\n    }\n\n    /** Class id → class name dict (matches Ultralytics' `model.names`). */\n    get names(): Readonly<Record<number, string>> {\n        return this._names;\n    }\n\n    /**\n     * The `[width, height]` this task preprocesses to.\n     *\n     * Resolved at creation time from the model's graph when it declares a static\n     * input, so reading it back tells you the resolution inference really runs at\n     * — not merely what was requested.\n     */\n    get inputSize(): readonly [number, number] {\n        return this._inputSize;\n    }\n\n    /** Number of classes the model can predict. */\n    get numClasses(): number {\n        return this._labels.length;\n    }\n\n    /** Alias for {@link predict} (parity with PyTorch `nn.Module.__call__`). */\n    async call(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        return this.predict(image, options);\n    }\n\n    /** Run classification on a single image. */\n    async predict(\n        image: ImageInput,\n        options: ClassifierPredictOptions = {},\n    ): Promise<ClassificationResults[]> {\n        const timer = new SpeedTimer();\n        const path = typeof image === \"string\" ? image : null;\n        const original = await loadImage(image);\n        timer.stage(\"load\");\n        const tensor = this._preprocess(original);\n        timer.stage(\"preprocess\");\n        const outputs = await this._session.run({ [this._session.inputName]: tensor });\n        timer.stage(\"inference\");\n        const firstOutputName = this._session.outputNames[0];\n        if (firstOutputName === undefined) {\n            throw new Error(\"Classifier model has no outputs.\");\n        }\n        const raw = outputs[firstOutputName];\n        if (raw === undefined) {\n            throw new Error(\n                `Classifier model output ${firstOutputName} missing from run() result.`,\n            );\n        }\n        const fullProbs = this._postprocess(raw.data as Float32Array);\n\n        const { indices, values } = topK(fullProbs, options.topK ?? null);\n        const probabilities: ClassProbability[] = [];\n        for (let i = 0; i < indices.length; i++) {\n            const id = indices[i] as number;\n            const className = this._labels[id] ?? `class_${id}`;\n            probabilities.push({\n                classId: id,\n                className,\n                probability: values[i] as number,\n                cls: id,\n                name: className,\n                conf: values[i] as number,\n            });\n        }\n        if (probabilities.length === 0) {\n            throw new Error(\"Classifier produced no probabilities (empty output).\");\n        }\n\n        const top = probabilities[0] as ClassProbability;\n        const result: ClassificationResult = {\n            classId: top.classId,\n            className: top.className,\n            confidence: top.probability,\n            cls: top.classId,\n            name: top.className,\n            conf: top.probability,\n            image: original,\n            probabilities,\n        };\n\n        const orig: readonly [number, number] = [original.height, original.width];\n        const probs = new Probs(fullProbs);\n        timer.stage(\"postprocess\");\n        return [\n            new ClassificationResults(\n                probs,\n                result,\n                this._names,\n                original,\n                orig,\n                path,\n                timer.speed(),\n            ),\n        ];\n    }\n\n    private _preprocess(image: RGBImage): ort.Tensor {\n        const [tw, th] = this._inputSize;\n        const resized = resize(image, tw, th);\n        const normalized = normalize(resized, this._mean, this._std);\n        const chw = toCHW(normalized, resized.width, resized.height, 3);\n        return toFloat32Tensor(chw, [1, 3, resized.height, resized.width]);\n    }\n\n    private _postprocess(raw: Float32Array): Float32Array {\n        return this._applySoftmax ? softmax(raw) : new Float32Array(raw);\n    }\n}\n"],"mappings":";;;;;;;;;;;AAmBA,IAAM,IAAmD;CAAC;CAAO;CAAO;AAAK,GACvE,IAAkD;CAAC;CAAO;CAAO;AAAK,GAqE/D,IAAb,MAAa,UAAmB,EAAW;CAGlB;CACA;CACA;CACA;CACA;CACA;CAPrB,YACI,GACA,GACA,GACA,GACA,GACA,GACA,GACF;EADmB,AAEjB,MAAM,CAAO,GAPI,KAAA,UAAA,GACA,KAAA,SAAA,GACA,KAAA,aAAA,GACA,KAAA,QAAA,GACA,KAAA,OAAA,GACA,KAAA,gBAAA;CAGrB;CAGA,aAAa,OAAO,GAAoB,IAA6B,CAAC,GAAwB;EAC1F,IAAM,IAAU,MAAM,EAAW,OAAO,GAAO,CAAO,GAChD,IACF,EAAQ,cAAc,EAAyB,EAAQ,WAAW,KAAK,KAAA,GACrE,IAAS,EAAc,EAAQ,UAAU,EAAW,EAAQ,QAAQ,GAAG,EACzE,cACJ,CAAC,GACK,IAAgC,CAAC;EACvC,KAAK,IAAI,IAAI,GAAG,IAAI,EAAO,QAAQ,KAC/B,EAAM,KAAK,EAAO;EAEtB,OAAO,IAAI,EACP,GACA,GACA,GACA,EAAiB;GACb,YAAY,EAAQ;GACpB,WAAW,EAAQ;GACnB,UAAU,CAAC,KAAK,GAAG;EACvB,CAAC,GACD,EAAQ,QAAQ,GAChB,EAAQ,OAAO,GACf,EAAQ,gBAAgB,EAC5B;CACJ;CAGA,IAAI,SAA4B;EAC5B,OAAO,KAAK;CAChB;CAGA,IAAI,QAA0C;EAC1C,OAAO,KAAK;CAChB;CASA,IAAI,YAAuC;EACvC,OAAO,KAAK;CAChB;CAGA,IAAI,aAAqB;EACrB,OAAO,KAAK,QAAQ;CACxB;CAGA,MAAM,KACF,GACA,IAAoC,CAAC,GACL;EAChC,OAAO,KAAK,QAAQ,GAAO,CAAO;CACtC;CAGA,MAAM,QACF,GACA,IAAoC,CAAC,GACL;EAChC,IAAM,IAAQ,IAAI,EAAW,GACvB,IAAO,OAAO,KAAU,WAAW,IAAQ,MAC3C,IAAW,MAAM,EAAU,CAAK;EACtC,EAAM,MAAM,MAAM;EAClB,IAAM,IAAS,KAAK,YAAY,CAAQ;EACxC,EAAM,MAAM,YAAY;EACxB,IAAM,IAAU,MAAM,KAAK,SAAS,IAAI,GAAG,KAAK,SAAS,YAAY,EAAO,CAAC;EAC7E,EAAM,MAAM,WAAW;EACvB,IAAM,IAAkB,KAAK,SAAS,YAAY;EAClD,IAAI,MAAoB,KAAA,GACpB,MAAU,MAAM,kCAAkC;EAEtD,IAAM,IAAM,EAAQ;EACpB,IAAI,MAAQ,KAAA,GACR,MAAU,MACN,2BAA2B,EAAgB,4BAC/C;EAEJ,IAAM,IAAY,KAAK,aAAa,EAAI,IAAoB,GAEtD,EAAE,YAAS,cAAW,EAAK,GAAW,EAAQ,QAAQ,IAAI,GAC1D,IAAoC,CAAC;EAC3C,KAAK,IAAI,IAAI,GAAG,IAAI,EAAQ,QAAQ,KAAK;GACrC,IAAM,IAAK,EAAQ,IACb,IAAY,KAAK,QAAQ,MAAO,SAAS;GAC/C,EAAc,KAAK;IACf,SAAS;IACT;IACA,aAAa,EAAO;IACpB,KAAK;IACL,MAAM;IACN,MAAM,EAAO;GACjB,CAAC;EACL;EACA,IAAI,EAAc,WAAW,GACzB,MAAU,MAAM,sDAAsD;EAG1E,IAAM,IAAM,EAAc,IACpB,IAA+B;GACjC,SAAS,EAAI;GACb,WAAW,EAAI;GACf,YAAY,EAAI;GAChB,KAAK,EAAI;GACT,MAAM,EAAI;GACV,MAAM,EAAI;GACV,OAAO;GACP;EACJ,GAEM,IAAkC,CAAC,EAAS,QAAQ,EAAS,KAAK,GAClE,IAAQ,IAAI,EAAM,CAAS;EAEjC,OADA,EAAM,MAAM,aAAa,GAClB,CACH,IAAI,EACA,GACA,GACA,KAAK,QACL,GACA,GACA,GACA,EAAM,MAAM,CAChB,CACJ;CACJ;CAEA,YAAoB,GAA6B;EAC7C,IAAM,CAAC,GAAI,KAAM,KAAK,YAChB,IAAU,EAAO,GAAO,GAAI,CAAE,GAC9B,IAAa,EAAU,GAAS,KAAK,OAAO,KAAK,IAAI,GACrD,IAAM,EAAM,GAAY,EAAQ,OAAO,EAAQ,QAAQ,CAAC;EAC9D,OAAO,EAAgB,GAAK;GAAC;GAAG;GAAG,EAAQ;GAAQ,EAAQ;EAAK,CAAC;CACrE;CAEA,aAAqB,GAAiC;EAClD,OAAO,KAAK,gBAAgB,EAAQ,CAAG,IAAI,IAAI,aAAa,CAAG;CACnE;AACJ"}

package/dist/vision/tasks/detectClassify.cjs

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