Performs classification on images. **Signature:** export declare class ImageClassifier extends VisionTaskRunner ## Methods | Method | Modifiers | Description | |---|---|---| | [createFromOptions(wasmFileset, imageClassifierOptions)](https://developers.google.com/edge/api/mediapipe/js/tasks-vision.imageclassifier#imageclassifiercreatefromoptions) | `static` | Initializes the Wasm runtime and creates a new image classifier from the provided options. | | [createFromModelBuffer(wasmFileset, modelAssetBuffer)](https://developers.google.com/edge/api/mediapipe/js/tasks-vision.imageclassifier#imageclassifiercreatefrommodelbuffer) | `static` | Initializes the Wasm runtime and creates a new image classifier based on the provided model asset buffer. | | [createFromModelPath(wasmFileset, modelAssetPath)](https://developers.google.com/edge/api/mediapipe/js/tasks-vision.imageclassifier#imageclassifiercreatefrommodelpath) | `static` | Initializes the Wasm runtime and creates a new image classifier based on the path to the model asset. | | [setOptions(options)](https://developers.google.com/edge/api/mediapipe/js/tasks-vision.imageclassifier#imageclassifiersetoptions) | | Sets new options for the image classifier. Calling `setOptions()` with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to `undefined`. | | [classify(image, imageProcessingOptions)](https://developers.google.com/edge/api/mediapipe/js/tasks-vision.imageclassifier#imageclassifierclassify) | | Performs image classification on the provided single image and waits synchronously for the response. Only use this method when the ImageClassifier is created with running mode `image`. | | [classifyForVideo(videoFrame, timestamp, imageProcessingOptions)](https://developers.google.com/edge/api/mediapipe/js/tasks-vision.imageclassifier#imageclassifierclassifyforvideo) | | Performs image classification on the provided video frame and waits synchronously for the response. Only use this method when the ImageClassifier is created with running mode `video`. | ## ImageClassifier.createFromOptions() {#imageclassifiercreatefromoptions} Initializes the Wasm runtime and creates a new image classifier from the provided options. **Signature:** static createFromOptions(wasmFileset: WasmFileset, imageClassifierOptions: ImageClassifierOptions): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | wasmFileset | WasmFileset | A configuration object that provides the location Wasm binary and its loader. | | imageClassifierOptions | ImageClassifierOptions | The options for the image classifier. Note that either a path to the model asset or a model buffer needs to be provided (via `baseOptions`). | **Returns:** Promise\ ## ImageClassifier.createFromModelBuffer() {#imageclassifiercreatefrommodelbuffer} Initializes the Wasm runtime and creates a new image classifier based on the provided model asset buffer. **Signature:** static createFromModelBuffer(wasmFileset: WasmFileset, modelAssetBuffer: Uint8Array | ReadableStreamDefaultReader): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. | | modelAssetBuffer | Uint8Array \| ReadableStreamDefaultReader | An array or a stream containing a binary representation of the model. | **Returns:** Promise\ ## ImageClassifier.createFromModelPath() {#imageclassifiercreatefrommodelpath} Initializes the Wasm runtime and creates a new image classifier based on the path to the model asset. **Signature:** static createFromModelPath(wasmFileset: WasmFileset, modelAssetPath: string): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. | | modelAssetPath | string | The path to the model asset. | **Returns:** Promise\ ## ImageClassifier.setOptions() {#imageclassifiersetoptions} Sets new options for the image classifier. Calling `setOptions()` with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to `undefined`. **Signature:** setOptions(options: ImageClassifierOptions): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | options | ImageClassifierOptions | The options for the image classifier. | **Returns:** Promise\ ## ImageClassifier.classify() {#imageclassifierclassify} Performs image classification on the provided single image and waits synchronously for the response. Only use this method when the ImageClassifier is created with running mode `image`. **Signature:** classify(image: ImageSource, imageProcessingOptions?: ImageProcessingOptions): ImageClassifierResult; ### Parameters | Parameter | Type | Description | |---|---|---| | image | ImageSource | An image to process. | | imageProcessingOptions | ImageProcessingOptions | the `ImageProcessingOptions` specifying how to process the input image before running inference. | **Returns:** ImageClassifierResult ## ImageClassifier.classifyForVideo() {#imageclassifierclassifyforvideo} Performs image classification on the provided video frame and waits synchronously for the response. Only use this method when the ImageClassifier is created with running mode `video`. **Signature:** classifyForVideo(videoFrame: ImageSource, timestamp: number, imageProcessingOptions?: ImageProcessingOptions): ImageClassifierResult; ### Parameters | Parameter | Type | Description | |---|---|---| | videoFrame | ImageSource | A video frame to process. | | timestamp | number | The timestamp of the current frame, in ms. | | imageProcessingOptions | ImageProcessingOptions | the `ImageProcessingOptions` specifying how to process the input image before running inference. | **Returns:** ImageClassifierResult