@huggingface/transformers/src/models/vitmatte/modeling_vitmatte.js

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

import { PreTrainedModel } from '../modeling_utils.js';
import { ImageMattingOutput } from '../modeling_outputs.js';

export class VitMattePreTrainedModel extends PreTrainedModel {}

/**
 * ViTMatte framework leveraging any vision backbone e.g. for ADE20k, CityScapes.
 *
 * **Example:** Perform image matting with a `VitMatteForImageMatting` model.
 * ```javascript
 * import { AutoProcessor, VitMatteForImageMatting, RawImage } from '@huggingface/transformers';
 *
 * // Load processor and model
 * const processor = await AutoProcessor.from_pretrained('Xenova/vitmatte-small-distinctions-646');
 * const model = await VitMatteForImageMatting.from_pretrained('Xenova/vitmatte-small-distinctions-646');
 *
 * // Load image and trimap
 * const image = await RawImage.fromURL('https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/vitmatte_image.png');
 * const trimap = await RawImage.fromURL('https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/vitmatte_trimap.png');
 *
 * // Prepare image + trimap for the model
 * const inputs = await processor(image, trimap);
 *
 * // Predict alpha matte
 * const { alphas } = await model(inputs);
 * // Tensor {
 * //   dims: [ 1, 1, 640, 960 ],
 * //   type: 'float32',
 * //   size: 614400,
 * //   data: Float32Array(614400) [ 0.9894027709960938, 0.9970508813858032, ... ]
 * // }
 * ```
 *
 * You can visualize the alpha matte as follows:
 * ```javascript
 * import { Tensor, cat } from '@huggingface/transformers';
 *
 * // Visualize predicted alpha matte
 * const imageTensor = image.toTensor();
 *
 * // Convert float (0-1) alpha matte to uint8 (0-255)
 * const alphaChannel = alphas
 *   .squeeze(0)
 *   .mul_(255)
 *   .clamp_(0, 255)
 *   .round_()
 *   .to('uint8');
 *
 * // Concatenate original image with predicted alpha
 * const imageData = cat([imageTensor, alphaChannel], 0);
 *
 * // Save output image
 * const outputImage = RawImage.fromTensor(imageData);
 * outputImage.save('output.png');
 * ```
 */
export class VitMatteForImageMatting extends VitMattePreTrainedModel {
    /**
     * @param {any} model_inputs
     */
    async _call(model_inputs) {
        return new ImageMattingOutput(await super._call(model_inputs));
    }
}