Sam Vit Large

🚀 Segment Anything Model with Transformers.js

This project adapts the facebook/sam-vit-large model with ONNX weights to be compatible with Transformers.js, enabling seamless mask generation in a JavaScript environment.

🚀 Quick Start

The model from https://huggingface.co/facebook/sam-vit-large is adapted with ONNX weights to work with Transformers.js.

📦 Installation

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

💻 Usage Examples

Basic Usage

import { SamModel, AutoProcessor, RawImage } from "@huggingface/transformers";

// Load model and processor
const model = await SamModel.from_pretrained("Xenova/sam-vit-large");
const processor = await AutoProcessor.from_pretrained("Xenova/sam-vit-large");

// Prepare image and input points
const img_url = "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/corgi.jpg";
const raw_image = await RawImage.read(img_url);
const input_points = [[[340, 250]]];

// Process inputs and perform mask generation
const inputs = await processor(raw_image, { input_points });
const outputs = await model(inputs);

// Post-process masks
const masks = await processor.post_process_masks(outputs.pred_masks, inputs.original_sizes, inputs.reshaped_input_sizes);
console.log(masks);
// [
//   Tensor {
//     dims: [ 1, 3, 410, 614 ],
//     type: 'bool',
//     data: Uint8Array(755220) [ ... ],
//     size: 755220
//   }
// ]
const scores = outputs.iou_scores;
console.log(scores);
// Tensor {
//   dims: [ 1, 1, 3 ],
//   type: 'float32',
//   data: Float32Array(3) [
//     1.0122944116592407,
//     0.9184409976005554,
//     0.9796935319900513
//   ],
//   size: 3
// }

Advanced Usage

You can then visualize the generated mask with:

const image = RawImage.fromTensor(masks[0][0].mul(255));
image.save('mask.png');

Next, select the channel with the highest IoU score, which in this case is the first (red) channel. Intersecting this with the original image gives us an isolated version of the subject:

📚 Documentation

We've also got an online demo, which you can try out here.

🔧 Technical Details

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web - ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).