metadata

library_name: transformers.js

https://huggingface.co/PekingU/rtdetr_r50vd with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

NOTE: RT-DETR support is experimental and requires you to install Transformers.js v3 from source.

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

npm install xenova/transformers.js#v3

Example: Perform object-detection with onnx-community/rtdetr_r50vd.

import { pipeline } from '@xenova/transformers';

const detector = await pipeline('object-detection', 'onnx-community/rtdetr_r50vd');

const img = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';
const output = await detector(img, { threshold: 0.9 });
// [{
//   score: 0.9720445871353149,
//   label: 'cat',
//   box: { xmin: 14, ymin: 54, xmax: 319, ymax: 472 }
// },
// ...
// {
//   score: 0.9795005917549133,
//   label: 'sofa',
//   box: { xmin: 0, ymin: 0, xmax: 640, ymax: 472 }
// }]

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).