Xenova/gelan-c_all

https://github.com/WongKinYiu/yolov9 with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

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

npm i @xenova/transformers

Example: Perform object-detection with Xenova/gelan-c_all.

import { AutoModel, AutoProcessor, RawImage } from '@xenova/transformers';

// Load model
const model = await AutoModel.from_pretrained('Xenova/gelan-c_all', {
    // quantized: false,    // (Optional) Use unquantized version.
})

// Load processor
const processor = await AutoProcessor.from_pretrained('Xenova/gelan-c_all');
// processor.feature_extractor.size = { shortest_edge: 128 }    // (Optional) Update resize value

// Read image and run processor
const url = 'https://huggingface.co./datasets/Xenova/transformers.js-docs/resolve/main/city-streets.jpg';
const image = await RawImage.read(url);
const inputs = await processor(image);

// Run object detection
const threshold = 0.3;
const { outputs } = await model(inputs);
const predictions = outputs.tolist();

for (const [xmin, ymin, xmax, ymax, score, id] of predictions) {
    if (score < threshold) break;
    const bbox = [xmin, ymin, xmax, ymax].map(x => x.toFixed(2)).join(', ')
    console.log(`Found "${model.config.id2label[id]}" at [${bbox}] with score ${score.toFixed(2)}.`)
}
// Found "car" at [63.06, 118.80, 139.61, 146.78] with score 0.84.
// Found "bicycle" at [158.32, 166.13, 195.02, 189.03] with score 0.81.
// Found "bicycle" at [123.22, 183.83, 162.71, 206.30] with score 0.79.
// Found "bicycle" at [0.56, 180.92, 39.26, 203.94] with score 0.78.
// Found "car" at [157.10, 132.38, 223.72, 167.69] with score 0.77.
// Found "person" at [193.04, 90.98, 207.09, 116.78] with score 0.77.
// Found "person" at [12.49, 164.97, 27.63, 197.55] with score 0.66.
// Found "traffic light" at [102.80, 74.25, 124.12, 95.75] with score 0.62.
// ...

Demo

Test it out here!

---

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).