Edit model card

https://huggingface.co/google/owlv2-base-patch16-ensemble 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: Zero-shot object detection w/ Xenova/owlv2-base-patch16-ensemble.

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

const detector = await pipeline('zero-shot-object-detection', 'Xenova/owlv2-base-patch16-ensemble');

const url = 'http://images.cocodataset.org/val2017/000000039769.jpg';
const candidate_labels = ['a photo of a cat', 'a photo of a dog'];
const output = await detector(url, candidate_labels);
// [
//   { score: 0.7400985360145569, label: 'a photo of a cat', box: { xmin: 0, ymin: 50, xmax: 323, ymax: 485 } },
//   { score: 0.6315087080001831, label: 'a photo of a cat', box: { xmin: 333, ymin: 23, xmax: 658, ymax: 378 } }
// ]


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).

Downloads last month
Inference API (serverless) does not yet support transformers.js models for this pipeline type.