Owlvit Base Patch32

🚀 Zero-shot Object Detection with Transformers.js

This project uses the google/owlvit-base-patch32 model with ONNX weights to be compatible with the transformers.js library. It enables zero-shot object detection tasks.

🚀 Quick Start

📦 Installation

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

npm i @xenova/transformers

💻 Usage Examples

🔍 Basic Usage

Example: Zero-shot object detection w/ Xenova/owlvit-base-patch32.

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

const detector = await pipeline('zero-shot-object-detection', 'Xenova/owlvit-base-patch32');

const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/astronaut.png';
const candidate_labels = ['human face', 'rocket', 'helmet', 'american flag'];
const output = await detector(url, candidate_labels);
// [
//   { score: 0.24392342567443848, label: 'human face', box: { xmin: 180, ymin: 67, xmax: 274, ymax: 175 } },
//   { score: 0.15129457414150238, label: 'american flag', box: { xmin: 0, ymin: 4, xmax: 106, ymax: 513 } },
//   { score: 0.13649864494800568, label: 'helmet', box: { xmin: 277, ymin: 337, xmax: 511, ymax: 511 } },
//   { score: 0.10262022167444229, label: 'rocket', box: { xmin: 352, ymin: -1, xmax: 463, ymax: 287 } }
// ]

🌟 Advanced Usage

Example: Zero-shot object detection w/ Xenova/owlvit-base-patch32 (additional parameters).

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

const detector = await pipeline('zero-shot-object-detection', 'Xenova/owlvit-base-patch32');

const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/beach.png';
const candidate_labels = ['hat', 'book', 'sunglasses', 'camera'];
const output = await detector(url, candidate_labels, { topk: 4, threshold: 0.05 });
// [
//   { score: 0.1606510728597641, label: 'sunglasses', box: { xmin: 347, ymin: 229, xmax: 429, ymax: 264 } },
//   { score: 0.08935828506946564, label: 'hat', box: { xmin: 38, ymin: 174, xmax: 258, ymax: 364 } },
//   { score: 0.08530698716640472, label: 'camera', box: { xmin: 187, ymin: 350, xmax: 260, ymax: 411 } },
//   { score: 0.08349756896495819, label: 'book', box: { xmin: 261, ymin: 280, xmax: 494, ymax: 425 } }
// ]

📚 Documentation

⚠️ Important 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).

📄 Model Information