Upload an image to detect objects
Find objects in images using text descriptions
Upload an image to detect objects
Detect and measure areas of objects in images
Upload an image to detect objects
Run object detection on videos
Detect traffic signs in uploaded images
Identify objects in images using a password-protected service
Detect objects in uploaded images
Stream webcam video and detect objects in real-time
Identify segments in an image using a Detectron2 model
Detect objects in anime images
Upload image to detect objects
Transformers.js is a powerful JavaScript library designed for object detection tasks. It enables developers to easily integrate real-time object detection into web applications by leveraging modern AI and machine learning frameworks. The library simplifies the process of detecting objects within images, making it accessible for both beginners and advanced users.
npm install transformers.js
import Transformers from 'transformers.js';
const detector = new Transformers.Detector('yolo');
const image = new Image();
image.src = 'path/to/your/image.jpg';
detector.detect(image).then(results => {
// Process the results
});
results.forEach(item => {
console.log(`Detected ${item.label} with ${item.confidence.toFixed(2)} confidence`);
});
What browsers are supported by Transformers.js?
Transformers.js is designed to work with modern browsers that support HTML5 and ES6 features. It is tested on Chrome, Firefox, and Edge.
How can I improve the performance of Transformers.js?
To optimize performance, ensure you're using a modern GPU, reduce the image size, or use a lighter model architecture.
Can I use custom models with Transformers.js?
Yes, Transformers.js allows you to use custom models. You can load a model using a TensorFlow.js or ONNX.js format and pass it to the detector.