Depth Anything Small Hf

🚀 Depth Estimation with Transformers.js

This project provides a depth estimation solution using the LiheYoung/depth-anything-small-hf base model with ONNX weights, making it compatible with the transformers.js library. It enables users to perform depth estimation tasks in a JavaScript environment.

🚀 Quick Start

This repo contains the ONNX weights of LiheYoung/depth-anything-small-hf to be compatible with Transformers.js.

📦 Installation

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

npm i @huggingface/transformers

💻 Usage Examples

Basic Usage

Example: Depth estimation with Xenova/depth-anything-small-hf.

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

// Create depth-estimation pipeline
const depth_estimator = await pipeline('depth-estimation', 'Xenova/depth-anything-small-hf');

// Predict depth map for the given image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/bread_small.png';
const output = await depth_estimator(url);
// {
//   predicted_depth: Tensor {
//     dims: [350, 518],
//     type: 'float32',
//     data: Float32Array(181300) [...],
//     size: 181300
//   },
//   depth: RawImage {
//     data: Uint8Array(271360) [...],
//     width: 640,
//     height: 424,
//     channels: 1
//   }
// }

Advanced Usage

You can visualize the output with:

output.depth.save('depth.png');

📚 Documentation

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).

📄 Information Table