Xenova/depth-anything-small-hf
作者 Xenova ｜ 下载 5.6K ｜ 点赞 11 ｜ 更新 2025-06-26
这个仓库里有什么
- 7 个 ONNX 模型（.onnx 文件）
- 12 个文件，其中 .onnx 7 个、.json 3 个、.md 1 个
- 仓库体积约 265 MB
- 最近更新：2025-06-26
ONNX 文件清单
| 文件 | 大小 | 下载 |
|---|---|---|
| onnx/model.onnx | 94.6 MB | 下载 |
| onnx/model_bnb4.onnx | 25.0 MB | 下载 |
| onnx/model_fp16.onnx | 47.6 MB | 下载 |
| onnx/model_q4.onnx | 26.3 MB | 下载 |
| onnx/model_q4f16.onnx | 19.4 MB | 下载 |
| onnx/model_quantized.onnx | 26.2 MB | 下载 |
| onnx/model_uint8.onnx | 26.0 MB | 下载 |
怎么用
这些 ONNX 文件可以直接用 ONNX Runtime 加载运行；想先看网络结构，可以把文件上传到 Netron 在线查看器 查看。下载链接指向 Hugging Face 原始文件。
说明文档
https://huggingface.co/LiheYoung/depth-anything-small-hf 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 @huggingface/transformers
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
// }
// }
You can visualize the output with:
output.depth.save('depth.png');
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).
模型信息
创建时间: 2024-01-24
更新时间: 2025-06-26
在 Hugging Face 上查看