---
license: apache-2.0
tags:
  - mediapipe
  - hand-detection
  - hand-landmarks
---

# MediaPipe Hand Landmarker

Pre-trained [MediaPipe Hand Landmarker](https://developers.google.com/mediapipe/solutions/vision/hand_landmarker)
model for hand detection and 21-point landmark estimation.

## License

**Apache License 2.0** — Copyright Google LLC

This model file is redistributed under the original Apache 2.0 License from Google's
[MediaPipe project](https://github.com/google-ai-edge/mediapipe).
Full license text: <https://github.com/google-ai-edge/mediapipe/blob/master/LICENSE>

## Files

| File | Size | Description |
|------|------|-------------|
| `hand_landmarker.task` | 7.5 MB | MediaPipe Hand Landmarker (float16) |

## Usage

```python
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="Leo-TX/mediapipe-hand", filename="hand_landmarker.task")
```

## Original Source

Downloaded from:
```
https://storage.googleapis.com/mediapipe-models/hand_landmarker/hand_landmarker/float16/latest/hand_landmarker.task
```

## Citation

```bibtex
@article{zhang2020mediapipe,
    title={MediaPipe Hands: On-device Real-time Hand Tracking},
    author={Zhang, Fan and Bazarevsky, Valentin and Vakunov, Andrey and Tkachenka, Andrei
            and Sung, George and Chang, Chuo-Ling and Grundmann, Matthias},
    journal={arXiv preprint arXiv:2006.10214},
    year={2020}
}
```