Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- primateface
|
| 5 |
+
- face-detection
|
| 6 |
+
- pose-estimation
|
| 7 |
+
- primates
|
| 8 |
+
- animal-behavior
|
| 9 |
+
- computer-vision
|
| 10 |
+
library_name: primateface
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# PrimateFace Models
|
| 14 |
+
|
| 15 |
+
Pre-trained models for [PrimateFace](https://github.com/KordingLab/PrimateFace) --- an open-source toolkit for primate face detection, landmark estimation, and facial behavior analysis across 60+ primate genera.
|
| 16 |
+
|
| 17 |
+
## Models
|
| 18 |
+
|
| 19 |
+
| Model | Task | Architecture | File | Size |
|
| 20 |
+
|---|---|---|---|---|
|
| 21 |
+
| **Face Detection** | Bounding box detection | Cascade R-CNN (ResNet-101 + FPN) | `detection/cascade_rcnn_r101_fpn.pth` | 340 MB |
|
| 22 |
+
| **Face Pose** | 68-keypoint landmark estimation | HRNetV2-W18-DARK | `pose/hrnetv2_w18_dark_68kpt.pth` | 38 MB |
|
| 23 |
+
|
| 24 |
+
Both models were trained on PrimateFace data spanning 60+ primate genera using the [MMDetection](https://github.com/open-mmlab/mmdetection) and [MMPose](https://github.com/open-mmlab/mmpose) frameworks.
|
| 25 |
+
|
| 26 |
+
## Keypoint Format
|
| 27 |
+
|
| 28 |
+
68-point facial landmarks following the dlib standard (COCO format: `[x, y, visibility] x 68`):
|
| 29 |
+
- Jaw contour (17 points)
|
| 30 |
+
- Eyebrows (10 points)
|
| 31 |
+
- Nose bridge + base (9 points)
|
| 32 |
+
- Eyes (12 points)
|
| 33 |
+
- Mouth outer + inner (20 points)
|
| 34 |
+
|
| 35 |
+
## Quick Start
|
| 36 |
+
|
| 37 |
+
```python
|
| 38 |
+
# Download models automatically
|
| 39 |
+
python demos/download_models.py
|
| 40 |
+
|
| 41 |
+
# Or use the Python API
|
| 42 |
+
from huggingface_hub import hf_hub_download
|
| 43 |
+
|
| 44 |
+
det_path = hf_hub_download(
|
| 45 |
+
repo_id="fparodi/primateface-models",
|
| 46 |
+
filename="cascade_rcnn_r101_fpn.pth",
|
| 47 |
+
subfolder="detection",
|
| 48 |
+
)
|
| 49 |
+
|
| 50 |
+
pose_path = hf_hub_download(
|
| 51 |
+
repo_id="fparodi/primateface-models",
|
| 52 |
+
filename="hrnetv2_w18_dark_68kpt.pth",
|
| 53 |
+
subfolder="pose",
|
| 54 |
+
)
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
## Citation
|
| 58 |
+
|
| 59 |
+
```bibtex
|
| 60 |
+
@article{parodi2025primateface,
|
| 61 |
+
title={PrimateFace: A Machine Learning Resource for Automated Face Analysis in Human and Non-human Primates},
|
| 62 |
+
author={Parodi, Felipe and Matelsky, Jordan and others},
|
| 63 |
+
year={2025},
|
| 64 |
+
url={https://www.biorxiv.org/content/10.1101/2025.08.12.669927}
|
| 65 |
+
}
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
## License
|
| 69 |
+
|
| 70 |
+
MIT --- same as the PrimateFace repository.
|