Pytorch Face Landmark Detection
Implementation of face landmark detection with PyTorch. The models were trained using coordinate-based or heatmap-based regression methods. Different face detetors were supported. A video demo and image detection results were displayed here.
- Support 68-point and 39-point landmark inference.
- Support automatic alignment and crop
- Support different backbone networks and face detectors.
- Support ONNX and OpenVINO inferences.
- Support heatmap-based models.
Inference
Test on a sample folder and save the landmark detection and cropped face results. Support different backbones and face detectors.
python3 test_batch_detections.py --backbone MobileFaceNet --detector Retinaface
- backbone: MobileNet/PFLD/MobileFaceNet; detector: MTCNN/FaceBoxes/Retinaface
Optimize with ONNX and test on a camera with MTCNN as a face detector.
python3 test_camera_mtcnn_onnx.py
Optimize with ONNX and test on a camera with a lightweight face detector. It can achieve real-time speed on CPU.
python3 test_camera_light_onnx.py
Optimize with OpenVINO and test on a camera with a lightweight face detector. About 10 times faster than ONNX.
python3 test_camera_mobilefacenet_openvino.py
Benchmark Results on 300W
- Inter-ocular Normalization (ION)
| Algorithms | Common | Challenge | Full Set | Param # (M) |
|---|---|---|---|---|
| ResNet18 (224×224) | 3.73 | 7.14 | 4.39 | 11.76 |
| Res2Net50_v1b (224×224) | 3.43 | 6.77 | 4.07 | 26.00 |
| Res2Net50_v1b_SE (224×224) | 3.37 | 6.67 | 4.01 | 27.05 |
| Res2Net50_v1b_ExternalData (224×224) | 3.30 | 5.92 | 3.81 | 26.00 |
| HRNet_w18_small_v2 (224×224) | 3.57 | 6.85 | 4.20 | 13.83 |
- Inter-ocular Normalization (ION) with Lightweight Models
| Algorithms | Common | Challenge | Full Set | Param # (M) | CPU Inference (s) |
|---|---|---|---|---|---|
| MobileNetV2 (224×224) | 3.70 | 7.27 | 4.39 | 3.74 | 1.2 |
| MobileNetV2_SE (224×224) | 3.63 | 7.01 | 4.28 | 4.15 | / |
| MobileNetV2_SE_RE (224×224) | 3.63 | 6.66 | 4.21 | 4.15 | / |
| MobileNetV2_ExternalData (224×224) | 3.48 | 6.0 | 3.96 | 3.74 | 1.2 |
| MobileNetV2 (56×56) | 4.50 | 8.50 | 5.27 | 3.74 | 0.01 (onnx) |
| MobileNetV2_SE_ExternalData (56×56) | 4.10 | 6.89 | 4.64 | 4.10 | 0.01 (onnx) |
| PFLD_ExternalData (112×112) | 3.49 | 6.01 | 3.97 | 0.73 | 0.01 (onnx) |
| MobileFaceNet_ExternalData (112×112) | 3.30 | 5.69 | 3.76 | 1.01 | / |
Note: SE (squeeze-and-excitation module), RE (random erasing module).
- Heatmap Inference (still under test)
| Algorithms | Common | Challenge | Full Set | Param # (M) |
|---|---|---|---|---|
| Hourglass2 | 3.06 | 5.54 | 3.55 | 8.73 |
Visualization Results
- Face alignment on 300W dataset
- Semi-frontal face alignment on Menpo dataset
- Profile face alignment on Menpo dataset
TODO
The following features will be added soon.
- Still to come:
- Support for the 39-point detection
- Support for the 106 point detection
- Support for heatmap-based inferences
Public Datasets:
Citations:
If you use library in your project, please, cite it as follows.
@misc{PFL,
title={{PyTorch Face Landmark}: A Fast and Accurate Facial Landmark Detector},
url={https://github.com/cunjian/pytorch_face_landmark},
note={Open-source software available at https://github.com/cunjian/pytorch_face_landmark},
author={Cunjian Chen},
year={2021},
}