Fork of deepcam-cn/yolov5-face

Differences between original repository and fork:

• Compatibility with PyTorch >=2.5. (🔥)
• Original pretrained models and converted ONNX models from GitHub releases page. (🔥)
• Installation with requirements.txt file.
• The wider_val.txt file for WIDERFace evaluation.
• The following deprecations and errors has been fixed:
  • UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument.
  • DeprecationWarning: 'np.float' is a deprecated alias for builtin 'float'.
  • FutureWarning: You are using 'torch.load' with 'weights_only=False'.
  • FutureWarning: Cython directive 'language_level' not set.
  • Cython Warning: Using deprecated NumPy API.
  • AttributeError: module 'numpy' has no attribute 'int'.
  • RuntimeError: result type Float can't be cast to the desired output type long int.
  • Fixed face bounding box drawing problem in the TensorRT example.
  • NameError: name 'warnings' is not defined.

Installation

pip install -r requirements.txt

Pretrained models

• Download links:

Name	Model Size (MB)	Link	SHA-256
YOLOv5-BlazeFace	0.5 4.4	PyTorch ONNX	942997451c57981608d9e7eb7b0e964f2a83583b8add2409a2c5254a1f36f2d9 071cbb36cdb8d0d3dfb9305ba30f96c08a24342a4e835f48b4cc6bf1b185a564
YOLOv5n-0.5-Face	1.1 5.7	PyTorch ONNX	9f7cdbcf5cd63f454c47b18e7400a69630b96a01efb7559367e91b6e962ad3bd 269eb1e54313f9d1f7941ed9939fa247767539bca5801fc7aa7895960e93ca43
YOLOv5n-Face	13.7 10.5	PyTorch ONNX	794c94da54630f2ca66167fea25530c68133c61a2b14131b073c0d4064934e50 ee6ba4ccdc3c075d205c9703aec53a2aa3010c8d7fa08b0eff078e33a4b4fe6c
YOLOv5s-Face	54.4 30.9	PyTorch ONNX	a594ade0f5e80f5cf15aef8997d285a3fb4b372a2af5262fbc6837d30318cda7 9083776982185402cfb3bd3cba8d453823068e72a0f9b0a6c6060439a850d9c5
YOLOv5m-Face	161.2 84.2	PyTorch ONNX	ca90ccc1b76c06d330a501bdb2cba63d3740fd3ef39baea89c7acc602557a4a2 c7ea51072e5f5c1ead34be14b3f4a23f44477448c271bc161b99d122fa0d8f10
YOLOv5l-Face	356.4 181.7	PyTorch ONNX	adfa3fbee5ba97ca86237cf8b45992aaea891ea481d59722da89bbd871a6a546 b8b13132e7dd609b82a7cf8ea76d7c6f7695cbd909dc77063e37166af0a12622
YOLOv5l-Face (non-original)	89.3 181.7	PyTorch ONNX	7e20bf0c79888b230264e2b5d812a12a69c68bcf1a234b469f86c30d82bd6c2a 5340f05f54f3e22ca63234aa4f2622975fd23a62ccd656158f78c94dbeaa33f2

• Evaluation results on WIDERFace dataset:

Name	Easy	Medium	Hard	GFLOPS	Params(M)
YOLOv5-BlazeFace	90.4	88.7	78.0	2.6	0.182
YOLOv5n-0.5-Face	90.76	88.12	73.82	1.5	0.447
YOLOv5n-Face	93.61	91.52	80.53	5.6	1.726
YOLOv5s-Face	94.33	92.61	83.15	15.2	7.075
YOLOv5m-Face	95.30	93.76	85.28	48.2	21.063
YOLOv5l-Face	95.78	94.30	86.13	110.6	46.627
YOLOv5l-Face (non-original)	95.63	94.06	85.49	110.6	46.627

YOLOv5l-Face (non-original) model training took about 10.57 hours using NVIDIA RTX 4090. Results can be found in the yolov5l-face.txt file

Inference

python detect_face.py --weights weights/yolov5s-face.pt --source data/images/bus.jpg --save-img

WIDERFace evaluation

• Download WIDERFace validation dataset.
• Move dataset to data/widerface/val directory.

python test_widerface.py --weights weights/yolov5s-face.pt --dataset_folder data/widerface/val/images

cd widerface_evaluate

python setup.py build_ext --inplace

python evaluation.py

Export to ONNX format

pip install onnx onnxruntime

python export.py --weights weights/yolov5s-face.pt

Export to TensorRT format

pip install tensorrt pycuda

python export.py --weights weights/yolov5s-face.pt --onnx2trt

TensorRT Inference

python torch2trt/main.py --trt_path weights/yolov5s-face.trt --img_path data/images/bus.jpg

PyTorch vs TensorRT speed comparison

python torch2trt/speed.py --torch_path weights/yolov5s-face.pt --trt_path weights/yolov5s-face.trt

Training

• Download WIDERFace training dataset.
• Download WIDERFace validation dataset.
• Download annotation files.
• Move WIDERFace training images WIDER_train/images to data/widerface/tmp/train/images.
• Move WIDERFace validation images WIDER_val/images to data/widerface/tmp/val/images.
• Move training annotation file train/label.txt to data/widerface/tmp/train/label.txt.
• Move validation annotation file val/label.txt to data/widerface/tmp/val/label.txt.

python data/train2yolo.py data/widerface/tmp/train data/widerface/train

python data/val2yolo.py data/widerface/tmp data/widerface/val

pip install tensorboard

• Start training:

python train.py --data data/widerface.yaml --cfg models/yolov5n-0.5.yaml

python train.py --data data/widerface.yaml --cfg models/yolov5l.yaml --weights weights/yolov5l.pt

• Resume training:

python train.py --data data/widerface.yaml --cfg models/yolov5n-0.5.yaml --resume

python train.py --data data/widerface.yaml --cfg models/yolov5l.yaml --resume