Fork of derronqi/yolov7-face

Differences between original repository and fork:

• Compatibility with PyTorch >=2.0. (🔥)
• Original pretrained models and converted ONNX models from GitHub releases page. (🔥)
• The wider_val.txt file for WIDERFace evaluation.
• The following deprecations 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: Cython directive 'language_level' not set.
  • Cython Warning: Using deprecated NumPy API.

Installation

pip install -r requirements.txt

Pretrained models

Method	Test Size	Easy	Medium	Hard	FLOPs (B) @640	Link
yolov7-lite-t	640	88.7	85.2	71.5	0.8	PyTorch, ONNX
yolov7-lite-s	640	92.7	89.9	78.5	3.0	PyTorch, ONNX
yolov7-tiny	640	94.7	92.6	82.1	13.2	PyTorch, ONNX
yolov7s	640	94.8	93.1	85.2	16.8	PyTorch, ONNX
yolov7	640	96.9	95.5	88.0	103.4	PyTorch, ONNX
yolov7+TTA	640	97.2	95.8	87.7	103.4	PyTorch
yolov7-w6	960	96.4	95.0	88.3	89.0	PyTorch, ONNX
yolov7-w6+TTA	1280	96.9	95.8	90.4	89.0	PyTorch

Inference

python detect.py --weights yolov7s-face.pt --source data/images/22_Picnic_Picnic_22_10.jpg

WIDERFace evaluation

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

python test_widerface.py --weights yolov7s-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

python models/export.py --weights yolov7s-face.pt --grid