windows10+SCRFD环境配置

1.安装pytorch

pip install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html

2.安装mmcv

pip install mmcv-full==1.3.5 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.8.1/index.html

3.在scrfd仓库下安装mmdet

pip install -r requirements/build.txt
pip install -v -e .  # or "python setup.py develop"

4.安装torchVision

pip install torchvision==0.9.1

5.运行脚本

PS E:\pycharmpro\face_recognize\scrfd> python .\demo\image_demo.py E:\pycharmpro\face_recognize\scrfd\images\chenyixun_0.jpg E:\pycharmpro\face_recognize\scrfd\configs\scrfd\scrfd_10g_bn
kps.py E:\pycharmpro\face_recognize\scrfd\weights\scrfd_10g_bnkps\model.pth
Use load_from_local loader
PS E:\pycharmpro\face_recognize\scrfd>