AI 实战 - pytorch框架基于retinaface实现face检测

简介

环境

开发环境

1. GPU服务器：pytorch1.13.0，python3.10，cuda==11.7
2. nvidia-smi 查看 CUDA 版本

conda create -n retinaface python=3.7
conda activate retinaface
pip3 install torch torchvision torchaudio -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install tensorboard scipy numpy matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install opencv_python Pillow==9.4.0 h5py -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install tqdm -i https://pypi.tuna.tsinghua.edu.cn/simple

数据

简介

Wider Face数据集，标记使用retinaface_gt_v1.1.zip

训练

测试