1、项目介绍：

2、环境安装

  • 平台：windows 10
  • 编译器：pycharm
  • cuda 11.3
  • cudnn 8.2.0.53
conda create -n cyclegan python=3.7
conda activate cyclegan 
pip install opencv-python
pip install pillow
pip install face_alignment
pip install tensorflow=1.15.0 
pip install protobuf==3.20.0
pip install dlib-19.19.0-cp37-cp37m-win_amd64.whl
pip install torch-1.11.0+cu113-cp37-cp37m-win_amd64.whl
pip install torchvision-0.11.2+cu113-cp37-cp37m-win_amd64.whl

3、执行代码

python test.py --photo_path ./images/1.jpg --save_path ./images/2.png

批量裁剪图像：

python data_process.py --data_path YourPhotoFolderPath --save_path YourSaveFolderPath

# 重新训练

# 请自己准备真实人脸图片进行训练。放在dataset\trainA和dataset\testA

python train.py --dataset photo2cartoon

4、效果展示

5、总结