The code relies on the official implementation of CLIP, and the Rosinality pytorch implementation of StyleGAN2.
In addition, run the following commands:
conda install --yes -c pytorch pytorch=1.7.1 torchvision cudatoolkit=<CUDA_VERSION>
pip install ftfy regex tqdm tensorboard tensorboardx
pip install git+https://github.com/openai/CLIP.gitTo convert a generator from one domain to another, run the training script:
bash adaptation.sh