Contrastive Learning for Unpaired Image-to-Image Translation
- Clone this repo:
git clone https://github.com/haomengz/Concise-CUT Concise-CUT
cd Concise-CUT
- Setup a virtual environment and install the requirements:
python3 -m venv env
source env/bin/activate
pip install -r requirements.txt
echo $PWD > env/lib/python3.8/site-packages/Concise-CUT.pth
...
deactivate
- Download a dataset:
bash ./datasets/download_cut_dataset.sh [DATASET_NAME]
- Train a model:
python train.py
- Test the model:
python test.py
Change the LOSS
in config.py
Code is inspired by taesungp and wilbertcaine.
@misc{park2020contrastive,
title={Contrastive Learning for Unpaired Image-to-Image Translation},
author={Taesung Park and Alexei A. Efros and Richard Zhang and Jun-Yan Zhu},
year={2020},
eprint={2007.15651},
archivePrefix={arXiv},
primaryClass={cs.CV}
}