Pytorch implementation of our paper: "Multi-mapping Image-to-Image Translation via Learning Disentanglement".
you can install all the dependencies by
pip install -r requirements.txt
Download and unzip preprocessed datasets by
bash ./scripts/download_datasets.sh summer2winter_yosemite
bash ./scripts/download_datasets.sh birds
Or you can manually download them from CycleGAN and AttnGAN.
bash ./scripts/train_season_transfer.sh
bash ./scripts/train_semantic_image_synthesis.sh
exp_name
.bash ./scripts/test_season_transfer.sh
bash ./scripts/test_semantic_image_synthesis.sh
checkpoints/{exp_name}/results
directory.Pretrained models can be downloaded from Google Drive or Baidu Wangpan with code 59tm
.
You can implement your Dataset and SubModel to start a new experiment.
If this work is useful for your research, please consider citing :
@inproceedings{yu2019multi,
title={Multi-mapping Image-to-Image Translation via Learning Disentanglement},
author={Yu, Xiaoming and Chen, Yuanqi and Liu, Shan and Li, Thomas and Li, Ge},
booktitle={Advances in Neural Information Processing Systems},
year={2019}
}
The code used in this research is inspired by BicycleGAN, MUNIT, DRIT, AttnGAN, and SingleGAN.
The diversity regulazation used in the current version is inspired by DSGAN and MSGAN.
Feel free to reach me if there is any questions (xiaomingyu@pku.edu.cn).