whrws / acl-gan Goto Github PK

Yihao Zhao, Ruihai Wu, Hao Dong, "Unpaired Image-to-Image Translation using Adversarial Consistency Loss", ECCV 2020

arXiv

project page

For environment:

conda env create -f acl-gan.yaml

For dataset: The dataset should be stored in the following format:

\dataset

|     \train

|     |     \trainA

|     |     \trainB

|     \test

|     |     \testA

|     |     \testB

For training:

python train.py --config configs/male2female.yaml

For test:

python test.py --config configs/male2female.yaml --input inputs/test_male.jpg --checkpoint ./outputs/male2female/checkpoints/test.pt

For more results, please refer to our paper.

If you find this code useful for your research, please cite our paper:

@inproceedings{zhao2020aclgan,
  title={Unpaired Image-to-Image Translation using Adversarial Consistency Loss},
  author={Zhao, Yihao and Wu, Ruihai and Dong, Hao},
  booktitle={ECCV},
  year={2020}
}