[Paper] [Pytorch]
StarGAN v2 β Official TensorFlow ImplementationJunho Kim
Implemented byRequirements
Tensorflow == 2.1.0
Tensorflow-addons == 0.9.1
opencv-python
Pillow
tqdm
Usage
βββ dataset
Β Β βββ YOUR_DATASET_NAME
Β Β βββ train
Β Β Β Β Β βββ domain1 (domain folder)
βββ xxx.jpg (domain1 image)
βββ yyy.png
βββ ...
βββ domain2
βββ aaa.jpg (domain2 image)
βββ bbb.png
βββ ...
βββ ...
Β Β βββ test
βββ ref_imgs (domain folder)
βββ domain1 (domain folder)
βββ ttt.jpg (domain1 image)
βββ aaa.png
βββ ...
βββ domain2
βββ kkk.jpg (domain2 image)
βββ iii.png
βββ ...
βββ ...
βββ src_imgs
βββ src1.jpg
βββ src2.png
βββ ...
Train
python main.py --dataset celebA-HQ_gender --phase train
Test
python main.py --dataset celebA-HQ_gender --phase test
Tensorflow results (100K)
Latent-guided synthesis
CelebA-HQ
AFHQ
Reference-guided synthesis
CelebA-HQ
AFHQ
License
The source code, pre-trained models, and dataset are available under Creative Commons BY-NC 4.0 license by NAVER Corporation. You can use, copy, tranform and build upon the material for non-commercial purposes as long as you give appropriate credit by citing our paper, and indicate if changes were made.
For business inquiries, please contact [email protected].
For technical and other inquires, please contact [email protected].
For questions about the tensorflow implementation, please contact [email protected].
Citation
If you find this work useful for your research, please cite our paper:
@inproceedings{choi2020starganv2,
title={StarGAN v2: Diverse Image Synthesis for Multiple Domains},
author={Yunjey Choi and Youngjung Uh and Jaejun Yoo and Jung-Woo Ha},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2020}
}