All Projects → researchmm → SariGAN

researchmm / SariGAN

Licence: other
[NeurIPS'20] Learning Semantic-aware Normalization for Generative Adversarial Networks

Programming Languages

python
139335 projects - #7 most used programming language
Cuda
1817 projects
C++
36643 projects - #6 most used programming language
shell
77523 projects

SariGAN

Code for NeurIPS 2020 spotlight paper "Learning Semantic-aware Normalization for Generative Adversarial Networks"

This code is mainly based on https://github.com/rosinality/stylegan2-pytorch.git

Please refer to the above link to prepare data and install dependencies.

To train SariGAN, please run:

bash train.sh

To test the model in the term of fid, please run:

bash fid.sh

Pretrained model can be found in https://drive.google.com/file/d/1eT2QEK-0ZNQFj-daL3ga6QOoXqBLe8oR/view?usp=sharing

Citation

@article{zheng2020learning,
  title={Learning Semantic-aware Normalization for Generative Adversarial Networks},
  author={Zheng, Heliang and Fu, Jianlong and Zeng, Yanhong and Luo, Jiebo and Zha, Zheng-Jun},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  pages={21853--21864},
  year={2020}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].