bojone / o-gan

O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks

o-gan

O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks

Requirement

Python 2.7 + Tensorflow 1.8 + Keras 2.2.4

Results

• CelebA HQ
  

• FFHQ
  

• LSUN-church
  

• LSUN-bedroom
  

Reference

• https://kexue.fm/archives/6409
• https://arxiv.org/abs/1903.01931

Cite

 @article{su2019gan,
  title={O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks},
  author={Su, Jianlin},
  journal={arXiv preprint arXiv:1903.01931},
  year={2019}
}

交流

QQ交流群：67729435，微信群请加机器人微信号spaces_ac_cn