Wasserstein GAN

Code

• github.com/labmlai/annotated_deep_learning_paper_implementations
  pytorch★ 66,103
• github.com/jesse1029/Fake-Face-Images-Detection-Tensorflow
  tf★ 95
• github.com/ChristophReich1996/Mode_Collapse
  pytorch★ 47
• github.com/Sinestro38/qosf-qgan
  none★ 27
• github.com/beresandras/gan-flavours-keras
  tf★ 8
• github.com/croesuslab/RCTGAN
  none★ 7
• github.com/catalyst-team/gan
  pytorch★ 5
• github.com/cjfghk5697/Pytorch-Research-Paper-Implementations
  pytorch★ 5
• github.com/yjhong89/Domain-Adaptation
  tf★ 0
• github.com/dabsdamoon/Anime-Colorization-v0.2
  mxnet★ 0

Abstract

We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to other distances between distributions.

Tasks

Reproductions