Skip to content

Tensorflow implementation of different GANs and their comparisions

License

Notifications You must be signed in to change notification settings

jypstory/tf-exercise-gan

This branch is up to date with sanghoon/tf-exercise-gan:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

01abe0d · Aug 9, 2017

History

18 Commits
Aug 9, 2017
Jul 31, 2017
Jul 15, 2017
May 25, 2017
May 25, 2017
Aug 9, 2017
Jul 31, 2017
Jul 15, 2017
Jul 31, 2017
Jul 31, 2017
Jul 31, 2017
Aug 9, 2017
Jul 31, 2017
Jul 31, 2017
Jun 30, 2017
Jul 31, 2017

Repository files navigation

tf-exercise-gan

Tensorflow implementation of different GANs and their comparisions

GAN implementations

Tasks

  • Impl. DCGAN, GoGAN, WGAN
  • Impl. BEGAN, MAD-GAN
  • Reproduce GANs on MNIST and CelebA datasets
  • Impl. training & evaluation on synthetic datasets
  • Add sample results
  • Impl. inference-only code for GANs (may require refactoring)
  • Impl. better evaluation function for real images (e.g. IvOM, energy dist., ...)
  • Impl. a result logger
  • Compare GANs (synthetic)
  • Compare GANs (MNIST and CelebA dataset)
  • Add quantitative comparisons
  • Add more GAN implementations

Experiments & Benchmarks

170718 / Comparison of different GAN models on synthetic datasets

  • Done without any hyper-parameter search.
  • MAD-GAN worked best in the tested datasets.
  • MADGAN_Spiral

170718 / Sample results on MNIST dataset

  • WGAN_MNIST

170809 / Sample results on CelebA dataset

  • BEGAN_CELEBA

Other References

About

Tensorflow implementation of different GANs and their comparisions

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%