Skip to content

A pytorch implementation of Paper "Improved Training of Wasserstein GANs"

License

Notifications You must be signed in to change notification settings

caogang/wgan-gp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Nov 28, 2017
ae47a18 · Nov 28, 2017

History

63 Commits
Aug 25, 2017
Aug 25, 2017
Nov 28, 2017
May 10, 2017
May 4, 2017
Aug 25, 2017
Nov 28, 2017
Jun 27, 2017
Jun 26, 2017
May 12, 2017
May 9, 2017

Repository files navigation

WGAN-GP

An pytorch implementation of Paper "Improved Training of Wasserstein GANs".

Prerequisites

Python, NumPy, SciPy, Matplotlib A recent NVIDIA GPU

A latest master version of Pytorch

Progress

  • gan_toy.py : Toy datasets (8 Gaussians, 25 Gaussians, Swiss Roll).(Finished in 2017.5.8)

  • gan_language.py : Character-level language model (Discriminator is using nn.Conv1d. Generator is using nn.Conv1d. Finished in 2017.6.23. Finished in 2017.6.27.)

  • gan_mnist.py : MNIST (Running Results while Finished in 2017.6.26. Discriminator is using nn.Conv1d. Generator is using nn.Conv1d.)

  • gan_64x64.py: 64x64 architectures(Looking forward to your pull request)

  • gan_cifar.py: CIFAR-10(Great thanks to robotcator)

Results

  • Toy Dataset

    Some Sample Result, you can refer to the results/toy/ folder for details.

    • 8gaussians 154500 iteration

    frame1612

    • 25gaussians 48500 iteration

      frame485

    • swissroll 69400 iteration

    frame694

  • Mnist Dataset

    Some Sample Result, you can refer to the results/mnist/ folder for details.

    mnist_samples_91899

    mnist_samples_91899

    mnist_samples_91899

    mnist_samples_199999

  • Billion Word Language Generation (Using CNN, character-level)

    Some Sample Result after 8699 epochs which is detailed in sample

    I haven't run enough epochs due to that this is very time-comsuming.

    He moved the mat all out clame t

    A fosts of shores forreuid he pe

    It whith Crouchy digcloued defor

    Pamreutol the rered in Car inson

    Nor op to the lecs ficomens o fe

    In is a " nored by of the ot can

    The onteon I dees this pirder ,

    It is Brobes aoracy of " medurn

    Rame he reaariod to thim atreast

    The stinl who herth of the not t

    The witl is f ont UAy Y nalence

    It a over , tose sho Leloch Cumm

  • Cifar10 Dataset

    Some Sample Result, you can refer to the results/cifar10/ folder for details.

    mnist_samples_91899

Acknowledge

Based on the implementation igul222/improved_wgan_training and martinarjovsky/WassersteinGAN

About

A pytorch implementation of Paper "Improved Training of Wasserstein GANs"

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages