Skip to content
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Branch: master
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
GAN Fix #61: remove entropy term on InfoGAN as it is a constant Aug 3, 2018
HelmholtzMachine Add Helmholtz Machine Sep 11, 2017
RBM Add biases to RBM Dec 11, 2017
VAE Update Jan 21, 2018
.gitignore Update compatibility with pytorch 0.2 Aug 24, 2017
LICENSE Create LICENSE Apr 18, 2017 Add GibbsNet Dec 22, 2017
environment.yml Initial commit: GAN & VAE codes Dec 7, 2016

Generative Models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow. Also present here are RBM and Helmholtz Machine.


Generated samples will be stored in GAN/{gan_model}/out (or VAE/{vae_model}/out, etc) directory during training.

What's in it?

Generative Adversarial Nets (GAN)

  1. Vanilla GAN
  2. Conditional GAN
  3. InfoGAN
  4. Wasserstein GAN
  5. Mode Regularized GAN
  6. Coupled GAN
  7. Auxiliary Classifier GAN
  8. Least Squares GAN
  9. Boundary Seeking GAN
  10. Energy Based GAN
  11. f-GAN
  12. Generative Adversarial Parallelization
  13. DiscoGAN
  14. Adversarial Feature Learning & Adversarially Learned Inference
  15. Boundary Equilibrium GAN
  16. Improved Training for Wasserstein GAN
  17. DualGAN
  18. MAGAN: Margin Adaptation for GAN
  19. Softmax GAN
  20. GibbsNet

Variational Autoencoder (VAE)

  1. Vanilla VAE
  2. Conditional VAE
  3. Denoising VAE
  4. Adversarial Autoencoder
  5. Adversarial Variational Bayes

Restricted Boltzmann Machine (RBM)

  1. Binary RBM with Contrastive Divergence
  2. Binary RBM with Persistent Contrastive Divergence

Helmholtz Machine

  1. Binary Helmholtz Machine with Wake-Sleep Algorithm


  1. Install miniconda
  2. Do conda env create
  3. Enter the env source activate generative-models
  4. Install Tensorflow
  5. Install Pytorch
You can’t perform that action at this time.