Counting 1,239 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Feb. 17, 2017
May. 17, 2016


Build Status Codacy Badge Python Version

Tars is the deep generative models library. It has the following features:

  • Various distributions
    • Gaussian, Bernoulli, Laplace, Gamma, Beta, Dirichlet, Bernoulli, Categorical, and so on.
    • We can draw samples from these distributions by the reparameterization trick .
  • Various models
    • Autoencoder
    • VAE
      • Conditional VAE
      • Importance weighted autoencoder
      • JMVAE
      • Multiple latent layers
    • GAN, Conditional GAN
    • VAE-GAN, conditional VAE-GAN
    • VAE-RNN
      • Variational RNN
      • DRAW, Convolutional DRAW
  • Various lower bounds

    • The evidence lower bound (ELBO, which is the same as the original lower bound)
    • The importance sampling lower bound
    • The variational R'enyi bound
  • Note: Some of the implementations of the above models have not yet been released in this version. If you want to use such models, please use the old version (v0.0.2).

  • For a more detailed explanation of this library, please refer to this page (in Japanese).


$ git clone
$ pip install -e Tars --process-dependency-links


$ pip install -e git:// --process-dependency-links

When you execute this command, the following packages will be automatically installed in your environment:

  • Theano
  • Lasagne
  • progressbar2
  • matplotlib
  • sklearn


Please go to the examples directory and try to run some examples.

Latest Releases
 Jan. 17 2017
 Nov. 14 2016