Skip to content

VAE-variant generative models, powered by PyTorch

License

Notifications You must be signed in to change notification settings

chris-tng/pizza

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pizza

Fast generative models composed with neural networks, powered by PyTorch

This is used for personal research so the code is far from bug-free.

Implementations of various variants of Variational Autoencoders:

  1. Vanilla VAE:

Diederik P. Kingma, Max Welling. Auto-Encoding Variational Bayes. 2013

  1. Gumbel-softmax trick to backprop through discrete variables:

Eric Jang, Shixiang Gu, Ben Poole. Categorial Reparameterization with Gumbel-Softmax. 2017

  1. Semi-supervised VAE:

Diederik P. Kingma, Danilo J. Rezende, Shakir Mohamed, Max Welling. Semi-supervised Learning with Deep Generative Models. 2014

  1. VAE using auxilary variables:

Lars Maaløe, Casper Kaae Sønderby, Søren Kaae Sønderby, Ole Winther. Auxiliary Deep Generative Models. 2016

  1. Distangled representations using β-VAE:

Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner. β-VAE: Learning basic visual concepts with a constrained variational framework. 2017

  1. Balancing Learning and Inference in VAE:

Shengjia Zhao, Jiaming Song, Stefano Ermon. InfoVAE: Information Maximizing Variational Autoencoders. 2018