https://github.com/karenullrich/binary-vae

A minimal implementation of a VAE with BinConcrete (relaxed Bernoulli) latent distribution in TensorFlow.
https://github.com/karenullrich/binary-vae

bernoulli binary concrete-distribution tensorflow tensorflow-eager tensorflow-probability vae variational-autoencoder variational-inference

Last synced: 7 months ago
JSON representation

A minimal implementation of a VAE with BinConcrete (relaxed Bernoulli) latent distribution in TensorFlow.

• Host: GitHub
• URL: https://github.com/karenullrich/binary-vae
• Owner: KarenUllrich
• License: gpl-3.0
• Created: 2019-06-12T09:22:47.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2020-02-01T11:03:07.000Z (about 6 years ago)
• Last Synced: 2025-04-02T05:01:43.484Z (11 months ago)
• Topics: bernoulli, binary, concrete-distribution, tensorflow, tensorflow-eager, tensorflow-probability, vae, variational-autoencoder, variational-inference
• Language: Python
• Size: 35.2 KB
• Stars: 21
• Watchers: 2
• Forks: 3
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
##  Binary VAE with BinConcrete latent distribution

Tensorflow implmentation of a VAE with Bininary Concrete (BinConcrete) latent distribution, based on:

["The concrete distribution: A continuous relaxation of discrete random variables"](https://arxiv.org/pdf/1611.00712.pdf)

Maddison, Chris J., Andriy Mnih, and Yee Whye Teh, ICLR, 2017

You can simply run this code by

	python experiment.py

### Requirements

This code has been tested with

-   `python 3.6`

-   `tensorflow 2.1.0` 

-   `tensorflow-probability 0.9.0` 

-   `matplotlib 3.1.2` 

Install conda environment via

	conda env create -f environment.yml 

	source activate binary_vae

### Maintenance

Please be warned that this repository is not going to be maintained regularly.