Skip to content

tolstikhin/wae

master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
1 branch 0 tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
images
 
 
LICENSE
 
 
README.md
 
 
configs.py
 
 
datahandler.py
 
 
improved_wae.py
 
 
models.py
 
 
ops.py
 
 
run.py
 
 
utils.py
 
 
wae.py
 
 
Repository info Repository structure Example of output pictures

README.md

Repository info

This project implements an unsupervised generative modeling technique called Wasserstein Auto-Encoders (WAE), proposed by Tolstikhin, Bousquet, Gelly, Schoelkopf (2017).

Repository structure

wae.py - everything specific to WAE, including encoder-decoder losses, various forms of a distribution matching penalties, and training pipelines

run.py - master script to train a specific model on a selected dataset with specified hyperparameters

Example of output pictures

The following picture shows various characteristics of the WAE-MMD model trained on CelebA after 50 epochs:

WAE-MMD progress

About

Wasserstein Auto-Encoders

Resources

Readme

License

BSD-3-Clause license

Stars

489 stars

Watchers

21 watching

Forks

92 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages