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

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

Name		Name	Last commit message	Last commit date
Latest commit History 44 Commits
images		images
LICENSE		LICENSE
README.md		README.md
configs.py		configs.py
datahandler.py		datahandler.py
improved_wae.py		improved_wae.py
models.py		models.py
ops.py		ops.py
run.py		run.py
utils.py		utils.py
wae.py		wae.py