Repository files navigation

This repository contains the code to reproduce the core results from the paperAdversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks.

To cite this work, please use

@INPROCEEDINGS{Mescheder2017ICML,  author = {Lars Mescheder and Sebastian Nowozin and Andreas Geiger},  title = {Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks},  booktitle = {International Conference on Machine Learning (ICML)},  year = {2017}}

This project uses Python 3.5.2. Before running the code, you have to install

• Tensorflow 1.0
• Numpy
• Scipy
• Matplotlib
• tqdm
• ite-toolbox

The former 5 dependencies can be installed using pip by running

pip install tensorflow-gpu numpy scipy matplotlib tqdm

Scripts to start the experiments can be found in theexperiments folder. If you have questions, pleaseopen an issue or write an email tolmescheder@tuebingen.mpg.de.

To run the experiments for mnist, you first need to create tfrecords files for MNIST:

cd toolspython download_mnist.py

Example scripts to run the scripts can be found in theexperiments folder.

Samples:

To run the experiments on celebA, first download the dataset fromhere and put all the images in thedatasets/celebA folder.

Samples:

Interpolations: