Adversarial Variational Bayes: Unifying VAE and GAN 代码

Adversarial Variational Bayes

This repository contains the code to reproduce the core results from the paper Adversarial 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}}

Dependencies

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

Usage

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

MNIST

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 the experiments folder.

Samples:

CelebA

To run the experiments on celebA, first download the dataset from here and put all the images in the datasets/celebA folder.

Samples:

Interpolations:

https://github.com/LMescheder/AdversarialVariationalBayes