WGAN-GP

Pure tensorflow implementation of WGAN-GP

Sources:

Improved Training of Wasserstein GANs

Requirements

python modules

terminaltables==3.1.0
colorama==0.3.9
matplotlib==2.0.2
tensorflow_gpu==1.3.0
tqdm==4.17.0
numpy==1.13.3
tensorflow==1.4.0rc1

Part 1. Getting the data

Go to http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
In the Downloads section, select Align&Cropped images.
In the dropbox page that follows, download the Anno, Eval and Img folders.
Copy these folders to /data/raw.
Extract the zip files.

We are only going to use the images

Part 2. Running the code

Follow these instructions