Skip to content

Latest commit

 

History

History

WassersteinGAN

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
data
data
 
 
figures
figures
 
 
models
models
 
 
src
src
 
 
README.md
README.md
 
 

README.md

Generative Adversarial Networks

Keras implementation of WassersteinGAN.

Sources:

Requirements

python modules

numpy==1.13.3 natsort==5.1.0 matplotlib==2.0.2 opencv_python==3.3.0.10 scipy==1.0.0 tqdm==4.17.0 Keras==2.0.8 parmap==1.5.1 h5py==2.7.0 Theano==0.9.0 or tensorflow==1.3.0

Part 1. Processing the data

Follow these instructions.

Part 2. Running the code

Follow these instructions

Part 3. Example results

CelebA example results

figure figure

For each image:

  • The first 2 rows are generated images
  • The last 2 rows are real images

MoG

Results on the unrolled GAN paper to dataset:

figure