Implementation of some different variants of GANs

This code is mainly implement some basic GANs about 'DCGAN', 'WGAN', 'WGAN-GP', 'LSGAN', 'SNGAN', 'RSGAN'&'RaSGAN', 'BEGAN', 'ACGAN', 'PGGAN', 'pix2pix', 'BigGAN'.

More details of these GANs, please see follow papers:

1. DCGAN: Unsupervised representation learning with deep convolutional generative adversarial networks

2. WGAN: Wasserstein gan

3. WGAN-GP: Improved training of wasserstein gans

4. LSGAN: Least Squares Generative Adversarial Networks

5. SNGAN: Spectral normalization for generative adversarial networks

6. RSGAN&RaSGAN: The relativistic discriminator: a key element missing from standard GAN

7. BEGAN:BEGAN: Boundary Equilibrium Generative Adversarial Networks

8. ACGAN: Conditional Image Synthesis With Auxiliary Classifier GANs

9. PGGAN: Progressive Growing of GANs for Improved Quality, Stability, and Variation

10. pix2pix: Image-to-Image Translation with Conditional Adversarial Networks

11. BigGAN: Large Scale GAN Training for High Fidelity Natural Image Synthesis [Code]

If your computer don't have GPU to accelerate the training process, please click Google Cloud Colab to train the GANs.

Firstly, you should download the data 'facedata.mat' from Baidu Drive or Google Drive, then put the file 'facedata.mat' into the folder 'TrainingSet'.

1. python3.5
2. tensorflow1.4.0
3. pillow
4. scipy
5. numpy

This result is using DCGAN trained about 8000 iterations.

dataset: download address: Baidu Drive password: 5egd

Fixed label, change noise slightly	Fixed noise, change label slightly

D_loss	G_loss	results

Dataset: Google maps download address: http://efrosgans.eecs.berkeley.edu/pix2pix/datasets/maps.tar.gz

Edges2Shoes download address: http://efrosgans.eecs.berkeley.edu/pix2pix/datasets/edges2shoes.tar.gz