Implementation of some different variants of GANs
This code is mainly implement some basic GANs about 'DCGAN', 'WGAN', 'WGAN-GP', 'LSGAN', 'SNGAN', 'RSGAN'&'RaSGAN'.
More details of these GANs, please see follow papers:
-
DCGAN: Unsupervised representation learning with deep convolutional generative adversarial networks
-
WGAN: Wasserstein gan
-
SNGAN: Spectral normalization for generative adversarial networks
-
RSGAN&RaSGAN: The relativistic discriminator: a key element missing from standard GAN
Firstly, you should download the data 'facedata.mat' from BaiduYun, then put the file 'facedata.mat' into the folder 'TrainingSet'.
Necessory python packages are as follow:
-
tensorflow
-
pillow
-
scipy
-
numpy
This result is using DCGAN trained about 8000 iterations.