A tensorflow implementation of GANs with variable loss function including Standard GAN, Least-Squared GAN (LSGAN), Wasserstein GAN (WGAN), improved Wasserstein GAN, and DRAGAN
I used celebA dataset and cropped the center face by 64X64 pixels.
- Standard GAN
- LSGAN
- WGAN
- Improved WGAN
- tensorflow >= 1.0.0
- numpy >= 1.12.0
hyperparams.py
includes all hyper parameters that are needed.data.py
loads training data and crops them.modules.py
contains customized conv net and so on.networks.py
builds a generator and a discriminator.train.py
is for training.
- STEP 1. Adjust hyper parameters in
hyperparams.py
, especially the hyperparameter "loss" that you want to train. - STEP 2. create 'data' directory, then download and extract celebA data at the directory.
- STEP 3. Run
train.py
and show result through tensorboard.