TensorFlow implementation of Deep Convolutional Generative Adversarial Networks and Variational Autoencoder (also Deep and Convolutional).
python main_***.py --working_directory /tmp/gan
Deep Convolutional Generative Adversarial Networks produce decent results after 10 epochs using default parameters.
###TODO:
- More complex data.
- Add attention.
- Add Adversarial Autoencoder
- Replace current attention mechanism with Spatial Transformer Layer