Train a Generative Adversarial Nets (GAN) model

This example is to train a Generative Adversarial Nets (GAN) model over the MNIST dataset.

Running instructions

1. Download the pre-processed MNIST dataset

2. Start the training

    python vanilla.py mnist.pkl.gz
   

By default the training code would run on CPU. To run it on a GPU card, please start the program with an additional argument

    python vanilla.py mnist.pkl.gz --use_gpu