Goal

Simple GAN to generate 'fake' digits that minic the MNIST dataset.

Note: tutorial states that they train for 100 epochs.

To do

It seems like after I do some training, the generated image only updates on the second call. Is that true?
Can I disconnect from a running kernel and reconnect to it?
What's the ratio of the time taken to do a training batch on my laptop vs on p2.xlarge? What's the optimum batch size?

Name		Name	Last commit message	Last commit date
Latest commit History 10 Commits
README.md		README.md
conv_gan.py		conv_gan.py
demo_simple_gan.py.ipynb		demo_simple_gan.py.ipynb
demonstration.ipynb		demonstration.ipynb
fc_net.py		fc_net.py
gan.py		gan.py
gan_modified.py		gan_modified.py
mnist_data.py		mnist_data.py
simple_gan.py		simple_gan.py