Building a GAN

Together with Ian, we've built a notebook that will lead you through building your own GAN and train it on MNIST. You'll build the generator and discriminator networks, as well as set up the losses and optimizers which requires something new since we need to train the networks in parallel. We've included a notebook with exercises where you'll implement the network and another notebook with solutions.

Getting the Notebooks

As usual, the notebooks are available from our public GitHub repo in the gan_mnist directory. To get the new notebooks, use git pull in your cloned repository.

If you don't have the repo yet, clone it with Git

git clone https://github.com/udacity/deep-learning.git