This is the core of this particular set of recipes. Let's remind ourselves what it looks like to work with Keras and TensorFlow. In the past, it would take hundreds of lines of code to define a simple network. In the Keras framework, a network can be instantiated in under three lines of code! For this recipe, we will introduce a few of the basic tools needed to understand the neural networks that we will work with in this chapter.
For this recipe, we need to ensure that we have all the appropriate tools to compile our code. You need the following pieces to make this recipe happen:
- A computer with an NVIDIA GPU
- Ubuntu 16.04
- NVIDIA Docker installed
With these two items, we can once again build the necessary run scripts and images to run our very first GAN. The GAN consists of three pieces (generator
, discriminator
, and loss
function) and all three can very simply be represented in the Keras framework. First, we will build the container...