Book Image

Generative Adversarial Networks Cookbook

By : Josh Kalin
Book Image

Generative Adversarial Networks Cookbook

By: Josh Kalin

Overview of this book

Developing Generative Adversarial Networks (GANs) is a complex task, and it is often hard to find code that is easy to understand. This book leads you through eight different examples of modern GAN implementations, including CycleGAN, simGAN, DCGAN, and 2D image to 3D model generation. Each chapter contains useful recipes to build on a common architecture in Python, TensorFlow and Keras to explore increasingly difficult GAN architectures in an easy-to-read format. The book starts by covering the different types of GAN architecture to help you understand how the model works. This book also contains intuitive recipes to help you work with use cases involving DCGAN, Pix2Pix, and so on. To understand these complex applications, you will take different real-world data sets and put them to use. By the end of this book, you will be equipped to deal with the challenges and issues that you may face while working with GAN models, thanks to easy-to-follow code solutions that you can implement right away.
Table of Contents (17 chapters)
Title Page
Copyright and Credits
About Packt

Building a neural network in Keras and TensorFlow

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.

Getting ready

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...