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


The training script from Chapter 3My First GAN in Under 100 Lines, has been modified to accept our new data format, and we have also added some new tricks to ensure that more complicated architecture is able to converge. We'll also fully implement a batch and epoch system for our GAN trainer in this section.

Getting ready

Add the following files, which you'll need to train the GAN:

├── data
├── docker
├── scripts
└── src

The and files will drive the training of your DCGAN architecture.

How to do it...

In this section, we'll focus on the training script's key changes.

Changes to class initialization

  1. First, notice that there is a new optional argument in the Trainer class called model_type, as shown in the following snippet:
class Trainer:
    def __init__(self, width = 28, height= 28, channels = 1,