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

Parsing our dataset

As with every one of these networks, data is life. Without good data, there's no way our network will be effective. In this case, we'll take advantage of data sources from the authors of the aforementioned paper to experiment with this network.

Getting ready

We always need to ensure that we're building the right structure in our repository. A tidy workspace will lead to cleaner code—trust me! The following tree is in our Pix2Pix folder at our $HOME directory in Ubuntu:

├── docker
│   ├──
│   ├──
│   └── Dockerfile
└── src
|   ├──

Create placeholders for all of the shell scripts in the docker folder; go ahead and make the src directory, which we'll use throughout this book.

How to do it...

By now, you must be used to building Docker images and downloading data. The following recipe streamlines those steps and downloads the data within the image for simplicity.

Building the Docker container with a new Dockerfile

The Docker container is...