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

Code implementation – GAN

The GAN architecture represents a way for us to put two or more neural networks in adversarial training. The only major thing we've changed in our current architecture is to use 3D convolutions and a new input format. This GAN architecture is very similar to other structures we've introduced throughout this book.

Getting ready

After defining the generator and discriminator, we're going to continue our development by defining a new file called This file will be located under the src folder. Check to make sure you have the same directory structure at this point:

├── data
├── docker
│   ├──
│   ├──
│   ├── Dockerfile
│   └── kaggle.json
├── out
└── src
    ├── encoder_model.h5
    ├── x_test_encoded.npy
    └── x_train_encoded.npy

How to do it...

The GAN class will be straightforward to implement—it's essentially the same class we...