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
Dedication
Contributors
Preface
Dedication2
Index

Code implementation – discriminator


The discriminator is simpler in comparison to the generator. Deep convolutional networks are commonplace in classification research. The key thing to remember with GANs, however, is that the training should be adversarial—simply grabbing state-of-the-art classification techniques may not give the generator the ability to learn. In essence, there is a balancing act to structuring your discriminator.

Getting ready

As always, keep track of your directory and make sure that you are placing newly developed structures in the right place, as follows:

DCGAN
├── data
├── docker
├── README.md
├── run.sh
├── scripts
└── src
    ├── discriminator.py
    ├── gan.py
    ├── generator.py
    ├── save_to_npy.py

Note

Note that discriminator.py and gan.py from the previous section will be integrated into the following recipe.

How to do it...

It's simple to modify the following structure from Goodfellow, to a DCGAN type; all you need to do is add two core changes to the Chapter...