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

Training the model and understanding the GAN output

The most important part of the lesson after building a model is training! How do you train this beautiful yet simple architecture you have just developed, you might ask? Quite simply, now that we have laid the appropriate framework to do so, the key part is to understand how to run all of these tools that we have developed and then understand the output we are getting from the model.

Getting ready

This is the moment of truth—have you completed all of the previous recipes up until this point? If not, go back and work on them. Your directory should look like the following, minus the items in the data folder if you haven't run the script yet:

├── data
│   ├── Discriminator_Model.png
│   ├── GAN_Model.png
│   ├── Generator_Model.png
│   ├── sample_0.png
│   ├── sample_1000.png
├── Dockerfile

It's important to get every one of these pieces...