Chapter 1, What is a Generative Adversarial Network?, introduces you to GAN architectures and looks at the implementation of each of them.

Chapter 2, Data First – Easy Environment and Data Preparation, lays down the groundwork for manipulating data, augmenting your data, and balancing imbalanced datasets or data with massive outliers.

Chapter 3, My First GAN in Under 100 Lines, covers how to take the theory we'll have discussed and produce a simple GAN model using Keras, TensorFlow, and Docker.

Chapter 4, Dreaming of New Outdoor Structures Using DCGAN, covers the building blocks required to build your first deep convolutional generative adversarial network (DCGAN) implementation.

Chapter 5, Pix2Pix Image-to-Image Translation, covers Pix2Pix, how it works, and how it is implemented.

Chapter 6, Style Transfering Your Image Using CycleGAN, explains what CycleGAN is, and how to parse the CycleGAN datasets and implementations.

Chapter 7, Using Simulated Images To Create Photo-Realistic Eyeballs with SimGAN, demonstrates how SimGAN works, and how it is implemented.

Chapter 8, From Images to 3D Models Using GANs, talks about 3D models and techniques to implement these 3D models using images.