GANs in Action: Deep learning with Generative Adversarial Networks

This book is quite dry to read, lack good explanation on the theory. The models and examples use toy dataset which aren't very useful at all.The first few chapters introducing the basics GANs are okay but you can find similar materials freely available on internet. Most of the code are taken from somebody else's Github repo, perhaps why there lacks in-depth explanation on why the models were constructed in such a way. As already mentioned by others, the later chapters get worse. There wasn't even model implementation for ProgressiveGAN but simply call APIs from TensorFlow Hub.I found Foster's "Generative Deep Learning" to be easier to read. It is good for simple models up to CycleGAN but it too is lacking in advanced GANs as it dedicates only about half of the book to GANs and the rest are RNN and RL. The best and most complete book on GANs on market now is Cheong's "Hands-on Image Generation with TensorFlow". Not only it is easy to read but also cover all the important techniques leading to state-of-the-art models like StyleGAN to generate photorealistic faces. This is the book if you are serious about learning GANs for practical datasets.