Hands-On Generative Adversarial Networks with Keras

This is the code repository for Hands-On Generative Adversarial Networks with Keras , published by Packt.

Your guide to implementing next-generation generative adversarial networks

What is this book about?

Generative Adversarial Networks (GANs) have revolutionized the fields of machine learning and deep learning. This book will be your first step towards understanding GAN architectures and tackling the challenges involved in training them.

This book covers the following exciting features:

Learn how GANs work and the advantages and challenges of working with them
Control the output of GANs with the help of conditional GANs, using embedding and space manipulation
Apply GANs to computer vision, NLP, and audio processing
Understand how to implement progressive growing of GANs
Use GANs for image synthesis and speech enhancement

If you feel this book is for you, get your copy today!

Instructions and Navigations

All of the code is organized into folders. For example, Chapter02.

The code will look like the following:

import numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.utils import np_utils
from keras.optimizers import SGD
from keras.layers.core import Dense,Activation

Following is what you need for this book: This book is for machine learning practitioners, deep learning researchers, and AI enthusiasts who are looking for a perfect mix of theory and hands-on content in order to implement GANs using Keras. Working knowledge of Python is expected.

With the following software and hardware list you can run all code files present in the book (Chapter 1-12).

Software and Hardware List

Chapter	Software required	OS required
All	Python 3.6 or later	Windows, Mac OS X, and Linux (Any)
All	Anaconda 5.2	Windows, Mac OS X, and Linux (Any)
All	Jupyter Notebook	Windows, Mac OS X, and Linux (Any)

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it.

Get to Know the Author

Rafael Valle is a research scientist at NVIDIA focusing on audio applications. He has years of experience developing high-performance machine learning models for data/audio analysis, synthesis and machine improvisation with formal specifications.

Dr. Valle was the first to generate speech samples from scratch with GANs and to show that simple yet efficient techniques can be used to identify GAN samples. He holds an Interdisciplinary Ph.D. in Machine Listening and Improvisation from UC Berkeley, a Master’s degree in Computer Music from the MH-Stuttgart in Germany and a Bachelor’s degree in Orchestral Conducting from UFRJ in Brazil.

Suggestions and Feedback

Click here if you have any feedback or suggestions.