Book Image

Hands-On Generative Adversarial Networks with PyTorch 1.x

By : John Hany, Greg Walters
Book Image

Hands-On Generative Adversarial Networks with PyTorch 1.x

By: John Hany, Greg Walters

Overview of this book

With continuously evolving research and development, Generative Adversarial Networks (GANs) are the next big thing in the field of deep learning. This book highlights the key improvements in GANs over generative models and guides in making the best out of GANs with the help of hands-on examples. This book starts by taking you through the core concepts necessary to understand how each component of a GAN model works. You'll build your first GAN model to understand how generator and discriminator networks function. As you advance, you'll delve into a range of examples and datasets to build a variety of GAN networks using PyTorch functionalities and services, and become well-versed with architectures, training strategies, and evaluation methods for image generation, translation, and restoration. You'll even learn how to apply GAN models to solve problems in areas such as computer vision, multimedia, 3D models, and natural language processing (NLP). The book covers how to overcome the challenges faced while building generative models from scratch. Finally, you'll also discover how to train your GAN models to generate adversarial examples to attack other CNN and GAN models. By the end of this book, you will have learned how to build, train, and optimize next-generation GAN models and use them to solve a variety of real-world problems.
Table of Contents (15 chapters)
Free Chapter
1
Section 1: Introduction to GANs and PyTorch
5
Section 2: Typical GAN Models for Image Synthesis

InfoGAN – unsupervised attribute extraction

In the previous sections, we have learned how to use auxiliary information such as the labels of data to improve the image quality generated by GANs. However, it is not always possible to prepare accurate labels of training samples beforehand. Sometimes, it is even difficult for us to accurately describe the labels of extremely complex data. In this section, we will introduce another excellent model from the GAN family, InfoGAN, which is capable of extracting data attributes during training in an unsupervised manner. InfoGAN was proposed by Xi Chen, Yan Duan, Rein Houthooft, et. al. in their paper, InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets. It showed that GANs could not only learn to generate realistic samples but also learn semantic features, which are essential to sample...