HomeMachine LearningMachine Learning EducationGuiding Books on Generative Adversarial Networks

Guiding Books on Generative Adversarial Networks

[ad_1]

Generative Adversarial Networks, or GANs for short, were first described in the 2014 paper by Ian Goodfellow, et al. titled “Generative Adversarial Networks.”

Since then, GANs have seen a lot of attention given that they are perhaps one of the most effective techniques for generating large, high-quality synthetic images.

As such, a number of books have been written about GANs, mostly focusing on how to develop and use the models in practice.

In this post, you will discover books written on Generative Adversarial Networks.

Discover how to develop DCGANs, conditional GANs, Pix2Pix, CycleGANs, and more with Keras in my new GANs book, with 29 step-by-step tutorials and full source code.

Let’s get started.

GAN Books

Most of the books have been written and released under the Packt publishing company.

Almost all of the books suffer the same problems: that is, they are generally low quality and summarize the usage of third-party code on GitHub with little original content. This particularly applies to the books from Packt.

Nevertheless, it is useful to have an idea of what books are available and the topics covered. This can be helpful both in choosing a book for self-study and to get an idea of the types of topics you may want to explore when getting started with GANs.

We will review the following seven books:

  1. GANs in Action.
  2. Generative Deep Learning.
  3. Advanced Deep Learning with Keras.
  4. Learning Generative Adversarial Networks.
  5. Generative Adversarial Networks Projects.
  6. Generative Adversarial Networks Cookbook.
  7. Hands-On Generative Adversarial Networks with Keras.

Additionally, we will also review the GAN section of two popular deep learning books.

  1. Deep Learning.
  2. Deep Learning with Python

If I have missed a book on GANs, please let me know in the comments below.

The books mostly seem to cover the same GAN architectures, such as:

  • Standard: GAN, DCGAN.
  • Conditional: cGAN, SS-GAN, InfoGAN, ACGAN.
  • Loss: WGAN, WGAN-GP, LSGAN.
  • Image Translation: Pix2Pix, CycleGAN.
  • Advanced GANs: BigGAN, PG-GAN, StyleGAN.
  • Other: StackGAN, 3DGAN, BEGAN, SRGAN, DiscoGAN, SEGAN.

Let’s take a closer look at the topics covered by each book.

1. GANs in Action

Title: GANs in Action: Deep learning with Generative Adversarial Networks

Written by Jakub Langr and Vladimir Bok, published in 2019.

https://github.com/GANs-in-Action/gans-in-action

This book provides a gentle introduction to GANs using the Keras deep learning library.

GANs in Action

Table of Contents

  • Chapter 1: Introduction to GANs
  • Chapter 2: Autoencoders as a Path to GANs
  • Chapter 3: Your First GAN: Generating Handwritten Digits
  • Chapter 4: Deep Convolutional GAN (DCGAN)
  • Chapter 5: Training and Common Challenges: GANing for Success
  • Chapter 6: Progressing with GANs
  • Chapter 7: Semi-Supervised GAN
  • Chapter 8: Conditional GAN
  • Chapter 9: CycleGaN
  • Chapter 10: Adversarial Examples
  • Chapter 11: Practical Applications of GANs
  • Chapter 12: Looking Ahead

2. Generative Deep Learning

Title: Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play

Written by David Foster, published in 2019.

Generative Deep Learning

This book focuses on the more general problem of generative modeling with deep learning, allowing variational autoencoders to be discussed. It does cover a range of GAN models, but also language modeling with LSTMs.

Amazon buy link

Table of Contents

  • Part 1: Introduction to Generative Deep Learning
    • Chapter 1. Generative Modeling
    • Chapter 2. Deep Learning
    • Chapter 3. Variational Autoencoders
    • Chapter 4. Generative Adversarial Networks
  • Part 2: Teaching Machines to Paint, Write, Compose and Play
    • Chapter 5. Paint
    • Chapter 6. Write
    • Chapter 7. Compose
    • Chapter 8. Play
    • Chapter 9. The Future of Generative Modeling

3. Advanced Deep Learning with Keras

Title: Advanced Deep Learning with Keras: Apply deep learning techniques, autoencoders, GANs, variational autoencoders, deep reinforcement learning, policy gradients, and more

Written by Rowel Atienza, published in 2018.

This book is on the more general topic of advanced deep learning with Keras, allowing the coverage of autoencoders, variational autoencoders, and deep reinforcement learning. Nevertheless, the book has four chapters on GANs and I consider it a GAN book.
https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras

Advanced Deep Learning with Keras

Table of Contents

  • Chapter 1: Introducing Advanced Deep Learning with Kera
  • Chapter 2: Deep Neural Networks
  • Chapter 3: Autoencoders
  • Chapter 4: Generative Adversarial Networks (GANs)
  • Chapter 5: Improved GANs
  • Chapter 6: Disentangled Representation GANs
  • Chapter 7: Cross-Domain GANs
  • Chapter 8: Variational Autoencoders (VAEs)
  • Chapter 9: Deep Reinforcement Learning
  • Chapter 10: Policy Gradient Methods

4. Learning Generative Adversarial Networks

Title: Learning Generative Adversarial Networks: Next-generation deep learning simplified.

Written by Kuntal Ganguly, published in 2017.

This book provides a very simple introduction to GANs. The book may have been removed or unpublished by Packt and replaced with a video course.
https://github.com/PacktPublishing/Learning-Generative-Adversarial-Networks

Learning Generative Adversarial Networks

Table of Contents

  • Chapter 1: Introduction to Deep Learning
  • Chapter 2: Unsupervised Learning with GAN
  • Chapter 3: Transfer Image Style Across Various Domains
  • Chapter 4: Building Realistic Images from Your Text
  • Chapter 5: Using Various Generative Models to Generate Images
  • Chapter 6: Taking Machine Learning to Production

5. Generative Adversarial Networks Projects

Title: Generative Adversarial Networks Projects: Build next-generation generative models using TensorFlow and Keras.

Written by Kailash Ahirwar, published in 2019.

This book summarizes a range of GANs with code examples in Keras.
https://github.com/PacktPublishing/Generative-Adversarial-Networks-Projects

Generative Adversarial Networks Projects

Table of Contents

  • Chapter 1: Introduction to Generative Adversarial Networks
  • Chapter 2: 3D-GAN – Generating Shapes Using GANs
  • Chapter 3: Face Aging Using Conditional GAN
  • Chapter 4: Generating Anime Characters Using DCGANs
  • Chapter 5: Using SRGANs to Generate Photo-Realistic Images
  • Chapter 6: StackGAN – Text to Photo-Realistic Image Synthesis
  • Chapter 7: CycleGAN – Turn Painting into Photos
  • Chapter 8: Conditional GAN – Image-to-Image Translation Using Conditional Adversarial Networks
  • Chapter 9: Predicting the Future of GANs

6. Generative Adversarial Networks Cookbook

Title: Generative Adversarial Networks Cookbook: Over 100 recipes to build generative models using Python, TensorFlow, and Keras

Written by Josh Kalin, published in 2018.
https://github.com/PacktPublishing/Generative-Adversarial-Networks-Cookbook

Generative Adversarial Networks Cookbook

Table of Contents

  • Chapter 1: What is a Generative Adversarial Network
  • Chapter 2: Data First, Easy Environment, and Data Prep
  • Chapter 3: My First GAN in Under 100 Lines
  • Chapter 4: Dreaming of New Outdoor Structures Using DCGAN
  • Chapter 5: Pix2Pix Image-to-Image Translation
  • Chapter 6: Style Transferring Your Image Using CycleGAN
  • Chapter 7: Using Simulated Images to Create Photo-Realistic Eyeballs with SimGAN
  • Chapter 8: From Image to 3D Models Using GANs

7. Hands-On Generative Adversarial Networks with Keras

Title: Hands-On Generative Adversarial Networks with Keras: Your guide to implementing next-generation generative adversarial networks

Written by Rafael Valle, published in 2019.

This may be one of the better Packt published books as the code appears to be better quality and a wider array of GANs are covered.
https://github.com/PacktPublishing/Hands-On-Generative-Adversarial-Networks-with-Keras

Hands-On Generative Adversarial Networks with Keras

Table of Contents

  • Section 1: Introduction and Environmental Setup
    • Chapter 1: Deep Learning Basics and Environment Setup
    • Chapter 2: Introduction to Generative Models
  • Section 2: Training GANs
    • Chapter 3: Training GANs
    • Chapter 4: Evaluating Your First GAN
    • Chapter 5: Improving Your First GAN
  • Section 3: Applications of GANS in Computer Vision, Natural Language Processing and Audio
    • Chapter 6: Synthesizing and Manipulating Images with GANs
    • Chapter 7: Progressive Growing of GANs
    • Chapter 8: Generation of Discrete Sequences Using GANs
    • Chapter 9: Text-to-Image Synthesis with GANs
    • Chapter 10: Speech Enhancement with GANs
    • Chapter 11: TequilaGAN – Identifying GAN Samples
    • Chapter 12: What’s next in GANs

GANs in Other Books

The topic of GANs has been covered in other modern books on deep learning.

Two important examples are listed below.

8. Deep Learning

GANs were described in the 2016 textbook titled “Deep Learning” by Ian Goodfellow, et al., specifically:

  • Chapter 20: Deep Generative Models.

Section 20.10.4 titled “Generative Adversarial Networks” provides a short introduction to GANs at the time of writing, two years after the original paper.

It would be great to see Goodfellow write a dedicated textbook on the topic sometime in the future.

Deep Learning

9. Deep Learning with Python

GANs were also covered by Francois Chollet in his 2017 book titled “Deep Learning with Python“, specifically:

  • Chapter 8: Generative Deep Learning.

In Section 8.5 titled “Introduction to generative adversarial networks,” the topic of GANs is introduced and a worked example of developing a GAN for one image class (frogs) in the CIFAR-10 dataset is covered. Source code is provided here:
https://github.com/fchollet/deep-learning-with-python-notebooks

Deep Learning with Python

Summary

In this post, you discovered a suite of books on the topic of Generative Adversarial Networks, or GANs.

Have you read any of the listed books?
[ad_2]

This article has been published from the source link without modifications to the text. Only the headline has been changed.

Source link

Most Popular