Generative Adversarial Networks Cookbook

Generative Adversarial Networks Cookbook

By : Josh Kalin

Buy this Book

Generative Adversarial Networks Cookbook

By: Josh Kalin

Buy this Book

Overview of this book

Developing Generative Adversarial Networks (GANs) is a complex task, and it is often hard to find code that is easy to understand. This book leads you through eight different examples of modern GAN implementations, including CycleGAN, simGAN, DCGAN, and 2D image to 3D model generation. Each chapter contains useful recipes to build on a common architecture in Python, TensorFlow and Keras to explore increasingly difficult GAN architectures in an easy-to-read format. The book starts by covering the different types of GAN architecture to help you understand how the model works. This book also contains intuitive recipes to help you work with use cases involving DCGAN, Pix2Pix, and so on. To understand these complex applications, you will take different real-world data sets and put them to use. By the end of this book, you will be equipped to deal with the challenges and issues that you may face while working with GAN models, thanks to easy-to-follow code solutions that you can implement right away.

Title Page

About Packt

Dedication

Contributors

Preface

Dedication2

Free Chapter

What Is a Generative Adversarial Network?

Introduction

Generative and discriminative models

A neural network love story

Deep neural networks

Architecture structure basics

Basic building block – generator

Basic building block – discriminator

Basic building block – loss functions

Training

GAN pieces come together in different ways

What does a GAN output?

Understanding the benefits of a GAN structure

Exercise

Data First, Easy Environment, and Data Prep

Introduction

Is data that important?

But first, set up your development environment

My First GAN in Under 100 Lines

Introduction

From theory to code – a simple example

Building a neural network in Keras and TensorFlow

Explaining your first GAN component – discriminator

Explaining your second GAN component – generator

Putting all the GAN pieces together

Training your first GAN

Training the model and understanding the GAN output

Exercise

Dreaming of New Outdoor Structures Using DCGAN

Introduction

What is DCGAN? A simple pseudocode example

Tools – do I need any unique tools?

Parsing the data – is our data unique?

Code implementation – generator

Code implementation – discriminator

Training

Evaluation – how do we know it worked?

Adjusting parameters for better performance

Exercise

Pix2Pix Image-to-Image Translation

Introduction

Introducing Pix2Pix with pseudocode

Parsing our dataset

Code implementation – generator

Code – the GAN network

Code implementation – discriminator

Training

Exercise

Style Transfering Your Image Using CycleGAN

Introduction

Pseudocode – how does it work?

Parsing the CycleGAN dataset

Code implementation – generator

Code implementation – discriminator

Code implementation – GAN

On to training

Exercise

Using Simulated Images To Create Photo-Realistic Eyeballs with SimGAN

Introduction

How SimGAN architecture works

Pseudocode – how does it work?

How to work with training data

Code implementation – loss functions

Code implementation – generator

Code implementation – discriminator

Code implementation – GAN

Training the simGAN network

Exercise

From Image to 3D Models Using GANs

Introduction

Introduction to using GANs in order to produce 3D models

Environment preparation

Encoding 2D data and matching to 3D objects

Code implementation – generator

Code implementation – discriminator

Code implementation – GAN

Training this model

Exercise

Other Books You May Enjoy

Leave a review - let other readers know what you think

Index

Customer Reviews

5 star

4 star

3 star

2 star

1 star

Code implementation – discriminator

Discriminators are the bread and butter of the discriminative modeling world—it's funny that we use them in such a unique way. Each discriminator that're designed is built to understand the difference between real and fake data but not too well. Why? If the discriminator could always tell the difference between the two types of data then the generator would never improve consistently. The next discriminator, based on the CycleGAN paper, will use a structure heavily based on their original implementation.

Getting ready

Your directory structure should look like the following tree:

├── data
│   ├── 
├── docker
│   ├── build.sh
│   ├── clean.sh
│   └── Dockerfile
├── README.md
├── run.sh
├── scripts
│   └── create_data.sh
├── src
│   ├── discriminator.py
│   ├── generator.py

How to do it...

The discriminator takes the image as input and outputs a decision (real or fake). We'll cover the general construction of the discriminator class (hint: it'll look pretty similar...

Generative Adversarial Networks Cookbook

By : Josh Kalin

Generative Adversarial Networks Cookbook

By: Josh Kalin

Overview of this book

Related Content you might be interested in

Current Title:

Generative Adversarial Networks Cookbook

Generative Adversarial Networks Projects

Keras Deep Learning Cookbook

Hands-On Generative Adversarial Networks with Keras

Code implementation – discriminator

Getting ready

How to do it...