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

The discriminator's purpose is to determine whether the generated sample is real or fake—there's a balance to strike in order to make sure the discriminator is just good enough to keep the generator moving in the right direction. The discriminator class we'll use is 3D convolutions to determine whether 3D samples are real or fake.

Getting ready

The generator is now complete and we're moving on to develop the discriminator class. In the src folder, add the discriminator.py file.

You should have the following directory structure:

├── data
├── docker
│   ├── build.sh
│   ├── clean.sh
│   ├── Dockerfile
│   └── kaggle.json
├── out
├── README.md
├── run_autoencoder.sh
└── src
    ├── discriminator.py
    ├── encoder_model.h5
    ├── encoder.py
    ├── generator.py
    ├── x_test_encoded.npy
    └── x_train_encoded.npy

How to do it...

The Discriminator class needs an initialization step, a block method, a model method, and a summary method. The following recipe...

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...