Generative Adversarial Networks Projects by Ahirwar, Kailash -- Read -- Imperial Library of Trantor

Index

Title Page Copyright and Credits

Generative Adversarial Networks Projects

About Packt

Why subscribe? Packt.com

Contributors

About the author About the reviewer Packt is searching for authors like you

Preface

Who this book is for What this book covers To get the most out of this book

Download the example code files Conventions used

Get in touch

Reviews

Introduction to Generative Adversarial Networks

What is a GAN?

What is a generator network? What is a discriminator network? Training through adversarial play in GANs

Practical applications of GANs The detailed architecture of a GAN

The architecture of the generator The architecture of the discriminator Important concepts related to GANs

Kullback-Leibler divergence Jensen-Shannon divergence Nash equilibrium Objective functions

Scoring algorithms

The inception score The Fréchet inception distance

Variants of GANs

Deep convolutional generative adversarial networks StackGANs CycleGANs 3D-GANs Age-cGANs pix2pix

Advantages of GANs Problems with training GANs

Mode collapse Vanishing gradients Internal covariate shift

Solving stability problems when training GANs

Feature matching Mini-batch discrimination Historical averaging One-sided label smoothing Batch normalization Instance normalization

Summary

3D-GAN - Generating Shapes Using GANs

Introduction to 3D-GANs

3D convolutions The architecture of a 3D-GAN

The architecture of the generator network The architecture of the discriminator network

Objective function Training 3D-GANs

Setting up a project Preparing the data

Download and extract the dataset Exploring the dataset

What is a voxel? Loading and visualizing a 3D image Visualizing a 3D image

A Keras implementation of a 3D-GAN

The generator network The discriminator network

Training a 3D-GAN

Training the networks Saving the models Testing the models Visualizing losses Visualizing graphs

Hyperparameter optimization Practical applications of 3D-GANs Summary

Face Aging Using Conditional GAN

Introducing cGANs for face aging

Understanding cGANs The architecture of the Age-cGAN

The encoder network The generator network The discriminator network Face recognition network

Stages of the Age-cGAN

Conditional GAN training

The training objective function

Initial latent vector approximation Latent vector optimization

Setting up the project Preparing the data

Downloading the dataset Extracting the dataset

A Keras implementation of an Age-cGAN

The encoder network The generator network The discriminator network

Training the cGAN

Training the cGAN Initial latent vector approximation Latent vector optimization Visualizing the losses Visualizing the graphs

Practical applications of Age-cGAN Summary

Generating Anime Characters Using DCGANs

Introducing to DCGANs

Architectural details of a DCGAN

Configuring the generator network Configuring the discriminator network

Setting up the project Downloading and preparing the anime characters dataset

Downloading the dataset Exploring the dataset Cropping and resizing images in the dataset

Implementing a DCGAN using Keras

Generator Discriminator

Training the DCGAN

Loading the samples Building and compiling the networks Training the discriminator network Training the generator network Generating images Saving the model Visualizing generated images Visualizing losses Visualizing graphs Tuning the hyperparameters

Practical applications of DCGAN Summary

Using SRGANs to Generate Photo-Realistic Images

Introducing SRGANs

The architecture of SRGANs

The architecture of the generator network The architecture of the discriminator network

The training objective function

Content loss

Pixel-wise MSE loss VGG loss

Adversarial loss

Setting up the project Downloading the CelebA dataset The Keras implementation of SRGAN

The generator network The discriminator network VGG19 network The adversarial network

Training the SRGAN

Building and compiling the networks Training the discriminator network Training the generator network Saving the models Visualizing generated images Visualizing losses Visualizing graphs

Practical applications of SRGANs Summary

StackGAN - Text to Photo-Realistic Image Synthesis

Introduction to StackGAN Architecture of StackGAN

The text encoder network The conditioning augmentation block

Getting the conditioning augmentation variable

Stage-I

The generator network The discriminator network Losses for Stage-I of StackGAN

Stack-II

The generator network The discriminator network Losses for Stage-II of StackGAN

Setting up the project Data preparation

Downloading the dataset Extracting the dataset Exploring the dataset

A Keras implementation of StackGAN

Stage-I

Text encoder network Conditional augmentation network The generator network The discriminator network The adversarial model

Stage-II

Generator network

Downsampling blocks The residual blocks Upsampling Blocks

The discriminator network

Downsampling blocks The concatenation block The fully connected classifier

Training a StackGAN

Training the Stage-I StackGAN

Loading the dataset Creating models Training the model

Training the Stage-II StackGAN

Loading the dataset Creating models Training the model

Visualizing the generated images Visualizing losses Visualizing the graphs

Practical applications of StackGAN Summary

CycleGAN - Turn Paintings into Photos

An introduction to CycleGANs

The architecture of a CycleGAN

The architecture of the generator The architecture of the discriminator

The training objective function

Adversarial loss Cycle consistency loss Full objective function

Setting up the project Downloading the dataset Keras implementation of CycleGAN

The generator network The discriminator network

Training the CycleGAN

Loading the dataset Building and compiling the networks

Creating and compiling an adversarial network

Starting the training

Training the discriminator networks Training the adversarial network

Saving the model Visualizing the images generated Visualizing losses Visualizing the graphs

Practical applications of CycleGANs Summary Further reading

Conditional GAN - Image-to-Image Translation Using Conditional Adversarial Networks

Introducing Pix2pix

The architecture of pix2pix

The generator network

The encoder network The decoder network

The discriminator network

The training objective function

Setting up the project Preparing the data

Visualizing images

A Keras implementation of pix2pix

The generator network The discriminator network The adversarial network

Training the pix2pix network

Saving the models Visualizing the generated images Visualizing the losses Visualizing the graphs

Practical applications of a pix2pix network Summary

Predicting the Future of GANs

Our predictions about the future of GANs

Improving existing deep learning methods The evolution of the commercial applications of GANs Maturation of the GAN training process

Potential future applications of GANs

Creating infographics from text Generating website designs Compressing data Drug discovery and development GANs for generating text GANs for generating music

Exploring GANs Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

← Prev
Back
Next →

← Prev
Back
Next →