万本电子书0元读

万本电子书0元读

顶部广告

Generative Adversarial Networks Projects电子书

售       价:¥

2人正在读 | 0人评论 9.8

作       者:Kailash Ahirwar

出  版  社:Packt Publishing

出版时间:2019-01-31

字       数:33.6万

所属分类: 进口书 > 外文原版书 > 电脑/网络

温馨提示:数字商品不支持退换货,不提供源文件,不支持导出打印

为你推荐

  • 读书简介
  • 目录
  • 累计评论(0条)
  • 读书简介
  • 目录
  • 累计评论(0条)
Explore various Generative Adversarial Network architectures using the Python ecosystem Key Features * Use different datasets to build advanced projects in the Generative Adversarial Network domain * Implement projects ranging from generating 3D shapes to a face aging application * Explore the power of GANs to contribute in open source research and projects Book Description Generative Adversarial Networks (GANs) have the potential to build next-generation models, as they can mimic any distribution of data. Major research and development work is being undertaken in this field since it is one of the rapidly growing areas of machine learning. This book will test unsupervised techniques for training neural networks as you build seven end-to-end projects in the GAN domain. Generative Adversarial Network Projects begins by covering the concepts, tools, and libraries that you will use to build efficient projects. You will also use a variety of datasets for the different projects covered in the book. The level of complexity of the operations required increases with every chapter, helping you get to grips with using GANs. You will cover popular approaches such as 3D-GAN, DCGAN, StackGAN, and CycleGAN, and you’ll gain an understanding of the architecture and functioning of generative models through their practical implementation. By the end of this book, you will be ready to build, train, and optimize your own end-to-end GAN models at work or in your own projects. What you will learn * Train a network on the 3D ShapeNet dataset to generate realistic shapes * Generate anime characters using the Keras implementation of DCGAN * Implement an SRGAN network to generate high-resolution images * Train Age-cGAN on Wiki-Cropped images to improve face verification * Use Conditional GANs for image-to-image translation * Understand the generator and discriminator implementations of StackGAN in Keras Who this book is for If you’re a data scientist, machine learning developer, deep learning practitioner, or AI enthusiast looking for a project guide to test your knowledge and expertise in building real-world GANs models, this book is for you.
目录展开

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

累计评论(0条) 0个书友正在讨论这本书 发表评论

发表评论

发表评论,分享你的想法吧!

买过这本书的人还买过

读了这本书的人还在读

回顶部