Book Image

Generative Adversarial Networks Projects

By : Kailash Ahirwar
Book Image

Generative Adversarial Networks Projects

By: Kailash Ahirwar

Overview of this book

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.

Related Content you might be interested in

Current Title:

Small book image
Generative Adversarial Networks Projects
Kailash Ahirwar
Jan, 2019 | 316 pages
Small book image
Hands-On Generative Adversarial Networks with PyTorch 1.x
Greg Walters | John Hany
Dec, 2019 | 312 pages
Small book image
Hands-On Image Generation with TensorFlow
Soon Yau Cheong
Dec, 2020 | 306 pages
Small book image
Hands-On Generative Adversarial Networks with Keras
Rafael Valle
May, 2019 | 272 pages
Table of Contents (11 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Introduction to Generative Adversarial Networks
Introduction to Generative Adversarial Networks
What is a GAN?
Practical applications of GANs
The detailed architecture of a GAN
Variants of GANs
Advantages of GANs
Problems with training GANs
Solving stability problems when training GANs
Summary
2
3D-GAN - Generating Shapes Using GANs
3D-GAN - Generating Shapes Using GANs
Introduction to 3D-GANs
Setting up a project
Preparing the data
A Keras implementation of a 3D-GAN
Training a 3D-GAN
Hyperparameter optimization
Practical applications of 3D-GANs
Summary
3
Face Aging Using Conditional GAN
Face Aging Using Conditional GAN
Introducing cGANs for face aging
Setting up the project
Preparing the data
A Keras implementation of an Age-cGAN
Training the cGAN
Practical applications of Age-cGAN
Summary
4
Generating Anime Characters Using DCGANs
Generating Anime Characters Using DCGANs
Introducing to DCGANs
Setting up the project
Downloading and preparing the anime characters dataset
Implementing a DCGAN using Keras
Training the DCGAN
Practical applications of DCGAN
Summary
5
Using SRGANs to Generate Photo-Realistic Images
Using SRGANs to Generate Photo-Realistic Images
Introducing SRGANs
Setting up the project
Downloading the CelebA dataset
The Keras implementation of SRGAN
Training the SRGAN
Practical applications of SRGANs
Summary
6
StackGAN - Text to Photo-Realistic Image Synthesis
StackGAN - Text to Photo-Realistic Image Synthesis
Introduction to StackGAN
Architecture of StackGAN
Setting up the project
Data preparation
A Keras implementation of StackGAN
Training a StackGAN
Practical applications of StackGAN
Summary
7
CycleGAN - Turn Paintings into Photos
CycleGAN - Turn Paintings into Photos
An introduction to CycleGANs
Setting up the project
Downloading the dataset
Keras implementation of CycleGAN
Training the CycleGAN
Practical applications of CycleGANs
Summary
Further reading
8
Conditional GAN - Image-to-Image Translation Using Conditional Adversarial Networks
Conditional GAN - Image-to-Image Translation Using Conditional Adversarial Networks
Introducing Pix2pix
Setting up the project
Preparing the data
A Keras implementation of pix2pix
Training the pix2pix network
Practical applications of a pix2pix network
Summary
9
Predicting the Future of GANs
Predicting the Future of GANs
Our predictions about the future of GANs
Potential future applications of GANs
Exploring GANs
Summary
10
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Hyperparameter optimization

The model that we trained might not be a perfect model, but we can optimize the hyperparameters to improve it. There are many hyperparameters in a 3D-GAN that can be optimized. These include the following:

  • Batch size: Experiment with values of 8, 16, 32, 54, or 128 for the batch size.
  • The number of epochs: Experiment with 100 epochs and gradually increase it to 1,000-5,000.
  • Learning rate: This is the most important hyperparameter. Experiment with 0.1, 0.001, 0.0001, and other small learning rates.
  • Activation functions in different layers of the generator and the discriminator network: Experiment with sigmoid, tanh, ReLU, LeakyReLU, ELU, SeLU, and other activation functions.
  • The optimization algorithm: Experiment with Adam, SGD, Adadelta, RMSProp, and other optimizers available in the Keras framework.
  • Loss functions: Binary cross entropy is the loss...
Previous Section
End of Section 7
Next Section