This book is meant for readers who want to understand GANs without the need for a strong mathematical background. Moreover, it covers the practical applications of GANs, making it an excellent resource for beginners. A Primer on Generative Adversarial Networks is suitable for researchers, developers, students, and anyone who wishes to learn about GANs. It is assumed that the reader has a basic understanding of machine learning and neural networks. The book comes with ready-to-run scripts that readers can use for further research. Python is used as the primary programming language, so readers should be familiar with its basics.The book starts by providing an overview of GAN architecture, explaining the concept of generative models. It then introduces the most straightforward GAN architecture, which explains how GANs work and covers the concepts of generator and discriminator. The book then goes into the more advanced real-world applications of GANs, such as human face generation, deep fake, CycleGANs, and more.
By the end of the book, readers will have an essential understanding of GANs and be able to write their own GAN code. They can apply this knowledge to their projects, regardless of whether they are beginners or experienced machine learning practitioners.
Author(s): Sanaa Kaddoura
Series: SpringerBriefs in Computer Science
Publisher: Springer
Year: 2023
Language: English
Pages: 94
City: Cham
Preface
Acknowledgments
Contents
Chapter 1: Overview of GAN Structure
1.1 Introduction
1.2 Generative Models
1.3 GANS
Overview of GAN Structure
The Discriminator
The Generator
Training the GAN
Loss Function
GANs Weaknesses
References
Chapter 2: Your First GAN
2.1 Preparing the Environment
Hardware Requirements
Software Requirements
Importing Required Modules and Libraries
Prepare and Preprocess the Dataset
2.2 Implementing the Generator
2.3 Implementing the Discriminator
2.4 Training Stage
Model Construction
Loss Function
Plot Generated Data Samples
Training GAN
Common Challenges While Implementing GANs
References
Chapter 3: Real-World Applications
3.1 Human Faces Generation
Data Collection and Preparation
Model Design
The Generator Model
The Discriminator Model
Training
Evaluation and Refinement
Deployment
3.2 Deep Fake
Data Collection and Preparation
Model Design
Training
3.3 Image-to-Image Translation
Data Collection and Preparation
Model Design
The Generator Model
The Discriminator Model
The Adversarial Network
Training
3.4 Text to Image
Module Requirements
Dataset
Data Preprocessing
Model Design
Generator Model
Discriminator Model
Adversarial Model
Training Stage
Evaluation and Refinement
3.5 CycleGAN
Dataset
Model Design
Generator Model
Discriminator Model
Training Stage
3.6 Enhancing Image Resolution
Dataset
Model Design
Generator Model
Discriminator Model
Training Stage
3.7 Semantic Image Inpainting
Dataset
Model Design
Generator Model
Discriminator Model
Training
3.8 Text to Speech
Dataset
Data Preprocessing
Model Design
Generator Model
Discriminator Model
Training
References
Chapter 4: Conclusion
