Cover image for GANs in Action

GANs in Action

Author Jakub Langr , Vladimir Bok
Release Date: 2019/09/01
ISBN: 9781617295560
Topic:
0%
30
Chapters
0-1
Hours read
0k
Total Words
    Start Reading Now    
       Add to Wishlist       
View table of contents

Book Description

GANs in Action teaches you to build and train your own Generative Adversarial Networks. You’ll start by creating simple generator and discriminator networks that are the foundation of GAN architecture. Then, following numerous hands-on examples, you’ll train GANs to generate high-resolution images, image-to-image translation, and targeted data generation. Along the way, you’ll find pro tips for making your system smart, effective, and fast.

Table of Contents

  1. Copyright
  2. Brief Table of Contents
  3. Table of Contents
  4. Preface
  5. Acknowledgments
  6. About this book
  7. About the cover illustration
  8. Part 1. Introduction to GANs and generative modeling
    1. Chapter 1. Introduction to GANs
      1. 1.1. What are Generative Adversarial Networks?
      2. 1.2. How do GANs work?
      3. 1.3. GANs in action
      4. 1.4. Why study GANs?
      5. Summary
    2. Chapter 2. Intro to generative modeling with autoencoders
      1. 2.1. Introduction to generative modeling
      2. 2.2. How do autoencoders function on a high level?
      3. 2.3. What are autoencoders to GANs?
      4. 2.4. What is an autoencoder made of?
      5. 2.5. Usage of autoencoders
      6. 2.6. Unsupervised learning
      7. 2.7. Code is life
      8. 2.8. Why did we try aGAN?
      9. Summary
    3. Chapter 3. Your first GAN: Generating handwritten digits
      1. 3.1. Foundations of GANs: Adversarial training
      2. 3.2. The Generator and the Discriminator
      3. 3.3. GAN training algorithm
      4. 3.4. Tutorial: Generating handwritten digits
      5. 3.5. Conclusion
      6. Summary
    4. Chapter 4. Deep Convolutional GAN
      1. 4.1. Convolutional neural networks
      2. 4.2. Brief history of the DCGAN
      3. 4.3. Batch normalization
      4. 4.4. Tutorial: Generating handwritten digits with DCGAN
      5. 4.5. Conclusion
      6. Summary
  9. Part 2. Advanced topics in GANs
    1. Chapter 5. Training and common challenges: GANing for success
      1. 5.1. Evaluation
      2. 5.2. Training challenges
      3. 5.3. Summary of game setups
      4. 5.4. Training hacks
      5. Summary
    2. Chapter 6. Progressing with GANs
      1. 6.1. Latent space interpolation
      2. 6.2. They grow up so fast
      3. 6.3. Summary of key innovations
      4. 6.4. TensorFlow Hub and hands-on
      5. 6.5. Practical applications
      6. Summary
    3. Chapter 7. Semi-Supervised GAN
      1. 7.1. Introducing the Semi-Supervised GAN
      2. 7.2. Tutorial: Implementing a Semi-Supervised GAN
      3. 7.3. Comparison to a fully supervised classifier
      4. 7.4. Conclusion
      5. Summary
    4. Chapter 8. Conditional GAN
      1. 8.1. Motivation
      2. 8.2. What is Conditional GAN?
      3. 8.3. Tutorial: Implementing a Conditional GAN
      4. 8.4. Conclusion
      5. Summary
    5. Chapter 9. CycleGAN
      1. 9.1. Image-to-image translation
      2. 9.2. Cycle-consistency loss: There and back aGAN
      3. 9.3. Adversarial loss
      4. 9.4. Identity loss
      5. 9.5. Architecture
      6. 9.6. Object-oriented design of GANs
      7. 9.7. Tutorial: CycleGAN
      8. 9.8. Expansions, augmentations, and applications
      9. Summary
  10. Part 3. Where to go from here
    1. Chapter 10. Adversarial examples
      1. 10.1. Context of adversarial examples
      2. 10.2. Lies, damned lies, and distributions
      3. 10.3. Use and abuse of training
      4. 10.4. Signal and the noise
      5. 10.5. Not all hope is lost
      6. 10.6. Adversaries to GANs
      7. 10.7. Conclusion
      8. Summary
    2. Chapter 11. Practical applications of GANs
      1. 11.1. GANs in medicine
      2. 11.2. GANs in fashion
      3. 11.3. Conclusion
      4. Summary
    3. Chapter 12. Looking ahead
      1. 12.1. Ethics
      2. 12.2. GAN innovations
      3. 12.3. Further reading
      4. 12.4. Looking back and closing thoughts
      5. Summary
  11. Training Generative Adversarial Networks (GANs)
  12. Index
  13. List of Figures
  14. List of Tables
  15. List of Listings