You're reading from Mastering PyTorch Build powerful neural network architectures using advanced PyTorch 1.x features

Product type Paperback

Published in Feb 2021

Publisher Packt

ISBN-13 9781789614381

Length 450 pages

Edition 1st Edition

Languages

Python

Tools

PyTorch

Concepts

Deep Learning

Author (1):

Ashish Ranjan Jha

View More author details

Table of Contents (20) Chapters

Preface

1. Section 1: PyTorch Overview

2. Chapter 1: Overview of Deep Learning using PyTorch FREE CHAPTER

3. Chapter 2: Combining CNNs and LSTMs

4. Section 2: Working with Advanced Neural Network Architectures

5. Chapter 3: Deep CNN Architectures

6. Chapter 4: Deep Recurrent Model Architectures

7. Chapter 5: Hybrid Advanced Models

8. Section 3: Generative Models and Deep Reinforcement Learning

9. Chapter 6: Music and Text Generation with PyTorch

10. Chapter 7: Neural Style Transfer

11. Chapter 8: Deep Convolutional GANs

12. Chapter 9: Deep Reinforcement Learning

13. Section 4: PyTorch in Production Systems

14. Chapter 10: Operationalizing PyTorch Models into Production

15. Chapter 11: Distributed Training

16. Chapter 12: PyTorch and AutoML

17. Chapter 13: PyTorch and Explainable AI

18. Chapter 14: Rapid Prototyping with PyTorch

19. Other Books You May Enjoy

Leave a review - let other readers know what you think

Summary

GANs have been an active area of research and development in recent years, ever since their inception in 2014. This chapter was an exploration of the concepts behind GANs, including the components of GANs, namely, the generator and the discriminator. We discussed the architectures of each of these components and the overall schematic of a GAN model.

Next, we did a deep dive into a particular type of GAN – the DCGAN. With the help of an exercise, we built a DCGAN model from scratch using PyTorch. We used the MNIST dataset to train the model. The generator of the trained DCGAN model successfully generated realistic-looking fake images of handwritten digits after 10 epochs of training.

In the last section of this chapter, we explored another type of GAN, which is used for the task of image-to-image translation – the pix2pix model. Instead of working on just a pair of images, the pix2pix GAN model is architectured to generalize any image-to-image translation...