Book Image

Mastering PyTorch

By : Ashish Ranjan Jha
Book Image

Mastering PyTorch

By: Ashish Ranjan Jha

Overview of this book

Deep learning is driving the AI revolution, and PyTorch is making it easier than ever before for anyone to build deep learning applications. This PyTorch book will help you uncover expert techniques to get the most out of your data and build complex neural network models. The book starts with a quick overview of PyTorch and explores using convolutional neural network (CNN) architectures for image classification. You'll then work with recurrent neural network (RNN) architectures and transformers for sentiment analysis. As you advance, you'll apply deep learning across different domains, such as music, text, and image generation using generative models and explore the world of generative adversarial networks (GANs). You'll not only build and train your own deep reinforcement learning models in PyTorch but also deploy PyTorch models to production using expert tips and techniques. Finally, you'll get to grips with training large models efficiently in a distributed manner, searching neural architectures effectively with AutoML, and rapidly prototyping models using PyTorch and fast.ai. By the end of this PyTorch book, you'll be able to perform complex deep learning tasks using PyTorch to build smart artificial intelligence models.
Table of Contents (20 chapters)
1
Section 1: PyTorch Overview
4
Section 2: Working with Advanced Neural Network Architectures
8
Section 3: Generative Models and Deep Reinforcement Learning
13
Section 4: PyTorch in Production Systems

Chapter 8: Deep Convolutional GANs

Generative neural networks have become a popular and active area of research and development. A huge amount of credit for this trend goes to a class of models that we are going to discuss in this chapter. These models are called generative adversarial networks (GANs) and were introduced in 2014. Ever since the introduction of the basic GAN model, various types of GANs have been, and are being, invented for different applications.

Essentially, a GAN is composed of two neural networks – a generator and a discriminator. Let's look at an example of the GAN that is used to generate images. For such a GAN, the task of the generator would be to generate realistic-looking fake images, and the task of the discriminator would be to tell the real images apart from the fake images.

In a joint optimization procedure, the generator would ultimately learn to generate such good fake images that the discriminator will essentially be unable to tell...