Textbook in PDF format

This book is intended to be a starting point for software engineers, data scientists, and motivated students who are fluent in Python and want to become comfortable using PyTorch to build deep learning projects. To that end, we take a hands-on approach; we encourage you to keep your computer at the ready so that you can play with the examples and take them a step further.
Though we stress the practical applications, we also believe that providing an accessible introduction to foundational deep learning tools like PyTorch is more than a way to facilitate the acquisition of new technical skills. It is also a step toward equipping a new generation of scientists, engineers, and practitioners from a wide range of disciplines with a working knowledge of the tools that will be the backbone of many software projects during the decades to come.
To get the most out of this book, you need two things:
Some experience programming in Python — We’re not going to pull any punches on that one: you’ll need to be up on Python data types, classes, floating-point numbers, and the like.
Willingness to dive in and get your hands dirty — It’ll be much easier for you to learn if you follow along with us.
Deep learning is a huge space. In this book, we’ll be covering a tiny part of that space — specifically, using PyTorch for smaller-scope projects. Most of the motivating examples use image processing of 2D and 3D data sets. We focus on practical PyTorch, with the aim of covering enough ground to allow you to solve realistic problems with deep learning or explore new models as they pop up in research literature