Deep Learning with PyTorch Step-by-Step

Why this book?

Are you looking for a book where you can learn about deep learning and PyTorch without having to spend hours deciphering cryptic text and code? A technical book that’s also easy and enjoyable to read?

This is it!

How is this book different?

• First, this book presents an easy-to-follow, structured, incremental, and from-first-principles approach to learning PyTorch.
• Second, this is a rather informal book: It is written as if you, the reader, were having a conversation with Daniel, the author.
• His job is to make you understand the topic well, so he avoids fancy mathematical notation as much as possible and spells everything out in plain English.

What will I learn?

In this first volume of the series, you’ll be introduced to the fundamentals of PyTorch: autograd, model classes, datasets, data loaders, and more. You will develop, step-by-step, not only the models themselves but also your understanding of them.

By the time you finish this book, you’ll have a thorough understanding of the concepts and tools necessary to start developing and training your own models using PyTorch.

If you have absolutely no experience with PyTorch, this is your starting point.

Table of Contents

Part I: Fundamentals

Chapter 0: Visualizing Gradient Descent

Chapter 1: A Simple Regression Problem

Chapter 2: Rethinking the Training Loop

Chapter 2.1: Going Classy

Chapter 3: A Simple Classification Problem

Part II: Computer Vision

Chapter 4: Classifying Images

Bonus Chapter: Feature Space

Chapter 5: Convolutions

Chapter 6: Rock, Paper, Scissors

Chapter 7: Transfer Learning

Extra Chapter: Vanishing and Exploding Gradients

Part Ill: Sequences

Chapter 8: Sequences

Chapter 9 – Part I: Sequence-to-Sequence

Chapter 9 – Part II: Sequence-to-Sequence

Chapter 10: Transform and Roll Out

Part IV: Natural Language Processing

Chapter 11: Down the Yellow Brick Rabbit Hole

About the Author

Daniel Voigt Godoy is a data scientist, developer, writer, and teacher. He has been teaching machine learning and distributed computing technologies at Data Science Retreat, the longest-running Berlin-based bootcamp, since 2016, helping more than 150 students advance their careers.

Daniel is also the main contributor of two Python packages: HandySpark and DeepReplay.

His professional background includes 20 years of experience working for companies in several industries: banking, government, fintech, retail, and mobility.