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!Tell Me More!
This is not a typical book: most tutorials start with some nice and pretty image classification problem to illustrate how to use PyTorch. It may seem cool, but I believe it distracts you from the main goal: how PyTorch works? In this book, I present a structured, incremental, and from first principles approach to learn PyTorch (and get to the pretty image classification problem in due time).
Moreover, this is not a formal book in any way: I am writing this book as if I were having a conversation with you, the reader. I will ask you questions (and give you answers shortly afterward) and I will also make (silly) jokes.
My job here is to make you understand the topic, so I will avoid fancy mathematical notation as much as possible and spell it out in plain English.
The book covers from the basics of gradient descent all the way up to fine-tuning large NLP models (BERT and GPT-2) using HuggingFace.
It is divided into four parts:
The FULL guide contains ALL the content from Volumes I, II, and III!
In the first volume of the series, you’ll be introduced to the fundamentals of PyTorch: autograd, model classes, datasets, data loaders, and more.
If you have absolutely no experience with PyTorch, this is your starting point.
By the time you finish this volume, you’ll have a thorough understanding of the concepts and tools necessary to start developing and training your own models using PyTorch.
In the second volume of the series, you’ll be introduced to deeper models and activation functions, convolutional neural networks, initialization schemes, learning rate schedulers, transfer learning, and more.
If your goal is to learn about deep learning models for computer vision, and you’re already comfortable training simple models in PyTorch, the second volume is the right one for you.
In this third volume of the series, you’ll be introduced to all things sequence-related: recurrent neural networks and their variations, sequence-to-sequence models, attention, self-attention, and Transformers.
This volume also includes a crash course on natural language processing (NLP), from the basics of word tokenization all the way up to fine-tuning large models (BERT and GPT-2) using the HuggingFace library.
This volume is more demanding than the other two, and you’re going to enjoy it more if you already have a solid understanding of deep learning models.
Machine Learning Engineer at Micron Technology, Smart Manufacturing and AI
"I am usually really picky in choosing books about ML/DL but I have to tell you, this book was one of the best books I have ever invested in. I cannot thank you enough for writing a book that gives so much clarity on the explanations of the inner workings of many DL techniques. Thank you so much and I hope you come up with even better books on other ML topics in the future."
Lead Data Scientist & Author, DL & NLP Workshop
"As an author myself who've co-authored two books in Deep Learning & NLP space, I'm extremely impressed by Daniel's step-by-step pedagogical approach. Starting with a toy problem and gradually building abstractions on top of each other massively helps beginner to understand the nuts and bolts of each models and neural architectures be it basic or advanced! Daniel has justified "step-by-step" part from the title in a true sense. Highly recommended!"
President of Blue Owl Press
"I am impressed! Your books are superb. Well laid out, nicely formatted, easy to read. The material is straightforward, complete, and correct."
The book’s official repository is available on GitHub:
It contains one Jupyter notebook for every chapter in this book. Each notebook contains all the code shown in its corresponding chapter, and you should be able to run its cells in sequence to get the same outputs, as shown in the book. I strongly believe that being able to reproduce the results brings confidence to the reader.
|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|
|Chapter 4 - Classifying Images|
|Chapter 5 - Convolutions|
|Chapter 6 - Rock, Paper, Scissors|
|Chapter 7 - Transfer Learning|
|Chapter Extra - Vanishing and Exploding Gradients|
|Chapter 8 - Sequences|
|Chapter 9 - Sequence-to-Sequence|
|Chapter 10 - Transform and Roll Out|
|Chapter 11 - Down the Yellow Brick Rabbit Hole|