PyTorch Deep Learning Hands-On: Build CNNs, RNNs, GANs, reinforcement learning, and more, quickly and easily

Sherin Thomas

Sudhanshu Passi

€18.99 per month

2.9 (10 Ratings)

Paperback Apr 2019 250 pages 1st Edition

Sherin Thomas

Sudhanshu Passi

€18.99 per month

2.9 (10 Ratings)

Paperback Apr 2019 250 pages 1st Edition

What do you get with a Packt Subscription?

Free for first 7 days. $19.99 p/m after that. Cancel any time!

Unlimited ad-free access to the largest independent learning library in tech. Access this title and thousands more!

50+ new titles added per month, including many first-to-market concepts and exclusive early access to books as they are being written.

Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.

Thousands of reference materials covering every tech concept you need to stay up to date.

Subscribe now

View plans & pricing

View table of contents

Preview Book

Key benefits

Internals and principles of PyTorch
Implement key deep learning methods in PyTorch: CNNs, GANs, RNNs, reinforcement learning, and more
Build deep learning workflows and take deep learning models from prototyping to production

Description

PyTorch Deep Learning Hands-On is a book for engineers who want a fast-paced guide to doing deep learning work with PyTorch. It is not an academic textbook and does not try to teach deep learning principles. The book will help you most if you want to get your hands dirty and put PyTorch to work quickly. PyTorch Deep Learning Hands-On shows how to implement the major deep learning architectures in PyTorch. It covers neural networks, computer vision, CNNs, natural language processing (RNN), GANs, and reinforcement learning. You will also build deep learning workflows with the PyTorch framework, migrate models built in Python to highly efficient TorchScript, and deploy to production using the most sophisticated available tools. Each chapter focuses on a different area of deep learning. Chapters start with a refresher on how the model works, before sharing the code you need to implement it in PyTorch. This book is ideal if you want to rapidly add PyTorch to your deep learning toolset.

Who is this book for?

Machine learning engineers who want to put PyTorch to work.

What you will learn

Use PyTorch to build:
Simple Neural Networks – build neural networks the PyTorch way, with high-level functions, optimizers, and more
Convolutional Neural Networks – create advanced computer vision systems
Recurrent Neural Networks – work with sequential data such as natural language and audio
Generative Adversarial Networks – create new content with models including SimpleGAN and CycleGAN
Reinforcement Learning – develop systems that can solve complex problems such as driving or game playing
Deep Learning workflows – move effectively from ideation to production with proper deep learning workflow using PyTorch and its utility packages
Production-ready models – package your models for high-performance production environments

What do you get with a Packt Subscription?

Free for first 7 days. $19.99 p/m after that. Cancel any time!

Unlimited ad-free access to the largest independent learning library in tech. Access this title and thousands more!

50+ new titles added per month, including many first-to-market concepts and exclusive early access to books as they are being written.

Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.

Thousands of reference materials covering every tech concept you need to stay up to date.

Subscribe now

View plans & pricing

Frequently bought together

€32.99

€32.99

€36.99

Total € 102.97

Filter reviews by

All

Amazon verified reviews

JB.Malone Jun 18, 2019

This is a good book if you want a quick dive into PyTorch and build some basic ML projects. It covers a lot of topics fast so don't expect a deep book or lots of theory, what you get is some really useful PyTorch coding templates for CNNs, RNNs, GANs, so you can create these with PyTorch. I'm now getting up and running in PyTorch, and PyTorch rocks. I recommend PyTorch if you know ML but haven't tried it yet.

Amazon Verified review

Stephan Miller May 08, 2019

This is one of the books I wish I had when I got started in machine learning. Of course, I wish the current version of PyTorch was around then too. It will definitely get you started correctly if you're a beginner, will be a great refresher if you are an expert and will widen your knowledge of machine learning techniques if your knowledge only includes a few of the modern methods of extracting answers from data.This book will walk you through setting up your development environment right before you jump right into building a simple neural network. But neural networks is not all this book covers. You will learn how to create a convolutional neural network, the secret behind computer vision. You will also dive into recurrent neural networks and use long short-term memory and gated recurrent units. You will also study generative networks and learn about autoregressive models. Then you will use OpenAI's Gym library to explore Markov decision processes, the Bellman equation and deep Q-learning. Each of these technologies are taught with hands-on step-by-step tutorials.But that is not all. Along the way you will learn how to set up a pipeline to make developing and deploying your machine learning system much simpler and hassle free. And you will learn how to deploy your deep learning system to production using Flask and RedisAI.I would recommend this book to anyone interested in learning AI and machine learning. It will get you started quick and provides a broad overview of features of PyTorch and how you can use it for your own projects.

Akshit Shah May 06, 2019

I am a Deep Learning Practioner, I have been primarily working with TensorFlow, I was thinking to migrate to Pytorch and explore the possibilities of the framework, This book helped me a lot in easy migration. It has all the building blocks required to learn Pytorch. Its advancing difficulty makes readers stick to the book. I especially loved the explanation of GANs. It is probably by far most up to date information provided.Thank You, Authors and Packt publishing for the amazing book.Cheers!

Jessica Apr 29, 2019

This book is very enjoyable to read. The content covers the several main streams of the current deep learning research: NLP, GAN, DRL, etc, and presents step-by-step tutorials on implementing the popular approaches within each field, e.g. CycleGAN, DQN, WaveNet, etc. As a deep learning researcher working primarily with pytorch, I find that this book can work as a good refresher for the fields that I already have experience with, and as a gentle introduction to areas that I am less familiar with while presenting the right amount of implementation details. A well-structured and well-presented guide to deep learning research with pytorch!

Colin Hagemeyer Jun 04, 2019

On the positive, the book walks you step-by-step through the various functions of PyTorch. However, there are a number of issues (in order of importance):1) The authors often use deprecated commands, and so you have to regularly check online if the way they are doing it is how it is currently done. Since this book was published 2 months ago, there's really no excuse.2) Sometimes they'll mention a command in a small paragraph, but fail to provide syntax, an example, or any clear explanation of what it does. In these cases you once again need to go online and figure out what the command does3) The writing is full of over-the-top cliched language like "turned the whole AI community upside down" or "be ready to be blown away". I find myself rolling my eyes almost constantly while reading this book. In addition, there are some awkward sentences, so the book probably needed another pass by the proof-readerMy conclusion is that the book needs more work. It's helpful to get some guidance rather than trying to start directly from online tutorials, but it's probably not worth the quite high price tag. It's also quite interesting how all the 5 star reviews are from unverified purchases, and one of them appears to have been posted a day before the book was published. I wonder why that would be.

PyTorch Deep Learning Hands-On: Build CNNs, RNNs, GANs, reinforcement learning, and more, quickly and easily

What do you get with a Packt Subscription?