Deep-Learning-with-PyTorch-1.x

This is the code repository for Deep Learning with PyTorch 1.x, published by Packt.

Implement deep learning techniques and neural network architecture variants using Python

What is this book about?

PyTorch is gaining the attention of deep learning researchers and data science professionals due to its accessibility and efficiency, along with the fact that it's more native to the Python way of development. This book will get you up and running with this cutting-edge deep learning library, effectively guiding you through implementing deep learning concepts. In this second edition, you'll learn the fundamental aspects that power modern deep learning, and explore the new features of the PyTorch 1.x library. You'll understand how to solve real-world problems using CNNs, RNNs, and LSTMs, along with discovering state-of-the-art modern deep learning architectures, such as ResNet, DenseNet, and Inception. You'll then focus on applying neural networks to domains such as computer vision and NLP. Later chapters will demonstrate how to build, train, and scale a model with PyTorch and also cover complex neural networks such as GANs and autoencoders for producing text and images. In addition to this, you'll explore GPU computing and how it can be used to perform heavy computations. Finally, you'll learn how to work with deep learning-based architectures for transfer learning and reinforcement learning problems. By the end of this book, you'll be able to confidently and easily implement deep learning applications in PyTorch.

This book covers the following exciting features:

• Build text classification and language modeling systems using neural networks
• Implement transfer learning using advanced CNN architectures
• Use deep reinforcement learning techniques to solve optimization problems in PyTorch
• Mix multiple models for a powerful ensemble model
• Build image classifiers by implementing CNN architectures using PyTorch
• Get up to speed with reinforcement learning, GANs, LSTMs, and RNNs with real-world examples

If you feel this book is for you, get your copy today!

<img src="https://raw.githubusercontent.com/PacktPublishing/GitHub/master/GitHub.png" alt="https://www.packtpub.com/" border="5" />

Instructions and Navigations

All of the code is organized into folders. For example, Chapter02.

The code will look like the following:

toy_story_review = "Just perfect. Script, character, animation....this manages to break free of the yoke of 'children's movie' to simply be one of the best movies of the 90's, full-stop."

print(list(toy_story_review))

Following is what you need for this book: This book is for data scientists and machine learning engineers who are looking to explore deep learning algorithms using PyTorch 1.x. Those who wish to migrate to PyTorch 1.x will find this book insightful. To make the most out of this book, working knowledge of Python programming and some knowledge of machine learning will be helpful.

With the following software and hardware list you can run all code files present in the book (Chapter 1-9).

Software and Hardware List

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it.

Related products

• PyTorch 1.x Reinforcement Learning Cookbook [Packt] [Amazon]

• PyTorch Deep Learning Hands-On [Packt] [Amazon]

Get to Know the Author

Laura Mitchell graduated with a degree in mathematics from the University of Edinburgh. With 15 years of experience in the tech and data science space, Laura is the lead data scientist at MagicLab whose brands have connected the lives of over 500 million people through dating, social and business. Laura has hands-on experience in the delivery of projects surrounding natural language processing, image classification and recommender systems, from initial conception to production. She has a passion for learning new technologies and keeping herself up to date with industry trends.

Sri. Yogesh K. is an experienced data scientist with a history of working in higher education. He is skilled in Python, Apache Spark, deep learning, Hadoop, and machine learning. He is a strong engineering professional with a Certificate of Engineering Excellence from the International School of Engineering (INSOFE) and is focused on big data analytics. Sri has trained over 500 working professionals in data science and deep learning from companies including Flipkart, Honeywell, GE, and Rakuten. Additionally, he has worked on various projects that involved deep learning and PyTorch.

Vishnu Subramanian has experience in leading, architecting, and implementing several big data analytical projects using artificial intelligence, machine learning, and deep learning. He specializes in machine learning, deep learning, distributed machine learning, and visualization. He has experience in retail, finance, and travel domains. Also, he is good at understanding and coordinating between businesses, AI, and engineering teams.

Suggestions and Feedback

Click here if you have any feedback or suggestions.