Название: Deep Learning with PyTorch, Second Edition (MEAP v3)
Автор: Luca Antiga, Eli Stevens, Howard Huang
Издательство: Manning Publications
Год: 2024
Страниц: 273
Язык: английский
Формат: pdf, epub
Размер: 13.7 MB

Everything you need to create neural networks with PyTorch, including Large Language and diffusion models.

Deep Learning with PyTorch, Second Edition updates the bestselling original guide with new insights into the transformers architecture and generative AI models. Instantly familiar to anyone who knows PyData tools like NumPy and Scikit-learn, PyTorch simplifies Deep Learning without sacrificing advanced features.

In Deep Learning with PyTorch, Second Edition you’ll find:
Deep learning fundamentals reinforced with hands-on projects
Mastering PyTorch's flexible APIs for neural network development
Implementing CNNs, RNNs and Transformers
Optimizing models for training and deployment
Generative AI models to create images and text

In Deep Learning with PyTorch, Second Edition you’ll learn how to create your own neural network and Deep Learning systems and take full advantage of PyTorch’s built-in tools for automatic differentiation, hardware acceleration, distributed training, and more. PyTorch makes it easy to build the powerful neural networks that underpin many modern advances in artificial intelligence. This second edition has been thoroughly revised by PyTorch core developer Howard Huang to cover the latest features and applications, including generative AI models.

The book is written for developers, students, or even hobbyists who have some prior experience with the Python programming language and want to gain a better understanding of Deep Learning. There is no better time to learn about deep learning than now as artificial intelligence gains an ever-growing significance in shaping our products and the world around us.

Throughout this book we will cover essential Deep Learning concepts that every practitioner should know. In parallel, we will navigate through the features of PyTorch, an open source deep learning framework, leveraging it as our primary tool in developing sophisticated deep learning models. As the industry standard, PyTorch has become an essential tool to any deep learning developer’s tool belt. Delving into PyTorch allows us to achieve two objectives at once – not only do we equip ourselves with the means to build cutting-edge models, but we also gain a deeper understanding of the intricacies behind Deep Learning principles.

about the book
Deep Learning with PyTorch, Second Edition is a hands-on guide to modern machine learning with PyTorch. You’ll discover how easy PyTorch makes it to build your entire DL pipeline, including using the PyTorch Tensor API, loading data in Python, monitoring training, and visualizing results. Each new technique you learn is put into action to build a full-size medical image classifier chapter-by-chapter.

In this modernized second edition, you’ll find new coverage of how to develop and train groundbreaking generative AI models. You’ll learn about the foundational building blocks of transformers to create large language models and generate exciting images by building your own diffusion model. Plus, you'll discover ways to improve your results by training with augmented data, make improvements to the model architecture, and perform fine tuning.

about the reader
For Python programmers with an interest in Machine Learning.

about the authors
Howard Huang is a software engineer and developer on the PyTorch library. During his tenure at PyTorch he has focused on large scale, distributed training. Eli Stevens, Luca Antiga, and Thomas Viehmann authored the first edition of Deep Learning with PyTorch.