Deep Learning with PyTorch, Second Edition

Autorentext

• Luca Antiga is a deep learning researcher and entrepreneur known for translating theory into high-impact AI applications. With extensive industry and academic collaborations, Luca brings clarity and pragmatic rigor to every page. He distills years of neural-network innovation into guidance that accelerates reader competence. 

• Eli Stevens is a seasoned machine-learning engineer recognized for simplifying complex architectures for production teams. With startup intensity and open-source spirit, Eli delivers frank, actionable insights throughout the book. He converts frontier research into approachable steps that help readers deploy real-world solutions. 

• Howard Huang is a software engineer on the core PyTorch team, known for advancing distributed training at scale. With insider knowledge of the framework, Howard injects authoritative best practices into the narrative. He turns deep infrastructure expertise into clear tactics that boost reader productivity. 

• Thomas Viehmann is a data-science consultant and educator praised for demystifying advanced AI concepts. With classroom experience and community mentorship, Thomas offers an encouraging, structured teaching style. He translates academic depth into tools and patterns readers can apply immediately. 

Klappentext

Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.

PyTorch core developer Howard Huang updates the bestselling original Deep Learning with PyTorch with new insights into the transformers architecture and generative AI models.

Instantly familiar to anyone who knows PyData tools like NumPy, PyTorch simplifies deep learning without sacrificing advanced features. In this book 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. 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 with practical code examples in each chapter, culminating into you building your own convolution neural networks, transformers, and even a real-world medical image classifier.

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, transformers, and diffusion models
• Optimizing models for training and deployment
• Generative AI models to create images and text

About the technology

The powerful PyTorch library makes deep learning simple—without sacrificing the features you need to create efficient neural networks, LLMs, and other ML models. Pythonic by design, it’s instantly familiar to users of NumPy, Scikit-learn, and other ML frameworks. This thoroughly-revised second edition covers the latest PyTorch innovations, including how to create and refine generative AI models.

About the book

Deep Learning with PyTorch, Second Edition shows you how to build neural network models using the latest version of PyTorch. Clear explanations and practical projects help you master the fundamentals and explore advanced architectures including transformers and LLMs. Along the way you’ll learn techniques for training using augmented data, improving model architecture, and fine tuning.

What's inside

• PyTorch APIs for neural network development
• LLMs, transformers, and diffusion models
• Model training and deployment

About the reader

For Python programmers with a background in machine learning.

About the author

Howard Huang is a software engineer and developer on the PyTorch library focusing on large scale, distributed training. Eli Stevens, Luca Antiga, and Thomas Viehmann authored the first edition of Deep Learning with PyTorch.

Table of Contents

Part 1
1 Introducing deep learning and the PyTorch library
2 Pretrained networks
3 It starts with a tensor
4 Real-world data representation using tensors
5 The mechanics of learning
6 Using a neural network to fit the data
7 Telling birds from airplanes: Learning from images
8 Using convolutions to generalize
Part 2
9 How transformers work
10 Diffusion models for images
11 Using PyTorch to fight cancer
12 Combining data sources into a unified dataset
13 Training a classification model to detect suspected tumors
14 Improving training with metrics and augmentation
15 Using segmentation to find suspected nodules
16 Training models on multiple GPU
17 Deploying to production

Zusammenfassung

Stop guessing at PyTorch syntax, start building production-ready models today. Bridge the gap between theory and working code with guided, hands-on projects. Confused by transformers and diffusion? Learn them through clear, incremental steps. Grow from basic tensors to complete neural networks without drowning in jargon. Feel confident diagnosing training issues using PyTorchs powerful visualization tools. Stay market-relevant by mastering the latest generative AI techniques right now. 

• Project-based learning: Build an end-to-end medical image classifier that cements every concept. 

• Flexible PyTorch APIs: Customize layers, losses, and optimizers for research or production speed. 

• CNNs, RNNs, Transformers: Apply the right architecture to vision, language, and multimodal tasks. 

• Generative models: Create text and images with large language models and diffusion networks. 

• Optimization know-how: Improve accuracy, reduce inference cost, and streamline model deployment. 
  Deep Learning with PyTorch, Second Edition, by Luca Antiga, Eli Stevens, Howard Huang, and Thomas Viehmann, delivers a credible, code-first roadmap for serious AI practitioners. The book guides you through every stage, from data loading to scaled deployment. 

Each chapter introduces a single concept, then immediately applies it to a working project. Updated coverage of transformers, diffusion, and distributed training keeps the content current. Friendly explanations, annotated code, and ample visuals make complex ideas clear and actionable. 

Finish the book able to design, train, and ship state-of-the-art models using PyTorchs flexible toolkit. You will upskill confidently and join the ranks of engineers pushing AI forward. 

Ideal for Python developers, data scientists, and ML engineers seeking practical mastery of modern deep learning.

Inhalt

PART 1: CORE PYTORCH 

1 INTRODUCING DEEP LEARNING AND THE PYTORCH LIBRARY 

2 PRETRAINED NETWORKS 

3 IT STARTS WITH A TENSOR 

4 REAL-WORLD DATA REPRESENTATION USING TENSORS  

5 THE MECHANICS OF LEARNING 

6 USING A NEURAL NETWORK TO FIT THE DATA 

7 TELLING BIRDS FROM AIRPLANES: LEARNING FROM IMAGES 

8 USING CONVOLUTIONS TO GENERALIZE 

PART 2: PRACTICAL APPLICATIONS 

9 HOW TRANSFORMERS WORK 

10 DIFFUSION MODELS FOR IMAGES 

11 USING PYTORCH TO FIGHT CANCER 

12 COMBINING DATA SOURCES INTO A UNIFIED DATASET 

13 TRAINING A CLASSIFICATION MODEL TO DETECT SUSPECTED TUMORS 

14 IMPROVING TRAINING WITH METRICS AND AUGMENTATION 

15 USING SEGMENTATION TO FIND SUSPECTED NODULES 

16 TRAINING MODELS ON MULTIPLE GPUS 

17 DEPLOYING TO PRODUCTION