Howard Huang – författare

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 youll learn how to create your own neural network and deep learning systems and take full advantage of PyTorchs built-in tools for automatic differentiation, hardware acceleration, distributed training, and more. Youll 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 youll 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 textAbout the technologyThe powerful PyTorch library makes deep learning simplewithout sacrificing the features you need to create efficient neural networks, LLMs, and other ML models. Pythonic by design, its 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 bookDeep 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 youll 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 deploymentAbout the readerFor Python programmers with a background in machine learning.About the authorHoward 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 ContentsPart 11 Introducing deep learning and the PyTorch library2 Pretrained networks3 It starts with a tensor4 Real-world data representation using tensors5 The mechanics of learning6 Using a neural network to fit the data7 Telling birds from airplanes: Learning from images8 Using convolutions to generalizePart 29 How transformers work10 Diffusion models for images11 Using PyTorch to fight cancer12 Combining data sources into a unified dataset13 Training a classification model to detect suspected tumors14 Improving training with metrics and augmentation15 Using segmentation to find suspected nodules16 Training models on multiple GPU17 Deploying to production