Learning PyTorch 2.0 Second Edition

<p><span style=color: rgba(51 51 51 1)>Learning PyTorch 2.0 Second Edition is a </span><strong style=color: rgba(51 51 51 1)>fast-learning hands-on book that emphasizes practical PyTorch scripting and efficient model development using PyTorch 2.3 and CUDA 12</strong><span style=color: rgba(51 51 51 1)>. This edition is centered on practical applications and presents a concise methodology for attaining proficiency in the most recent features of PyTorch. The book presents a practical program based on the fish dataset which provides </span><strong style=color: rgba(51 51 51 1)>step-by-step guidance through the processes of building training and deploying neural networks with each example prepared for immediate implementation</strong><span style=color: rgba(51 51 51 1)>. Given your familiarity with machine learning and neural networks this book offers concise explanations of foundational topics allowing you to proceed directly to the practical advanced aspects of PyTorch programming. </span></p><p><span style=color: rgba(51 51 51 1)>The </span><strong style=color: rgba(51 51 51 1)>key learnings include the design of various types of neural networks the use of torch.compile() for performance optimization the deployment of models using TorchServe and the implementation of quantization for efficient inference</strong><span style=color: rgba(51 51 51 1)>. Furthermore you will also </span><strong style=color: rgba(51 51 51 1)>learn to migrate TensorFlow models to PyTorch using the ONNX format</strong><span style=color: rgba(51 51 51 1)>. The book employs </span><strong style=color: rgba(51 51 51 1)>essential libraries including torchvision torchserve tf2onnx onnxruntime and requests to facilitate seamless integration of PyTorch with production environments</strong><span style=color: rgba(51 51 51 1)>.</span></p><p><br></p><h2>Key Learnings</h2><p>Master tensor manipulations and advanced operations using PyTorch's efficient tensor libraries.</p><p>Build feedforward convolutional and recurrent neural networks from scratch.</p><p>Implement transformer models for modern natural language processing tasks.</p><p>Use CUDA 12 and mixed precision training (AMP) to accelerate model training and inference.</p><p>Deploy PyTorch models in production using TorchServe including multi-model serving and versioning.</p><p>Migrate TensorFlow models to PyTorch using ONNX format for seamless cross-framework compatibility.</p><p>Optimize neural network architectures using torch.compile() for improved speed and efficiency.</p><p>Utilize PyTorch's Quantization API to reduce model size and speed up inference.</p><p>Setup custom layers and architectures for neural networks to tackle domain-specific problems.</p><p>Monitor and log model performance in real-time using TorchServe's built-in tools and configurations.</p><p><br></p><h2>Table of Content</h2><ol><li data-list=ordered><span class=ql-ui contenteditable=false></span>Introduction To PyTorch 2.3 and CUDA 12</li><li data-list=ordered><span class=ql-ui contenteditable=false></span>Getting Started with Tensors</li><li data-list=ordered><span class=ql-ui contenteditable=false></span>Building Neural Networks with PyTorch</li><li data-list=ordered><span class=ql-ui contenteditable=false></span>Training Neural Networks</li><li data-list=ordered><span class=ql-ui contenteditable=false></span>Advanced Neural Network Architectures</li><li data-list=ordered><span class=ql-ui contenteditable=false></span>Quantization and Model Optimization</li><li data-list=ordered><span class=ql-ui contenteditable=false></span>Migrating TensorFlow to PyTorch</li><li data-list=ordered><span class=ql-ui contenteditable=false></span>Deploying PyTorch Models with TorchServe</li></ol>