A comprehensive, self-contained guide to PyTorch, the deep-learning framework that powers most modern AI research and a great deal of production.

Welcome to PyTorch: Deep Learning the Pythonic Way.

A comprehensive, self-contained guide to PyTorch, the deep-learning framework that powers most modern AI research and a great deal of production. PyTorch's appeal is that it feels like Python and NumPy with gradients and a GPU — you write ordinary code, and the framework differentiates it. This book teaches that style end to end: tensors and autograd, the nn.Module abstraction, the explicit training loop that is PyTorch's signature, Dataset/DataLoader input pipelines, CNNs and transformers, transfer learning, and deployment with TorchScript, torch.compile, ONNX, and ExecuTorch. It blends intuition, the concepts behind the API, and runnable code.

This title is part of the ShriIra library and is free to read in full, right here — our small contribution to making world-class knowledge easy to reach.

A note on reading it: open the Contents menu at the top of the reader to jump between chapters, use the Aa menu to set a comfortable text size, theme (light, sepia, or night), and single- or two-page layout. Your place is saved automatically, so you can always pick up where you left off.

We hope it serves you well.

— Shriira Press

Contents

1. Chapter 1 — What Is PyTorch?
2. Chapter 2 — Tensors and Autograd
3. Chapter 3 — Your First Neural Network
4. Chapter 4 — Building Models with nn.Module
5. Chapter 5 — The Training Loop in Depth
6. Chapter 6 — Data: Datasets, DataLoaders, and Transforms
7. Chapter 7 — Layers, Activations, and Building Blocks
8. Chapter 8 — Convolutional Networks for Images
9. Chapter 9 — Sequence Models: RNNs, LSTMs, and Transformers
10. Chapter 10 — Regularization, Tuning, and Training Tricks
11. Chapter 11 — Transfer Learning and Pretrained Models
12. Chapter 12 — Saving, Compiling, and Deployment
13. Chapter 13 — The Ecosystem, Scaling, and the Profession
14. Appendix A — Glossary and API Quick Reference
15. Appendix B — Further Reading and Resources