This book offers a practical, start-to-finish guide to building deep learning projects using the PyTorch library. Readers will learn fundamental concepts such as tensors and neural network architectures, gain hands-on experience in training models from examples, and discover how to deploy solutions for real-world applications. Through major projects like developing language models, image generation systems, and medical image segmentation, the content equips learners with essential skills for a career in artificial intelligence development.
This page is free — overview and chapter list only.
The complete book body is sold separately.
Full book: $2.99 USDC via x402 ·
Per chapter: $0.25 USDC
Buy / open complete book (HTML)
· Complete book Markdown (.md)
Agents: start with free /library/discovery.json, sample free teaser chapters,
then pay for individual chapters or the complete book URL above.
Append .md to any content URL for Markdown with YAML front matter.
Chapters
- About The Cover Illustration (Free teaser)
- 16 Hardware And Software Requirements ($0.25)
- 21 A Pretrained Network That Recognizes The Subject Of An Im ($0.25)
- 22 Generating And Editing Images ($0.25)
- 24 A Pretrained Network That Describes Scenes ($0.25)
- Summary ($0.25)
- 32 Tensors Multidimensional Arrays ($0.25)
- 35 Named Tensors ($0.25)
- 36 Tensor Element Types ($0.25)
- 391 Views Of Another Tensors Storage ($0.25)
- 3101 Managing A Tensors Device Attribute ($0.25)
- This Chapter Covers ($0.25)
- 413 Changing The Layout ($0.25)
- 433 Representing Scores ($0.25)
- 443 Ready For Training ($0.25)
- 455 Text Embeddings As A Blueprint ($0.25)
- 524 Choosing A Linear Model As A First Try ($0.25)
- Broadcasting ($0.25)
- 543 Iterating To Fit The Model ($0.25)
- 544 Normalizing Inputs ($0.25)
- 551 Computing The Gradient Automatically ($0.25)
- 552 Optimizers La Carte ($0.25)
- 555 Autograd Nits And Switching It Off ($0.25)
- 613 Adding Nonlinearity With Activation Functions ($0.25)
- 616 What Learning Means For A Neural Network ($0.25)
- 622 Returning To The Linear Model ($0.25)
- 633 Comparing To The Linear Model ($0.25)
- 711 Downloading Cifar 10 ($0.25)
- 714 Normalizing Data ($0.25)
- 724 Representing The Output As Probabilities ($0.25)
- 725 Training The Classifier ($0.25)
- 73 Conclusion ($0.25)
- 82 Convolutions In Action ($0.25)
- 823 Looking Further With Depth And Pooling ($0.25)
- 83 Subclassing Nn Module ($0.25)
- 84 Training Our Convolutional Neural Network ($0.25)
- 85 Model Design ($0.25)
- Batch Normalization ($0.25)
- 91 A Motivating Example Generating Names Character By Charac ($0.25)
- 93 Generating Our Training Data ($0.25)
- 95 Attention ($0.25)
- 952 Scaled Dot Product Causal Self Attention ($0.25)
- Gpt Style Decoder ($0.25)
- Transformer Encoder ($0.25)
- 99 The Vision Transformer ($0.25)
- Summary 2 ($0.25)
- 105 The Forward Process ($0.25)
- 107 Reversing Diffusion How To Sample ($0.25)
- 108 Conclusion ($0.25)
- 113 What Is A Ct Scan Exactly ($0.25)
- On The Shoulders Of Giants ($0.25)
- 1142 Our Data Source The Luna Grand Challenge ($0.25)
- 122 Parsing Lunas Annotation Data ($0.25)
- 123 Loading Individual Ct Scans ($0.25)
- 1244 Extracting A Nodule From A Ct Scan ($0.25)
- 1254 Rendering The Data ($0.25)
- Dataparallel Vs Distributeddataparallel ($0.25)
- 1341 The Core Convolutions ($0.25)
- 1342 The Full Model ($0.25)
- 1351 The Computebatchloss Function ($0.25)
- Listing 1317 Masking For Classification Metrics ($0.25)
- 1372 Interlude The Tqdm Function ($0.25)
- 1462 Seeing The Improvement From Data Augmentation ($0.25)
- 151 Utilizing A Second Model In Our Project ($0.25)
- 1531 The Segment Anything Model Sam ($0.25)
- 1541 Trying Out An Off The Shelf Model For Our Project ($0.25)
- 1563 Training A Model To Flag Potential Candidates ($0.25)
- 1571 How To Fine Tune A Model ($0.25)
- 1574 Saving Our Model ($0.25)
- 1613 Initializing A Distributed Program ($0.25)
- Listing 169 Creating A Data Loader With Distributedsampler ($0.25)
- 1651 Pipeline Parallelism ($0.25)
- Listing 1614 Synchronizing Model Parameters ($0.25)
- 1682 Expert Parallelism ($0.25)
- This Chapter Covers 2 ($0.25)
- 1712 Our Model Behind A Fastapi Server ($0.25)
- Implementation ($0.25)
- Add Quantization ($0.25)
- 1721 Interoperability Beyond Pytorch With Onnx ($0.25)
- History And Motivations Behind Torchcompile ($0.25)