Pretrained networks

This book offers a foundational introduction to deep learning using the PyTorch library, guiding readers through its core concepts and practical applications. It covers fundamental aspects such as understanding PyTorch's anatomy, manipulating tensors as basic data structures, and building neural networks. Readers will learn how programs acquire knowledge from examples, implement various neural network architectures, and apply these techniques to solve problems like image classification, including the use of convolutional neural networks.

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

  1. Part 1 (Free teaser)
  2. Core Pytorch ($0.25)
  3. 15 Hardware And Software Requirements ($0.25)
  4. This Chapter Covers ($0.25)
  5. 21 A Pretrained Network That Recognizes The Subject Of An Im ($0.25)
  6. 214 Ready Set Almost Run ($0.25)
  7. 31 The World As Floating Point Numbers ($0.25)
  8. 322 Constructing Our First Tensors ($0.25)
  9. 34 Named Tensors ($0.25)
  10. 351 Specifying The Numeric Type With Dtype ($0.25)
  11. 381 Views Of Another Tensors Storage ($0.25)
  12. 382 Transposing Without Copying ($0.25)
  13. 384 Contiguous Tensors ($0.25)
  14. 411 Adding Color Channels ($0.25)
  15. 414 Normalizing The Data ($0.25)
  16. 433 Representing Scores ($0.25)
  17. 436 Finding Thresholds ($0.25)
  18. 442 Shaping The Data By Time Period ($0.25)
  19. 451 Converting Text To Numbers ($0.25)
  20. 453 One Hot Encoding Whole Words ($0.25)
  21. 554 Autograd Nits And Switching It Off ($0.25)
  22. This Chapter Covers 2 ($0.25)
  23. 613 All We Need Is Activation ($0.25)
  24. 615 Choosing The Best Activation Function ($0.25)
  25. 616 What Learning Means For A Neural Network ($0.25)
  26. 622 Returning To The Linear Model ($0.25)
  27. 632 Inspecting The Parameters ($0.25)
  28. 713 Dataset Transforms ($0.25)
  29. 723 Output Of A Classifier ($0.25)
  30. This Chapter Covers 3 ($0.25)
  31. 822 Detecting Features With Convolutions ($0.25)
  32. The Receptive Field Of Output Pixels ($0.25)
  33. 831 Our Network As An Nnmodule ($0.25)
  34. 833 The Functional Api ($0.25)
  35. 84 Training Our Convnet ($0.25)
  36. 843 Training On The Gpu ($0.25)
  37. 851 Adding Memory Capacity Width ($0.25)
  38. 852 Helping Our Model To Converge And Generalize Regularizat ($0.25)
  39. 853 Going Deeper To Learn More Complex Structures Depth ($0.25)
  40. 854 Comparing The Designs From This Section ($0.25)
  41. Voxel ($0.25)
  42. On The Shoulders Of Giants ($0.25)
  43. 941 Why Cant We Just Throw Data At A Neural Network Until It ($0.25)
  44. 944 Downloading The Luna Data ($0.25)
  45. 1021 Training And Validation Sets ($0.25)
  46. Listing 103 Dsetspy40 Def Getcandidateinfolist ($0.25)
  47. 1044 Extracting A Nodule From A Ct Scan ($0.25)
  48. Listing 1013 Dsetspy179 Lunadatasetgetitem ($0.25)
  49. 1051 Caching Candidate Arrays With The Getctrawcandidate Fun ($0.25)
  50. Listing 1018 Dsetspy149 Class Lunadataset ($0.25)
  51. Listing 113 Trainingpy31 Class Lunatrainingapp ($0.25)
  52. Dataparallel Vs Distributeddataparallel ($0.25)
  53. 1132 Care And Feeding Of Data Loaders ($0.25)
  54. Constructing Masks ($0.25)
  55. Listing 1120 Utilpy143 Def Enumeratewithestimate ($0.25)
  56. Writing Scalars To Tensorboard ($0.25)
  57. Updating The Logging Output To Include Precision Recall And ($0.25)
  58. 1356 Implementing Trainingluna2Dsegmentationdataset ($0.25)
  59. 1362 Using The Adam Optimizer ($0.25)
  60. 1364 Getting Images Into Tensorboard ($0.25)
  61. 1365 Updating Our Metrics Logging ($0.25)
  62. 1366 Saving Our Model ($0.25)
  63. 1431 Segmentation ($0.25)
  64. 1432 Grouping Voxels Into Nodule Candidates ($0.25)
  65. 1433 Did We Find A Nodule Classification To Reduce False Pos ($0.25)
  66. Fully Automated Vs Assistive Systems ($0.25)
  67. 1451 Getting Malignancy Information ($0.25)
  68. 1452 An Area Under The Curve Baseline Classifying By Diamete ($0.25)
  69. 1481 Behind The Curtain ($0.25)
  70. 1511 Our Model Behind A Flask Server ($0.25)
  71. 1512 What We Want From Deployment ($0.25)
  72. 1513 Request Batching ($0.25)
  73. 1521 Interoperability Beyond Pytorch With Onnx ($0.25)
  74. 1531 What To Expect From Moving Beyond Classic Pythonpytorch ($0.25)
  75. 1533 Torchscript ($0.25)
  76. 1534 Scripting The Gaps Of Traceability ($0.25)
  77. 1541 Running Jited Models From C ($0.25)
  78. Listing 1512 Cmakeliststxt ($0.25)
  79. 1551 Improving Efficiency Model Design And Quantization ($0.25)
  80. Numerics ($0.25)