Deep Learning with PyTorch video edition

Video description

With this publication, we finally have a definitive treatise on PyTorch. It covers the basics and abstractions in great detail.
From the Foreword by Soumith Chintala, Cocreator of PyTorch

Every other day we hear about new ways to put deep learning to good use: improved medical imaging, accurate credit card fraud detection, long range weather forecasting, and more. PyTorch puts these superpowers in your hands, providing a comfortable Python experience that gets you started quickly and then grows with you as you—and your deep learning skills—become more sophisticated. Deep Learning with PyTorch will make that journey engaging and fun.

about the technology

Although many deep learning tools use Python, the PyTorch library is truly Pythonic. Instantly familiar to anyone who knows PyData tools like NumPy and scikit-learn, PyTorch simplifies deep learning without sacrificing advanced features. It's excellent for building quick models, and it scales smoothly from laptop to enterprise. Because companies like Apple, Facebook, and JPMorgan Chase rely on PyTorch, it's a great skill to have as you expand your career options. It's easy to get started with PyTorch. It minimizes cognitive overhead without sacrificing the access to advanced features, meaning you can focus on what matters the most - building and training the latest and greatest deep learning models and contribute to making a dent in the world. PyTorch is also a snap to scale and extend, and it partners well with other Python tooling. PyTorch has been adopted by hundreds of deep learning practitioners and several first-class players like FAIR, OpenAI, FastAI and Purdue.

about the book

Deep Learning with PyTorch teaches you to create neural networks and deep learning systems with PyTorch. This practical book quickly gets you to work building a real-world example from scratch: a tumor image classifier. Along the way, it covers best practices for the entire DL pipeline, including the PyTorch Tensor API, loading data in Python, monitoring training, and visualizing results. After covering the basics, the book will take you on a journey through larger projects. The centerpiece of the book is a neural network designed for cancer detection. You'll discover ways for training networks with limited inputs and start processing data to get some results. You'll sift through the unreliable initial results and focus on how to diagnose and fix the problems in your neural network. Finally, you'll look at ways to improve your results by training with augmented data, make improvements to the model architecture, and perform other fine tuning.

what's inside

  • Training deep neural networks
  • Implementing modules and loss functions
  • Utilizing pretrained models from PyTorch Hub
  • Exploring code samples in Jupyter Notebooks

about the audience

For Python programmers with an interest in machine learning.

about the authors

Eli Stevens had roles from software engineer to CTO, and is currently working on machine learning in the self-driving-car industry. Luca Antiga is cofounder of an AI engineering company and an AI tech startup, as well as a former PyTorch contributor. Thomas Viehmann is a PyTorch core developer and machine learning trainer and consultant.

Deep learning divided into digestible chunks with code samples that build up logically.
Mathieu Zhang, NVIDIA

Timely, practical, and thorough. Don’t put it on your bookshelf, but next to your laptop.
Philippe Van Bergen, PC Consulting

Deep Learning with PyTorch offers a very pragmatic overview of deep learning. It is a didactical resource.
Orlando Alejo Mendez Morales, Experian

NARRATED BY MARK THOMAS

Table of contents

  1. Part 1. Core PyTorch
  2. Chapter 1. Introducing deep learning and the PyTorch Library
  3. Chapter 1. Why PyTorch?
  4. Chapter 1. An overview of how PyTorch supports deep learning projects
  5. Chapter 1. Hardware and software requirements
  6. Chapter 2. Pretrained networks
  7. Chapter 2. Obtaining a pretrained network for image recognition
  8. Chapter 2. Ready, set, almost run
  9. Chapter 2. A pretrained model that fakes it until it makes it
  10. Chapter 2. A network that turns horses into zebras
  11. Chapter 2. A pretrained network that describes scenes
  12. Chapter 3. It starts with a tensor
  13. Chapter 3. Indexing tensors
  14. Chapter 3. The tensor API
  15. Chapter 3. Tensor metadata: Size, offset, and stride
  16. Chapter 3. NumPy interoperability
  17. Chapter 4. Real-world data representation using tensors
  18. Chapter 4. 3D images: Volumetric data
  19. Chapter 4. Representing scores
  20. Chapter 4. Working with time series
  21. Chapter 4. Ready for training
  22. Chapter 4. One-hot encoding whole words
  23. Chapter 4. Text embeddings as a blueprint
  24. Chapter 5. The mechanics of learning
  25. Chapter 5. Gathering some data
  26. Chapter 5. Down along the gradient
  27. Chapter 5. Normalizing inputs
  28. Chapter 5. Optimizers a la carte
  29. Chapter 5. Generalizing to the validation set
  30. Chapter 6. Using a neural network to fit the data
  31. Chapter 6. More activation functions
  32. Chapter 6. The PyTorch nn module
  33. Chapter 6. Finally a neural network
  34. Chapter 7. Telling birds from airplanes: Learning from images
  35. Chapter 7. Distinguishing birds from airplanes
  36. Chapter 7. Representing the output as probabilities
  37. Chapter 7. Training the classifier
  38. Chapter 7. The limits of going fully connected
  39. Chapter 8. Using convolutions to generalize
  40. Chapter 8. Convolutions in action
  41. Chapter 8. Looking further with depth and pooling
  42. Chapter 8. Subclassing nn.Module
  43. Chapter 8. Training our convnet
  44. Chapter 8. Helping our model to converge and generalize: Regularization
  45. Chapter 8. Going deeper to learn more complex structures: Depth
  46. Chapter 8. Comparing the designs from this section
  47. Part 2. Learning from images in the real world: Early detection of lung cancer
  48. Chapter 9. Using PyTorch to fight cancer
  49. Chapter 9. What is a CT scan, exactly?
  50. Chapter 9. In more detail, we will do the following
  51. Chapter 9. Why can’t we just throw data at a neural network until it works?
  52. Chapter 9. What is a nodule?
  53. Chapter 10. Combining data sources into a unified dataset
  54. Chapter 10. Training and validation sets
  55. Chapter 10. Loading individual CT scans
  56. Chapter 10. Locating a nodule using the patient coordinate system
  57. Chapter 10. A straightforward dataset implementation
  58. Chapter 10. Constructing our dataset in LunaDataset.__init__
  59. Chapter 11. Training a classification model to detect suspected tumors
  60. Chapter 11. Pretraining setup and initialization
  61. Chapter 11. Our first-pass neural network design
  62. Chapter 11. The full model
  63. Chapter 11. Outputting performance metrics
  64. Chapter 11. Needed data for training
  65. Chapter 11. Running TensorBoard
  66. Chapter 11. Why isn’t the model learning to detect nodules?
  67. Chapter 12. Improving training with metrics and augmentation
  68. Chapter 12. Graphing the positives and negatives
  69. Chapter 12. Our ultimate performance metric: The F1 score
  70. Chapter 12. What does an ideal dataset look like?
  71. Chapter 12. Samplers can reshape datasets
  72. Chapter 12. Revisiting the problem of overfitting
  73. Chapter 12. Seeing the improvement from data augmentation
  74. Chapter 13. Using segmentation to find suspected nodules
  75. Chapter 13. Semantic segmentation: Per-pixel classification
  76. Chapter 13. Updating the model for segmentation
  77. Chapter 13. Updating the dataset for segmentation
  78. Chapter 13. Building the ground truth data
  79. Chapter 13. Implementing Luna2dSegmentationDataset
  80. Chapter 13. Designing our training and validation data
  81. Chapter 13. Updating the training script for segmentation
  82. Chapter 13. Getting images into TensorBoard
  83. Chapter 13. Results
  84. Chapter 14. End-to-end nodule analysis, and where to go next
  85. Chapter 14. Bridging CT segmentation and nodule candidate classification
  86. Chapter 14. Did we find a nodule? Classification to reduce false positives
  87. Chapter 14. Quantitative validation
  88. Chapter 14. Reusing preexisting weights: Fine-tuning
  89. Chapter 14. What we see when we diagnose
  90. Chapter 14. Beyond a single best model: Ensembling
  91. Chapter 14. Conclusion
  92. Part 3. Deployment
  93. Chapter 15. Deploying to production
  94. Chapter 15. Request batching
  95. Chapter 15. Exporting models
  96. Chapter 15. Interacting with the PyTorch JIT
  97. Chapter 15. TorchScript
  98. Chapter 15. LibTorch: PyTorch in C++
  99. Chapter 15. C++ from the start: The C++ API
  100. Chapter 15. Going mobile
  101. Chapter 15. Improving efficiency: Model design and quantization

Product information

  • Title: Deep Learning with PyTorch video edition
  • Author(s): Eli Stevens, Luca Antiga, Thomas Viehmann
  • Release date: July 2020
  • Publisher(s): Manning Publications
  • ISBN: None