Deep Learning with PyTorch
Eli Stevens and Luca Antiga
  • MEAP began April 2018
  • Publication in Fall 2020 (estimated)
  • ISBN 9781617295263
  • 450 pages (estimated)
  • printed in black & white

Perfectly motivating and practical without being shallow.

Carlos Andres Mariscal
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.
Table of Contents detailed table of contents

Part 1: Core PyTorch

1 Introducing Deep Learning and the PyTorch Library

1.1 What is PyTorch?

1.2 What is this book?

1.3 Why PyTorch

1.3.1 The Deep Learning Revolution

1.3.2 Immediate vs. deferred execution

1.3.3 The deep learning competitive landscape

1.4 PyTorch has the batteries included

1.4.1 Hardware for deep learning

1.4.2 Using Jupyter notebooks

1.5 Conclusion

1.6 Exercises

1.7 Summary

2 Pre-Trained Networks

2.1 A pre-trained network that recognizes the subject of an image

2.1.1 Obtaining a pre-trained network for image recognition

2.1.2 AlexNet

2.1.3 ResNet

2.1.4 Ready, set, almost run

2.1.5 Run!

2.2 A pre-trained model that fakes it until it makes it

2.2.1 The GAN game

2.2.2 CycleGAN

2.2.3 A network that turns horses into zebras

2.3 A pre-trained network that describes scenes

2.3.1 NeuralTalk2

2.4 Torch Hub

2.5 Conclusion

2.6 Exercises

2.7 Summary

3 It Starts with a Tensor

3.1 Tensors Fundamentals

3.2 Tensors and Storages

3.3 Size, offset, stride

3.4 Numeric Types

3.5 Indexing Tensors

3.6 NumPy interoperability

3.7 Serializing tensors

3.8 Moving tensors to the GPU

3.9 The tensor API

3.10 Conclusion

3.11 Exercises

3.11 Summary

4 Real-World Data Representation Using Tensors

4.1 Tabular Data

4.2 Time Series

4.3 Text

4.3.1 Text embeddings

4.4 Images

4.5 Volumetric Data

4.6 Conclusion

4.7 Exercises

4.8 Summary

5 The Mechanics of Learning

5.1 Learning is just parameter estimation

5.1.1 A Hot Problem

5.1.2 Choosing a linear model as a first try

5.1.3 Less loss is what we want

5.1.4 From Problem to PyTorch

5.1.5 Down Along the Gradient

5.1.6 Getting Analytical

5.1.7 The Training Loop

5.2 PyTorch’s Autograd: Back-propagate all things

5.2.1 Optimizers a-la Carte

5.2.2 Training, Validation, and Overfitting

5.2.3 Autograd Nits and Switching it Off

5.3 Conclusion

5.4 Exercises

5.5 Summary

6 Using A Neural Network To Fit Our Data

6.1 Artificial Neurons

6.1.1 All We Need is Activation

6.1.2 What learning means for a neural network

6.2 The PyTorch nn module

6.2.1 Finally a Neural Network

6.3 Subclassing nn.Module

6.3.1 The Functional API

6.4 Conclusion

6.5 Exercises

6.6 Summary

7 Telling Birds from Airplanes - Learning from Images

7.1 A dataset of tiny images

7.1.1 Downloading CIFAR10

7.1.2 The Dataset class

7.1.3 Dataset transforms

7.1.4 Normalizing data

7.2 Distinguishing birds from airplanes

7.2.1 Building the dataset

7.2.2 A fully connected classifier

7.2.3 A loss for classifying

7.2.4 Training the classifier

7.2.5 The limits of going fully connected

7.3 Conclusion

7.4 Exercises

7.5 Summary

8 Using Convolutions To Generalize

8.1 The case for convolutions

8.2 Convolutions in action

8.2.1 Looking further with depth and pooling

8.3 Subclassing nn.Module

8.3.1 The Functional API

8.4 Training our Convnet

8.5 Model Design

8.5.1 Witdh

8.5.2 Depth

8.5.3 Building very deep models in PyTorch

8.5.4 Now it’s already outdated

8.6 Conclusion

8.7 Exercises

8.8 Summary

Part 2: Learning from Images in the Real-World: Early Detection of Lung Cancer

9 Using PyTorch To Fight Cancer

9.1 What is a CT scan, exactly?

9.2 The project: an end-to-end malignancy detector for lung cancer

9.2.1 Why can’t we just throw data at a neural network until it works?

9.2.2 What is a nodule?

9.2.3 The LUNA Grand Challenge

9.2.4 How to download the LUNA data

9.3 Conclusion

9.4 Summary

10 Ready, Dataset, Go!

10.1 Parsing LUNA’s annotation data

10.2 Loading individual CT scans

10.2.1 Hounsfield Units

10.3 Locating a nodule using the patient coordinate system

10.3.1 Extracting a nodule from a CT scan

10.4 A straightforward Dataset implementation

10.4.1 The getCtRawNodule function

10.4.2 LunaDataset.init

10.4.3 A Training / Validation Split

10.4.4 Rendering the data

10.5 Conclusion

10.6 Exercises

10.7 Summary

11 Classifying Suspected Tumors

11.1 The main entrypoint for our application

11.2 Pre-training setup and initialization

11.2.1 Initalizing the model and optimizer

11.2.2 Care and feeding of DataLoaders

11.3 Our first-pass neural network design

11.3.1 The Core Convolutions

11.3.2 The Full Model

11.4 Training and validating the model

11.4.1 Deleting the loss variable

11.4.2 The computeBatchLoss function

11.4.3 The validation loop is similar

11.5 The logMetrics function

11.6 Running the training script

11.6.1 Needed data for training

11.6.2 Interlude: the enumerateWithEstimate function

11.7 Getting 99.7% correct means we’re done, right?

11.8 Graphing training metrics with TensorBoard

11.8.1 Running TensorBoard

11.8.2 Adding tensorboard support to our metrics logging function

11.9 Why is the model not learning how to detect malignant tumors?

11.10 Conclusion

11.11 Exercises

11.12 Summary

12 Monitoring Metrics: Precision, Recall, and Pretty Pictures

12.1 Good dogs versus bad guys: false positives and false negatives

12.2 Graphing the positives and negatives

12.2.1 Recall

12.2.2 Precision

12.2.3 Implementing precision and recall in logMetrics

12.2.4 Our ultimate performance metric: the F1 score

12.2.5 How does our model perform with our new metrics?

12.3 What does an ideal data set look like

12.3.1 Making the data look less like the actual, and more like the "ideal"

12.3.2 Changes to training.py, dset.py to balance benign and malignant samples

12.3.3 Contrasting training with a balanced LunaDataset to previous runs

12.4 Revisiting the problem of over-fitting

12.4.1 An over-fit face-to-age prediction model

12.4.2 Detecting over-fitting

12.5 Data Augmentation

12.5.1 Specific Data Augmentation Techniques

12.5.2 Seeing the improvement from data augmentation

12.6 Conclusion

12.7 Exercises

12.8 Summary

13 Using Segmentation To Find Suspected Nodules

13.1 Segmentation is per-pixel classification

13.1.1 The UNet architecture

13.1.2 An off-the-shelf model: adding UNet to our project

13.2 A 3D Dataset in 2D

13.2.1 UNet has very specific input size requirements

13.2.2 UNet in 3D would use too much RAM

13.2.3 Building the ground truth data

13.2.4 Implementing the Luna2dSegmentationDataset

13.3 Updating the training script

13.3.1 Getting images into tensorboard

13.3.2 Dice loss

13.3.3 Updating our metrics logging

13.3.4 Saving our model

13.4 Implementing the clustering and diagnosis script

13.4.1 Segmenting

13.4.2 Clustering

13.4.3 Classifying

13.4.4 What do we see when we diagnose

13.5 Deploying to production

13.5.1 Our model behind a Flask server

13.5.2 Moving away from Python

13.5.3 TorchScript

13.6 Additional sources of inspiration (and data)

13.6.1 The Data Science Bowl 2017

13.6.2 LUNA papers

13.7 Conclusion

13.7.1 Behind the curtain

13.8 Exercises

13.9 Summary

About the Technology

PyTorch is a machine learning framework with a strong focus on deep neural networks. Because it emphasizes GPU-based acceleration, PyTorch performs exceptionally well on readily-available hardware and scales easily to larger systems. Plus it’s Pythonic! Thanks to its define-by-run computation graph model, PyTorch plays nicely with the Python data science ecosystem. It’s instantly familiar if you’re using Numpy, Pandas, or other similar tools.

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 how to implement deep learning algorithms with Python and PyTorch. This book takes you into a fascinating case study: building an algorithm capable of detecting malignant lung tumors using CT scans. As the authors guide you through this real example, you'll discover just how effective and fun PyTorch can be. After a quick introduction to the deep learning landscape, you'll explore the use of pre-trained networks and start sharpening your skills on working with tensors. You'll find out how to represent the most common types of data with tensors and how to build and train neural networks from scratch on practical examples, focusing on images and sequences.

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

  • Using the PyTorch tensor API
  • Understanding automatic differentiation in PyTorch
  • Training deep neural networks
  • Monitoring training and visualizing results
  • Implementing modules and loss functions
  • Loading data in Python for PyTorch
  • Interoperability with NumPy
  • Deploying a PyTorch model for inference

About the reader

Written for developers with some knowledge of Python as well as basic linear algebra skills. Some understanding of deep learning will be helpful, however no experience with PyTorch or other deep learning frameworks is required.

About the author

Eli Stevens has worked in Silicon Valley for the past 15 years as a software engineer, and the past 7 years as Chief Technical Officer of a startup making medical device software. Luca Antiga is co-founder and CEO of an AI engineering company located in Bergamo, Italy, and a regular contributor to PyTorch.
Deep Learning with PyTorch authors Luca Antiga (L) and Eli Stevenson (R) eating dessert in San Francisco's Mission District with the book's editor Frances Lefkowitz. Luca is from Bergamo, Italy, Eli lives in San Jose, and Frances hails from San Francisco.

Manning Early Access Program (MEAP) Read chapters as they are written, get the finished eBook as soon as it’s ready, and receive the pBook long before it's in bookstores.
MEAP combo $49.99 pBook + eBook + liveBook
MEAP eBook $39.99 pdf + ePub + kindle + liveBook
Prices displayed in rupees will be charged in USD when you check out.

placing your order...

Don't refresh or navigate away from the page.

FREE domestic shipping on three or more pBooks