What better option for this week’s free eBook than the brand new Manning published Deep Learning with PyTorch, made freely available via PyTorch’s website for a limited time (we don’t know how limited, so grab it now).
Written by Eli Stevens, Luca Antiga, and Thomas Viehmann, 3 people with serious PyTorch bona fides, Soumith Chintala, co-creator of PyTorch, writes the following in the foreword:
With the publication of Deep Learning with PyTorch, we finally have a definitive treatise on PyTorch. It covers the basics and abstractions in great detail, tearing apart the underpinnings of data structures like tensors and neural networks and making sure you understand their implementation. Additionally, it covers advanced subjects such as JIT and deployment to production (an aspect of PyTorch that no other book currently covers).
Lots of organizations have made the move to PyTorch, and it doesn’t seem to be a trend that will stop anytime soon. The project has a large community, and numerous recent APIs such as PyTorch Lightning, fastai, and torchlayers make the library even more flexible and easy to use than ever. A robust ecosystem centered on PyTorch has evolved and rivals that of any other neural network framework out there.
Why PyTorch? From the first chapter of the book:
As Python does for programming, PyTorch provides an excellent introduction to deep learning. At the same time, PyTorch has been proven to be fully qualified for use in professional contexts for real-world, high-profile work. We believe that PyTorch’s clear syntax, streamlined API, and easy debugging make it an excellent choice for introducing deep learning. We highly recommend studying PyTorch for your first deep learning library. Whether it ought to be the last deep learning library you learn is a decision we leave up to you.
If you head over to the PyTorch website you can grab your own PDF copy by filling out the simple form — which only asks what your role is and what it is you are going to build with PyTorch (no email == no spam) — a seemingly reasonable trade-off to get your hands on the book. Once you do, you can see what is covered in the table of contents:
- Introduction to Deep Learning and the PyTorch Library
- Pre-trained Networks
- It Starts with a Tensor
- Real-World Data Representation Using Tensors
- The Mechanics of Learning
- Using a Neural Network to Fit the Data
- Telling Birds from Airplanes: Learning from Images
- Using Convolutions to Generalize
- Using PyTorch to Fight Cancer
- Ready, Dataset, Go!
- Training a Classification Model to Detect Suspected Tumors
- Monitoring Metrics: Precision, Recall, and Pretty Pictures
- Using Segmentation to Find Suspected Nodules
- End-to-End Nodule Analysis, and Where to Got Next
- Deploying to Production
Manning highlights these main points on their website as to what you will find in the book:
- Training deep neural networks
- Implementing modules and loss functions
- Utilizing pretrained models from PyTorch Hub
- Exploring code samples in Jupyter Notebooks
I, for one, am excited to get into this book, and am appreciative of PyTorch’s move to make it freely available for a limited time before it is officially released. A great public relations move, but also one which benefits the community of PyTorch researchers and students just the same.