Deep Learning with PyTorch: A 60 Minute Blitz

Author: Soumith Chintala

What is PyTorch?

PyTorch is a Python-based scientific computing package serving two broad purposes:

• A replacement for NumPy to use the power of GPUs and other accelerators.

• An automatic differentiation library that is useful to implement neural networks.

Goal of this tutorial:

• Understand PyTorch’s Tensor library and neural networks at a high level.

• Train a small neural network to classify images

To run the tutorials below, make sure you have the torch, torchvision, and matplotlib packages installed.

Tensors

In this tutorial, you will learn the basics of PyTorch tensors.

Code

blitz/tensor_tutorial.html

A Gentle Introduction to torch.autograd

Learn about autograd.

Code

blitz/autograd_tutorial.html

Neural Networks

This tutorial demonstrates how you can train neural networks in PyTorch.

Code

blitz/neural_networks_tutorial.html

Training a Classifier

Learn how to train an image classifier in PyTorch by using the CIFAR10 dataset.

Code

blitz/cifar10_tutorial.html