Logo
  • Get Started
  • Features
  • Ecosystem
  • Blog
  • Tutorials
  • Docs
  • Resources
  • Github
0.4.1

Beginner Tutorials

  • Deep Learning with PyTorch: A 60 Minute Blitz
    • What is PyTorch?
    • Autograd: automatic differentiation
    • Neural Networks
    • Training a classifier
    • Optional: Data Parallelism
  • PyTorch for former Torch users
  • Learning PyTorch with Examples
  • Transfer Learning tutorial
  • Data Loading and Processing Tutorial
  • Deep Learning for NLP with Pytorch

Intermediate Tutorials

  • Classifying Names with a Character-Level RNN
  • Generating Names with a Character-Level RNN
  • Translation with a Sequence to Sequence Network and Attention
  • Reinforcement Learning (DQN) tutorial
  • Writing Distributed Applications with PyTorch
  • Spatial Transformer Networks Tutorial

Advanced Tutorials

  • Neural Transfer with PyTorch
  • Creating extensions using numpy and scipy
  • Transfering a model from PyTorch to Caffe2 and Mobile using ONNX
  • Custom C++ and CUDA Extensions
  • Docs »
  • Deep Learning with PyTorch: A 60 Minute Blitz
  • View page source

Deep Learning with PyTorch: A 60 Minute Blitz¶

Author: Soumith Chintala

Goal of this tutorial:

  • Understand PyTorch’s Tensor library and neural networks at a high level.
  • Train a small neural network to classify images

This tutorial assumes that you have a basic familiarity of numpy

Note

Make sure you have the torch and torchvision packages installed.

../_images/tensor_illustration_flat.png

What is PyTorch?

../_images/mnist1.png

Neural Networks

../_images/cifar101.png

Training a classifier

../_images/data_parallel.png

Optional: Data Parallelism

Next Previous

© Copyright 2017, PyTorch.

Built with Sphinx using a theme provided by Read the Docs.