PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing. It is primarily developed by Facebook's AI Research lab.

Tutorials

Learning PyTorch with Examples
This tutorial introduces the fundamental concepts of PyTorch through self-contained examples.
pytorch tutorial
Machine Learning Basics
A practical set of notebooks on machine learning basics, implemented in both TF2.0 + Keras and PyTorch.
deep-learning natural-language-processing tensorflow pytorch
Understanding PyTorch with an example: a step-by-step tutorial
Structured, incremental and from first principles approach to PyTorch.
pytorch tutorial article

Libraries

General
Fast Block Sparse Matrices for Pytorch
Enables networks which are both smaller and faster to let anybody use neural networks in production at low cost, and to improve the experience for the end ...
sparsity pytorch gpu efficiency
Einops
Flexible and powerful tensor operations for readable and reliable code. Supports numpy, pytorch, tensorflow, and others.
einops numpy pytorch tensorflow
Torchfunc
PyTorch functions & utilities to make your deep learning life easier
pytorch functions utilities library
Torchlayers
Shape inference for PyTorch (like Keras) & new layers
pytorch library inference shape
Torchdata
Equip PyTorch's Dataset with map, cache etc. (like tf.data)
pytorch tensorflow dataset cache
Torchlambda
Lightweight tool to deploy PyTorch models to AWS Lambda
deep-learning pytorch aws deployment
PyTorch Metric Learning
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
metrics custom-metrics pytorch losses
TorchCDE
Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.
neural-ode time-series pytorch torchcde
Table of Contents
Share a project
Share something you or the community has made with ML.
Topic experts
Share