Home Projects MinkowskiEngine
MinkowskiEngine
Python

MinkowskiEngine

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

by NVIDIA · GitHub
Stars
Forks
Created
Last commit
Language
3d-convolutional-network3d-vision4d-convolutional-neural-networkPython
View on GitHub
In plain words

Build and train neural networks that work with complex data structures using a library designed for high-dimensional data.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
MinkowskiEngine — GitHub preview card
📈 Star history
2 9412 939
2026-07-072026-08-31
📈 Track MinkowskiEngine

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

MinkowskiEngine has 2.9k stars on GitHub. It has been forked 480 times. MinkowskiEngine is written mainly in Python. It has been in active development since 2019. Its main topics are 3d-convolutional-network, 3d-vision, 4d-convolutional-neural-network, auto-differentiation.

Frequently asked questions

What is MinkowskiEngine?

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Is MinkowskiEngine open source?

MinkowskiEngine is an open-source project.

Is MinkowskiEngine free?

Yes. MinkowskiEngine is free and open source — you can use, modify and self-host it.

What language is MinkowskiEngine written in?

MinkowskiEngine is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — MinkowskiEngine

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=nvidia-minkowskiengine)](https://olud.ai/project/nvidia-minkowskiengine.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.