Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
| Date | Stars |
|---|---|
| 2026-07-24 | 2946 |
| 2026-07-25 | 2946 |
| 2026-07-28 | 2950 |
| 2026-07-30 | 2950 |
| 2026-07-31 | 2952 |
| 2026-08-02 | 2952 |
| 2026-08-03 | 2952 |
| 2026-08-05 | 2953 |
| 2026-08-06 | 2953 |
Today
— stars today
This week
+3 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.10%/day
[pypi-image]: https://badge.fury.io/py/MinkowskiEngine.svg [pypi-url]: https://pypi.org/project/MinkowskiEngine/ [pypi-download]: https://img.shields.io/pypi/dm/MinkowskiEngine [slack-badge]: https://img.shields.io/badge/slack-join%20chats-brightgreen [slack-url]: https://join.slack.com/t/minkowskiengine/shared_invite/zt-piq2x02a-31dOPocLt6bRqOGY3U_9Sw # Minkowski Engine [![PyPI Version][pypi-image]][pypi-url] [![pypi monthly download][pypi-download]][pypi-url] [![slack chat][slack-badge]][slack-url] The Minkowski Engine is an auto-differentiation library for sparse tensors. It supports all standard neural network layers such as convolution, pooling, unpooling, and broadcasting operations for sparse tensors. For more information, please visit [the documentation page](http://nvidia.github.io/MinkowskiEngine/overview.html). ## News - 2021-08-11 Docker installation instruction added - 2021-08-06 All installation errors with pytorch 1.8 and 1.9 have been resolved. - 2021-04-08 Due to recent errors in [pytorch 1.8 + CUDA 11](https://github.com/NVIDIA/MinkowskiEngine/issues/330), it is recommended to use [anaconda for installation](#anaconda). - 2020-12-24 v0.5 is now available! The new version provides CUDA accelerations for all coordinate management functions. ## Example Networks The Minkowski Engine supports various functions that can be built on a sparse tensor. We list a few popular network architectures and applications here. To run the examples, please install the package and run the command in the package root directory. | Examples | Networks and Commands | |:---------------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| | Semantic Segmentation | <img src="https://nvidia.github.io/MinkowskiEngine/_images/segmentation_3d_net.png"> <br /> <img src="https://nvidia.github.io/MinkowskiEngine/_images/segmentation.png" width="256"> <br /> `python -m examples.indoor` | | Classification |  <br /> `python -m examples.classification_modelnet40` | | Reconstruction | <img src="https://nvidia.github.io/MinkowskiEngine/_images/generative_3d_net.png"> <br /> <img src="https://nvidia.github.io/MinkowskiEngine/_images/generative_3d_results.gif" width="256"> <br /> `python -m examples.reconstruction` | | Completion | <img src="https://nvidia.github.io/MinkowskiEngine/_images/completion_3d_net.png"> <br /> `python -m examples.completion` | | Detection | <img src="https://nvidia.github.io/MinkowskiEngine/_images/detection_3d_net.png"> | ## Sparse Tensor Networks: Neural Networks for Spatially Sparse Tensors Compressing a neural network to speedup inference and minimize memory footprint has been studied widely. One of the popular techniques for model compression is pruning the weights in convnets, is also known as [*sparse convolutional networks*](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Liu_Sparse_Convolutional_Neural_2015_CVPR_paper.pdf). Such parameter-space sparsity used for model compression compresses networks that operate on dense tensors and all intermediate activations of these networks are also dense tensors. However, in this work, we focus on [*spatially* sparse data](https://arxiv.org/abs/1409.6070), in particular, spatially sparse high-dimensional inputs and 3D data and convolution on the surface of 3D objects, first proposed in [Siggraph'17](https://wang-ps.github.io/O-CNN.html). W
Excerpt of 19,943 characters
Read on GitHub
Chris Choy · NVIDIA
503
3
Jan Lebert · University of California, San Francisco · United States
2
Ran Cheng · Canada
2
Xiaoyang Wu · The University of Hong Kong
1
1
1
1
Charles Coulombe · Calcul Québec - DRAC - UseGalaxy.ca · Canada
1
1
1
1
Ignacio Rocco
1
1
1
Nicolas Chaulet · @CanoaPBC · United States
1
Rémi Lacroix · IDRIS - CNRS · France
1
1
Jiabao Lei · China
1
ZhuLifa
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ba437d2c04c4a9a9, topic:deep-learning, topic:neural-network, topic:pytorch