rusty1s/pytorch_cluster
A PyTorch C++ extension library of optimized graph clustering algorithms for deep learning.
Not currently ranked — collecting fresh signals.
star history
This library provides highly optimized implementations of graph cluster algorithms designed to integrate with PyTorch. It includes algorithms such as Graclus for weighted graph cuts, Voxel Grid pooling, Iterative Farthest Point Sampling, k-NN and radius graph generation, and Random Walk sampling. These are commonly used as building blocks in graph neural networks, point cloud processing (e.g., PointNet++), and other geometric deep learning architectures.
Frequently asked
- What is rusty1s/pytorch_cluster?
- A PyTorch C++ extension library of optimized graph clustering algorithms for deep learning.
- Is pytorch_cluster open source?
- Yes — rusty1s/pytorch_cluster is open source, released under the MIT license.
- What language is pytorch_cluster written in?
- rusty1s/pytorch_cluster is primarily written in C++.
- How popular is pytorch_cluster?
- rusty1s/pytorch_cluster has 927 stars on GitHub.
- Where can I find pytorch_cluster?
- rusty1s/pytorch_cluster is on GitHub at https://github.com/rusty1s/pytorch_cluster.