GitHunt
MA

maxschelski/pytorch-cluster-metrics

Pytorch implementation of standard metrics for clustering

pytorch-cluster-metrics

Pytorch implementation of standard metrics for clustering.
Tested on PyTorch = 1.10.1 / cuda11.3_cudnn8_0

So far only the Silhouette score is implemented.
Code for the Silhouette score was developed in NumPy by Alexandre Abraham:
https://gist.github.com/AlexandreAbraham/5544803

Installation

  1. Open a terminal, navigate to the folder where you want to put the repository and clone it:

git clone https://github.com/maxschelski/pytorch-cluster-metrics.git

  1. Navigate into the folder of the repository (pytorch-cluster-metrics):

cd pytorch-cluster-metrics

  1. Install torchclustermetrics locally using pip:

pip install -e .

For any questions feel free to contact me via E-Mail to max.schelski@googlemail.com.

Usage

from torchclustermetrics import silhouette

score = silhouette.score(X, labels)

Languages

Python100.0%

Contributors

GNU General Public License v3.0
Created March 19, 2022
Updated January 12, 2025
maxschelski/pytorch-cluster-metrics | GitHunt