基于PyTorch的自组织映射开源库，支持高效训练与可视化。
torchsom: The Reference PyTorch Library for Self-Organizing Maps
- 采用PyTorch实现SOM，支持GPU加速和快速训练。
- 提供降维、聚类与友好可视化功能，兼容scikit-learn接口。
- 适合需要高效SOM实现的机器学习开发者与研究人员。
本文介绍torchsom，一个基于PyTorch的开源Python库，提供自组织映射（SOM）的参考实现。该库具备三大功能：(i) 降维，(ii) 聚类，(iii) 友好的数据可视化。其基于PyTorch后端，实现(i) 通过GPU加速实现快速高效的SOM训练，(ii) 与PyTorch生态系统的易用性和可扩展集成。此外，torchsom遵循scikit-learn API，便于使用与扩展。该库以Apache 2.0许可证发布，测试覆盖率高达90%，源代码与文档可在https://github.com/michelin/TorchSOM获取。
原文摘要 · Abstract (English)
This paper introduces torchsom, an open-source Python library that provides a reference implementation of the Self-Organizing Map (SOM) in PyTorch. This package offers three main features: (i) dimensionality reduction, (ii) clustering, and (iii) friendly data visualization. It relies on a PyTorch backend, enabling (i) fast and efficient training of SOMs through GPU acceleration, and (ii) easy and scalable integrations with PyTorch ecosystem. Moreover, torchsom follows the scikit-learn API for ease of use and extensibility. The library is released under the Apache 2.0 license with 90% test coverage, and its source code and documentation are available at https://github.com/michelin/TorchSOM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。