Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/fx2y/densim
Densim is a library for efficient similarity search and clustering of dense vectors, which are numerical representations of data such as images, text, or audio.
https://github.com/fx2y/densim
audio-processing clustering data-science dense-vectors image-processing large-scale-dataset machine-learning numerical-representation parameter-tuning performance-optimization similarity-search text-analysis
Last synced: about 2 months ago
JSON representation
Densim is a library for efficient similarity search and clustering of dense vectors, which are numerical representations of data such as images, text, or audio.
- Host: GitHub
- URL: https://github.com/fx2y/densim
- Owner: fx2y
- License: mit
- Created: 2023-09-24T08:53:41.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-09-24T13:48:46.000Z (over 1 year ago)
- Last Synced: 2024-01-26T07:10:25.382Z (12 months ago)
- Topics: audio-processing, clustering, data-science, dense-vectors, image-processing, large-scale-dataset, machine-learning, numerical-representation, parameter-tuning, performance-optimization, similarity-search, text-analysis
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Densim
Densim is a library for efficient similarity search and clustering of dense vectors, which are numerical representations of data such as images, text, or audio. It supports various methods for similarity search, such as exact search, approximate search, binary search, and product quantization, as well as cosine similarity, Jaccard distance, and additive quantization. The library can handle large-scale datasets that do not fit in RAM, and provides tools for evaluation and parameter tuning.
## Contributing
Contributions to Densim are welcome! Please see the [CONTRIBUTING.md](CONTRIBUTING.md) file for guidelines.
## License
Densim is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.