Fast and memory-efficient clustering
Project description
PQk-means [Matsui, Ogaki, Yamasaki, and Aizawa, ACMMM 17] is a Python library for efficient clustering of large-scale data. By first compressing input vectors into short product-quantized (PQ) codes, PQk-means achieves fast and memory-efficient clustering, even for high-dimensional vectors. Similar to k-means, PQk-means repeats the assignment and update steps, both of which can be performed in the PQ-code domain. For a comparison, we provide the ITQ encoding for the binary conversion and Binary k-means [Gong+, CVPR 15] for the clustering of binary codes. The library is written in C++ for the main algorithm with wrappers for Python. All encoding/clustering codes are compatible with scikit-learn.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for pqkmeans-1.0.3-py3.7-macosx-10.7-x86_64.egg
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4a03b8e8bdba9b2613ac80de8ac28d502d1f68cfaaff3570c78c78f7f6633a5b |
|
MD5 | 71ea66f6cbbd6cec5d31ea24f5a0996f |
|
BLAKE2b-256 | f1469a74f06962861ac31789f288ae49f2d4516ec54c29631ad582dec031634a |