ziyzhu / scalable-k-means-plus-plus

Stanford Scalable K-Means++ implementation in C++ with benchmarking.

Scalable-K-Means-plus-plus

Stanford Scalable Kmeans|| implementation in C++

Files

• ./datasets: test datasets
• ./generator.py: python script used to generate test datasets
• ./kmeans_parallel.cpp: contains both parallelized k-means|| and kmeans++ implementation
• ./kmeans_serial.cpp: sequential k-means clustering implementation

Requirements

• at least gcc-5.4.0
• TBB

build

make

run

make test // modify ./Makefile to change test dataset