FaissClusteringParameters

Class for the clustering parameters. Can be passed to the constructor of the Clustering object.

Members

Variables

decode_block_size
size_t decode_block_size;

< how many vectors at a time to decode

frozen_centroids
int frozen_centroids;

< (bool) use the centroids provided as input and do

int_centroids
int int_centroids;

< (bool) round centroids coordinates to integer

max_points_per_centroid
int max_points_per_centroid;

< to limit size of dataset

min_points_per_centroid
int min_points_per_centroid;

< not change them during iterations +////< otherwise you get a warnin

niter
int niter;

< clustering iterations

nredo
int nredo;

< redo clustering this many times and keep best

seed
int seed;

< seed for the random number generator

spherical
int spherical;

< (bool) do we want normalized centroids?

update_index
int update_index;

< (bool) update index after each iteration?

verbose
int verbose;

< (bool)

Meta