#include <ProductQuantizer.h>

Public Types
enum	train_type_t { Train_default, Train_hot_start, Train_shared, Train_hypercube, Train_hypercube_pca }
	initialization More...

Public Member Functions
float *	get_centroids (size_t m, size_t i)
	return the centroids associated with subvector m

const float *	get_centroids (size_t m, size_t i) const

void	train (int n, const float *x)

	ProductQuantizer (size_t d, size_t M, size_t nbits)

void	set_derived_values ()
	compute derived values when d, M and nbits have been set

void	set_params (const float *centroids, int m)
	Define the centroids for subquantizer m.

void	compute_code (const float x, uint8_t code) const
	Quantize one vector with the product quantizer.

void	compute_codes (const float x, uint8_t codes, size_t n) const
	same as compute_code for several vectors

void	decode (const uint8_t code, float x) const
	decode a vector from a given code (or n vectors if third argument)

void	decode (const uint8_t code, float x, size_t n) const

void	compute_code_from_distance_table (const float tab, uint8_t code) const

void	compute_distance_table (const float x, float dis_table) const

void	compute_inner_prod_table (const float x, float dis_table) const

void	compute_distance_tables (size_t nx, const float x, float dis_tables) const

void	compute_inner_prod_tables (size_t nx, const float x, float dis_tables) const

void	search (const float x, size_t nx, const uint8_t codes, const size_t ncodes, float_maxheap_array_t *res, bool init_finalize_heap=true) const

void	search_ip (const float x, size_t nx, const uint8_t codes, const size_t ncodes, float_minheap_array_t *res, bool init_finalize_heap=true) const

void	compute_sdc_table ()

void	search_sdc (const uint8_t qcodes, size_t nq, const uint8_t bcodes, const size_t ncodes, float_maxheap_array_t *res, bool init_finalize_heap=true) const

Public Attributes
size_t	d
	size of the input vectors

size_t	M
	number of subquantizers

size_t	nbits
	number of bits per quantization index

size_t	dsub
	dimensionality of each subvector

size_t	byte_per_idx
	nb bytes per code component (1 or 2)

size_t	code_size
	byte per indexed vector

size_t	ksub
	number of centroids for each subquantizer

bool	verbose
	verbose during training?

train_type_t	train_type

ClusteringParameters	cp
	parameters used during clustering

std::vector< float >	centroids
	Centroid table, size M * ksub * dsub.

std::vector< float >	sdc_table
	Symmetric Distance Table.

Detailed Description

Product Quantizer. Implemented only for METRIC_L2

Definition at line 26 of file ProductQuantizer.h.

Member Enumeration Documentation

enum faiss::ProductQuantizer::train_type_t

initialization

Enumerator
Train_hot_start	the centroids are already initialized
Train_shared	share dictionary accross PQ segments
Train_hypercube	intialize centroids with nbits-D hypercube
Train_hypercube_pca	intialize centroids with nbits-D hypercube

Definition at line 41 of file ProductQuantizer.h.

Member Function Documentation

void faiss::ProductQuantizer::compute_code_from_distance_table	(	const float *	tab,
		uint8_t *	code
	)		const

If we happen to have the distance tables precomputed, this is more efficient to compute the codes.

Definition at line 363 of file ProductQuantizer.cpp.

void faiss::ProductQuantizer::compute_distance_table	(	const float *	x,
		float *	dis_table
	)		const

Compute distance table for one vector.

The distance table for x = [x_0 x_1 .. x_(M-1)] is a M * ksub matrix that contains

dis_table (m, j) = || x_m - c_(m, j)||^2 for m = 0..M-1 and j = 0 .. ksub - 1

where c_(m, j) is the centroid no j of sub-quantizer m.

Parameters

x	input vector size d
dis_table	output table, size M * ksub

Definition at line 410 of file ProductQuantizer.cpp.

void faiss::ProductQuantizer::compute_distance_tables	(	size_t	nx,
		const float *	x,
		float *	dis_tables
	)		const

compute distance table for several vectors

Parameters

nx	nb of input vectors
x	input vector size nx * d
dis_table	output table, size nx * M * ksub

Definition at line 439 of file ProductQuantizer.cpp.

void faiss::ProductQuantizer::search	(	const float *	x,
		size_t	nx,
		const uint8_t *	codes,
		const size_t	ncodes,
		float_maxheap_array_t *	res,
		bool	init_finalize_heap = `true`
	)		const

perform a search (L2 distance)

Parameters

x	query vectors, size nx * d
nx	nb of queries
codes	database codes, size ncodes * byte_per_idx
ncodes	nb of nb vectors
res	heap array to store results (nh == nx)
init_finalize_heap	initialize heap (input) and sort (output)?

Definition at line 540 of file ProductQuantizer.cpp.

void faiss::ProductQuantizer::search_ip	(	const float *	x,
		size_t	nx,
		const uint8_t *	codes,
		const size_t	ncodes,
		float_minheap_array_t *	res,
		bool	init_finalize_heap = `true`
	)		const

same as search, but with inner product similarity

Definition at line 564 of file ProductQuantizer.cpp.

The documentation for this struct was generated from the following files:

Public Types

Public Member Functions

Public Attributes

Detailed Description

Member Enumeration Documentation

Member Function Documentation