#include <IndexPQ.h>

Inheritance diagram for faiss::IndexPQ:

Public Types
enum	Search_type_t { ST_PQ, ST_HE, ST_generalized_HE, ST_SDC, ST_polysemous, ST_polysemous_generalize }
	how to perform the search in search_core More...

Public Types inherited from faiss::Index
typedef long	idx_t
	all indices are this type

Public Member Functions
	IndexPQ (int d, size_t M, size_t nbits, MetricType metric=METRIC_L2)

void	train (idx_t n, const float *x) override

void	add (idx_t n, const float *x) override

void	search (idx_t n, const float x, idx_t k, float distances, idx_t *labels) const override

void	reset () override
	removes all elements from the database.

void	reconstruct_n (idx_t i0, idx_t ni, float *recons) const override

void	reconstruct (idx_t key, float *recons) const override

void	search_core_polysemous (idx_t n, const float x, idx_t k, float distances, idx_t *labels) const

void	hamming_distance_histogram (idx_t n, const float x, idx_t nb, const float xb, long *dist_histogram)

void	hamming_distance_table (idx_t n, const float x, int32_t dis) const

Public Member Functions inherited from faiss::Index
	Index (idx_t d=0, MetricType metric=METRIC_INNER_PRODUCT)

virtual void	add_with_ids (idx_t n, const float x, const long xids)

virtual void	range_search (idx_t n, const float x, float radius, RangeSearchResult result) const

void	assign (idx_t n, const float x, idx_t labels, idx_t k=1)

virtual long	remove_ids (const IDSelector &sel)

void	compute_residual (const float x, float residual, idx_t key) const

void	display () const

Public Attributes
ProductQuantizer	pq
	The product quantizer used to encode the vectors.

std::vector< uint8_t >	codes
	Codes. Size ntotal * pq.code_size.

bool	do_polysemous_training
	false = standard PQ

PolysemousTraining	polysemous_training
	parameters used for the polysemous training

Search_type_t	search_type

bool	encode_signs

int	polysemous_ht
	Hamming threshold used for polysemy.

Public Attributes inherited from faiss::Index
int	d
	vector dimension

idx_t	ntotal
	total nb of indexed vectors

bool	verbose
	verbosity level

bool	is_trained
	set if the Index does not require training, or if training is done already

MetricType	metric_type
	type of metric this index uses for search

Detailed Description

Index based on a product quantizer. Stored vectors are approximated by PQ codes.

Definition at line 28 of file IndexPQ.h.

Member Enumeration Documentation

enum faiss::IndexPQ::Search_type_t

how to perform the search in search_core

Enumerator
ST_PQ	asymmetric product quantizer (default)
ST_HE	Hamming distance on codes.
ST_generalized_HE	nb of same codes
ST_SDC	symmetric product quantizer (SDC)
ST_polysemous	HE filter (using ht) + PQ combination.
ST_polysemous_generalize	Filter on generalized Hamming.

Definition at line 75 of file IndexPQ.h.

Constructor & Destructor Documentation

faiss::IndexPQ::IndexPQ	(	int	d,
		size_t	M,
		size_t	nbits,
		MetricType	metric = `METRIC_L2`
	)

Constructor.

Parameters

d	dimensionality of the input vectors
M	number of subquantizers
nbits	number of bit per subvector index

Parameters

d	dimensionality of the input vectors
M	number of subquantizers
nbits	number of bit per subvector index

Definition at line 33 of file IndexPQ.cpp.

Member Function Documentation

void faiss::IndexPQ::add	(	idx_t	n,
		const float *	x
	)

overridevirtual

Add n vectors of dimension d to the index.

Vectors are implicitly assigned labels ntotal .. ntotal + n - 1 This function slices the input vectors in chuncks smaller than blocksize_add and calls add_core.

Parameters

x	input matrix, size n * d

Implements faiss::Index.

Definition at line 78 of file IndexPQ.cpp.

void faiss::IndexPQ::hamming_distance_histogram	(	idx_t	n,
		const float *	x,
		idx_t	nb,
		const float *	xb,
		long *	dist_histogram
	)

prepare query for a polysemous search, but instead of computing the result, just get the histogram of Hamming distances. May be computed on a provided dataset if xb != NULL

Parameters

dist_histogram (M * nbits + 1)

Definition at line 382 of file IndexPQ.cpp.

void faiss::IndexPQ::hamming_distance_table	(	idx_t	n,
		const float *	x,
		int32_t *	dis
	)		const

compute pairwise distances between queries and database

Parameters

n	nb of query vectors
x	query vector, size n * d
dis	output distances, size n * ntotal

Definition at line 370 of file IndexPQ.cpp.

void faiss::IndexPQ::reconstruct	(	idx_t	key,
		float *	recons
	)		const

overridevirtual

Reconstruct a stored vector (or an approximation if lossy coding)

this function may not be defined for some indexes

Parameters

key	id of the vector to reconstruct
recons	reconstucted vector (size d)

Reimplemented from faiss::Index.

Definition at line 104 of file IndexPQ.cpp.

void faiss::IndexPQ::reconstruct_n	(	idx_t	i0,
		idx_t	ni,
		float *	recons
	)		const

overridevirtual

Reconstruct vectors i0 to i0 + ni - 1

this function may not be defined for some indexes

Parameters

recons reconstucted vector (size ni * d)

Reimplemented from faiss::Index.

Definition at line 94 of file IndexPQ.cpp.

void faiss::IndexPQ::search	(	idx_t	n,
		const float *	x,
		idx_t	k,
		float *	distances,
		idx_t *	labels
	)		const

overridevirtual

query n vectors of dimension d to the index.

return at most k vectors. If there are not enough results for a query, the result array is padded with -1s.

Parameters

x	input vectors to search, size n * d
labels	output labels of the NNs, size n*k
distances	output pairwise distances, size n*k

Implements faiss::Index.

Definition at line 124 of file IndexPQ.cpp.

void faiss::IndexPQ::train	(	idx_t	n,
		const float *	x
	)

overridevirtual

Perform training on a representative set of vectors

Parameters

n	nb of training vectors
x	training vecors, size n * d

Reimplemented from faiss::Index.

Definition at line 54 of file IndexPQ.cpp.

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

/data/users/matthijs/github_faiss/faiss/IndexPQ.h
/data/users/matthijs/github_faiss/faiss/IndexPQ.cpp

Public Types

Public Member Functions

Public Attributes

Detailed Description

Member Enumeration Documentation

Constructor & Destructor Documentation

Member Function Documentation