#include <IndexBinaryFlat.h>

Inheritance diagram for faiss::IndexBinaryFlat:

Public Member Functions
	IndexBinaryFlat (idx_t d)

void	add (idx_t n, const uint8_t *x) override

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

void	search (idx_t n, const uint8_t x, idx_t k, int32_t distances, idx_t *labels) const override

void	reconstruct (idx_t key, uint8_t *recons) const override

long	remove_ids (const IDSelector &sel) override

Public Member Functions inherited from faiss::IndexBinary
	IndexBinary (idx_t d=0, MetricType metric=METRIC_L2)

virtual void	train (idx_t n, const uint8_t *x)

virtual void	add_with_ids (idx_t n, const uint8_t x, const long xids)

virtual void	range_search (idx_t n, const uint8_t x, int radius, RangeSearchResult result) const

void	assign (idx_t n, const uint8_t x, idx_t labels, idx_t k=1)

virtual void	reconstruct_n (idx_t i0, idx_t ni, uint8_t *recons) const

virtual void	search_and_reconstruct (idx_t n, const uint8_t x, idx_t k, int32_t distances, idx_t labels, uint8_t recons) const

void	display () const

Public Attributes
std::vector< uint8_t >	xb
	database vectors, size ntotal * d / 8

bool	use_heap = true

size_t	query_batch_size = 32

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

int	code_size
	number of bytes per vector ( = d / 8 )

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

Additional Inherited Members
Public Types inherited from faiss::IndexBinary
using	idx_t = Index::idx_t
	all indices are this type

using	component_t = uint8_t

using	distance_t = int32_t

Detailed Description

Index that stores the full vectors and performs exhaustive search.

Definition at line 21 of file IndexBinaryFlat.h.

Member Function Documentation

void faiss::IndexBinaryFlat::add	(	idx_t	n,
		const uint8_t *	x
	)

overridevirtual

Add n vectors of dimension d to the index.

Vectors are implicitly assigned labels ntotal .. ntotal + n - 1

Parameters

x	input matrix, size n * d / 8

Implements faiss::IndexBinary.

Definition at line 24 of file IndexBinaryFlat.cpp.

void faiss::IndexBinaryFlat::reconstruct	(	idx_t	key,
		uint8_t *	recons
	)		const

overridevirtual

Reconstruct a stored vector.

This function may not be defined for some indexes.

Parameters

key	id of the vector to reconstruct
recons	reconstucted vector (size d / 8)

Reimplemented from faiss::IndexBinary.

Definition at line 78 of file IndexBinaryFlat.cpp.

long faiss::IndexBinaryFlat::remove_ids ( const IDSelector & sel )

overridevirtual

Remove some ids. Note that because of the indexing structure, the semantics of this operation are different from the usual ones: the new ids are shifted.

Reimplemented from faiss::IndexBinary.

Definition at line 58 of file IndexBinaryFlat.cpp.

void faiss::IndexBinaryFlat::search	(	idx_t	n,
		const uint8_t *	x,
		idx_t	k,
		int32_t *	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 / 8
labels	output labels of the NNs, size n*k
distances	output pairwise distances, size n*k

Implements faiss::IndexBinary.

Definition at line 34 of file IndexBinaryFlat.cpp.

Member Data Documentation

bool faiss::IndexBinaryFlat::use_heap = true

Select between using a heap or counting to select the k smallest values when scanning inverted lists.

Definition at line 28 of file IndexBinaryFlat.h.

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

/data/users/hoss/faiss/IndexBinaryFlat.h
/data/users/hoss/faiss/IndexBinaryFlat.cpp

Public Member Functions

Public Attributes

Additional Inherited Members

Detailed Description

Member Function Documentation

Member Data Documentation