#include <VectorTransform.h>

Inheritance diagram for faiss::OPQMatrix:

Public Member Functions
	OPQMatrix (int d=0, int M=1, int d2=-1)
	if d2 != -1, output vectors of this dimension

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

virtual void	reverse_transform (idx_t n, const float xt, float x) const override

Public Member Functions inherited from faiss::LinearTransform
	LinearTransform (int d_in=0, int d_out=0, bool have_bias=false)
	both d_in > d_out and d_out < d_in are supported

virtual void	apply_noalloc (idx_t n, const float x, float xt) const
	same as apply, but result is pre-allocated

void	transform_transpose (idx_t n, const float y, float x) const

const float *	maybe_subsample_train_set (Index::idx_t n, const float x)

Public Member Functions inherited from faiss::VectorTransform
	VectorTransform (int d_in=0, int d_out=0)
	! output dimension

float *	apply (idx_t n, const float *x) const

Public Attributes
int	M
	nb of subquantizers

int	niter
	Number of outer training iterations.

int	niter_pq
	Number of training iterations for the PQ.

int	niter_pq_0

int	max_points_per_d
	if there are too many training points, resample

bool	verbose

Public Attributes inherited from faiss::LinearTransform
bool	have_bias

std::vector< float >	A
	! whether to use the bias term More...

std::vector< float >	b
	bias vector, size d_out

size_t	max_points_per_d

bool	verbose

Public Attributes inherited from faiss::VectorTransform
int	d_in

int	d_out
	! input dimension

bool	is_trained

Additional Inherited Members
Public Types inherited from faiss::VectorTransform
typedef Index::idx_t	idx_t

Detailed Description

Applies a rotation to align the dimensions with a PQ to minimize the reconstruction error. Can be used before an IndexPQ or an IndexIVFPQ. The method is the non-parametric version described in:

"Optimized Product Quantization for Approximate Nearest Neighbor Search" Tiezheng Ge, Kaiming He, Qifa Ke, Jian Sun, CVPR'13

Definition at line 188 of file VectorTransform.h.

Member Function Documentation

void OPQMatrix::reverse_transform	(	idx_t	n,
		const float *	xt,
		float *	x
	)		const

overridevirtual

reverse transformation. May not be implemented or may return approximate result

Reimplemented from faiss::VectorTransform.

Definition at line 630 of file VectorTransform.cpp.

void OPQMatrix::train	(	Index::idx_t	n,
		const float *	x
	)

overridevirtual

Perform training on a representative set of vectors. Does nothing by default.

Parameters

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

Reimplemented from faiss::VectorTransform.

Definition at line 469 of file VectorTransform.cpp.

Member Data Documentation

int faiss::OPQMatrix::niter_pq_0

same, for the first outer iteration

Definition at line 193 of file VectorTransform.h.

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

Public Member Functions

Public Attributes

Additional Inherited Members

Detailed Description

Member Function Documentation

Member Data Documentation