faiss::ScalarQuantizer Struct Reference

#include <IndexIVFScalarQuantizer.h>

Public Types
enum	QuantizerType { QT_8bit, QT_4bit, QT_8bit_uniform, QT_4bit_uniform }
enum	RangeStat { RS_minmax, RS_meanstd, RS_quantiles, RS_optim }

Public Member Functions
	ScalarQuantizer (size_t d, QuantizerType qtype)
void	train (size_t n, const float *x)
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, size_t n) const
	decode a vector from a given code (or n vectors if third argument)

Public Attributes
QuantizerType	qtype
RangeStat	rangestat
float	rangestat_arg
size_t	d
	dimension of input vectors
size_t	code_size
	bytes per vector
std::vector< float >	trained
	trained values (including the range)

Detailed Description

An IVF implementation where the components of the residuals are encoded with a scalar uniform quantizer. All distance computations are asymmetric, so the encoded vectors are decoded and approximate distances are computed.

The uniform quantizer has a range [vmin, vmax]. The range can be the same for all dimensions (uniform) or specific per dimension (default).

Definition at line 34 of file IndexIVFScalarQuantizer.h.

Member Enumeration Documentation

enum faiss::ScalarQuantizer::QuantizerType

Enumerator
QT_8bit	8 bits per component
QT_4bit	4 bits per component
QT_8bit_uniform	same, shared range for all dimensions

Definition at line 36 of file IndexIVFScalarQuantizer.h.

enum faiss::ScalarQuantizer::RangeStat

The uniform encoder can estimate the range of representable values of the unform encoder using different statistics. Here rs = rangestat_arg

Enumerator
RS_minmax	[min - rs*(max-min), max + rs*(max-min)]
RS_meanstd	[mean - std * rs, mean + std * rs]
RS_quantiles	[Q(rs), Q(1-rs)]
RS_optim	alternate optimization of reconstruction error

Definition at line 50 of file IndexIVFScalarQuantizer.h.

---

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

• /data/users/matthijs/github_faiss/faiss/IndexIVFScalarQuantizer.h
• /data/users/matthijs/github_faiss/faiss/IndexIVFScalarQuantizer.cpp