File IndexIVFPQ.h¶
-
namespace faiss
Copyright (c) Facebook, Inc. and its affiliates.
This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree.
Throughout the library, vectors are provided as float * pointers. Most algorithms can be optimized when several vectors are processed (added/searched) together in a batch. In this case, they are passed in as a matrix. When n vectors of size d are provided as float * x, component j of vector i is
x[ i * d + j ]
where 0 <= i < n and 0 <= j < d. In other words, matrices are always compact. When specifying the size of the matrix, we call it an n*d matrix, which implies a row-major storage.
Copyright (c) Facebook, Inc. and its affiliates.
This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. I/O functions can read/write to a filename, a file handle or to an object that abstracts the medium.
The read functions return objects that should be deallocated with delete. All references within these objectes are owned by the object.
Copyright (c) Facebook, Inc. and its affiliates.
This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. Definition of inverted lists + a few common classes that implement the interface.
Copyright (c) Facebook, Inc. and its affiliates.
This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. Since IVF (inverted file) indexes are of so much use for large-scale use cases, we group a few functions related to them in this small library. Most functions work both on IndexIVFs and IndexIVFs embedded within an IndexPreTransform.
Copyright (c) Facebook, Inc. and its affiliates.
This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. In this file are the implementations of extra metrics beyond L2 and inner product
Copyright (c) Facebook, Inc. and its affiliates.
This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. Defines a few objects that apply transformations to a set of vectors Often these are pre-processing steps.
Functions
-
void initialize_IVFPQ_precomputed_table(int &use_precomputed_table, const Index *quantizer, const ProductQuantizer &pq, AlignedTable<float> &precomputed_table, bool by_residual, bool verbose)¶
Pre-compute distance tables for IVFPQ with by-residual and METRIC_L2
- Parameters:
use_precomputed_table – (I/O) =-1: force disable =0: decide heuristically (default: use tables only if they are < precomputed_tables_max_bytes), set use_precomputed_table on output =1: tables that work for all quantizers (size 256 * nlist * M) =2: specific version for MultiIndexQuantizer (much more compact)
precomputed_table – precomputed table to initialize
Variables
- FAISS_API size_t precomputed_table_max_bytes
- FAISS_API int index_ivfpq_add_core_o_bs
- FAISS_API IndexIVFPQStats indexIVFPQ_stats
-
struct IVFPQSearchParameters : public faiss::SearchParametersIVF¶
-
struct IndexIVFPQ : public faiss::IndexIVF¶
- #include <IndexIVFPQ.h>
Inverted file with Product Quantizer encoding. Each residual vector is encoded as a product quantizer code.
Subclassed by faiss::IndexIVFPQR
Public Functions
-
IndexIVFPQ(Index *quantizer, size_t d, size_t nlist, size_t M, size_t nbits_per_idx, MetricType metric = METRIC_L2)¶
-
virtual void encode_vectors(idx_t n, const float *x, const idx_t *list_nos, uint8_t *codes, bool include_listnos = false) const override¶
Encodes a set of vectors as they would appear in the inverted lists
- Parameters:
list_nos – inverted list ids as returned by the quantizer (size n). -1s are ignored.
codes – output codes, size n * code_size
include_listno – include the list ids in the code (in this case add ceil(log8(nlist)) to the code size)
-
virtual void sa_decode(idx_t n, const uint8_t *bytes, float *x) const override¶
decode a set of vectors
- Parameters:
n – number of vectors
bytes – input encoded vectors, size n * sa_code_size()
x – output vectors, size n * d
-
virtual void add_core(idx_t n, const float *x, const idx_t *xids, const idx_t *precomputed_idx) override¶
Implementation of vector addition where the vector assignments are predefined. The default implementation hands over the code extraction to encode_vectors.
- Parameters:
precomputed_idx – quantization indices for the input vectors (size n)
-
void add_core_o(idx_t n, const float *x, const idx_t *xids, float *residuals_2, const idx_t *precomputed_idx = nullptr)¶
same as add_core, also:
output 2nd level residuals if residuals_2 != NULL
accepts precomputed_idx = nullptr
-
void train_residual_o(idx_t n, const float *x, float *residuals_2)¶
same as train_residual, also output 2nd level residuals
-
virtual void reconstruct_from_offset(int64_t list_no, int64_t offset, float *recons) const override¶
Reconstruct a vector given the location in terms of (inv list index + inv list offset) instead of the id.
Useful for reconstructing when the direct_map is not maintained and the inv list offset is computed by search_preassigned() with
store_pairs
set.
-
size_t find_duplicates(idx_t *ids, size_t *lims) const¶
Find exact duplicates in the dataset.
the duplicates are returned in pre-allocated arrays (see the max sizes).
- Parameters:
lims – limits between groups of duplicates (max size ntotal / 2 + 1)
ids – ids[lims[i]] : ids[lims[i+1]-1] is a group of duplicates (max size ntotal)
- Returns:
n number of groups found
-
void encode_multiple(size_t n, idx_t *keys, const float *x, uint8_t *codes, bool compute_keys = false) const¶
Encode multiple vectors
- Parameters:
n – nb vectors to encode
keys – posting list ids for those vectors (size n)
x – vectors (size n * d)
codes – output codes (size n * code_size)
compute_keys – if false, assume keys are precomputed, otherwise compute them
-
void decode_multiple(size_t n, const idx_t *keys, const uint8_t *xcodes, float *x) const¶
inverse of encode_multiple
-
virtual InvertedListScanner *get_InvertedListScanner(bool store_pairs, const IDSelector *sel) const override¶
Get a scanner for this index (store_pairs means ignore labels)
The default search implementation uses this to compute the distances
-
void precompute_table()¶
build precomputed table
-
IndexIVFPQ()¶
Public Members
-
bool by_residual¶
Encode residual or plain vector?
-
ProductQuantizer pq¶
produces the codes
-
bool do_polysemous_training¶
reorder PQ centroids after training?
-
PolysemousTraining *polysemous_training¶
if NULL, use default
-
size_t scan_table_threshold¶
use table computation or on-the-fly?
-
int polysemous_ht¶
Hamming thresh for polysemous filtering.
-
int use_precomputed_table¶
Precompute table that speed up query preprocessing at some memory cost (used only for by_residual with L2 metric)
-
AlignedTable<float> precomputed_table¶
if use_precompute_table size nlist * pq.M * pq.ksub
-
IndexIVFPQ(Index *quantizer, size_t d, size_t nlist, size_t M, size_t nbits_per_idx, MetricType metric = METRIC_L2)¶
-
struct IndexIVFPQStats¶
- #include <IndexIVFPQ.h>
statistics are robust to internal threading, but not if IndexIVFPQ::search_preassigned is called by multiple threads
-
void initialize_IVFPQ_precomputed_table(int &use_precomputed_table, const Index *quantizer, const ProductQuantizer &pq, AlignedTable<float> &precomputed_table, bool by_residual, bool verbose)¶