|
Faiss
|
|
Faiss
|
#include <IndexBinaryIVF.h>
Public Member Functions | |
| void | train_q1 (size_t n, const uint8_t *x, bool verbose) |
| Trains the quantizer and calls train_residual to train sub-quantizers. | |
| IndexBinaryIVF (IndexBinary *quantizer, size_t d, size_t nlist) | |
| void | reset () override |
| Removes all elements from the database. | |
| void | train (idx_t n, const uint8_t *x) override |
| Trains the quantizer and calls train_residual to train sub-quantizers. | |
| void | add (idx_t n, const uint8_t *x) override |
| Quantizes x and calls add_with_key. | |
| void | add_with_ids (idx_t n, const uint8_t *x, const long *xids) override |
| void | add_core (idx_t n, const uint8_t *x, const long *xids, const long *precomputed_idx) |
| same as add_with_ids, with precomputed coarse quantizer | |
| void | search_preassigned (idx_t n, const uint8_t *x, idx_t k, const idx_t *assign, const int32_t *centroid_dis, int32_t *distances, idx_t *labels, bool store_pairs, const IVFSearchParameters *params=nullptr) const |
| virtual BinaryInvertedListScanner * | get_InvertedListScanner (bool store_pairs=false) const |
| virtual 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 |
| void | reconstruct_n (idx_t i0, idx_t ni, uint8_t *recons) const override |
| void | search_and_reconstruct (idx_t n, const uint8_t *x, idx_t k, int32_t *distances, idx_t *labels, uint8_t *recons) const override |
| virtual void | reconstruct_from_offset (long list_no, long offset, uint8_t *recons) const |
| long | remove_ids (const IDSelector &sel) override |
| Dataset manipulation functions. | |
| virtual void | merge_from (IndexBinaryIVF &other, idx_t add_id) |
| size_t | get_list_size (size_t list_no) const |
| void | make_direct_map (bool new_maintain_direct_map=true) |
| double | imbalance_factor () const |
| 1= perfectly balanced, >1: imbalanced | |
| void | print_stats () const |
| display some stats about the inverted lists | |
| void | replace_invlists (InvertedLists *il, bool own=false) |
 Public Member Functions inherited from faiss::IndexBinary | |
| IndexBinary (idx_t d=0, MetricType metric=METRIC_L2) | |
| 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) |
| void | display () const |
Public Attributes | |
| InvertedLists * | invlists |
| Acess to the actual data. | |
| bool | own_invlists |
| size_t | nprobe |
| number of probes at query time | |
| size_t | max_codes |
| max nb of codes to visit to do a query | |
| bool | use_heap = true |
| bool | maintain_direct_map |
| map for direct access to the elements. Enables reconstruct(). | |
| std::vector< long > | direct_map |
| IndexBinary * | quantizer |
| quantizer that maps vectors to inverted lists | |
| size_t | nlist |
| number of possible key values | |
| bool | own_fields |
| whether object owns the quantizer | |
| ClusteringParameters | cp |
| to override default clustering params | |
| Index * | clustering_index |
| to override index used during clustering | |
| 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 | |
| typedef long | idx_t |
| all indices are this type | |
Index based on a inverted file (IVF)
In the inverted file, the quantizer (an IndexBinary instance) provides a quantization index for each vector to be added. The quantization index maps to a list (aka inverted list or posting list), where the id of the vector is stored.
Otherwise the object is similar to the IndexIVF
Definition at line 36 of file IndexBinaryIVF.h.
| faiss::IndexBinaryIVF::IndexBinaryIVF | ( | IndexBinary * | quantizer, |
| size_t | d, | ||
| size_t | nlist | ||
| ) |
The Inverted file takes a quantizer (an IndexBinary) on input, which implements the function mapping a vector to a list identifier. The pointer is borrowed: the quantizer should not be deleted while the IndexBinaryIVF is in use.
Definition at line 27 of file IndexBinaryIVF.cpp.
|
overridevirtual |
Same as add, but stores xids instead of sequential ids.
The default implementation fails with an assertion, as it is not supported by all indexes.
| xids | if non-null, ids to store for the vectors (size n) |
Reimplemented from faiss::IndexBinary.
Definition at line 61 of file IndexBinaryIVF.cpp.
| void faiss::IndexBinaryIVF::make_direct_map | ( | bool | new_maintain_direct_map = true | ) |
intialize a direct map
| new_maintain_direct_map | if true, create a direct map, else clear it |
Definition at line 105 of file IndexBinaryIVF.cpp.
|
virtual |
moves the entries from another dataset to self. On output, other is empty. add_id is added to all moved ids (for sequential ids, this would be this->ntotal
Definition at line 286 of file IndexBinaryIVF.cpp.
|
overridevirtual |
Reconstruct a stored vector.
This function may not be defined for some indexes.
| key | id of the vector to reconstruct |
| recons | reconstucted vector (size d / 8) |
Reimplemented from faiss::IndexBinary.
Definition at line 141 of file IndexBinaryIVF.cpp.
|
virtual |
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.
Definition at line 203 of file IndexBinaryIVF.cpp.
|
overridevirtual |
Reconstruct a subset of the indexed vectors.
Overrides default implementation to bypass reconstruct() which requires direct_map to be maintained.
| i0 | first vector to reconstruct |
| ni | nb of vectors to reconstruct |
| recons | output array of reconstructed vectors, size ni * d / 8 |
Reimplemented from faiss::IndexBinary.
Definition at line 149 of file IndexBinaryIVF.cpp.
|
overridevirtual |
assign the vectors, then call search_preassign
Implements faiss::IndexBinary.
Definition at line 128 of file IndexBinaryIVF.cpp.
|
overridevirtual |
Similar to search, but also reconstructs the stored vectors (or an approximation in the case of lossy coding) for the search results.
Overrides default implementation to avoid having to maintain direct_map and instead fetch the code offsets through the store_pairs flag in search_preassigned().
| recons | reconstructed vectors size (n, k, d / 8) |
Reimplemented from faiss::IndexBinary.
Definition at line 168 of file IndexBinaryIVF.cpp.
| void faiss::IndexBinaryIVF::search_preassigned | ( | idx_t | n, |
| const uint8_t * | x, | ||
| idx_t | k, | ||
| const idx_t * | assign, | ||
| const int32_t * | centroid_dis, | ||
| int32_t * | distances, | ||
| idx_t * | labels, | ||
| bool | store_pairs, | ||
| const IVFSearchParameters * | params = nullptr |
||
| ) | const |
Search a set of vectors, that are pre-quantized by the IVF quantizer. Fill in the corresponding heaps with the query results. search() calls this.
| n | nb of vectors to query |
| x | query vectors, size nx * d |
| assign | coarse quantization indices, size nx * nprobe |
| centroid_dis | distances to coarse centroids, size nx * nprobe |
| distance | output distances, size n * k |
| labels | output labels, size n * k |
| store_pairs | store inv list index + inv list offset instead in upper/lower 32 bit of result, instead of ids (used for reranking). |
| params | used to override the object's search parameters |
Definition at line 662 of file IndexBinaryIVF.cpp.
| bool faiss::IndexBinaryIVF::use_heap = true |
Select between using a heap or counting to select the k smallest values when scanning inverted lists.
Definition at line 47 of file IndexBinaryIVF.h.
1.8.5
