knncolle_annoy
Annoy nearest neighbors in knncolle
|
Prebuilt index for an Annoy search. More...
#include <knncolle_annoy.hpp>
Public Member Functions | |
size_t | num_dimensions () const |
Index_ | num_observations () const |
std::unique_ptr< knncolle::Searcher< Index_, Data_, Distance_ > > | initialize () const |
![]() |
Friends | |
class | AnnoySearcher< Index_, Data_, Distance_, AnnoyDistance_, AnnoyIndex_, AnnoyData_, AnnoyRng_, AnnoyThreadPolicy_ > |
Prebuilt index for an Annoy search.
Instances of this class are usually constructed using AnnoyBuilder::build_raw()
.
Index_ | Integer type for the observation indices. |
Data_ | Numeric type for the input and query data. |
Distance_ | Floating-point type for the distances. |
AnnoyDistance_ | An Annoy-compatible class to compute the distance between vectors, e.g., Annoy::Euclidean , Annoy::Manhattan . Note that this is not the same as knncolle::DistanceMetric . |
AnnoyIndex_ | Integer type for the observation indices in the Annoy index. |
AnnoyData_ | Floating-point type for data in the Annoy index. This defaults to a float instead of a double to sacrifice some accuracy for performance. |
AnnoyRng_ | An Annoy class for random number generation. |
AnnoyThreadPolicy_ | An Annoy class for the threadedness of Annoy index building. |
|
inlinevirtual |
Creates a AnnoySearcher
instance.
Implements knncolle::Prebuilt< Index_, Data_, Distance_ >.
|
inlinevirtual |
Implements knncolle::Prebuilt< Index_, Data_, Distance_ >.
|
inlinevirtual |
Implements knncolle::Prebuilt< Index_, Data_, Distance_ >.