|
mlpack
master
|
TrainVisitor sets the reference set to a new reference set on the given NSType. More...
Public Types | |
| template<template< typename TreeMetricType, typename TreeStatType, typename TreeMatType > class TreeType> | |
| using | NSTypeT = NSType< SortPolicy, TreeType > |
| Alias template necessary for visual c++ compiler. More... | |
Public Member Functions | |
| TrainVisitor (arma::mat &&referenceSet, const size_t leafSize, const double tau, const double rho) | |
| Construct the TrainVisitor object with the given reference set, leafSize for BinarySpaceTrees, and tau and rho for spill trees. More... | |
| template<template< typename TreeMetricType, typename TreeStatType, typename TreeMatType > class TreeType> | |
| void | operator() (NSTypeT< TreeType > *ns) const |
| Default Train on the given NSType instance. More... | |
| void | operator() (NSTypeT< tree::KDTree > *ns) const |
| Train on the given NSType specialized for KDTrees. More... | |
| void | operator() (NSTypeT< tree::BallTree > *ns) const |
| Train on the given NSType specialized for BallTrees. More... | |
| void | operator() (SpillKNN *ns) const |
| Train specialized for SPTrees. More... | |
| void | operator() (NSTypeT< tree::Octree > *ns) const |
| Train specialized for octrees. More... | |
Private Member Functions | |
| template<typename NSType > | |
| void | TrainLeaf (NSType *ns) const |
| Train on the given NSType considering the leafSize. More... | |
Private Attributes | |
| size_t | leafSize |
| The leaf size, used only by BinarySpaceTree. More... | |
| arma::mat && | referenceSet |
| The reference set to use for training. More... | |
| const double | rho |
| Balance threshold (for spill trees). More... | |
| const double | tau |
| Overlapping size (for spill trees). More... | |
TrainVisitor sets the reference set to a new reference set on the given NSType.
We use template specialization to differentiate those tree types that accept leafSize as a parameter. In these cases, a reference tree with proper leafSize is built from the referenceSet.
Definition at line 35 of file neighbor_search.hpp.
| using mlpack::neighbor::TrainVisitor< SortPolicy >::NSTypeT = NSType<SortPolicy, TreeType> |
Alias template necessary for visual c++ compiler.
Definition at line 183 of file ns_model.hpp.
| mlpack::neighbor::TrainVisitor< SortPolicy >::TrainVisitor | ( | arma::mat && | referenceSet, |
| const size_t | leafSize, | ||
| const double | tau, | ||
| const double | rho | ||
| ) |
Construct the TrainVisitor object with the given reference set, leafSize for BinarySpaceTrees, and tau and rho for spill trees.
| void mlpack::neighbor::TrainVisitor< SortPolicy >::operator() | ( | NSTypeT< TreeType > * | ns | ) | const |
Default Train on the given NSType instance.
| void mlpack::neighbor::TrainVisitor< SortPolicy >::operator() | ( | NSTypeT< tree::KDTree > * | ns | ) | const |
Train on the given NSType specialized for KDTrees.
| void mlpack::neighbor::TrainVisitor< SortPolicy >::operator() | ( | NSTypeT< tree::BallTree > * | ns | ) | const |
Train on the given NSType specialized for BallTrees.
| void mlpack::neighbor::TrainVisitor< SortPolicy >::operator() | ( | SpillKNN * | ns | ) | const |
Train specialized for SPTrees.
| void mlpack::neighbor::TrainVisitor< SortPolicy >::operator() | ( | NSTypeT< tree::Octree > * | ns | ) | const |
Train specialized for octrees.
|
private |
Train on the given NSType considering the leafSize.
|
private |
The leaf size, used only by BinarySpaceTree.
Definition at line 168 of file ns_model.hpp.
|
private |
The reference set to use for training.
Definition at line 166 of file ns_model.hpp.
|
private |
Balance threshold (for spill trees).
Definition at line 172 of file ns_model.hpp.
|
private |
Overlapping size (for spill trees).
Definition at line 170 of file ns_model.hpp.
1.8.11
