create_class_knnT_create_class_knnCreateClassKnnCreateClassKnncreate_class_knn (算子)

名称

create_class_knnT_create_class_knnCreateClassKnnCreateClassKnncreate_class_knn — 创建一个 k-最近邻（k-NN）分类器。

签名

描述

create_class_knncreate_class_knnCreateClassKnnCreateClassKnnCreateClassKnncreate_class_knn creates a k-nearest neighbors (k-NN) data structure. This can be either used to classify data or to approximately locate nearest neighbors in a NumDimNumDimNumDimNumDimnumDimnum_dim-dimensional space.

Most of the operators described in Classification/K-Nearest-Neighbor use the resulting handle KNNHandleKNNHandleKNNHandleKNNHandleKNNHandleknnhandle。

The k-NN classifies by searching approximately the nearest neighbors and returning their classes as result. With the used approximation, the search time is logarithmically to the number of samples and dimensions.

The dimension of the feature vectors is the only parameter that necessarily has to be set in NumDimNumDimNumDimNumDimnumDimnum_dim。

执行信息

• 多线程类型：可重入（与非独占算子并行运行）。
• 多线程作用域：全局（可从任何线程调用）。
• 未采用并行化处理。

此算子返回一个句柄。请注意，即使该句柄被用作特定算子的输入参数，这些算子仍可能改变此句柄类型的实例状态。

参数

结果

如果参数有效，算子 create_class_knncreate_class_knnCreateClassKnnCreateClassKnnCreateClassKnncreate_class_knn 返回值 2 ( H_MSG_TRUE )。如有必要，则抛出异常。

可能的后继

add_sample_class_knnadd_sample_class_knnAddSampleClassKnnAddSampleClassKnnAddSampleClassKnnadd_sample_class_knn, train_class_knntrain_class_knnTrainClassKnnTrainClassKnnTrainClassKnntrain_class_knn

替代

create_class_svmcreate_class_svmCreateClassSvmCreateClassSvmCreateClassSvmcreate_class_svm, create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpCreateClassMlpcreate_class_mlp

另见

select_feature_set_knnselect_feature_set_knnSelectFeatureSetKnnSelectFeatureSetKnnSelectFeatureSetKnnselect_feature_set_knn, read_class_knnread_class_knnReadClassKnnReadClassKnnReadClassKnnread_class_knn

参考文献

Marius Muja, David G. Lowe: “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration”; International Conference on Computer Vision Theory and Applications (VISAPP 09); 2009.

模块

基础