get_support_vector_num_class_svmT_get_support_vector_num_class_svmGetSupportVectorNumClassSvmGetSupportVectorNumClassSvmget_support_vector_num_class_svm (Operator)
Name
get_support_vector_num_class_svmT_get_support_vector_num_class_svmGetSupportVectorNumClassSvmGetSupportVectorNumClassSvmget_support_vector_num_class_svm — Return the number of support vectors of a support vector machine.
Signature
def get_support_vector_num_class_svm(svmhandle: HHandle) -> Tuple[int, Sequence[int]]
Description
get_support_vector_num_class_svmget_support_vector_num_class_svmGetSupportVectorNumClassSvmGetSupportVectorNumClassSvmget_support_vector_num_class_svm returns in
NumSupportVectorsNumSupportVectorsNumSupportVectorsnumSupportVectorsnum_support_vectors the number of support vectors that are
stored in the support vector machine (SVM) given by
SVMHandleSVMHandleSVMHandleSVMHandlesvmhandle. get_support_vector_num_class_svmget_support_vector_num_class_svmGetSupportVectorNumClassSvmGetSupportVectorNumClassSvmget_support_vector_num_class_svm should
be called before the labels of individual support vectors are read
out with get_support_vector_class_svmget_support_vector_class_svmGetSupportVectorClassSvmGetSupportVectorClassSvmget_support_vector_class_svm, e.g., for visualizing
which the training data become a SV (see
get_support_vector_class_svmget_support_vector_class_svmGetSupportVectorClassSvmGetSupportVectorClassSvmget_support_vector_class_svm). The number of SVs in each
classifier is listed in NumSVPerSVMNumSVPerSVMNumSVPerSVMnumSVPerSVMnum_svper_svm. The reason that its
sum differs from the Number obtained in NumSupportVectorsNumSupportVectorsNumSupportVectorsnumSupportVectorsnum_support_vectors
is that SV evaluations are reused throughout different
sub-classifiers. NumSVPerSVMNumSVPerSVMNumSVPerSVMnumSVPerSVMnum_svper_svm provides the possibility for
controlling the process of speeding up SVM classification time with
the operator reduce_class_svmreduce_class_svmReduceClassSvmReduceClassSvmreduce_class_svm.
Execution Information
- Multithreading type: reentrant (runs in parallel with non-exclusive operators).
- Multithreading scope: global (may be called from any thread).
- Processed without parallelization.
Parameters
SVMHandleSVMHandleSVMHandleSVMHandlesvmhandle (input_control) class_svm → HClassSvm, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
SVM handle.
NumSupportVectorsNumSupportVectorsNumSupportVectorsnumSupportVectorsnum_support_vectors (output_control) integer → HTupleintHTupleHtuple (integer) (int / long) (Hlong) (Hlong)
Total number of support vectors.
NumSVPerSVMNumSVPerSVMNumSVPerSVMnumSVPerSVMnum_svper_svm (output_control) integer-array → HTupleSequence[int]HTupleHtuple (integer) (int / long) (Hlong) (Hlong)
Number of SV of each sub-SVM.
Result
If SVMHandleSVMHandleSVMHandleSVMHandlesvmhandle is valid the operator
get_sample_num_class_svmget_sample_num_class_svmGetSampleNumClassSvmGetSampleNumClassSvmget_sample_num_class_svm returns the value 2 (
H_MSG_TRUE)
. If
necessary, an exception is raised.
Possible Predecessors
train_class_svmtrain_class_svmTrainClassSvmTrainClassSvmtrain_class_svm
Possible Successors
get_sample_class_svmget_sample_class_svmGetSampleClassSvmGetSampleClassSvmget_sample_class_svm
See also
create_class_svmcreate_class_svmCreateClassSvmCreateClassSvmcreate_class_svm
Module
Foundation