| Operators |
add_sample_class_svm — Add a training sample to the training data of a support vector machine.
add_sample_class_svm adds a training sample to the support vector machine (SVM) given by SVMHandle. The training sample is given by Features and Class. Features is the feature vector of the sample, and consequently must be a real vector of length NumFeatures, as specified in create_class_svm. Class is the target of the sample, which must be in the range of 0 to NumClasses-1 (see create_class_svm). In the special case of novelty detection the class is to be set to 0 as only one class is assumed. Before the SVM can be trained with train_class_svm, training samples must be added to the SVM with add_sample_class_svm. The usage of support vectors of an already trained SVM as training samples is described in train_class_svm.
The number of currently stored training samples can be queried with get_sample_num_class_svm. Stored training samples can be read out again with get_sample_class_svm.
Normally, it is useful to save the training samples in a file with write_samples_class_svm to facilitate reusing the samples and to facilitate that, if necessary, new training samples can be added to the data set, and hence to facilitate that a newly created SVM can be trained with the extended data set.
This operator modifies the state of the following input parameter:
The value of this parameter may not be shared across multiple threads without external synchronization.SVM handle.
Feature vector of the training sample to be stored.
Class of the training sample to be stored.
If the parameters are valid the operator add_sample_class_svm returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.
train_class_svm, write_samples_class_svm, get_sample_num_class_svm, get_sample_class_svm
clear_samples_class_svm, get_support_vector_class_svm
Foundation
| Operators |