Create an svm-problem of all available data. In case of FeatureTables all the tables in FeatureData are read to create one svm_problem. In case of distributed precomputed kernels it makes a dummy svm_problem. If Filter...Fold is called, this function wil only return a part of the whole set. The returned structure must be deleted with FreeProblem(). Implemented in Impala::Core::Training::TrainDataSrcFeature, Impala::Core::Training::TrainDataSrcFeatureTable, Impala::Core::Training::TrainDataSrcKernelDistributed, Impala::Core::Training::TrainDataSrcKernelMatrix, and Impala::Core::Training::TrainDataSrcKernelTable. Referenced by Impala::Core::Training::Svm::Predict(), Impala::Core::Training::Tester::TestMakeSvmProblem(), and Impala::Core::Training::Svm::Train().
|
1.5.1