SVM

Objective-C

@interface SVM : StatModel

Swift

class SVM : StatModel

Support Vector Machines.

See

REF: ml_intro_svm

Member of Ml

Methods

  • See

    -setClassWeights:

    Declaration

    Objective-C

    - (nonnull Mat *)getClassWeights;

    Swift

    func getClassWeights() -> Mat

  • Retrieves all the support vectors

     The method returns all the support vectors as a floating-point matrix, where support vectors are
 stored as matrix rows.

    Declaration

    Objective-C

    - (nonnull Mat *)getSupportVectors;

    Swift

    func getSupportVectors() -> Mat

  • Retrieves all the uncompressed support vectors of a linear %SVM

     The method returns all the uncompressed support vectors of a linear %SVM that the compressed
 support vector, used for prediction, was derived from. They are returned in a floating-point
 matrix, where the support vectors are stored as matrix rows.

    Declaration

    Objective-C

    - (nonnull Mat *)getUncompressedSupportVectors;

    Swift

    func getUncompressedSupportVectors() -> Mat

  • Generates a grid for %SVM parameters.

    Declaration

    Objective-C

    + (nonnull ParamGrid *)getDefaultGridPtr:(int)param_id;

    Swift

    class func getDefaultGridPtr(param_id: Int32) -> ParamGrid

    Parameters

    param_id

    %SVM parameters IDs that must be one of the SVM::ParamTypes. The grid is generated for the parameter with this ID.

    The function generates a grid pointer for the specified parameter of the %SVM algorithm. The grid may be passed to the function SVM::trainAuto.

  • Creates empty model. Use StatModel::train to train the model. Since %SVM has several parameters, you may want to find the best parameters for your problem, it can be done with SVM::trainAuto.

    Declaration

    Objective-C

    + (nonnull SVM *)create;

    Swift

    class func create() -> SVM

  • Loads and creates a serialized svm from a file

    Use SVM::save to serialize and store an SVM to disk. Load the SVM from this file again, by calling this function with the path to the file.

    Declaration

    Objective-C

    + (nonnull SVM *)load:(nonnull NSString *)filepath;

    Swift

    class func load(filepath: String) -> SVM

    Parameters

    filepath

    path to serialized svm

  • See

    -setTermCriteria:

    Declaration

    Objective-C

    - (nonnull TermCriteria *)getTermCriteria;

    Swift

    func getTermCriteria() -> TermCriteria

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold
            Cgrid:(nonnull ParamGrid *)Cgrid
        gammaGrid:(nonnull ParamGrid *)gammaGrid
            pGrid:(nonnull ParamGrid *)pGrid
           nuGrid:(nonnull ParamGrid *)nuGrid
        coeffGrid:(nonnull ParamGrid *)coeffGrid
       degreeGrid:(nonnull ParamGrid *)degreeGrid
         balanced:(BOOL)balanced;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32, Cgrid: ParamGrid, gammaGrid: ParamGrid, pGrid: ParamGrid, nuGrid: ParamGrid, coeffGrid: ParamGrid, degreeGrid: ParamGrid, balanced: Bool) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is
    Cgrid

    grid for C
    gammaGrid

    grid for gamma
    pGrid

    grid for p
    nuGrid

    grid for nu
    coeffGrid

    grid for coeff
    degreeGrid

    grid for degree
    balanced

    If true and the problem is 2-class classification then the method creates more balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold
            Cgrid:(nonnull ParamGrid *)Cgrid
        gammaGrid:(nonnull ParamGrid *)gammaGrid
            pGrid:(nonnull ParamGrid *)pGrid
           nuGrid:(nonnull ParamGrid *)nuGrid
        coeffGrid:(nonnull ParamGrid *)coeffGrid
       degreeGrid:(nonnull ParamGrid *)degreeGrid;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32, Cgrid: ParamGrid, gammaGrid: ParamGrid, pGrid: ParamGrid, nuGrid: ParamGrid, coeffGrid: ParamGrid, degreeGrid: ParamGrid) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is
    Cgrid

    grid for C
    gammaGrid

    grid for gamma
    pGrid

    grid for p
    nuGrid

    grid for nu
    coeffGrid

    grid for coeff
    degreeGrid

    grid for degree balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold
            Cgrid:(nonnull ParamGrid *)Cgrid
        gammaGrid:(nonnull ParamGrid *)gammaGrid
            pGrid:(nonnull ParamGrid *)pGrid
           nuGrid:(nonnull ParamGrid *)nuGrid
        coeffGrid:(nonnull ParamGrid *)coeffGrid;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32, Cgrid: ParamGrid, gammaGrid: ParamGrid, pGrid: ParamGrid, nuGrid: ParamGrid, coeffGrid: ParamGrid) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is
    Cgrid

    grid for C
    gammaGrid

    grid for gamma
    pGrid

    grid for p
    nuGrid

    grid for nu
    coeffGrid

    grid for coeff balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold
            Cgrid:(nonnull ParamGrid *)Cgrid
        gammaGrid:(nonnull ParamGrid *)gammaGrid
            pGrid:(nonnull ParamGrid *)pGrid
           nuGrid:(nonnull ParamGrid *)nuGrid;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32, Cgrid: ParamGrid, gammaGrid: ParamGrid, pGrid: ParamGrid, nuGrid: ParamGrid) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is
    Cgrid

    grid for C
    gammaGrid

    grid for gamma
    pGrid

    grid for p
    nuGrid

    grid for nu balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold
            Cgrid:(nonnull ParamGrid *)Cgrid
        gammaGrid:(nonnull ParamGrid *)gammaGrid
            pGrid:(nonnull ParamGrid *)pGrid;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32, Cgrid: ParamGrid, gammaGrid: ParamGrid, pGrid: ParamGrid) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is
    Cgrid

    grid for C
    gammaGrid

    grid for gamma
    pGrid

    grid for p balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold
            Cgrid:(nonnull ParamGrid *)Cgrid
        gammaGrid:(nonnull ParamGrid *)gammaGrid;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32, Cgrid: ParamGrid, gammaGrid: ParamGrid) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is
    Cgrid

    grid for C
    gammaGrid

    grid for gamma balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold
            Cgrid:(nonnull ParamGrid *)Cgrid;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32, Cgrid: ParamGrid) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is
    Cgrid

    grid for C balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses
            kFold:(int)kFold;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat, kFold: Int32) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples.
    kFold

    Cross-validation parameter. The training set is divided into kFold subsets. One subset is used to test the model, the others form the train set. So, the %SVM algorithm is balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • Trains an %SVM with optimal parameters

    Declaration

    Objective-C

    - (BOOL)trainAuto:(nonnull Mat *)samples
           layout:(int)layout
        responses:(nonnull Mat *)responses;

    Swift

    func trainAuto(samples: Mat, layout: Int32, responses: Mat) -> Bool

    Parameters

    samples

    training samples
    layout

    See ml::SampleTypes.
    responses

    vector of responses associated with the training samples. subset is used to test the model, the others form the train set. So, the %SVM algorithm is balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

    The method trains the %SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree. Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

    This function only makes use of SVM::getDefaultGrid for parameter optimization and thus only offers rudimentary parameter options.

    This function works for the classification (SVM::C_SVC or SVM::NU_SVC) as well as for the regression (SVM::EPS_SVR or SVM::NU_SVR). If it is SVM::ONE_CLASS, no optimization is made and the usual %SVM with parameters specified in params is executed.

  • See

    -setC:

    Declaration

    Objective-C

    - (double)getC;

    Swift

    func getC() -> Double

  • See

    -setCoef0:

    Declaration

    Objective-C

    - (double)getCoef0;

    Swift

    func getCoef0() -> Double

  • Retrieves the decision function

    Declaration

    Objective-C

    - (double)getDecisionFunction:(int)i
                        alpha:(nonnull Mat *)alpha
                        svidx:(nonnull Mat *)svidx;

    Swift

    func getDecisionFunction(i: Int32, alpha: Mat, svidx: Mat) -> Double

    Parameters

    i

    the index of the decision function. If the problem solved is regression, 1-class or 2-class classification, then there will be just one decision function and the index should always be 0. Otherwise, in the case of N-class classification, there will be

    N(N-1)/2
    decision functions.
    alpha

    the optional output vector for weights, corresponding to different support vectors. In the case of linear %SVM all the alpha’s will be 1’s.
    svidx

    the optional output vector of indices of support vectors within the matrix of support vectors (which can be retrieved by SVM::getSupportVectors). In the case of linear %SVM each decision function consists of a single “compressed” support vector.

    The method returns rho parameter of the decision function, a scalar subtracted from the weighted sum of kernel responses.

  • See

    -setDegree:

    Declaration

    Objective-C

    - (double)getDegree;

    Swift

    func getDegree() -> Double

  • See

    -setGamma:

    Declaration

    Objective-C

    - (double)getGamma;

    Swift

    func getGamma() -> Double

  • See

    -setNu:

    Declaration

    Objective-C

    - (double)getNu;

    Swift

    func getNu() -> Double

  • See

    -setP:

    Declaration

    Objective-C

    - (double)getP;

    Swift

    func getP() -> Double

  • Type of a %SVM kernel. See SVM::KernelTypes. Default value is SVM::RBF.

    Declaration

    Objective-C

    - (int)getKernelType;

    Swift

    func getKernelType() -> Int32

  • See

    -setType:

    Declaration

    Objective-C

    - (int)getType;

    Swift

    func getType() -> Int32

  • getC - see: -getC:

    Declaration

    Objective-C

    - (void)setC:(double)val;

    Swift

    func setC(val: Double)

  • getClassWeights - see: -getClassWeights:

    Declaration

    Objective-C

    - (void)setClassWeights:(nonnull Mat *)val;

    Swift

    func setClassWeights(val: Mat)

  • getCoef0 - see: -getCoef0:

    Declaration

    Objective-C

    - (void)setCoef0:(double)val;

    Swift

    func setCoef0(val: Double)

  • getDegree - see: -getDegree:

    Declaration

    Objective-C

    - (void)setDegree:(double)val;

    Swift

    func setDegree(val: Double)

  • getGamma - see: -getGamma:

    Declaration

    Objective-C

    - (void)setGamma:(double)val;

    Swift

    func setGamma(val: Double)

  • Initialize with one of predefined kernels. See SVM::KernelTypes.

    Declaration

    Objective-C

    - (void)setKernel:(int)kernelType;

    Swift

    func setKernel(kernelType: Int32)

  • getNu - see: -getNu:

    Declaration

    Objective-C

    - (void)setNu:(double)val;

    Swift

    func setNu(val: Double)

  • getP - see: -getP:

    Declaration

    Objective-C

    - (void)setP:(double)val;

    Swift

    func setP(val: Double)

  • getTermCriteria - see: -getTermCriteria:

    Declaration

    Objective-C

    - (void)setTermCriteria:(nonnull TermCriteria *)val;

    Swift

    func setTermCriteria(val: TermCriteria)

  • getType - see: -getType:

    Declaration

    Objective-C

    - (void)setType:(int)val;

    Swift

    func setType(val: Int32)