org.bytedeco.javacpp

Class opencv_ml.ANN_MLP

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.javacpp.opencv_core.Algorithm

org.bytedeco.javacpp.helper.opencv_ml.AbstractStatModel

org.bytedeco.javacpp.opencv_ml.StatModel

org.bytedeco.javacpp.opencv_ml.ANN_MLP

All Implemented Interfaces:

AutoCloseable

Enclosing class:

opencv_ml

@Namespace(value="cv::ml")
public static class opencv_ml.ANN_MLP
extends opencv_ml.StatModel

\brief Artificial Neural Networks - Multi-Layer Perceptrons.

Unlike many other models in ML that are constructed and trained at once, in the MLP model these steps are separated. First, a network with the specified topology is created using the non-default constructor or the method ANN_MLP::create. All the weights are set to zeros. Then, the network is trained using a set of input and output vectors. The training procedure can be repeated more than once, that is, the weights can be adjusted based on the new training data.

Additional flags for StatModel::train are available: ANN_MLP::TrainFlags.

\sa \ref ml_intro_ann

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator

Field Summary

Fields

Modifier and Type	Field and Description
static int	BACKPROP enum cv::ml::ANN_MLP::TrainingMethods
static int	GAUSSIAN enum cv::ml::ANN_MLP::ActivationFunctions
static int	IDENTITY enum cv::ml::ANN_MLP::ActivationFunctions
static int	NO_INPUT_SCALE enum cv::ml::ANN_MLP::TrainFlags
static int	NO_OUTPUT_SCALE enum cv::ml::ANN_MLP::TrainFlags
static int	RPROP enum cv::ml::ANN_MLP::TrainingMethods
static int	SIGMOID_SYM enum cv::ml::ANN_MLP::ActivationFunctions
static int	UPDATE_WEIGHTS enum cv::ml::ANN_MLP::TrainFlags

Fields inherited from class org.bytedeco.javacpp.opencv_ml.StatModel

COMPRESSED_INPUT, PREPROCESSED_INPUT, RAW_OUTPUT, UPDATE_MODEL

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
opencv_ml.ANN_MLP(Pointer p) Pointer cast constructor.

Method Summary

Methods

Modifier and Type	Method and Description
static opencv_ml.ANN_MLP	create() \brief Creates empty model
double	getBackpropMomentumScale()
double	getBackpropWeightScale()
opencv_core.Mat	getLayerSizes() Integer vector specifying the number of neurons in each layer including the input and output layers.
double	getRpropDW0()
double	getRpropDWMax()
double	getRpropDWMin()
double	getRpropDWMinus()
double	getRpropDWPlus()
opencv_core.TermCriteria	getTermCriteria()
int	getTrainMethod() Returns current training method
opencv_core.Mat	getWeights(int layerIdx)
void	setActivationFunction(int type)
void	setActivationFunction(int type, double param1, double param2) Initialize the activation function for each neuron.
void	setBackpropMomentumScale(double val) \copybrief getBackpropMomentumScale @see getBackpropMomentumScale
void	setBackpropWeightScale(double val) \copybrief getBackpropWeightScale @see getBackpropWeightScale
void	setLayerSizes(opencv_core.Mat _layer_sizes) Integer vector specifying the number of neurons in each layer including the input and output layers.
void	setRpropDW0(double val) \copybrief getRpropDW0 @see getRpropDW0
void	setRpropDWMax(double val) \copybrief getRpropDWMax @see getRpropDWMax
void	setRpropDWMin(double val) \copybrief getRpropDWMin @see getRpropDWMin
void	setRpropDWMinus(double val) \copybrief getRpropDWMinus @see getRpropDWMinus
void	setRpropDWPlus(double val) \copybrief getRpropDWPlus @see getRpropDWPlus
void	setTermCriteria(opencv_core.TermCriteria val) \copybrief getTermCriteria @see getTermCriteria
void	setTrainMethod(int method)
void	setTrainMethod(int method, double param1, double param2) Sets training method and common parameters.

Methods inherited from class org.bytedeco.javacpp.opencv_ml.StatModel

calcError, empty, getVarCount, isClassifier, isTrained, predict, predict, train, train, train

Methods inherited from class org.bytedeco.javacpp.helper.opencv_ml.AbstractStatModel

loadANN_MLP, loadANN_MLP, loadBoost, loadBoost, loadDTrees, loadDTrees, loadEM, loadEM, loadKNearest, loadKNearest, loadLogisticRegression, loadLogisticRegression, loadNormalBayesClassifier, loadNormalBayesClassifier, loadRTrees, loadRTrees, loadSVM, loadSVM

Methods inherited from class org.bytedeco.javacpp.opencv_core.Algorithm

clear, getDefaultName, position, read, save, save, write

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, hashCode, isNull, limit, limit, maxBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, position, put, setNull, sizeof, toString, totalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

BACKPROP

public static final int BACKPROP

enum cv::ml::ANN_MLP::TrainingMethods

See Also:

Constant Field Values

RPROP

public static final int RPROP

enum cv::ml::ANN_MLP::TrainingMethods

See Also:

Constant Field Values

IDENTITY

public static final int IDENTITY

enum cv::ml::ANN_MLP::ActivationFunctions

See Also:

Constant Field Values

SIGMOID_SYM

public static final int SIGMOID_SYM

enum cv::ml::ANN_MLP::ActivationFunctions

See Also:

Constant Field Values

GAUSSIAN

public static final int GAUSSIAN

enum cv::ml::ANN_MLP::ActivationFunctions

See Also:

Constant Field Values

UPDATE_WEIGHTS

public static final int UPDATE_WEIGHTS

enum cv::ml::ANN_MLP::TrainFlags

See Also:

Constant Field Values

NO_INPUT_SCALE

public static final int NO_INPUT_SCALE

enum cv::ml::ANN_MLP::TrainFlags

See Also:

Constant Field Values

NO_OUTPUT_SCALE

public static final int NO_OUTPUT_SCALE

enum cv::ml::ANN_MLP::TrainFlags

See Also:

Constant Field Values

Constructor Detail

opencv_ml.ANN_MLP

public opencv_ml.ANN_MLP(Pointer p)

Pointer cast constructor. Invokes Pointer.Pointer(Pointer).

Method Detail

setTrainMethod

public void setTrainMethod(int method,
                  double param1,
                  double param2)

Sets training method and common parameters.

Parameters:

method - Default value is ANN_MLP::RPROP. See ANN_MLP::TrainingMethods.

param1 - passed to setRpropDW0 for ANN_MLP::RPROP and to setBackpropWeightScale for ANN_MLP::BACKPROP

param2 - passed to setRpropDWMin for ANN_MLP::RPROP and to setBackpropMomentumScale for ANN_MLP::BACKPROP.

setTrainMethod

public void setTrainMethod(int method)

getTrainMethod

public int getTrainMethod()

Returns current training method

setActivationFunction

public void setActivationFunction(int type,
                         double param1,
                         double param2)

Initialize the activation function for each neuron. Currently the default and the only fully supported activation function is ANN_MLP::SIGMOID_SYM.

Parameters:

type - The type of activation function. See ANN_MLP::ActivationFunctions.

param1 - The first parameter of the activation function, \f$\alpha\f$. Default value is 0.

param2 - The second parameter of the activation function, \f$\beta\f$. Default value is 0.

setActivationFunction

public void setActivationFunction(int type)

setLayerSizes

public void setLayerSizes(@ByVal
                 opencv_core.Mat _layer_sizes)

Integer vector specifying the number of neurons in each layer including the input and output layers. The very first element specifies the number of elements in the input layer. The last element - number of elements in the output layer. Default value is empty Mat. \sa getLayerSizes

getLayerSizes

@ByVal
public opencv_core.Mat getLayerSizes()

Integer vector specifying the number of neurons in each layer including the input and output layers. The very first element specifies the number of elements in the input layer. The last element - number of elements in the output layer. \sa setLayerSizes

getTermCriteria

@ByVal
public opencv_core.TermCriteria getTermCriteria()

See Also:

setTermCriteria

setTermCriteria

public void setTermCriteria(@ByVal
                   opencv_core.TermCriteria val)

\copybrief getTermCriteria @see getTermCriteria

getBackpropWeightScale

public double getBackpropWeightScale()

See Also:

setBackpropWeightScale

setBackpropWeightScale

public void setBackpropWeightScale(double val)

\copybrief getBackpropWeightScale @see getBackpropWeightScale

getBackpropMomentumScale

public double getBackpropMomentumScale()

See Also:

setBackpropMomentumScale

setBackpropMomentumScale

public void setBackpropMomentumScale(double val)

\copybrief getBackpropMomentumScale @see getBackpropMomentumScale

getRpropDW0

public double getRpropDW0()

See Also:

setRpropDW0

setRpropDW0

public void setRpropDW0(double val)

\copybrief getRpropDW0 @see getRpropDW0

getRpropDWPlus

public double getRpropDWPlus()

See Also:

setRpropDWPlus

setRpropDWPlus

public void setRpropDWPlus(double val)

\copybrief getRpropDWPlus @see getRpropDWPlus

getRpropDWMinus

public double getRpropDWMinus()

See Also:

setRpropDWMinus

setRpropDWMinus

public void setRpropDWMinus(double val)

\copybrief getRpropDWMinus @see getRpropDWMinus

getRpropDWMin

public double getRpropDWMin()

See Also:

setRpropDWMin

setRpropDWMin

public void setRpropDWMin(double val)

\copybrief getRpropDWMin @see getRpropDWMin

getRpropDWMax

public double getRpropDWMax()

See Also:

setRpropDWMax

setRpropDWMax

public void setRpropDWMax(double val)

\copybrief getRpropDWMax @see getRpropDWMax

getWeights

@ByVal
public opencv_core.Mat getWeights(int layerIdx)

create

@opencv_core.Ptr
public static opencv_ml.ANN_MLP create()

\brief Creates empty model

Use StatModel::train to train the model, Algorithm::load\(filename) to load the pre-trained model. Note that the train method has optional flags: ANN_MLP::TrainFlags.