Package org.opencv.ml

Class ANN_MLP


public class ANN_MLP extends StatModel
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. SEE: REF: ml_intro_ann
  • Field Details

  • Constructor Details

    • ANN_MLP

      protected ANN_MLP(long addr)
  • Method Details

    • __fromPtr__

      public static ANN_MLP __fromPtr__(long addr)
    • 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 and to initialT for ANN_MLP::ANNEAL.
      param2 - passed to setRpropDWMin for ANN_MLP::RPROP and to setBackpropMomentumScale for ANN_MLP::BACKPROP and to finalT for ANN_MLP::ANNEAL.
    • setTrainMethod

      public void setTrainMethod(int method, double param1)
      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 and to initialT for ANN_MLP::ANNEAL.
    • setTrainMethod

      public void setTrainMethod(int method)
      Sets training method and common parameters.
      Parameters:
      method - Default value is ANN_MLP::RPROP. See ANN_MLP::TrainingMethods.
    • getTrainMethod

      public int getTrainMethod()
      Returns current training method
      Returns:
      automatically generated
    • 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, \(\alpha\). Default value is 0.
      param2 - The second parameter of the activation function, \(\beta\). Default value is 0.
    • setActivationFunction

      public void setActivationFunction(int type, double param1)
      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, \(\alpha\). Default value is 0.
    • setActivationFunction

      public void setActivationFunction(int type)
      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.
    • setLayerSizes

      public void setLayerSizes(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. SEE: getLayerSizes
      Parameters:
      _layer_sizes - automatically generated
    • getLayerSizes

      public 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. SEE: setLayerSizes
      Returns:
      automatically generated
    • getTermCriteria

      public TermCriteria getTermCriteria()
      SEE: setTermCriteria
      Returns:
      automatically generated
    • setTermCriteria

      public void setTermCriteria(TermCriteria val)
      getTermCriteria SEE: getTermCriteria
      Parameters:
      val - automatically generated
    • getBackpropWeightScale

      public double getBackpropWeightScale()
      SEE: setBackpropWeightScale
      Returns:
      automatically generated
    • setBackpropWeightScale

      public void setBackpropWeightScale(double val)
      getBackpropWeightScale SEE: getBackpropWeightScale
      Parameters:
      val - automatically generated
    • getBackpropMomentumScale

      public double getBackpropMomentumScale()
      SEE: setBackpropMomentumScale
      Returns:
      automatically generated
    • setBackpropMomentumScale

      public void setBackpropMomentumScale(double val)
      getBackpropMomentumScale SEE: getBackpropMomentumScale
      Parameters:
      val - automatically generated
    • getRpropDW0

      public double getRpropDW0()
      SEE: setRpropDW0
      Returns:
      automatically generated
    • setRpropDW0

      public void setRpropDW0(double val)
      getRpropDW0 SEE: getRpropDW0
      Parameters:
      val - automatically generated
    • getRpropDWPlus

      public double getRpropDWPlus()
      SEE: setRpropDWPlus
      Returns:
      automatically generated
    • setRpropDWPlus

      public void setRpropDWPlus(double val)
      getRpropDWPlus SEE: getRpropDWPlus
      Parameters:
      val - automatically generated
    • getRpropDWMinus

      public double getRpropDWMinus()
      SEE: setRpropDWMinus
      Returns:
      automatically generated
    • setRpropDWMinus

      public void setRpropDWMinus(double val)
      getRpropDWMinus SEE: getRpropDWMinus
      Parameters:
      val - automatically generated
    • getRpropDWMin

      public double getRpropDWMin()
      SEE: setRpropDWMin
      Returns:
      automatically generated
    • setRpropDWMin

      public void setRpropDWMin(double val)
      getRpropDWMin SEE: getRpropDWMin
      Parameters:
      val - automatically generated
    • getRpropDWMax

      public double getRpropDWMax()
      SEE: setRpropDWMax
      Returns:
      automatically generated
    • setRpropDWMax

      public void setRpropDWMax(double val)
      getRpropDWMax SEE: getRpropDWMax
      Parameters:
      val - automatically generated
    • getAnnealInitialT

      public double getAnnealInitialT()
      SEE: setAnnealInitialT
      Returns:
      automatically generated
    • setAnnealInitialT

      public void setAnnealInitialT(double val)
      getAnnealInitialT SEE: getAnnealInitialT
      Parameters:
      val - automatically generated
    • getAnnealFinalT

      public double getAnnealFinalT()
      SEE: setAnnealFinalT
      Returns:
      automatically generated
    • setAnnealFinalT

      public void setAnnealFinalT(double val)
      getAnnealFinalT SEE: getAnnealFinalT
      Parameters:
      val - automatically generated
    • getAnnealCoolingRatio

      public double getAnnealCoolingRatio()
      SEE: setAnnealCoolingRatio
      Returns:
      automatically generated
    • setAnnealCoolingRatio

      public void setAnnealCoolingRatio(double val)
      getAnnealCoolingRatio SEE: getAnnealCoolingRatio
      Parameters:
      val - automatically generated
    • getAnnealItePerStep

      public int getAnnealItePerStep()
      SEE: setAnnealItePerStep
      Returns:
      automatically generated
    • setAnnealItePerStep

      public void setAnnealItePerStep(int val)
      getAnnealItePerStep SEE: getAnnealItePerStep
      Parameters:
      val - automatically generated
    • getWeights

      public Mat getWeights(int layerIdx)
    • create

      public static ANN_MLP create()
      Creates empty model Use StatModel::train to train the model, Algorithm::load<ANN_MLP>(filename) to load the pre-trained model. Note that the train method has optional flags: ANN_MLP::TrainFlags.
      Returns:
      automatically generated
    • load

      public static ANN_MLP load(String filepath)
      Loads and creates a serialized ANN from a file Use ANN::save to serialize and store an ANN to disk. Load the ANN from this file again, by calling this function with the path to the file.
      Parameters:
      filepath - path to serialized ANN
      Returns:
      automatically generated
    • finalize

      protected void finalize() throws Throwable
      Overrides:
      finalize in class StatModel
      Throws:
      Throwable