Click or drag to resize

ANN_MLP Class

Artificial Neural Networks - Multi-Layer Perceptrons.
Inheritance Hierarchy

Namespace:  OpenCvSharp.ML
Assembly:  OpenCvSharp (in OpenCvSharp.dll) Version: 1.0.0
Syntax
public class ANN_MLP : StatModel

The ANN_MLP type exposes the following members.

Constructors
  NameDescription
Protected methodANN_MLP
Creates instance by raw pointer cv::ml::ANN_MLP*
Top
Properties
  NameDescription
Protected propertyAllocatedMemory
Gets or sets a memory address allocated by AllocMemory.
(Inherited from DisposableObject.)
Protected propertyAllocatedMemorySize
Gets or sets the byte length of the allocated memory
(Inherited from DisposableObject.)
Public propertyBackpropMomentumScale
Strength of the momentum term (the difference between weights on the 2 previous iterations). This parameter provides some inertia to smooth the random fluctuations of the weights. It can vary from 0 (the feature is disabled) to 1 and beyond. The value 0.1 or so is good enough. Default value is 0.1.
Public propertyBackpropWeightScale
Strength of the weight gradient term. The recommended value is about 0.1. Default value is 0.1.
Public propertyCvPtr
Native pointer of OpenCV structure
(Inherited from DisposableCvObject.)
Protected propertyDataHandle
Gets or sets a handle which allocates using cvSetData.
(Inherited from DisposableObject.)
Public propertyEmpty
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read
(Inherited from Algorithm.)
Public propertyIsDisposed
Gets a value indicating whether this instance has been disposed.
(Inherited from DisposableObject.)
Public propertyIsEnabledDispose
Gets or sets a value indicating whether you permit disposing this instance.
(Inherited from DisposableObject.)
Public propertyRpropDW0
Initial value Delta_0 of update-values Delta_{ij}. Default value is 0.1.
Public propertyRpropDWMax
Update-values upper limit Delta_{max}. It must be >1. Default value is 50.
Public propertyRpropDWMin
Update-values lower limit Delta_{min}. It must be positive. Default value is FLT_EPSILON.
Public propertyRpropDWMinus
Decrease factor eta^-. It must be \>1. Default value is 0.5.
Public propertyRpropDWPlus
Increase factor eta^+. It must be >1. Default value is 1.2.
Public propertyTermCriteria
Termination criteria of the training algorithm.
Top
Methods
  NameDescription
Protected methodAllocGCHandle
Pins the object to be allocated by cvSetData.
(Inherited from DisposableObject.)
Protected methodAllocMemory
Allocates the specified size of memory.
(Inherited from DisposableObject.)
Public methodCalcError
Computes error on the training or test dataset
(Inherited from StatModel.)
Public methodStatic memberCreate
Creates the empty model.
Public methodDispose
Releases the resources
(Inherited from DisposableObject.)
Protected methodDispose(Boolean)
Releases the resources
(Inherited from DisposableObject.)
Protected methodDisposeManaged
Releases managed resources
(Overrides DisposableObjectDisposeManaged.)
Protected methodDisposeUnmanaged
releases unmanaged resources
(Inherited from DisposableCvObject.)
Public methodEmpty
(Inherited from StatModel.)
Public methodEquals
Determines whether the specified object is equal to the current object.
(Inherited from Object.)
Protected methodFinalize
Destructor
(Inherited from DisposableObject.)
Public methodGetDefaultName
Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.
(Inherited from Algorithm.)
Public methodGetHashCode
Serves as the default hash function.
(Inherited from Object.)
Public methodGetLayerSizes
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.
Public methodGetType
Gets the Type of the current instance.
(Inherited from Object.)
Public methodGetVarCount
Returns the number of variables in training samples
(Inherited from StatModel.)
Public methodIsClassifier
Returns true if the model is classifier
(Inherited from StatModel.)
Public methodIsTrained
Returns true if the model is trained
(Inherited from StatModel.)
Public methodStatic memberLoad
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.
Public methodStatic memberLoadFromString
Loads algorithm from a String.
Protected methodMemberwiseClone
Creates a shallow copy of the current Object.
(Inherited from Object.)
Protected methodNotifyMemoryPressure
Notifies the allocated size of memory.
(Inherited from DisposableObject.)
Public methodPredict
Predicts response(s) for the provided sample(s)
(Inherited from StatModel.)
Public methodRead
Reads algorithm parameters from a file storage
(Inherited from Algorithm.)
Public methodSave
Saves the algorithm to a file. In order to make this method work, the derived class must implement Algorithm::write(FileStorage fs).
(Inherited from Algorithm.)
Public methodSetLayerSizes
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.
Public methodThrowIfDisposed
If this object is disposed, then ObjectDisposedException is thrown.
(Inherited from DisposableObject.)
Public methodToString
Returns a string that represents the current object.
(Inherited from Object.)
Public methodTrain(TrainData, Int32)
Trains the statistical model
(Inherited from StatModel.)
Public methodTrain(InputArray, SampleTypes, InputArray)
Trains the statistical model
(Inherited from StatModel.)
Public methodWrite
Stores algorithm parameters in a file storage
(Inherited from Algorithm.)
Top
Fields
  NameDescription
Protected fieldptr
Data pointer
(Inherited from DisposableCvObject.)
Top
See Also