weka.dl4j.listener

Class TrainingListener

java.lang.Object

org.deeplearning4j.optimize.api.BaseTrainingListener

weka.dl4j.listener.TrainingListener

All Implemented Interfaces:

java.io.Serializable, org.deeplearning4j.optimize.api.TrainingListener, weka.core.OptionHandler

Direct Known Subclasses:

EpochListener

public abstract class TrainingListener
extends org.deeplearning4j.optimize.api.BaseTrainingListener
implements weka.core.OptionHandler, java.io.Serializable

Iteration listener that can be attached to a Dl4j model.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
TrainingListener()

Method Summary

Modifier and Type	Method and Description
java.lang.String[]	getOptions() Gets the current settings of the Classifier.
void	init(int numClasses, int currentEpoch, int numEpochs, int numSamples, org.nd4j.linalg.dataset.api.iterator.DataSetIterator trainIterator, org.nd4j.linalg.dataset.api.iterator.DataSetIterator validationIterator) Initialize the iterator with its necessary member variables
void	iterationDone(org.deeplearning4j.nn.api.Model model, int iteration, int epoch)
java.util.Enumeration<weka.core.Option>	listOptions() Returns an enumeration describing the available options.
abstract void	log(java.lang.String msg) Log a message
void	setOptions(java.lang.String[] options) Parses a given list of options.

Methods inherited from class org.deeplearning4j.optimize.api.BaseTrainingListener

onBackwardPass, onEpochEnd, onEpochStart, onForwardPass, onForwardPass, onGradientCalculation

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface weka.core.OptionHandler

makeCopy

Constructor Detail

TrainingListener

public TrainingListener()

Method Detail

init

public void init(int numClasses,
                 int currentEpoch,
                 int numEpochs,
                 int numSamples,
                 org.nd4j.linalg.dataset.api.iterator.DataSetIterator trainIterator,
                 org.nd4j.linalg.dataset.api.iterator.DataSetIterator validationIterator)

Initialize the iterator with its necessary member variables

Parameters:

numClasses - Number of classes

numEpochs - Number of epochs

numSamples - Number of Samples

trainIterator - Training iterator

validationIterator - Validation iterator

log

public abstract void log(java.lang.String msg)

Log a message

Parameters:

msg - Message

iterationDone

public void iterationDone(org.deeplearning4j.nn.api.Model model,
                          int iteration,
                          int epoch)

Specified by:

iterationDone in interface org.deeplearning4j.optimize.api.TrainingListener

Overrides:

iterationDone in class org.deeplearning4j.optimize.api.BaseTrainingListener

listOptions

public java.util.Enumeration<weka.core.Option> listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface weka.core.OptionHandler

Returns:

an enumeration of all the available options.

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the Classifier.

Specified by:

getOptions in interface weka.core.OptionHandler

Returns:

an array of strings suitable for passing to setOptions

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Specified by:

setOptions in interface weka.core.OptionHandler

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported