Package org.deeplearning4j.earlystopping.scorecalc

Class ClassificationScoreCalculator

java.lang.Object

org.deeplearning4j.earlystopping.scorecalc.base.BaseIEvaluationScoreCalculator<Model,Evaluation>

org.deeplearning4j.earlystopping.scorecalc.ClassificationScoreCalculator

All Implemented Interfaces:

Serializable, ScoreCalculator<Model>

public class ClassificationScoreCalculator
extends BaseIEvaluationScoreCalculator<Model,Evaluation>

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected Evaluation.Metric	metric

Fields inherited from class org.deeplearning4j.earlystopping.scorecalc.base.BaseIEvaluationScoreCalculator

iter, iterator

Constructor Summary

Constructors

Constructor	Description
ClassificationScoreCalculator(Evaluation.Metric metric, DataSetIterator iterator)
ClassificationScoreCalculator(Evaluation.Metric metric, MultiDataSetIterator iterator)

Method Summary

Modifier and Type	Method	Description
protected double	finalScore(Evaluation e)
boolean	minimizeScore()
protected Evaluation	newEval()

Methods inherited from class org.deeplearning4j.earlystopping.scorecalc.base.BaseIEvaluationScoreCalculator

calculateScore

Methods inherited from class java.lang.Object

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

Field Detail

metric

protected final Evaluation.Metric metric

Constructor Detail

ClassificationScoreCalculator

public ClassificationScoreCalculator(Evaluation.Metric metric,
                                     DataSetIterator iterator)

ClassificationScoreCalculator

public ClassificationScoreCalculator(Evaluation.Metric metric,
                                     MultiDataSetIterator iterator)

Method Detail

newEval

protected Evaluation newEval()

Specified by:

newEval in class BaseIEvaluationScoreCalculator<Model,Evaluation>

finalScore

protected double finalScore(Evaluation e)

Specified by:

finalScore in class BaseIEvaluationScoreCalculator<Model,Evaluation>

minimizeScore

public boolean minimizeScore()

Returns:

If true: the score should be minimized. If false: the score should be maximized.