org.deeplearning4j.eval

Interface IEvaluation<T extends IEvaluation>

All Superinterfaces:

Serializable

All Known Implementing Classes:

BaseEvaluation, Evaluation, EvaluationBinary, EvaluationCalibration, RegressionEvaluation, ROC, ROCBinary, ROCMultiClass

public interface IEvaluation<T extends IEvaluation>
extends Serializable

A general purpose interface for evaluating neural networks - methods are shared by implemetations such as Evaluation, RegressionEvaluation, ROC, ROCMultiClass

Author:

Alex Black

Method Summary

Modifier and Type	Method and Description
void	eval(INDArray labels, INDArray networkPredictions)
void	eval(INDArray labels, INDArray networkPredictions, INDArray maskArray)
void	eval(INDArray labels, INDArray networkPredictions, List<? extends Serializable> recordMetaData)
void	evalTimeSeries(INDArray labels, INDArray predicted)
void	evalTimeSeries(INDArray labels, INDArray predicted, INDArray labelsMaskArray)
void	merge(T other)
void	reset()
String	stats()
String	toJson()
String	toYaml()

Method Detail

eval

void eval(INDArray labels,
          INDArray networkPredictions)

Parameters:

labels -

networkPredictions -

eval

void eval(INDArray labels,
          INDArray networkPredictions,
          List<? extends Serializable> recordMetaData)

Parameters:

labels -

networkPredictions -

recordMetaData -

eval

void eval(INDArray labels,
          INDArray networkPredictions,
          INDArray maskArray)

Parameters:

labels -

networkPredictions -

maskArray -

evalTimeSeries

void evalTimeSeries(INDArray labels,
                    INDArray predicted)

Parameters:

labels -

predicted -

evalTimeSeries

void evalTimeSeries(INDArray labels,
                    INDArray predicted,
                    INDArray labelsMaskArray)

Parameters:

labels -

predicted -

labelsMaskArray -

merge

void merge(T other)

Parameters:

other -

reset

void reset()

stats

String stats()

Returns:

toJson

String toJson()

Returns:

toYaml

String toYaml()

Returns: