org.nd4j.linalg.dataset.api.preprocessor

Class NormalizerStandardize

java.lang.Object

org.nd4j.linalg.dataset.api.preprocessor.AbstractNormalizer

org.nd4j.linalg.dataset.api.preprocessor.AbstractDataSetNormalizer<DistributionStats>

org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize

All Implemented Interfaces:

Serializable, DataSetPreProcessor, DataNormalization, Normalizer<DataSet>

public class NormalizerStandardize
extends AbstractDataSetNormalizer<DistributionStats>

Created by susaneraly, Ede Meijer variance and mean Pre processor for DataSet that normalizes feature values (and optionally label values) to have 0 mean and a standard deviation of 1

See Also:

Serialized Form

Field Summary

Fields inherited from class org.nd4j.linalg.dataset.api.preprocessor.AbstractDataSetNormalizer

strategy

Constructor Summary

Constructors

Constructor and Description
NormalizerStandardize()
NormalizerStandardize(INDArray featureMean, INDArray featureStd)
NormalizerStandardize(INDArray featureMean, INDArray featureStd, INDArray labelMean, INDArray labelStd)

Method Summary

Modifier and Type	Method and Description
INDArray	getLabelMean()
INDArray	getLabelStd()
INDArray	getMean()
INDArray	getStd()
NormalizerType	getType() Get the enum opType of this normalizer
void	load(File... files) Load the means and standard deviations from the file system
protected NormalizerStats.Builder	newBuilder()
void	save(File... files) Deprecated. use NormalizerSerializer instead Save the current means and standard deviations to the file system
void	setLabelStats(INDArray labelMean, INDArray labelStd)

Methods inherited from class org.nd4j.linalg.dataset.api.preprocessor.AbstractDataSetNormalizer

fit, fit, fitLabel, getFeatureStats, getLabelStats, isFit, isFitLabel, preProcess, revert, revertFeatures, revertFeatures, revertLabels, revertLabels, transform, transform, transform, transformLabel, transformLabel

Methods inherited from class java.lang.Object

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

Constructor Detail

NormalizerStandardize

public NormalizerStandardize(@NonNull
                             INDArray featureMean,
                             @NonNull
                             INDArray featureStd)

NormalizerStandardize

public NormalizerStandardize(@NonNull
                             INDArray featureMean,
                             @NonNull
                             INDArray featureStd,
                             @NonNull
                             INDArray labelMean,
                             @NonNull
                             INDArray labelStd)

NormalizerStandardize

public NormalizerStandardize()

Method Detail

setLabelStats

public void setLabelStats(@NonNull
                          INDArray labelMean,
                          @NonNull
                          INDArray labelStd)

getMean

public INDArray getMean()

getLabelMean

public INDArray getLabelMean()

getStd

public INDArray getStd()

getLabelStd

public INDArray getLabelStd()

load

public void load(File... files)
          throws IOException

Load the means and standard deviations from the file system

Parameters:

files - the files to load from. Needs 4 files if normalizing labels, otherwise 2.

Throws:

IOException

save

public void save(File... files)
          throws IOException

Deprecated. use NormalizerSerializer instead

Save the current means and standard deviations to the file system

Parameters:

files - the files to save to. Needs 4 files if normalizing labels, otherwise 2.

Throws:

IOException

newBuilder

protected NormalizerStats.Builder newBuilder()

Specified by:

newBuilder in class AbstractDataSetNormalizer<DistributionStats>

getType

public NormalizerType getType()

Description copied from interface: Normalizer

Get the enum opType of this normalizer

Returns:

the opType

See Also:

NormalizerSerializerStrategy.getSupportedType()