Package org.nd4j.linalg.dataset.api.preprocessor

Interface DataNormalization

All Superinterfaces:

DataSetPreProcessor, Normalizer<DataSet>, Serializable

All Known Implementing Classes:

AbstractDataSetNormalizer, ImagePreProcessingScaler, NormalizerMinMaxScaler, NormalizerStandardize, VGG16ImagePreProcessor

public interface DataNormalization
extends Normalizer<DataSet>, DataSetPreProcessor

Method Summary

Modifier and Type	Method	Description
void	fit(DataSetIterator iterator)	Iterates over a dataset accumulating statistics for normalization
void	fitLabel(boolean fitLabels)	Flag to specify if the labels/outputs in the dataset should be also normalized.
boolean	isFitLabel()	Whether normalization for the labels is also enabled.
void	preProcess(DataSet toPreProcess)	Pre process a dataset
void	revertFeatures(INDArray features)	Undo (revert) the normalization applied by this DataNormalization instance to the specified features array
void	revertFeatures(INDArray features, INDArray featuresMask)	Undo (revert) the normalization applied by this DataNormalization instance to the specified features array
void	revertLabels(INDArray labels)	Undo (revert) the normalization applied by this DataNormalization instance to the specified labels array.
void	revertLabels(INDArray labels, INDArray labelsMask)	Undo (revert) the normalization applied by this DataNormalization instance to the specified labels array.
void	transform(INDArray features)	Transform the dataset
void	transform(INDArray features, INDArray featuresMask)	Transform the features, with an optional mask array
void	transformLabel(INDArray labels)	Transform the labels.
void	transformLabel(INDArray labels, INDArray labelsMask)	Transform the labels.

Methods inherited from interface org.nd4j.linalg.dataset.api.preprocessor.Normalizer

fit, getType, revert, transform

Method Detail

fit

void fit(DataSetIterator iterator)

Iterates over a dataset accumulating statistics for normalization

Parameters:

iterator - the iterator to use for collecting statistics.

preProcess

void preProcess(DataSet toPreProcess)

Description copied from interface: DataSetPreProcessor

Pre process a dataset

Specified by:

preProcess in interface DataSetPreProcessor

Parameters:

toPreProcess - the data set to pre process

transform

void transform(INDArray features)

Transform the dataset

Parameters:

features - the features to pre process

transform

void transform(INDArray features,
               INDArray featuresMask)

Transform the features, with an optional mask array

Parameters:

features - the features to pre process

featuresMask - the mask array to pre process

transformLabel

void transformLabel(INDArray labels)

Transform the labels. If isFitLabel() == false, this is a no-op

transformLabel

void transformLabel(INDArray labels,
                    INDArray labelsMask)

Transform the labels. If isFitLabel() == false, this is a no-op

revertFeatures

void revertFeatures(INDArray features)

Undo (revert) the normalization applied by this DataNormalization instance to the specified features array

Parameters:

features - Features to revert the normalization on

revertFeatures

void revertFeatures(INDArray features,
                    INDArray featuresMask)

Undo (revert) the normalization applied by this DataNormalization instance to the specified features array

Parameters:

features - Features to revert the normalization on

featuresMask -

revertLabels

void revertLabels(INDArray labels)

Undo (revert) the normalization applied by this DataNormalization instance to the specified labels array. If labels normalization is disabled (i.e., #isFitLabels() == false) then this is a no-op. Can also be used to undo normalization for network output arrays, in the case of regression.

Parameters:

labels - Labels array to revert the normalization on

revertLabels

void revertLabels(INDArray labels,
                  INDArray labelsMask)

Undo (revert) the normalization applied by this DataNormalization instance to the specified labels array. If labels normalization is disabled (i.e., #isFitLabels() == false) then this is a no-op. Can also be used to undo normalization for network output arrays, in the case of regression.

Parameters:

labels - Labels array to revert the normalization on

labelsMask - Labels mask array (may be null)

fitLabel

void fitLabel(boolean fitLabels)

Flag to specify if the labels/outputs in the dataset should be also normalized. Default value is usually false.

isFitLabel

boolean isFitLabel()

Whether normalization for the labels is also enabled. Most commonly used for regression, not classification.

Returns:

True if labels will be