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

Class ImageMultiPreProcessingScaler

java.lang.Object

org.nd4j.linalg.dataset.api.preprocessor.ImageMultiPreProcessingScaler

All Implemented Interfaces:

MultiDataSetPreProcessor, MultiDataNormalization, Normalizer<MultiDataSet>

public class ImageMultiPreProcessingScaler
extends Object
implements MultiDataNormalization

Constructor Summary

Constructors

Constructor	Description
ImageMultiPreProcessingScaler(double a, double b, int[] featureIndices)
ImageMultiPreProcessingScaler(double a, double b, int maxBits, int[] featureIndices)	Preprocessor can take a range as minRange and maxRange
ImageMultiPreProcessingScaler(int... featureIndices)

Method Summary

Modifier and Type	Method	Description
void	fit(MultiDataSetIterator iterator)	Iterates over a dataset accumulating statistics for normalization
void	fit(MultiDataSet dataSet)	Fit a dataset (only compute based on the statistics from this dataset)
NormalizerType	getType()	Get the enum opType of this normalizer
void	preProcess(MultiDataSet multiDataSet)	Preprocess the MultiDataSet
void	revert(MultiDataSet toRevert)	Undo (revert) the normalization applied by this DataNormalization instance (arrays are modified in-place)
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(MultiDataSet toPreProcess)	Transform the dataset

Methods inherited from class java.lang.Object

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

Constructor Detail

ImageMultiPreProcessingScaler

public ImageMultiPreProcessingScaler(int... featureIndices)

ImageMultiPreProcessingScaler

public ImageMultiPreProcessingScaler(double a,
                                     double b,
                                     int[] featureIndices)

ImageMultiPreProcessingScaler

public ImageMultiPreProcessingScaler(double a,
                                     double b,
                                     int maxBits,
                                     int[] featureIndices)

Preprocessor can take a range as minRange and maxRange

Parameters:

a - , default = 0

b - , default = 1

maxBits - in the image, default = 8

featureIndices - Indices of feature arrays to process. If only one feature array is present, this should always be 0

Method Detail

fit

public void fit(MultiDataSetIterator iterator)

Description copied from interface: MultiDataNormalization

Iterates over a dataset accumulating statistics for normalization

Specified by:

fit in interface MultiDataNormalization

Parameters:

iterator - the iterator to use for collecting statistics.

preProcess

public void preProcess(MultiDataSet multiDataSet)

Description copied from interface: MultiDataSetPreProcessor

Preprocess the MultiDataSet

Specified by:

preProcess in interface MultiDataNormalization

Specified by:

preProcess in interface MultiDataSetPreProcessor

revertFeatures

public void revertFeatures(INDArray[] features,
                           INDArray[] featuresMask)

Description copied from interface: MultiDataNormalization

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

Specified by:

revertFeatures in interface MultiDataNormalization

Parameters:

features - Features to revert the normalization on

revertFeatures

public void revertFeatures(INDArray[] features)

Description copied from interface: MultiDataNormalization

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

Specified by:

revertFeatures in interface MultiDataNormalization

Parameters:

features - Features to revert the normalization on

revertLabels

public void revertLabels(INDArray[] labels,
                         INDArray[] labelsMask)

Description copied from interface: MultiDataNormalization

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

Specified by:

revertLabels in interface MultiDataNormalization

Parameters:

labels - Labels array to revert the normalization on

labelsMask - Labels mask array (may be null)

revertLabels

public void revertLabels(INDArray[] labels)

Description copied from interface: MultiDataNormalization

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

Specified by:

revertLabels in interface MultiDataNormalization

Parameters:

labels - Labels array to revert the normalization on

fit

public void fit(MultiDataSet dataSet)

Description copied from interface: Normalizer

Fit a dataset (only compute based on the statistics from this dataset)

Specified by:

fit in interface Normalizer<MultiDataSet>

Parameters:

dataSet - the dataset to compute on

transform

public void transform(MultiDataSet toPreProcess)

Description copied from interface: Normalizer

Transform the dataset

Specified by:

transform in interface Normalizer<MultiDataSet>

Parameters:

toPreProcess - the dataset to re process

revert

public void revert(MultiDataSet toRevert)

Description copied from interface: Normalizer

Undo (revert) the normalization applied by this DataNormalization instance (arrays are modified in-place)

Specified by:

revert in interface Normalizer<MultiDataSet>

Parameters:

toRevert - DataSet to revert the normalization on

getType

public NormalizerType getType()

Description copied from interface: Normalizer

Get the enum opType of this normalizer

Specified by:

getType in interface Normalizer<MultiDataSet>

Returns:

the opType

See Also:

NormalizerSerializerStrategy.getSupportedType()