Uses of Interface
org.nd4j.linalg.dataset.api.DataSetPreProcessor

Packages that use DataSetPreProcessor

Package	Description
org.nd4j.linalg.dataset
org.nd4j.linalg.dataset.api.iterator
org.nd4j.linalg.dataset.api.preprocessor
org.nd4j.linalg.dataset.api.preprocessor.classimbalance

Uses of DataSetPreProcessor in org.nd4j.linalg.dataset

Methods in org.nd4j.linalg.dataset that return DataSetPreProcessor

Modifier and Type	Method and Description
DataSetPreProcessor	ViewIterator.getPreProcessor()
DataSetPreProcessor	MiniBatchFileDataSetIterator.getPreProcessor()
DataSetPreProcessor	ExistingMiniBatchDataSetIterator.getPreProcessor()
DataSetPreProcessor	AsyncDataSetIterator.getPreProcessor() Returns preprocessors, if defined

Methods in org.nd4j.linalg.dataset with parameters of type DataSetPreProcessor

Modifier and Type	Method and Description
void	ViewIterator.setPreProcessor(DataSetPreProcessor preProcessor)
void	MiniBatchFileDataSetIterator.setPreProcessor(DataSetPreProcessor preProcessor)
void	ExistingMiniBatchDataSetIterator.setPreProcessor(DataSetPreProcessor preProcessor)
void	AsyncDataSetIterator.setPreProcessor(DataSetPreProcessor preProcessor) Set a pre processor

Uses of DataSetPreProcessor in org.nd4j.linalg.dataset.api.iterator

Fields in org.nd4j.linalg.dataset.api.iterator declared as DataSetPreProcessor

Modifier and Type	Field and Description
protected DataSetPreProcessor	KFoldIterator.preProcessor
protected DataSetPreProcessor	BaseDatasetIterator.preProcessor

Methods in org.nd4j.linalg.dataset.api.iterator that return DataSetPreProcessor

Modifier and Type	Method and Description
DataSetPreProcessor	TestDataSetIterator.getPreProcessor()
DataSetPreProcessor	SamplingDataSetIterator.getPreProcessor()
DataSetPreProcessor	MultipleEpochsIterator.getPreProcessor() Deprecated.
DataSetPreProcessor	KFoldIterator.getPreProcessor()
DataSetPreProcessor	DataSetIterator.getPreProcessor() Returns preprocessors, if defined
DataSetPreProcessor	CachingDataSetIterator.getPreProcessor()
DataSetPreProcessor	BaseDatasetIterator.getPreProcessor()

Methods in org.nd4j.linalg.dataset.api.iterator with parameters of type DataSetPreProcessor

Modifier and Type	Method and Description
void	TestDataSetIterator.setPreProcessor(DataSetPreProcessor preProcessor)
void	SamplingDataSetIterator.setPreProcessor(DataSetPreProcessor preProcessor) Set a pre processor
void	MultipleEpochsIterator.setPreProcessor(DataSetPreProcessor preProcessor) Deprecated. Set a pre processor
void	KFoldIterator.setPreProcessor(DataSetPreProcessor preProcessor)
void	DataSetIterator.setPreProcessor(DataSetPreProcessor preProcessor) Set a pre processor
void	CachingDataSetIterator.setPreProcessor(DataSetPreProcessor preProcessor)
void	BaseDatasetIterator.setPreProcessor(DataSetPreProcessor preProcessor) Set a pre processor

Uses of DataSetPreProcessor in org.nd4j.linalg.dataset.api.preprocessor

Subinterfaces of DataSetPreProcessor in org.nd4j.linalg.dataset.api.preprocessor

Modifier and Type	Interface and Description
interface	DataNormalization An interface for data normalizers.

Classes in org.nd4j.linalg.dataset.api.preprocessor that implement DataSetPreProcessor

Modifier and Type	Class and Description
class	AbstractDataSetNormalizer<S extends NormalizerStats> Abstract base class for normalizers that act upon DataSet instances or iterators
class	CompositeDataSetPreProcessor A simple Composite DataSetPreProcessor - allows you to apply multiple DataSetPreProcessors sequentially on the one DataSet, in the order they are passed to the constructor
class	CropAndResizeDataSetPreProcessor The CropAndResizeDataSetPreProcessor will crop and resize the processed dataset.
class	ImageFlatteningDataSetPreProcessor A DataSetPreProcessor used to flatten a 4d CNN features array to a flattened 2d format (for use in networks such as a DenseLayer/multi-layer perceptron)
class	ImagePreProcessingScaler Created by susaneraly on 6/23/16.
class	LabelLastTimeStepPreProcessor Used to extract the labels from a 3d format (shape: [minibatch, nOut, sequenceLength]) to a 2d format (shape: [minibatch, nOut]) where the values are the last time step of the labels. For example, for 2 sequences: [a, b, c, 0, 0] [p, q, r, s, t] (where a/b/p etc represet a vector of size numOutputs), and each row is the sequence for each [1, 1, 1, 0, 0] [1, 1, 1, 1, 1] The new labels would be a rank 2 array of shape [minibatch, nOut] with values: [c] [t] This preprocessor can be used for example to convert from "single non-masked time step" labels format (produced by RecordReaderDataSetIterator, used in RnnOutputLayer) to 2d labels format (used in OutputLayer).
class	NormalizerMinMaxScaler Pre processor for DataSets that normalizes feature values (and optionally label values) to lie between a minimum and maximum value (by default between 0 and 1)
class	NormalizerStandardize 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
class	PermuteDataSetPreProcessor The PermuteDataSetPreProcessor will rearrange the dimensions.
class	RGBtoGrayscaleDataSetPreProcessor The RGBtoGrayscaleDataSetPreProcessor will turn a DataSet of a RGB image into a grayscale one.
class	VGG16ImagePreProcessor This is a preprocessor specifically for VGG16.

Constructors in org.nd4j.linalg.dataset.api.preprocessor with parameters of type DataSetPreProcessor

Constructor and Description
CompositeDataSetPreProcessor(boolean stopOnEmptyDataSet, DataSetPreProcessor... preProcessors)
CompositeDataSetPreProcessor(DataSetPreProcessor... preProcessors)

Uses of DataSetPreProcessor in org.nd4j.linalg.dataset.api.preprocessor.classimbalance

Classes in org.nd4j.linalg.dataset.api.preprocessor.classimbalance that implement DataSetPreProcessor

Modifier and Type

Class and Description

class

UnderSamplingByMaskingPreProcessor For use in time series with unbalanced binary classes trained with truncated back prop through time Undersamples the majority class by randomly masking time steps belonging to it Given a target distribution for the minority class and the window size (usually the value used with tbptt) the preprocessor will approximate the given target distribution for every window of given size for every sample of the minibatch By default '0' is considered the majority class and '1' the minorityLabel class Default can be overriden with .overrideMinorityDefault()