Package | Description |
---|---|
org.nd4j.linalg.dataset.api.iterator | |
org.nd4j.linalg.dataset.api.preprocessor | |
org.nd4j.linalg.dataset.api.preprocessor.classimbalance |
Modifier and Type | Method and Description |
---|---|
MultiDataSetPreProcessor |
TestMultiDataSetIterator.getPreProcessor() |
MultiDataSetPreProcessor |
MultiDataSetIterator.getPreProcessor()
Get the
MultiDataSetPreProcessor , if one has previously been set. |
Modifier and Type | Method and Description |
---|---|
void |
TestMultiDataSetIterator.setPreProcessor(MultiDataSetPreProcessor preProcessor) |
void |
MultiDataSetIterator.setPreProcessor(MultiDataSetPreProcessor preProcessor)
Set the preprocessor to be applied to each MultiDataSet, before each MultiDataSet is returned.
|
Modifier and Type | Interface and Description |
---|---|
interface |
MultiDataNormalization
An interface for multi dataset normalizers.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractMultiDataSetNormalizer<S extends NormalizerStats>
Abstract base class for normalizers that act upon
MultiDataSet instances or iterators |
class |
CompositeMultiDataSetPreProcessor
A simple Composite MultiDataSetPreProcessor - allows you to apply multiple MultiDataSetPreProcessors sequentially
on the one MultiDataSet, in the order they are passed to the constructor
|
class |
ImageMultiPreProcessingScaler
A preprocessor specifically for images that applies min max scaling to one or more of the feature arrays
in a MultiDataSet.
Can take a range, so pixel values can be scaled from 0->255 to minRange->maxRange default minRange = 0 and maxRange = 1; If pixel values are not 8 bits, you can specify the number of bits as the third argument in the constructor For values that are already floating point, specify the number of bits as 1 |
class |
MultiNormalizerHybrid
Pre processor for MultiDataSet that can be configured to use different normalization strategies for different inputs
and outputs, or none at all.
|
class |
MultiNormalizerMinMaxScaler
Pre processor for MultiDataSet that normalizes feature values (and optionally label values) to lie between a minimum
and maximum value (by default between 0 and 1)
|
class |
MultiNormalizerStandardize
Pre processor for MultiDataSet that normalizes feature values (and optionally label values) to have 0 mean and
a standard deviation of 1
|
Constructor and Description |
---|
CompositeMultiDataSetPreProcessor(MultiDataSetPreProcessor... preProcessors) |
Modifier and Type | Class and Description |
---|---|
class |
UnderSamplingByMaskingMultiDataSetPreProcessor
The multidataset version of the UnderSamplingByMaskingPreProcessor
Constructor takes a map - keys are indices of the multidataset to apply preprocessor to, values are the target distributions
|
Copyright © 2018. All rights reserved.