public class MultiNormalizerStandardize extends Object implements MultiDataSetPreProcessor
Constructor and Description |
---|
MultiNormalizerStandardize() |
Modifier and Type | Method and Description |
---|---|
void |
fit(MultiDataSet dataSet)
Fit the model with a MultiDataSet to calculate means and standard deviations with
|
void |
fit(MultiDataSetIterator iterator)
FFit the model with a MultiDataSetIterator to calculate means and standard deviations with
|
void |
fitLabel(boolean fitLabels) |
INDArray |
getFeatureMean(int input) |
INDArray |
getFeatureStd(int input) |
INDArray |
getLabelMean(int output) |
INDArray |
getLabelStd(int output) |
protected boolean |
isFit() |
boolean |
isFitLabel() |
void |
load(List<File> featureFiles,
List<File> labelFiles)
Load means and standard deviations from the file system
|
protected void |
preProcess(INDArray theFeatures,
DistributionStats stats) |
void |
preProcess(MultiDataSet toPreProcess)
Preprocess the MultiDataSet
|
void |
revert(MultiDataSet data)
Revert the data to what it was before transform
|
void |
save(List<File> featureFiles,
List<File> labelFiles)
Save the current means and standard deviations to the file system
|
public void fitLabel(boolean fitLabels)
public boolean isFitLabel()
public void fit(@NonNull MultiDataSet dataSet)
dataSet
- public void fit(@NonNull MultiDataSetIterator iterator)
iterator
- public void preProcess(@NonNull MultiDataSet toPreProcess)
MultiDataSetPreProcessor
preProcess
in interface MultiDataSetPreProcessor
public void revert(@NonNull MultiDataSet data)
data
- the dataset to revert backpublic INDArray getFeatureMean(int input)
public INDArray getLabelMean(int output)
public INDArray getFeatureStd(int input)
public INDArray getLabelStd(int output)
protected boolean isFit()
public void load(@NonNull List<File> featureFiles, @NonNull List<File> labelFiles) throws IOException
featureFiles
- source files for features, requires 2 files per input, alternating mean and stddev fileslabelFiles
- source files for labels, requires 2 files per output, alternating mean and stddev filesIOException
public void save(@NonNull List<File> featureFiles, @NonNull List<File> labelFiles) throws IOException
featureFiles
- target files for features, requires 2 files per input, alternating mean and stddev fileslabelFiles
- target files for labels, requires 2 files per output, alternating mean and stddev filesIOException
protected void preProcess(INDArray theFeatures, DistributionStats stats)
Copyright © 2016. All Rights Reserved.