public class ImagePreProcessingScaler extends Object implements DataNormalization
Constructor and Description |
---|
ImagePreProcessingScaler() |
ImagePreProcessingScaler(double a,
double b) |
ImagePreProcessingScaler(double a,
double b,
int maxBits)
Preprocessor can take a range as minRange and maxRange
|
Modifier and Type | Method and Description |
---|---|
void |
fit(DataSet dataSet)
Fit a dataset (only compute
based on the statistics from this dataset0
|
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 |
load(File... statistics)
Load the statistics
for the data normalizer
|
void |
preProcess(DataSet toPreProcess)
Pre process a dataset
|
void |
preProcess(INDArray features) |
void |
revert(DataSet 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 |
revertLabels(INDArray labels)
Undo (revert) the normalization applied by this DataNormalization instance to the specified labels array.
|
void |
save(File... statistics)
Save the accumulated statistics
|
void |
transform(DataSet toPreProcess)
Transform the data
|
void |
transform(INDArray features)
Transform the dataset
|
void |
transformLabel(INDArray label)
Transform the labels.
|
public ImagePreProcessingScaler()
public ImagePreProcessingScaler(double a, double b)
public ImagePreProcessingScaler(double a, double b, int maxBits)
a,
- default = 0b,
- default = 1maxBits
- in the image, default = 8public void fit(DataSet dataSet)
fit
in interface DataNormalization
dataSet
- the dataset to compute onpublic void fit(DataSetIterator iterator)
fit
in interface DataNormalization
iterator
- the iterator to use for
collecting statistics.public void preProcess(DataSet toPreProcess)
DataSetPreProcessor
preProcess
in interface DataSetPreProcessor
preProcess
in interface DataNormalization
toPreProcess
- the data set to pre processpublic void preProcess(INDArray features)
public void transform(DataSet toPreProcess)
transform
in interface DataNormalization
toPreProcess
- the dataset to transformpublic void transform(INDArray features)
DataNormalization
transform
in interface DataNormalization
features
- the features to pre processpublic void transformLabel(INDArray label)
DataNormalization
DataNormalization.isFitLabel()
== false, this is a no-optransformLabel
in interface DataNormalization
public void revert(DataSet toRevert)
DataNormalization
revert
in interface DataNormalization
toRevert
- DataSet to revert the normalization onpublic void revertFeatures(INDArray features)
DataNormalization
revertFeatures
in interface DataNormalization
features
- Features to revert the normalization onpublic void revertLabels(INDArray labels)
DataNormalization
#isFitLabels()
== false) then this is a no-op.
Can also be used to undo normalization for network output arrays, in the case of regression.revertLabels
in interface DataNormalization
labels
- Labels array to revert the normalization onpublic void fitLabel(boolean fitLabels)
DataNormalization
fitLabel
in interface DataNormalization
public boolean isFitLabel()
DataNormalization
isFitLabel
in interface DataNormalization
public void load(File... statistics) throws IOException
load
in interface DataNormalization
statistics
- the files to persistIOException
public void save(File... statistics) throws IOException
save
in interface DataNormalization
statistics
- the statistics to saveIOException
Copyright © 2016. All Rights Reserved.