Class MinMaxStrategy
- java.lang.Object
-
- org.nd4j.linalg.dataset.api.preprocessor.MinMaxStrategy
-
- All Implemented Interfaces:
Serializable
,NormalizerStrategy<MinMaxStats>
public class MinMaxStrategy extends Object implements NormalizerStrategy<MinMaxStats>, Serializable
- See Also:
- Serialized Form
-
-
Constructor Summary
Constructors Constructor Description MinMaxStrategy()
MinMaxStrategy(double minRange, double maxRange)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description NormalizerStats.Builder
newStatsBuilder()
Create a newNormalizerStats.Builder
instance that can be used to fit new data and of the opType that belongs to the current NormalizerStrategy implementationvoid
preProcess(INDArray array, INDArray maskArray, MinMaxStats stats)
Normalize a data arrayvoid
revert(INDArray array, INDArray maskArray, MinMaxStats stats)
Denormalize a data array
-
-
-
Method Detail
-
preProcess
public void preProcess(INDArray array, INDArray maskArray, MinMaxStats stats)
Normalize a data array- Specified by:
preProcess
in interfaceNormalizerStrategy<MinMaxStats>
- Parameters:
array
- the data to normalizestats
- statistics of the data population
-
revert
public void revert(INDArray array, INDArray maskArray, MinMaxStats stats)
Denormalize a data array- Specified by:
revert
in interfaceNormalizerStrategy<MinMaxStats>
- Parameters:
array
- the data to denormalizestats
- statistics of the data population
-
newStatsBuilder
public NormalizerStats.Builder newStatsBuilder()
Create a newNormalizerStats.Builder
instance that can be used to fit new data and of the opType that belongs to the current NormalizerStrategy implementation- Specified by:
newStatsBuilder
in interfaceNormalizerStrategy<MinMaxStats>
- Returns:
- the new builder
-
-