public class GaussianNoise extends Object implements IDropout
GaussianDropout
, which applies Modifier | Constructor and Description |
---|---|
|
GaussianNoise(double stddev) |
protected |
GaussianNoise(double stddev,
org.nd4j.linalg.schedule.ISchedule stddevSchedule) |
|
GaussianNoise(org.nd4j.linalg.schedule.ISchedule stddevSchedule) |
Modifier and Type | Method and Description |
---|---|
org.nd4j.linalg.api.ndarray.INDArray |
applyDropout(org.nd4j.linalg.api.ndarray.INDArray inputActivations,
int iteration,
int epoch,
boolean inPlace) |
IDropout |
clone() |
public GaussianNoise(double stddev)
stddev
- Standard deviation for the mean 0 Gaussian noisepublic GaussianNoise(org.nd4j.linalg.schedule.ISchedule stddevSchedule)
stddevSchedule
- Schedule for standard deviation for the mean 0 Gaussian noiseprotected GaussianNoise(double stddev, org.nd4j.linalg.schedule.ISchedule stddevSchedule)
public org.nd4j.linalg.api.ndarray.INDArray applyDropout(org.nd4j.linalg.api.ndarray.INDArray inputActivations, int iteration, int epoch, boolean inPlace)
applyDropout
in interface IDropout
inputActivations
- Input activations arrayiteration
- Current iteration numberepoch
- Current epoch numberinPlace
- If true: modify the input activations in-place. False: Copy the input activations and
apply dropout on the copy insteadCopyright © 2018. All rights reserved.