Class GaussianDropout
- java.lang.Object
-
- org.deeplearning4j.nn.conf.dropout.GaussianDropout
-
- All Implemented Interfaces:
Serializable
,Cloneable
,IDropout
public class GaussianDropout extends Object implements IDropout
- See Also:
- Serialized Form
-
-
Constructor Summary
Constructors Modifier Constructor Description GaussianDropout(double rate)
protected
GaussianDropout(double rate, ISchedule rateSchedule)
GaussianDropout(ISchedule rateSchedule)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description INDArray
applyDropout(INDArray inputActivations, INDArray output, int iteration, int epoch, LayerWorkspaceMgr workspaceMgr)
INDArray
backprop(INDArray gradAtOutput, INDArray gradAtInput, int iteration, int epoch)
Perform backprop.void
clear()
Clear the internal state (for example, dropout mask) if any is presentGaussianDropout
clone()
-
-
-
Constructor Detail
-
GaussianDropout
public GaussianDropout(double rate)
- Parameters:
rate
- Rate parameter, seeGaussianDropout
-
GaussianDropout
public GaussianDropout(ISchedule rateSchedule)
- Parameters:
rateSchedule
- Schedule for rate parameter, seeGaussianDropout
-
GaussianDropout
protected GaussianDropout(double rate, ISchedule rateSchedule)
-
-
Method Detail
-
applyDropout
public INDArray applyDropout(INDArray inputActivations, INDArray output, int iteration, int epoch, LayerWorkspaceMgr workspaceMgr)
- Specified by:
applyDropout
in interfaceIDropout
- Parameters:
inputActivations
- Input activations arrayoutput
- The result array (same as inputArray for in-place ops) for the post-dropout activationsiteration
- Current iteration numberepoch
- Current epoch numberworkspaceMgr
- Workspace manager, if any storage is required (use ArrayType.INPUT)- Returns:
- The output (resultArray) after applying dropout
-
backprop
public INDArray backprop(INDArray gradAtOutput, INDArray gradAtInput, int iteration, int epoch)
Description copied from interface:IDropout
Perform backprop. This should also clear the internal state (dropout mask) if any is present- Specified by:
backprop
in interfaceIDropout
- Parameters:
gradAtOutput
- Gradients at the output of the dropout op - i.e., dL/dOutgradAtInput
- Gradients at the input of the dropout op - i.e., dL/dIn. Use the same array as gradAtOutput to apply the backprop gradient in-placeiteration
- Current iterationepoch
- Current epoch- Returns:
- Same array as gradAtInput - i.e., gradient after backpropagating through dropout op - i.e., dL/dIn
-
clear
public void clear()
Description copied from interface:IDropout
Clear the internal state (for example, dropout mask) if any is present
-
clone
public GaussianDropout clone()
-
-