org.deeplearning4j.nn.conf.dropout

Interface IDropout

All Superinterfaces:

Cloneable, Serializable

All Known Implementing Classes:

AlphaDropout, Dropout, GaussianDropout, GaussianNoise, SpatialDropout

public interface IDropout
extends Serializable, Cloneable

Method Summary

Modifier and Type	Method and Description
INDArray	applyDropout(INDArray inputActivations, INDArray resultArray, 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 present
IDropout	clone()

Method Detail

applyDropout

INDArray applyDropout(INDArray inputActivations,
                      INDArray resultArray,
                      int iteration,
                      int epoch,
                      LayerWorkspaceMgr workspaceMgr)

Parameters:

inputActivations - Input activations array

resultArray - The result array (same as inputArray for in-place ops) for the post-dropout activations

iteration - Current iteration number

epoch - Current epoch number

workspaceMgr - Workspace manager, if any storage is required (use ArrayType.INPUT)

Returns:

The output (resultArray) after applying dropout

backprop

INDArray backprop(INDArray gradAtOutput,
                  INDArray gradAtInput,
                  int iteration,
                  int epoch)

Perform backprop. This should also clear the internal state (dropout mask) if any is present

Parameters:

gradAtOutput - Gradients at the output of the dropout op - i.e., dL/dOut

gradAtInput - Gradients at the input of the dropout op - i.e., dL/dIn. Use the same array as gradAtOutput to apply the backprop gradient in-place

iteration - Current iteration

epoch - Current epoch

Returns:

Same array as gradAtInput - i.e., gradient after backpropagating through dropout op - i.e., dL/dIn

clear

void clear()

Clear the internal state (for example, dropout mask) if any is present

clone

IDropout clone()