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

IDropout instances operate on an activations array, modifying or dropping values at training time only. IDropout instances are not applied at test time.

Author:

Alex Black

Method Summary

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()

Method Detail

applyDropout

org.nd4j.linalg.api.ndarray.INDArray applyDropout(org.nd4j.linalg.api.ndarray.INDArray inputActivations,
                                                  int iteration,
                                                  int epoch,
                                                  boolean inPlace)

Parameters:

inputActivations - Input activations array

iteration - Current iteration number

epoch - Current epoch number

inPlace - If true: modify the input activations in-place. False: Copy the input activations and apply dropout on the copy instead

Returns:

clone

IDropout clone()