org.deeplearning4j.nn.conf.dropout

Class SpatialDropout

java.lang.Object

org.deeplearning4j.nn.conf.dropout.SpatialDropout

All Implemented Interfaces:

Serializable, Cloneable, IDropout

public class SpatialDropout
extends Object
implements IDropout

Spatial dropout: can only be applied to 4D (convolutional) activations. Dropout mask is generated along the depth dimension, and is applied to each x/y location in an image.
Note that the dropout mask is generated independently for each example: i.e., a dropout mask of shape [minibatch, channels] is generated and applied to activations of shape [minibatch, channels, height, width]

Reference: Efficient Object Localization Using Convolutional Networks: https://arxiv.org/abs/1411.4280

Author:

Alex Black

See Also:

Serialized Form

Constructor Summary

Constructors

Modifier	Constructor and Description
	SpatialDropout(double activationRetainProbability)
protected	SpatialDropout(double activationRetainProbability, org.nd4j.linalg.schedule.ISchedule activationRetainProbabilitySchedule)
	SpatialDropout(org.nd4j.linalg.schedule.ISchedule activationRetainProbabilitySchedule)

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()

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

SpatialDropout

public SpatialDropout(double activationRetainProbability)

Parameters:

activationRetainProbability - Probability of retaining an activation - see Dropout javadoc

SpatialDropout

public SpatialDropout(org.nd4j.linalg.schedule.ISchedule activationRetainProbabilitySchedule)

Parameters:

activationRetainProbabilitySchedule - Schedule for probability of retaining an activation - see Dropout javadoc

SpatialDropout

protected SpatialDropout(double activationRetainProbability,
                         org.nd4j.linalg.schedule.ISchedule activationRetainProbabilitySchedule)

Method Detail

applyDropout

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

Specified by:

applyDropout in interface IDropout

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

public IDropout clone()

Specified by:

clone in interface IDropout

Overrides:

clone in class Object