org.deeplearning4j.nn.layers

Class ActivationLayer

java.lang.Object

org.deeplearning4j.nn.layers.AbstractLayer<ActivationLayer>

org.deeplearning4j.nn.layers.ActivationLayer

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model, Trainable

public class ActivationLayer
extends AbstractLayer<ActivationLayer>

Activation Layer Used to apply activation on input and corresponding derivative on epsilon. Decouples activation from the layer type and ideal for cases when applying BatchNormLayer. For example, use "identity" activation on the layer prior to BatchNorm and apply this layer after the BatchNorm.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Field Summary

Fields inherited from class org.deeplearning4j.nn.layers.AbstractLayer

cacheMode, conf, dataType, dropoutApplied, epochCount, index, input, inputModificationAllowed, iterationCount, maskArray, maskState, preOutput, trainingListeners

Constructor Summary

Constructors

Constructor and Description
ActivationLayer(NeuralNetConfiguration conf, DataType dataType)

Method Summary

Modifier and Type	Method and Description
INDArray	activate(boolean training, LayerWorkspaceMgr mgr) Perform forward pass and return the activations array with the last set input
Pair<Gradient,INDArray>	backpropGradient(INDArray epsilon, LayerWorkspaceMgr workspaceMgr) Calculate the gradient relative to the error in the next layer
double	calcRegularizationScore(boolean backpropParamsOnly) Calculate the regularization component of the score, for the parameters in this layer For example, the L1, L2 and/or weight decay components of the loss function
void	clearNoiseWeightParams()
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)
INDArray	params() Returns the parameters of the neural network as a flattened row vector
Layer.Type	type() Returns the layer type

Methods inherited from class org.deeplearning4j.nn.layers.AbstractLayer

activate, addListeners, allowInputModification, applyConstraints, applyDropOutIfNecessary, applyMask, assertInputSet, backpropDropOutIfPresent, batchSize, clear, close, computeGradientAndScore, conf, feedForwardMaskArray, fit, fit, getConfig, getEpochCount, getGradientsViewArray, getHelper, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, getParam, gradient, gradientAndScore, init, input, layerConf, layerId, numParams, numParams, paramTable, paramTable, score, setBackpropGradientsViewArray, setCacheMode, setConf, setEpochCount, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParams, setParamsViewArray, setParamTable, update, update, updaterDivideByMinibatch

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.nn.api.Layer

getIterationCount, setIterationCount

Constructor Detail

ActivationLayer

public ActivationLayer(NeuralNetConfiguration conf,
                       DataType dataType)

Method Detail

calcRegularizationScore

public double calcRegularizationScore(boolean backpropParamsOnly)

Description copied from interface: Layer

Calculate the regularization component of the score, for the parameters in this layer
For example, the L1, L2 and/or weight decay components of the loss function

Specified by:

calcRegularizationScore in interface Layer

Overrides:

calcRegularizationScore in class AbstractLayer<ActivationLayer>

Parameters:

backpropParamsOnly - If true: calculate regularization score based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

Returns:

the regularization score of

type

public Layer.Type type()

Description copied from interface: Layer

Returns the layer type

Specified by:

type in interface Layer

Overrides:

type in class AbstractLayer<ActivationLayer>

Returns:

backpropGradient

public Pair<Gradient,INDArray> backpropGradient(INDArray epsilon,
                                                LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Calculate the gradient relative to the error in the next layer

Parameters:

epsilon - w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.

workspaceMgr - Workspace manager

Returns:

Pair where Gradient is gradient for this layer, INDArray is epsilon (activation gradient) needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == dL/dIn = (w^(L)*(delta^(L))^T)^T. Note that the returned array should be placed in the ArrayType.ACTIVATION_GRAD workspace via the workspace manager

activate

public INDArray activate(boolean training,
                         LayerWorkspaceMgr mgr)

Description copied from interface: Layer

Perform forward pass and return the activations array with the last set input

Parameters:

training - training or test mode

mgr - Workspace manager

Returns:

the activation (layer output) of the last specified input. Note that the returned array should be placed in the ArrayType.ACTIVATIONS workspace via the workspace manager

isPretrainLayer

public boolean isPretrainLayer()

Description copied from interface: Layer

Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)

Returns:

true if the layer can be pretrained (using fit(INDArray), false otherwise

clearNoiseWeightParams

public void clearNoiseWeightParams()

params

public INDArray params()

Description copied from class: AbstractLayer

Returns the parameters of the neural network as a flattened row vector

Specified by:

params in interface Model

Specified by:

params in interface Trainable

Overrides:

params in class AbstractLayer<ActivationLayer>

Returns:

the parameters of the neural network