org.deeplearning4j.nn.layers.convolution.subsampling

Class Subsampling1DLayer

java.lang.Object

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

org.deeplearning4j.nn.layers.convolution.subsampling.SubsamplingLayer

org.deeplearning4j.nn.layers.convolution.subsampling.Subsampling1DLayer

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model, Trainable

public class Subsampling1DLayer
extends SubsamplingLayer

1D (temporal) subsampling layer. Currently, we just subclass off the SubsamplingLayer and override the preOutput and backpropGradient methods. Specifically, since this layer accepts RNN (not CNN) InputTypes, we need to add a singleton fourth dimension before calling the respective superclass method, then remove it from the result. This approach treats a multivariate time series with L timesteps and P variables as an L x 1 x P image (L rows high, 1 column wide, P channels deep). The kernel should be H

Author:

[email protected]

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.convolution.subsampling.SubsamplingLayer

convolutionMode, helper, helperCountFail

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
Subsampling1DLayer(NeuralNetConfiguration conf, DataType dataType)

Method Summary

Modifier and Type	Method and Description
INDArray	activate(boolean training, LayerWorkspaceMgr workspaceMgr) 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
Pair<INDArray,MaskState>	feedForwardMaskArray(INDArray maskArray, MaskState currentMaskState, int minibatchSize) Feed forward the input mask array, setting in the layer as appropriate.

Methods inherited from class org.deeplearning4j.nn.layers.convolution.subsampling.SubsamplingLayer

calcRegularizationScore, clearNoiseWeightParams, fit, fit, getHelper, getParam, gradient, isPretrainLayer, numParams, params, score, setParams, type, update

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

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

Subsampling1DLayer

public Subsampling1DLayer(NeuralNetConfiguration conf,
                          DataType dataType)

Method Detail

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

Specified by:

backpropGradient in interface Layer

Overrides:

backpropGradient in class SubsamplingLayer

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 workspaceMgr)

Description copied from interface: Layer

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

Specified by:

activate in interface Layer

Overrides:

activate in class SubsamplingLayer

Parameters:

training - training or test mode

workspaceMgr - 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

feedForwardMaskArray

public Pair<INDArray,MaskState> feedForwardMaskArray(INDArray maskArray,
                                                     MaskState currentMaskState,
                                                     int minibatchSize)

Description copied from interface: Layer

Feed forward the input mask array, setting in the layer as appropriate. This allows different layers to handle masks differently - for example, bidirectional RNNs and normal RNNs operate differently with masks (the former sets activations to 0 outside of the data present region (and keeps the mask active for future layers like dense layers), whereas normal RNNs don't zero out the activations/errors )instead relying on backpropagated error arrays to handle the variable length case.
This is also used for example for networks that contain global pooling layers, arbitrary preprocessors, etc.

Specified by:

feedForwardMaskArray in interface Layer

Overrides:

feedForwardMaskArray in class SubsamplingLayer

Parameters:

maskArray - Mask array to set

currentMaskState - Current state of the mask - see MaskState

minibatchSize - Current minibatch size. Needs to be known as it cannot always be inferred from the activations array due to reshaping (such as a DenseLayer within a recurrent neural network)

Returns:

New mask array after this layer, along with the new mask state.