org.deeplearning4j.nn.layers.convolution

Class Convolution1DLayer

java.lang.Object

org.deeplearning4j.nn.layers.BaseLayer<ConvolutionLayer>

org.deeplearning4j.nn.layers.convolution.ConvolutionLayer

org.deeplearning4j.nn.layers.convolution.Convolution1DLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Layer, Model

public class Convolution1DLayer
extends ConvolutionLayer

1D (temporal) convolutional layer. Currently, we just subclass off the ConvolutionLayer 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

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.ConvolutionLayer

convolutionMode, helper, log

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

conf, dropoutApplied, dropoutMask, gradient, gradientsFlattened, gradientViews, index, input, iterationListeners, maskArray, maskState, optimizer, params, paramsFlattened, score, solver

Constructor Summary

Constructors

Constructor and Description
Convolution1DLayer(NeuralNetConfiguration conf)
Convolution1DLayer(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray input)

Method Summary

Modifier and Type	Method and Description
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon) Calculate the gradient relative to the error in the next layer
org.nd4j.linalg.api.ndarray.INDArray	preOutput(boolean training)
protected org.nd4j.linalg.api.ndarray.INDArray	preOutput4d(boolean training) preOutput4d: Used so that ConvolutionLayer subclasses (such as Convolution1DLayer) can maintain their standard non-4d preOutput method, while overriding this to return 4d activations (for use in backprop) without modifying the public API

Methods inherited from class org.deeplearning4j.nn.layers.convolution.ConvolutionLayer

activate, calcGradient, calcL1, calcL2, fit, isPretrainLayer, merge, params, setParams, transpose, type

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

accumulateScore, activate, activate, activate, activate, activate, activationMean, applyDropOutIfNecessary, applyLearningRateScoreDecay, applyMask, batchSize, clear, clone, computeGradientAndScore, conf, createGradient, derivativeActivation, error, feedForwardMaskArray, fit, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, getParam, gradient, gradientAndScore, init, initParams, input, iterate, layerConf, layerNameAndIndex, numParams, numParams, paramTable, paramTable, preOutput, preOutput, preOutput, score, setBackpropGradientsViewArray, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParamsViewArray, setParamTable, setScoreWithZ, toString, update, update, validateInput

Methods inherited from class java.lang.Object

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

Constructor Detail

Convolution1DLayer

public Convolution1DLayer(NeuralNetConfiguration conf)

Convolution1DLayer

public Convolution1DLayer(NeuralNetConfiguration conf,
                          org.nd4j.linalg.api.ndarray.INDArray input)

Method Detail

backpropGradient

public Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)

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 ConvolutionLayer

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.

Returns:

Pair where Gradient is gradient for this layer, INDArray is epsilon 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() == (w^(L)*(delta^(L))^T)^T

preOutput4d

protected org.nd4j.linalg.api.ndarray.INDArray preOutput4d(boolean training)

Description copied from class: ConvolutionLayer

preOutput4d: Used so that ConvolutionLayer subclasses (such as Convolution1DLayer) can maintain their standard non-4d preOutput method, while overriding this to return 4d activations (for use in backprop) without modifying the public API

Overrides:

preOutput4d in class ConvolutionLayer

preOutput

public org.nd4j.linalg.api.ndarray.INDArray preOutput(boolean training)

Overrides:

preOutput in class ConvolutionLayer