org.deeplearning4j.nn.layers.convolution.upsampling

Class Upsampling1D

java.lang.Object

org.deeplearning4j.nn.layers.AbstractLayer<Upsampling2D>

org.deeplearning4j.nn.layers.convolution.upsampling.Upsampling2D

org.deeplearning4j.nn.layers.convolution.upsampling.Upsampling1D

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model

public class Upsampling1D
extends Upsampling2D

1D Upsampling layer.

Used for upsampling a 1D convolution. Currently derived from 2D version. For forward and backward pass we add a dummy dimension, apply the 2D version and strip the extra dimension again. Eventually, we will want to migrate to a proper 1D version without this overhead.

Author:

Max Pumperla

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, dropoutApplied, dropoutMask, epochCount, index, input, iterationCount, maskArray, maskState, preOutput, trainingListeners

Constructor Summary

Constructors

Constructor and Description
Upsampling1D(NeuralNetConfiguration conf)
Upsampling1D(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray input)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training, LayerWorkspaceMgr workspaceMgr) Perform forward pass and return the activations array with the last set input
org.nd4j.linalg.primitives.Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon, LayerWorkspaceMgr workspaceMgr) Calculate the gradient relative to the error in the next layer
protected int[]	getSize()
protected org.nd4j.linalg.api.ndarray.INDArray	preOutput(boolean training, boolean forBackprop, LayerWorkspaceMgr workspaceMgr)

Methods inherited from class org.deeplearning4j.nn.layers.convolution.upsampling.Upsampling2D

accumulateScore, calcL1, calcL2, clearNoiseWeightParams, clone, fit, fit, getParam, gradient, isPretrainLayer, numParams, params, score, setParams, transpose, type, update

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

activate, addListeners, applyConstraints, applyDropOutIfNecessary, applyMask, assertInputSet, batchSize, clear, computeGradientAndScore, conf, feedForwardMaskArray, getGradientsViewArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, gradientAndScore, init, initParams, input, layerConf, layerId, numParams, paramTable, paramTable, setBackpropGradientsViewArray, setCacheMode, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParamsViewArray, setParamTable, update, validateInput

Methods inherited from class java.lang.Object

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

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

getEpochCount, getIterationCount, setEpochCount, setIterationCount

Constructor Detail

Upsampling1D

public Upsampling1D(NeuralNetConfiguration conf)

Upsampling1D

public Upsampling1D(NeuralNetConfiguration conf,
                    org.nd4j.linalg.api.ndarray.INDArray input)

Method Detail

backpropGradient

public org.nd4j.linalg.primitives.Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.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 Upsampling2D

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

getSize

protected int[] getSize()

Overrides:

getSize in class Upsampling2D

activate

public org.nd4j.linalg.api.ndarray.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 Upsampling2D

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

preOutput

protected org.nd4j.linalg.api.ndarray.INDArray preOutput(boolean training,
                                                         boolean forBackprop,
                                                         LayerWorkspaceMgr workspaceMgr)

Overrides:

preOutput in class Upsampling2D