org.deeplearning4j.nn.layers.recurrent

Class RnnOutputLayer

java.lang.Object

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

org.deeplearning4j.nn.layers.BaseOutputLayer<RnnOutputLayer>

org.deeplearning4j.nn.layers.recurrent.RnnOutputLayer

All Implemented Interfaces:

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

public class RnnOutputLayer
extends BaseOutputLayer<RnnOutputLayer>

Recurrent Neural Network Output Layer.
Handles calculation of gradients etc for various objective functions.
Functionally the same as OutputLayer, but handles output and label reshaping automatically.
Input and output activations are same as other RNN layers: 3 dimensions with shape [miniBatchSize,nIn,timeSeriesLength] and [miniBatchSize,nOut,timeSeriesLength] respectively.

See Also:

BaseOutputLayer, OutputLayer, 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.BaseOutputLayer

inputMaskArray, inputMaskArrayState, labels

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

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

Constructor Summary

Constructors

Constructor and Description
RnnOutputLayer(NeuralNetConfiguration conf)
RnnOutputLayer(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) Trigger an activation with the last specified input
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	computeScoreForExamples(double fullNetworkL1, double fullNetworkL2) Compute the score for each example individually, after labels and input have been set.
double	f1Score(org.nd4j.linalg.api.ndarray.INDArray examples, org.nd4j.linalg.api.ndarray.INDArray labels) Returns the f1 score for the given examples.
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize) Feed forward the input mask array, setting in in the layer as appropriate.
org.nd4j.linalg.api.ndarray.INDArray	getInput()
protected org.nd4j.linalg.api.ndarray.INDArray	getLabels2d()
org.nd4j.linalg.api.ndarray.INDArray	output(boolean training) Classify input
org.nd4j.linalg.api.ndarray.INDArray	output(org.nd4j.linalg.api.ndarray.INDArray input)
org.nd4j.linalg.api.ndarray.INDArray	preOutput(org.nd4j.linalg.api.ndarray.INDArray x, boolean training) Raw activations
protected org.nd4j.linalg.api.ndarray.INDArray	preOutput2d(boolean training)
void	setMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray) Set the mask array.
Layer.Type	type() Returns the layer type

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

activate, activate, activate, applyMask, clear, computeGradientAndScore, computeScore, f1Score, fit, fit, fit, fit, fit, getLabels, gradient, gradientAndScore, isPretrainLayer, iterate, labelProbabilities, numLabels, output, predict, predict, setLabels, setScoreWithZ

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

accumulateScore, activate, activate, activationMean, applyDropOutIfNecessary, applyLearningRateScoreDecay, batchSize, calcGradient, calcL1, calcL2, clone, conf, createGradient, derivativeActivation, error, fit, getIndex, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, getParam, init, initParams, input, layerConf, layerNameAndIndex, merge, numParams, numParams, params, paramTable, paramTable, preOutput, preOutput, preOutput, score, setBackpropGradientsViewArray, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setParam, setParams, setParams, setParamsViewArray, setParamTable, toString, transpose, update, update, validateInput

Methods inherited from class java.lang.Object

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

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

activate, activate, activationMean, calcGradient, calcL1, calcL2, clone, derivativeActivation, error, getIndex, getInputMiniBatchSize, getListeners, getMaskArray, merge, preOutput, preOutput, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, transpose

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

accumulateScore, applyLearningRateScoreDecay, batchSize, conf, fit, getOptimizer, getParam, init, initParams, input, numParams, numParams, params, paramTable, paramTable, score, setBackpropGradientsViewArray, setConf, setParam, setParams, setParamsViewArray, setParamTable, update, update, validateInput

Constructor Detail

RnnOutputLayer

public RnnOutputLayer(NeuralNetConfiguration conf)

RnnOutputLayer

public RnnOutputLayer(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 BaseOutputLayer<RnnOutputLayer>

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

f1Score

public double f1Score(org.nd4j.linalg.api.ndarray.INDArray examples,
                      org.nd4j.linalg.api.ndarray.INDArray labels)

Returns the f1 score for the given examples. Think of this to be like a percentage right. The higher the number the more it got right. This is on a scale from 0 to 1.

Specified by:

f1Score in interface Classifier

Overrides:

f1Score in class BaseOutputLayer<RnnOutputLayer>

Parameters:

examples - te the examples to classify (one example in each row)

labels - the true labels

Returns:

the scores for each ndarray

getInput

public org.nd4j.linalg.api.ndarray.INDArray getInput()

Overrides:

getInput in class BaseLayer<RnnOutputLayer>

type

public Layer.Type type()

Description copied from interface: Layer

Returns the layer type

Specified by:

type in interface Layer

Overrides:

type in class BaseLayer<RnnOutputLayer>

Returns:

preOutput

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

Description copied from interface: Layer

Raw activations

Specified by:

preOutput in interface Layer

Overrides:

preOutput in class BaseLayer<RnnOutputLayer>

Parameters:

x - the input to transform

Returns:

the raw activation for this layer

preOutput2d

protected org.nd4j.linalg.api.ndarray.INDArray preOutput2d(boolean training)

Overrides:

preOutput2d in class BaseOutputLayer<RnnOutputLayer>

getLabels2d

protected org.nd4j.linalg.api.ndarray.INDArray getLabels2d()

Overrides:

getLabels2d in class BaseOutputLayer<RnnOutputLayer>

output

public org.nd4j.linalg.api.ndarray.INDArray output(org.nd4j.linalg.api.ndarray.INDArray input)

Overrides:

output in class BaseOutputLayer<RnnOutputLayer>

output

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

Description copied from class: BaseOutputLayer

Classify input

Overrides:

output in class BaseOutputLayer<RnnOutputLayer>

Parameters:

training - determines if its training the input (can either be a matrix or vector) If it's a matrix, each row is considered an example and associated rows are classified accordingly. Each row will be the likelihood of a label given that example

Returns:

a probability distribution for each row

activate

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

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<RnnOutputLayer>

Parameters:

training - training or test mode

Returns:

the activation of the last specified input

setMaskArray

public void setMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray)

Description copied from interface: Layer

Set the mask array. Note: In general, Layer.feedForwardMaskArray(INDArray, MaskState, int) should be used in preference to this.

Specified by:

setMaskArray in interface Layer

Overrides:

setMaskArray in class BaseLayer<RnnOutputLayer>

Parameters:

maskArray - Mask array to set

feedForwardMaskArray

public Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState> feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray,
                                                                                 MaskState currentMaskState,
                                                                                 int minibatchSize)

Description copied from interface: Layer

Feed forward the input mask array, setting in 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 BaseLayer<RnnOutputLayer>

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.

computeScoreForExamples

public org.nd4j.linalg.api.ndarray.INDArray computeScoreForExamples(double fullNetworkL1,
                                                                    double fullNetworkL2)

Compute the score for each example individually, after labels and input have been set.

Specified by:

computeScoreForExamples in interface IOutputLayer

Overrides:

computeScoreForExamples in class BaseOutputLayer<RnnOutputLayer>

Parameters:

fullNetworkL1 - L1 regularization term for the entire network (or, 0.0 to not include regularization)

fullNetworkL2 - L2 regularization term for the entire network (or, 0.0 to not include regularization)

Returns:

A column INDArray of shape [numExamples,1], where entry i is the score of the ith example