org.deeplearning4j.nn.layers

Class BaseOutputLayer<LayerConfT extends BaseOutputLayer>

java.lang.Object

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

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

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

All Implemented Interfaces:

Serializable, Cloneable, Classifier, Layer, IOutputLayer, Model

Direct Known Subclasses:

CenterLossOutputLayer, OCNNOutputLayer, OutputLayer, RnnOutputLayer

public abstract class BaseOutputLayer<LayerConfT extends BaseOutputLayer>
extends BaseLayer<LayerConfT>
implements Serializable, IOutputLayer

Output layer with different objective in co-occurrences for different objectives. This includes classification as well as prediction

Author:

Adam Gibson

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

Modifier and Type	Field and Description
protected org.nd4j.linalg.api.ndarray.INDArray	inputMaskArray
protected MaskState	inputMaskArrayState
protected org.nd4j.linalg.api.ndarray.INDArray	labels

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

gradient, gradientsFlattened, gradientViews, optimizer, params, paramsFlattened, score, weightNoiseParams

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

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input, boolean training, LayerWorkspaceMgr workspaceMgr) Perform forward pass and return the activations array with the specified input
protected void	applyMask(org.nd4j.linalg.api.ndarray.INDArray to)
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
void	clear() Clear input
void	computeGradientAndScore(LayerWorkspaceMgr workspaceMgr) Update the score
double	computeScore(double fullNetworkL1, double fullNetworkL2, boolean training, LayerWorkspaceMgr workspaceMgr) Compute score after labels and input have been set.
org.nd4j.linalg.api.ndarray.INDArray	computeScoreForExamples(double fullNetworkL1, double fullNetworkL2, LayerWorkspaceMgr workspaceMgr) Compute the score for each example individually, after labels and input have been set.
double	f1Score(org.nd4j.linalg.dataset.api.DataSet data) Sets the input and labels and returns a score for the prediction wrt true labels
double	f1Score(org.nd4j.linalg.api.ndarray.INDArray examples, org.nd4j.linalg.api.ndarray.INDArray labels) Returns the f1 score for the given examples.
void	fit(org.nd4j.linalg.dataset.api.DataSet data) Fit the model
void	fit(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iter) Train the model based on the datasetiterator
void	fit(org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray labels) Fit the model
void	fit(org.nd4j.linalg.api.ndarray.INDArray examples, int[] labels) Fit the model
void	fit(org.nd4j.linalg.api.ndarray.INDArray data, LayerWorkspaceMgr workspaceMgr) Fit the model to the given data
org.nd4j.linalg.api.ndarray.INDArray	getLabels() Get the labels array previously set with IOutputLayer.setLabels(INDArray)
protected abstract org.nd4j.linalg.api.ndarray.INDArray	getLabels2d(LayerWorkspaceMgr workspaceMgr, ArrayType arrayType)
Gradient	gradient() Gets the gradient from one training iteration
org.nd4j.linalg.primitives.Pair<Gradient,Double>	gradientAndScore() Get the gradient and score
boolean	hasBias() Does this layer have no bias term? Many layers (dense, convolutional, output, embedding) have biases by default, but no-bias versions are possible via configuration
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)
org.nd4j.linalg.api.ndarray.INDArray	labelProbabilities(org.nd4j.linalg.api.ndarray.INDArray examples) Returns the probabilities for each label for each example row wise
boolean	needsLabels() Returns true if labels are required for this output layer
int	numLabels() Returns the number of possible labels
List<String>	predict(org.nd4j.linalg.dataset.api.DataSet dataSet) Return predicted label names
int[]	predict(org.nd4j.linalg.api.ndarray.INDArray input) Returns the predictions for each example in the dataset
protected org.nd4j.linalg.api.ndarray.INDArray	preOutput2d(boolean training, LayerWorkspaceMgr workspaceMgr)
void	setLabels(org.nd4j.linalg.api.ndarray.INDArray labels) Set the labels array for this output layer
protected void	setScoreWithZ(org.nd4j.linalg.api.ndarray.INDArray z)

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

accumulateScore, activate, calcL1, calcL2, clearNoiseWeightParams, clone, fit, getGradientsViewArray, getOptimizer, getParam, getParamWithNoise, initParams, layerConf, numParams, params, paramTable, paramTable, preOutput, score, setBackpropGradientsViewArray, setParam, setParams, setParams, setParamsViewArray, setParamTable, toString, transpose, update, update

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

addListeners, applyConstraints, applyDropOutIfNecessary, assertInputSet, batchSize, conf, feedForwardMaskArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, init, input, layerId, numParams, setCacheMode, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, type, 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, calcL1, calcL2, clearNoiseWeightParams, clone, feedForwardMaskArray, getEpochCount, getIndex, getInputMiniBatchSize, getIterationCount, getListeners, getMaskArray, setCacheMode, setEpochCount, setIndex, setInput, setInputMiniBatchSize, setIterationCount, setListeners, setListeners, setMaskArray, transpose, type

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

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

Field Detail

labels

protected org.nd4j.linalg.api.ndarray.INDArray labels

inputMaskArray

protected org.nd4j.linalg.api.ndarray.INDArray inputMaskArray

inputMaskArrayState

protected MaskState inputMaskArrayState

Constructor Detail

BaseOutputLayer

public BaseOutputLayer(NeuralNetConfiguration conf)

BaseOutputLayer

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

Method Detail

computeScore

public double computeScore(double fullNetworkL1,
                           double fullNetworkL2,
                           boolean training,
                           LayerWorkspaceMgr workspaceMgr)

Compute score after labels and input have been set.

Specified by:

computeScore in interface IOutputLayer

Parameters:

fullNetworkL1 - L1 regularization term for the entire network

fullNetworkL2 - L2 regularization term for the entire network

training - whether score should be calculated at train or test time (this affects things like application of dropout, etc)

Returns:

score (loss function)

needsLabels

public boolean needsLabels()

Description copied from interface: IOutputLayer

Returns true if labels are required for this output layer

Specified by:

needsLabels in interface IOutputLayer

Returns:

true if this output layer needs labels or not

computeScoreForExamples

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

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

Specified by:

computeScoreForExamples in interface IOutputLayer

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

computeGradientAndScore

public void computeGradientAndScore(LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Model

Update the score

Specified by:

computeGradientAndScore in interface Model

Overrides:

computeGradientAndScore in class BaseLayer<LayerConfT extends BaseOutputLayer>

setScoreWithZ

protected void setScoreWithZ(org.nd4j.linalg.api.ndarray.INDArray z)

Overrides:

setScoreWithZ in class BaseLayer<LayerConfT extends BaseOutputLayer>

gradientAndScore

public org.nd4j.linalg.primitives.Pair<Gradient,Double> gradientAndScore()

Description copied from interface: Model

Get the gradient and score

Specified by:

gradientAndScore in interface Model

Overrides:

gradientAndScore in class AbstractLayer<LayerConfT extends BaseOutputLayer>

Returns:

the gradient and score

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 BaseLayer<LayerConfT extends BaseOutputLayer>

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

gradient

public Gradient gradient()

Gets the gradient from one training iteration

Specified by:

gradient in interface Model

Overrides:

gradient in class BaseLayer<LayerConfT extends BaseOutputLayer>

Returns:

the gradient (bias and weight matrix)

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input,
                                                     boolean training,
                                                     LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Perform forward pass and return the activations array with the specified input

Specified by:

activate in interface Layer

Overrides:

activate in class AbstractLayer<LayerConfT extends BaseOutputLayer>

Parameters:

input - the input to use

training - train or test mode

workspaceMgr - Workspace manager.

Returns:

Activations array. Note that the returned array should be placed in the ArrayType.ACTIVATIONS workspace via the workspace manager

f1Score

public double f1Score(org.nd4j.linalg.dataset.api.DataSet data)

Sets the input and labels and returns a score for the prediction wrt true labels

Specified by:

f1Score in interface Classifier

Parameters:

data - the data to score

Returns:

the score for the given input,label pairs

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

Parameters:

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

labels - the true labels

Returns:

the scores for each ndarray

numLabels

public int numLabels()

Returns the number of possible labels

Specified by:

numLabels in interface Classifier

Returns:

the number of possible labels for this classifier

fit

public void fit(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iter)

Description copied from interface: Classifier

Train the model based on the datasetiterator

Specified by:

fit in interface Classifier

Parameters:

iter - the iterator to train on

predict

public int[] predict(org.nd4j.linalg.api.ndarray.INDArray input)

Returns the predictions for each example in the dataset

Specified by:

predict in interface Classifier

Parameters:

input - the matrix to predict

Returns:

the prediction for the dataset

predict

public List<String> predict(org.nd4j.linalg.dataset.api.DataSet dataSet)

Return predicted label names

Specified by:

predict in interface Classifier

Parameters:

dataSet - to predict

Returns:

the predicted labels for the dataSet

labelProbabilities

public org.nd4j.linalg.api.ndarray.INDArray labelProbabilities(org.nd4j.linalg.api.ndarray.INDArray examples)

Returns the probabilities for each label for each example row wise

Specified by:

labelProbabilities in interface Classifier

Parameters:

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

Returns:

the likelihoods of each example and each label

fit

public void fit(org.nd4j.linalg.api.ndarray.INDArray input,
                org.nd4j.linalg.api.ndarray.INDArray labels)

Fit the model

Specified by:

fit in interface Classifier

Parameters:

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

labels - the example labels(a binary outcome matrix)

fit

public void fit(org.nd4j.linalg.dataset.api.DataSet data)

Fit the model

Specified by:

fit in interface Classifier

Parameters:

data - the data to train on

fit

public void fit(org.nd4j.linalg.api.ndarray.INDArray examples,
                int[] labels)

Fit the model

Specified by:

fit in interface Classifier

Parameters:

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

labels - the labels for each example (the number of labels must match

clear

public void clear()

Description copied from interface: Model

Clear input

Specified by:

clear in interface Model

Overrides:

clear in class BaseLayer<LayerConfT extends BaseOutputLayer>

fit

public void fit(org.nd4j.linalg.api.ndarray.INDArray data,
                LayerWorkspaceMgr workspaceMgr)

Fit the model to the given data

Specified by:

fit in interface Model

Overrides:

fit in class BaseLayer<LayerConfT extends BaseOutputLayer>

Parameters:

data - the data to fit the model to

getLabels

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

Description copied from interface: IOutputLayer

Get the labels array previously set with IOutputLayer.setLabels(INDArray)

Specified by:

getLabels in interface IOutputLayer

Returns:

Labels array, or null if it has not been set

setLabels

public void setLabels(org.nd4j.linalg.api.ndarray.INDArray labels)

Description copied from interface: IOutputLayer

Set the labels array for this output layer

Specified by:

setLabels in interface IOutputLayer

Parameters:

labels - Labels array to set

preOutput2d

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

applyMask

protected void applyMask(org.nd4j.linalg.api.ndarray.INDArray to)

Overrides:

applyMask in class AbstractLayer<LayerConfT extends BaseOutputLayer>

getLabels2d

protected abstract org.nd4j.linalg.api.ndarray.INDArray getLabels2d(LayerWorkspaceMgr workspaceMgr,
                                                                    ArrayType arrayType)

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)

Specified by:

isPretrainLayer in interface Layer

Returns:

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

hasBias

public boolean hasBias()

Description copied from class: BaseLayer

Does this layer have no bias term? Many layers (dense, convolutional, output, embedding) have biases by default, but no-bias versions are possible via configuration

Overrides:

hasBias in class BaseLayer<LayerConfT extends BaseOutputLayer>

Returns:

True if a bias term is present, false otherwise