org.deeplearning4j.nn.layers.ocnn

Class OCNNOutputLayer

java.lang.Object

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

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

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

org.deeplearning4j.nn.layers.ocnn.OCNNOutputLayer

All Implemented Interfaces:

Serializable, Cloneable, Classifier, Layer, IOutputLayer, Model

public class OCNNOutputLayer
extends BaseOutputLayer<OCNNOutputLayer>

Layer implementation for OCNNOutputLayer See OCNNOutputLayer for details.

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	OCNNOutputLayer.OCNNLossFunction

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

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
OCNNOutputLayer(NeuralNetConfiguration conf)
OCNNOutputLayer(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.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
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
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.api.ndarray.INDArray examples, org.nd4j.linalg.api.ndarray.INDArray labels) Returns the f1 score for the given examples.
org.nd4j.linalg.api.ndarray.INDArray	getLabels() Get the labels array previously set with IOutputLayer.setLabels(INDArray)
protected org.nd4j.linalg.api.ndarray.INDArray	getLabels2d(LayerWorkspaceMgr workspaceMgr, ArrayType arrayType)
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
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
Layer.Type	type() Returns the layer type

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

applyMask, clear, computeGradientAndScore, f1Score, fit, fit, fit, fit, fit, gradient, gradientAndScore, hasBias, isPretrainLayer, numLabels, predict, predict, setScoreWithZ

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

accumulateScore, 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, 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

calcL1, calcL2, clearNoiseWeightParams, clone, feedForwardMaskArray, getEpochCount, getIndex, getInputMiniBatchSize, getIterationCount, getListeners, getMaskArray, setCacheMode, setEpochCount, setIndex, setInput, setInputMiniBatchSize, setIterationCount, setListeners, setListeners, setMaskArray, transpose

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

Constructor Detail

OCNNOutputLayer

public OCNNOutputLayer(NeuralNetConfiguration conf)

OCNNOutputLayer

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

Method Detail

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

Overrides:

getLabels in class BaseOutputLayer<OCNNOutputLayer>

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

Overrides:

setLabels in class BaseOutputLayer<OCNNOutputLayer>

Parameters:

labels - Labels array to set

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

Overrides:

computeScore in class BaseOutputLayer<OCNNOutputLayer>

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

Overrides:

needsLabels in class BaseOutputLayer<OCNNOutputLayer>

Returns:

true if this output layer needs labels or not

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 BaseOutputLayer<OCNNOutputLayer>

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 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 BaseOutputLayer<OCNNOutputLayer>

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.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<OCNNOutputLayer>

Parameters:

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

labels - the true labels

Returns:

the scores for each ndarray

labelProbabilities

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

Description copied from class: BaseOutputLayer

Returns the probabilities for each label for each example row wise

Specified by:

labelProbabilities in interface Classifier

Overrides:

labelProbabilities in class BaseOutputLayer<OCNNOutputLayer>

Parameters:

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

Returns:

the likelihoods of each example and each label

type

public Layer.Type type()

Description copied from interface: Layer

Returns the layer type

Specified by:

type in interface Layer

Overrides:

type in class AbstractLayer<OCNNOutputLayer>

Returns:

preOutput2d

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

Overrides:

preOutput2d in class BaseOutputLayer<OCNNOutputLayer>

getLabels2d

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

Specified by:

getLabels2d in class BaseOutputLayer<OCNNOutputLayer>

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 BaseLayer<OCNNOutputLayer>

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

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

Overrides:

computeScoreForExamples in class BaseOutputLayer<OCNNOutputLayer>

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