org.deeplearning4j.nn.api.layers

Interface IOutputLayer

All Superinterfaces:

Classifier, Cloneable, Layer, Model, Serializable, Trainable

All Known Implementing Classes:

BaseOutputLayer, CenterLossOutputLayer, CnnLossLayer, LossLayer, OCNNOutputLayer, OutputLayer, RnnLossLayer, RnnOutputLayer, SameDiffOutputLayer, Yolo2OutputLayer

public interface IOutputLayer
extends Layer, Classifier

Interface for output layers (those that calculate gradients with respect to a labels array)

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Method Summary

Modifier and Type	Method and Description
double	computeScore(double fullNetworkL1, double fullNetworkL2, boolean training, LayerWorkspaceMgr workspaceMgr) Compute score after labels and input have been set.
INDArray	computeScoreForExamples(double fullNetworkL1, double fullNetworkL2, LayerWorkspaceMgr workspaceMgr) Compute the score for each example individually, after labels and input have been set.
INDArray	getLabels() Get the labels array previously set with setLabels(INDArray)
boolean	needsLabels() Returns true if labels are required for this output layer
void	setLabels(INDArray labels) Set the labels array for this output layer

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

activate, activate, allowInputModification, backpropGradient, calcL1, calcL2, clearNoiseWeightParams, feedForwardMaskArray, getEpochCount, getHelper, getIndex, getInputMiniBatchSize, getIterationCount, getListeners, getMaskArray, isPretrainLayer, setCacheMode, setEpochCount, setIndex, setInput, setInputMiniBatchSize, setIterationCount, setListeners, setListeners, setMaskArray, type

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

getConfig, getGradientsViewArray, numParams, params, paramTable

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

f1Score, f1Score, fit, fit, fit, fit, labelProbabilities, numLabels, predict, predict

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

addListeners, applyConstraints, batchSize, clear, computeGradientAndScore, conf, fit, fit, getGradientsViewArray, getOptimizer, getParam, gradient, gradientAndScore, init, input, numParams, numParams, params, paramTable, paramTable, score, setBackpropGradientsViewArray, setConf, setParam, setParams, setParamsViewArray, setParamTable, update, update

Method Detail

needsLabels

boolean needsLabels()

Returns true if labels are required for this output layer

Returns:

true if this output layer needs labels or not

setLabels

void setLabels(INDArray labels)

Set the labels array for this output layer

Parameters:

labels - Labels array to set

getLabels

INDArray getLabels()

Get the labels array previously set with setLabels(INDArray)

Returns:

Labels array, or null if it has not been set

computeScore

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

Compute score after labels and input have been set.

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)

computeScoreForExamples

INDArray computeScoreForExamples(double fullNetworkL1,
                                 double fullNetworkL2,
                                 LayerWorkspaceMgr workspaceMgr)

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

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