org.deeplearning4j.nn.layers

Class LossLayer

java.lang.Object

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

org.deeplearning4j.nn.layers.LossLayer

All Implemented Interfaces:

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

public class LossLayer
extends BaseLayer<LossLayer>
implements java.io.Serializable, IOutputLayer

LossLayer is a flexible output "layer" that performs a loss function on an input without MLP logic.

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

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate() Trigger an activation with the last specified input
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training) Trigger an activation with the last specified input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input) Initialize the layer with the given input and return the activation for this layer given this input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input, boolean training) Initialize the layer with the given input and return the activation for this layer given this 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
Gradient	calcGradient(Gradient layerError, org.nd4j.linalg.api.ndarray.INDArray indArray) Calculate the gradient
double	calcL1(boolean backpropParamsOnly) Calculate the l1 regularization term 0.0 if regularization is not used.
double	calcL2(boolean backpropParamsOnly) Calculate the l2 regularization term 0.0 if regularization is not used.
void	clear() Clear input
void	computeGradientAndScore() Update the score
double	computeScore(double fullNetworkL1, double fullNetworkL2, boolean training) Compute score after labels and input have been set.
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.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) Fit the model to the given data
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
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()
Gradient	gradient() Gets the gradient from one training iteration
Pair<Gradient,java.lang.Double>	gradientAndScore() Get the gradient and score
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)
void	iterate(org.nd4j.linalg.api.ndarray.INDArray input) iterate one iteration of the network
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
void	merge(Layer layer, int batchSize) Averages the given logistic regression from a mini batch into this layer
int	numLabels() Returns the number of possible labels
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	output(org.nd4j.linalg.api.ndarray.INDArray input, boolean training)
org.nd4j.linalg.api.ndarray.INDArray	params() Returns the parameters of the neural network as a flattened row vector
java.util.List<java.lang.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
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)
Layer	transpose() Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)
Layer.Type	type() Returns the layer type

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

accumulateScore, activate, activate, activationMean, applyDropOutIfNecessary, applyLearningRateScoreDecay, applyMask, batchSize, clone, conf, createGradient, derivativeActivation, error, feedForwardMaskArray, fit, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, getParam, init, initParams, input, layerConf, layerNameAndIndex, numParams, numParams, paramTable, paramTable, preOutput, preOutput, preOutput, preOutput, score, setBackpropGradientsViewArray, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParams, setParamsViewArray, setParamTable, toString, 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, clone, derivativeActivation, error, feedForwardMaskArray, getIndex, getInputMiniBatchSize, getListeners, getMaskArray, preOutput, preOutput, preOutput, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray

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

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

Field Detail

labels

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

Constructor Detail

LossLayer

public LossLayer(NeuralNetConfiguration conf)

LossLayer

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

Method Detail

computeScore

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

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)

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

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()

Description copied from interface: Model

Update the score

Specified by:

computeGradientAndScore in interface Model

Overrides:

computeGradientAndScore in class BaseLayer<LossLayer>

setScoreWithZ

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

Overrides:

setScoreWithZ in class BaseLayer<LossLayer>

gradientAndScore

public Pair<Gradient,java.lang.Double> gradientAndScore()

Description copied from interface: Model

Get the gradient and score

Specified by:

gradientAndScore in interface Model

Overrides:

gradientAndScore in class BaseLayer<LossLayer>

Returns:

the gradient and score

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 BaseLayer<LossLayer>

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

gradient

public Gradient gradient()

Gets the gradient from one training iteration

Specified by:

gradient in interface Model

Overrides:

gradient in class BaseLayer<LossLayer>

Returns:

the gradient (bias and weight matrix)

calcL2

public double calcL2(boolean backpropParamsOnly)

Description copied from interface: Layer

Calculate the l2 regularization term
0.0 if regularization is not used. Or 0.5 * l2Coeff * l2Magnitude otherwise.
Note that this does not divide by mini-batch size

Specified by:

calcL2 in interface Layer

Overrides:

calcL2 in class BaseLayer<LossLayer>

Parameters:

backpropParamsOnly - If true: calculate L2 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

Returns:

the l2 regularization term for this layer.

calcL1

public double calcL1(boolean backpropParamsOnly)

Description copied from interface: Layer

Calculate the l1 regularization term
0.0 if regularization is not used. Or l1Coeff * l1Magnitude otherwise.
Note that this does not divide by mini-batch size

Specified by:

calcL1 in interface Layer

Overrides:

calcL1 in class BaseLayer<LossLayer>

Parameters:

backpropParamsOnly - If true: calculate L1 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

Returns:

the l1 regularization term for this layer.

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<LossLayer>

Returns:

fit

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

Description copied from interface: Model

Fit the model to the given data

Specified by:

fit in interface Model

Overrides:

fit in class BaseLayer<LossLayer>

Parameters:

input - the data to fit the model to

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<LossLayer>

Parameters:

training - training or test mode

Returns:

the activation of the last specified input

activate

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

Description copied from interface: Layer

Initialize the layer with the given input and return the activation for this layer given this input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<LossLayer>

Parameters:

input - the input to use

training - train or test mode

Returns:

activate

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

Description copied from interface: Layer

Initialize the layer with the given input and return the activation for this layer given this input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<LossLayer>

Parameters:

input - the input to use

Returns:

activate

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

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<LossLayer>

Returns:

the activation of the last specified input

output

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

output

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

output

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

Classify input

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

transpose

public Layer transpose()

Description copied from interface: Layer

Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)

Specified by:

transpose in interface Layer

Overrides:

transpose in class BaseLayer<LossLayer>

Returns:

the transposed layer

isPretrainLayer

public boolean isPretrainLayer()

Description copied from interface: Layer

Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)

Specified by:

isPretrainLayer in interface Layer

Returns:

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

calcGradient

public Gradient calcGradient(Gradient layerError,
                             org.nd4j.linalg.api.ndarray.INDArray indArray)

Description copied from interface: Layer

Calculate the gradient

Specified by:

calcGradient in interface Layer

Overrides:

calcGradient in class BaseLayer<LossLayer>

Parameters:

layerError - the layer error

Returns:

the gradient

merge

public void merge(Layer layer,
                  int batchSize)

Description copied from class: BaseLayer

Averages the given logistic regression from a mini batch into this layer

Specified by:

merge in interface Layer

Overrides:

merge in class BaseLayer<LossLayer>

Parameters:

layer - the logistic regression layer to average into this layer

batchSize - the batch size

params

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

Description copied from class: BaseLayer

Returns the parameters of the neural network as a flattened row vector

Specified by:

params in interface Model

Overrides:

params in class BaseLayer<LossLayer>

Returns:

the parameters of the neural network

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 java.util.List<java.lang.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<LossLayer>

iterate

public void iterate(org.nd4j.linalg.api.ndarray.INDArray input)

Description copied from class: BaseLayer

iterate one iteration of the network

Specified by:

iterate in interface Model

Overrides:

iterate in class BaseLayer<LossLayer>

Parameters:

input - the input to iterate on

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

getLabels2d

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