Class LossMAE
- java.lang.Object
-
- org.nd4j.linalg.lossfunctions.impl.LossL1
-
- org.nd4j.linalg.lossfunctions.impl.LossMAE
-
- All Implemented Interfaces:
Serializable
,ILossFunction
public class LossMAE extends LossL1
- See Also:
- Serialized Form
-
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description INDArray
computeGradient(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask)
Compute the gradient of the loss function with respect to the inputs: dL/dOutputdouble
computeScore(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask, boolean average)
Compute the score (loss function value) for the given inputs.INDArray
computeScoreArray(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask)
Compute the score (loss function value) for each example individually.String
name()
The opName of this functionString
toString()
-
Methods inherited from class org.nd4j.linalg.lossfunctions.impl.LossL1
computeGradientAndScore, scoreArray
-
-
-
-
Constructor Detail
-
LossMAE
public LossMAE()
-
LossMAE
public LossMAE(INDArray weights)
Mean Absolute Error loss function where each the output is (optionally) weighted/scaled by a flags scalar value. Note that the weights array must be a row vector, of length equal to the labels/output dimension 1 size. A weight vector of 1s should give identical results to no weight vector.- Parameters:
weights
- Weights array (row vector). May be null.
-
-
Method Detail
-
computeScore
public double computeScore(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask, boolean average)
Description copied from interface:ILossFunction
Compute the score (loss function value) for the given inputs.- Specified by:
computeScore
in interfaceILossFunction
- Overrides:
computeScore
in classLossL1
- Parameters:
labels
- Label/expected preOutputpreOutput
- Output of the model (neural network)activationFn
- Activation function that should be applied to preOutputmask
- Mask array; may be nullaverage
- Whether the score should be averaged (divided by number of rows in labels/preOutput) or not @return Loss function value
-
computeScoreArray
public INDArray computeScoreArray(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask)
Description copied from interface:ILossFunction
Compute the score (loss function value) for each example individually. For input [numExamples,nOut] returns scores as a column vector: [numExamples,1]- Specified by:
computeScoreArray
in interfaceILossFunction
- Overrides:
computeScoreArray
in classLossL1
- Parameters:
labels
- Labels/expected outputpreOutput
- Output of the model (neural network)activationFn
- Activation function that should be applied to preOutput- Returns:
- Loss function value for each example; column vector
-
computeGradient
public INDArray computeGradient(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask)
Description copied from interface:ILossFunction
Compute the gradient of the loss function with respect to the inputs: dL/dOutput- Specified by:
computeGradient
in interfaceILossFunction
- Overrides:
computeGradient
in classLossL1
- Parameters:
labels
- Label/expected outputpreOutput
- Output of the model (neural network), before the activation function is appliedactivationFn
- Activation function that should be applied to preOutputmask
- Mask array; may be null- Returns:
- Gradient dL/dPreOut
-
name
public String name()
The opName of this function- Specified by:
name
in interfaceILossFunction
- Overrides:
name
in classLossL1
- Returns:
-
-