Package ai.djl.training.loss
Class L1Loss
- java.lang.Object
-
- ai.djl.training.evaluator.Evaluator
-
- ai.djl.training.loss.Loss
-
- ai.djl.training.loss.L1Loss
-
public class L1Loss extends Loss
L1Loss
calculates L1 loss between label and prediction.L1 loss is defined by \(L = \sum_i \vert {label}_i - {prediction}_i \vert\).
-
-
Field Summary
-
Fields inherited from class ai.djl.training.evaluator.Evaluator
totalInstances
-
-
Constructor Summary
Constructors Constructor Description L1Loss()
Calculates L1 Loss between the label and prediction, a.k.a.L1Loss(java.lang.String name)
Calculates L1 Loss between the label and prediction, a.k.a.L1Loss(java.lang.String name, float weight)
Calculates L1 Loss between the label and prediction, a.k.a.
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description NDArray
evaluate(NDList label, NDList prediction)
Calculates the evaluation between the labels and the predictions.-
Methods inherited from class ai.djl.training.loss.Loss
addAccumulator, elasticNetWeightedDecay, elasticNetWeightedDecay, elasticNetWeightedDecay, elasticNetWeightedDecay, getAccumulator, hingeLoss, hingeLoss, hingeLoss, l1Loss, l1Loss, l1Loss, l1WeightedDecay, l1WeightedDecay, l1WeightedDecay, l2Loss, l2Loss, l2Loss, l2WeightedDecay, l2WeightedDecay, l2WeightedDecay, maskedSoftmaxCrossEntropyLoss, maskedSoftmaxCrossEntropyLoss, maskedSoftmaxCrossEntropyLoss, resetAccumulator, sigmoidBinaryCrossEntropyLoss, sigmoidBinaryCrossEntropyLoss, sigmoidBinaryCrossEntropyLoss, softmaxCrossEntropyLoss, softmaxCrossEntropyLoss, softmaxCrossEntropyLoss, updateAccumulator
-
Methods inherited from class ai.djl.training.evaluator.Evaluator
checkLabelShapes, checkLabelShapes, getName
-
-
-
-
Constructor Detail
-
L1Loss
public L1Loss()
Calculates L1 Loss between the label and prediction, a.k.a. MAE(Mean Absolute Error).
-
L1Loss
public L1Loss(java.lang.String name)
Calculates L1 Loss between the label and prediction, a.k.a. MAE(Mean Absolute Error).- Parameters:
name
- the name of the loss
-
L1Loss
public L1Loss(java.lang.String name, float weight)
Calculates L1 Loss between the label and prediction, a.k.a. MAE(Mean Absolute Error).- Parameters:
name
- the name of the lossweight
- the weight to apply on loss value, default 1
-
-