Package ai.djl.training.loss

Class L2Loss

  • public class L2Loss
extends Loss
    Calculates L2Loss between label and prediction, a.k.a. MSE(Mean Square Error).

    L2 loss is defined by \(L = \frac{1}{2} \sum_i \vert {label}_i - {prediction}_i \vert^2\)

    • Constructor Detail

      • L2Loss

        public L2Loss()
        Calculate L2Loss between the label and prediction, a.k.a. MSE(Mean Square Error).

      • L2Loss

        public L2Loss​(java.lang.String name)
        Calculate L2Loss between the label and prediction, a.k.a. MSE(Mean Square Error).
        Parameters:
        name - the name of the loss

      • L2Loss

        public L2Loss​(java.lang.String name,
              float weight)
        Calculates L2Loss between the label and prediction, a.k.a. MSE(Mean Square Error).
        Parameters:
        name - the name of the loss
        weight - the weight to apply on loss value, default 1/2

    • Method Detail

      • evaluate

        public NDArray evaluate​(NDList label,
                        NDList prediction)
        Calculates the evaluation between the labels and the predictions.
        Specified by:
        evaluate in class Evaluator
        Parameters:
        label - the correct values
        prediction - the predicted values
        Returns:
        the evaluation result