Package ai.djl.training.optimizer

Class Optimizer.OptimizerBuilder<T extends Optimizer.OptimizerBuilder>

    • Constructor Summary

      Constructors 
      Modifier Constructor Description
      protected OptimizerBuilder()  

    • Method Summary

      All Methods Instance Methods Abstract Methods Concrete Methods 
      Modifier and Type Method Description
      T optBeginNumUpdate​(int beginNumUpdate)
      Sets the initial value of the number of updates.
      T optClipGrad​(float clipGrad)
      Sets the value of the \(clipGrad\).
      T optWeightDecays​(float weightDecays)
      Sets the value of weight decay.
      protected abstract T self()  
      T setRescaleGrad​(float rescaleGrad)
      Sets the value used to rescale the gradient.

      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    • Constructor Detail

      • OptimizerBuilder

        protected OptimizerBuilder()

    • Method Detail

      • setRescaleGrad

        public T setRescaleGrad​(float rescaleGrad)
        Sets the value used to rescale the gradient. This is used to alleviate the effect of batching on the loss. Usually, the value is set to \( 1/batch_size \). Defaults to 1.
        Parameters:
        rescaleGrad - the value used to rescale the gradient
        Returns:
        this Builder

      • optWeightDecays

        public T optWeightDecays​(float weightDecays)
        Sets the value of weight decay. Weight decay augments the objective function with a regularization term that penalizes large weights.
        Parameters:
        weightDecays - the value of weight decay to be set
        Returns:
        this Builder

      • optClipGrad

        public T optClipGrad​(float clipGrad)
        Sets the value of the \(clipGrad\). Clips the gradient to the range of \([-clipGrad, clipGrad]\). If \(clipGrad \lt 0\), gradient clipping is turned off.

        \(grad = max(min(grad, clipGrad), -clipGrad)\)

        Parameters:
        clipGrad - the value of \(clipGrad\)
        Returns:
        this Builder

      • optBeginNumUpdate

        public T optBeginNumUpdate​(int beginNumUpdate)
        Sets the initial value of the number of updates.
        Parameters:
        beginNumUpdate - the initial value of the number of updates
        Returns:
        this Builder

      • self

        protected abstract T self()