Package ai.djl.training.optimizer

Class RmsProp.Builder

java.lang.Object
ai.djl.training.optimizer.Optimizer.OptimizerBuilder<RmsProp.Builder>
ai.djl.training.optimizer.RmsProp.Builder
Enclosing class:
RmsProp
public static final class RmsProp.Builder extends Optimizer.OptimizerBuilder<RmsProp.Builder>
The Builder to construct an RmsProp object.

  • Method Details

    • self

      protected RmsProp.Builder self()
      Specified by:
      self in class Optimizer.OptimizerBuilder<RmsProp.Builder>

    • optLearningRateTracker

      public RmsProp.Builder optLearningRateTracker(ParameterTracker learningRateTracker)
      Sets the ParameterTracker for this optimizer.
      Parameters:
      learningRateTracker - the ParameterTracker to be set
      Returns:
      this Builder

    • optRho

      public RmsProp.Builder optRho(float rho)
      Sets the decay factor for the moving average over the past squared gradient.
      Parameters:
      rho - the decay factor for the moving average over past squared gradient
      Returns:
      this Builder

    • optMomentum

      public RmsProp.Builder optMomentum(float momentum)
      Sets the momentum factor. This is only used if centered is set to true.
      Parameters:
      momentum - the momentum factor
      Returns:
      this Builder

    • optEpsilon

      public RmsProp.Builder optEpsilon(float epsilon)
      Sets \(epsilon\) - a small quantity for numerical stability.
      Parameters:
      epsilon - a small quantity for numerical stability
      Returns:
      this Builder

    • optCentered

      public RmsProp.Builder optCentered(boolean centered)
      Sets which version of RMSProp to use.

      True: Grave's version False: Tieleman and Hinton's version

      Parameters:
      centered - the RMSProp version
      Returns:
      this Builder

    • build

      public RmsProp build()
      Builds a RmsProp block.
      Returns:
      the RmsProp block