Class DFunctionDropOut_F64

java.lang.Object
deepboof.impl.forward.standard.BaseFunction<T>
deepboof.impl.backward.standard.BaseDFunction<deepboof.tensors.Tensor_F64>
deepboof.impl.backward.standard.DFunctionDropOut_F64
All Implemented Interfaces:
DFunctionDropOut<deepboof.tensors.Tensor_F64>, deepboof.DFunction<deepboof.tensors.Tensor_F64>, deepboof.Function<deepboof.tensors.Tensor_F64>

public class DFunctionDropOut_F64
extends BaseDFunction<deepboof.tensors.Tensor_F64>
implements DFunctionDropOut<deepboof.tensors.Tensor_F64>
Implementation of DFunctionDropOut for Tensor_F64
  • Field Summary

    Fields inherited from class deepboof.impl.backward.standard.BaseDFunction

    learningMode

    Fields inherited from class deepboof.impl.forward.standard.BaseFunction

    miniBatchSize, parameters, shapeInput, shapeOutput, shapeParameters
  • Constructor Summary

    Constructors
    Constructor Description
    DFunctionDropOut_F64​(long randomSeed, double dropRate)
    Configures drop out
  • Method Summary

    Modifier and Type Method Description
    protected void _backwards​(deepboof.tensors.Tensor_F64 input, deepboof.tensors.Tensor_F64 dout, deepboof.tensors.Tensor_F64 gradientInput, List<deepboof.tensors.Tensor_F64> gradientParameters)  
    void _forward​(deepboof.tensors.Tensor_F64 input, deepboof.tensors.Tensor_F64 output)  
    void _initialize()  
    void _setParameters​(List<deepboof.tensors.Tensor_F64> parameters)  
    double getDropRate()
    Returns a number from 0 to 1 indicating the likelihood of a neuron being dropped.
    Class<deepboof.tensors.Tensor_F64> getTensorType()  

    Methods inherited from class deepboof.impl.backward.standard.BaseDFunction

    backwards, evaluating, isLearning, learning

    Methods inherited from class deepboof.impl.forward.standard.BaseFunction

    forward, getOutputShape, getParameters, getParameterShapes, initialize, setParameters

    Methods inherited from class java.lang.Object

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

    Methods inherited from interface deepboof.DFunction

    backwards, evaluating, isLearning, learning

    Methods inherited from interface deepboof.Function

    forward, getOutputShape, getParameters, getParameterShapes, initialize, setParameters
  • Constructor Details

    • DFunctionDropOut_F64

      public DFunctionDropOut_F64​(long randomSeed, double dropRate)
      Configures drop out
      Parameters:
      randomSeed - random seed used to pick which neurons are dropped
      dropRate - Fraction of time a neuron is dropped
  • Method Details

    • _initialize

      public void _initialize()
      Specified by:
      _initialize in class deepboof.impl.forward.standard.BaseFunction<deepboof.tensors.Tensor_F64>
    • _setParameters

      public void _setParameters​(List<deepboof.tensors.Tensor_F64> parameters)
      Specified by:
      _setParameters in class deepboof.impl.forward.standard.BaseFunction<deepboof.tensors.Tensor_F64>
    • _forward

      public void _forward​(deepboof.tensors.Tensor_F64 input, deepboof.tensors.Tensor_F64 output)
      Specified by:
      _forward in class deepboof.impl.forward.standard.BaseFunction<deepboof.tensors.Tensor_F64>
    • getDropRate

      public double getDropRate()
      Description copied from interface: DFunctionDropOut
      Returns a number from 0 to 1 indicating the likelihood of a neuron being dropped. 0 = 0% change and 1 = 100% chance
      Specified by:
      getDropRate in interface DFunctionDropOut<deepboof.tensors.Tensor_F64>
      Returns:
      drop rate
    • _backwards

      protected void _backwards​(deepboof.tensors.Tensor_F64 input, deepboof.tensors.Tensor_F64 dout, deepboof.tensors.Tensor_F64 gradientInput, List<deepboof.tensors.Tensor_F64> gradientParameters)
      Specified by:
      _backwards in class BaseDFunction<deepboof.tensors.Tensor_F64>
    • getTensorType

      public Class<deepboof.tensors.Tensor_F64> getTensorType()
      Specified by:
      getTensorType in interface deepboof.Function<deepboof.tensors.Tensor_F64>