Class

com.intel.analytics.zoo.pipeline.api.autograd

CustomLossWithVariable

Related Doc: package autograd

Permalink

class CustomLossWithVariable[T] extends CustomLoss[T]

Linear Supertypes
CustomLoss[T], TensorLossFunction[T], LossFunction[Tensor[T], Tensor[T], T], AbstractCriterion[Tensor[T], Tensor[T], T], Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. CustomLossWithVariable
  2. CustomLoss
  3. TensorLossFunction
  4. LossFunction
  5. AbstractCriterion
  6. Serializable
  7. Serializable
  8. AnyRef
  9. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new CustomLossWithVariable(inputs: Array[Variable[T]], lossVar: Variable[T], sizeAverage: Boolean = true)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    Permalink

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  4. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  5. def backward(input: Tensor[T], target: Tensor[T]): Tensor[T]

    Permalink
    Definition Classes
    AbstractCriterion

  6. def canEqual(other: Any): Boolean

    Permalink
    Definition Classes
    AbstractCriterion

  7. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  8. def cloneCriterion(): AbstractCriterion[Tensor[T], Tensor[T], T]

    Permalink
    Definition Classes
    AbstractCriterion

  9. def doGetLoss(inputs: Array[Variable[T]]): AbstractModule[Activity, Activity, T]

    Permalink
    Attributes
    protected
    Definition Classes
    CustomLossWithVariable → CustomLoss

  10. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  11. def equals(other: Any): Boolean

    Permalink
    Definition Classes
    AbstractCriterion → AnyRef → Any

  12. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  13. def forward(input: Tensor[T], target: Tensor[T]): T

    Permalink
    Definition Classes
    AbstractCriterion

  14. final def generateLossFromVars(inVars: Array[Variable[T]], outVar: Variable[T]): Model[T]

    Permalink
    Definition Classes
    CustomLoss

  15. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any

  16. def getInputVars(inputShapes: Array[Shape]): Array[Variable[T]]

    Permalink
    Attributes
    protected
    Definition Classes
    CustomLossWithVariable → CustomLoss

  17. final def getLoss(inputShapes: Array[Shape]): AbstractModule[Activity, Activity, T]

    Permalink
    Definition Classes
    CustomLoss

  18. var gradInput: Tensor[T]

    Permalink
    Definition Classes
    AbstractCriterion

  19. def hashCode(): Int

    Permalink
    Definition Classes
    AbstractCriterion → AnyRef → Any

  20. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  21. val loss: CustomLossWithVariable[T]

    Permalink
    Definition Classes
    CustomLossWithVariable → LossFunction

  22. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  23. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  24. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  25. var output: T

    Permalink
    Definition Classes
    AbstractCriterion

  26. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef

  27. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  28. def updateGradInput(yPred: Tensor[T], yTrue: Tensor[T]): Tensor[T]

    Permalink

    Computing the gradient of the criterion with respect to its own input.

    Computing the gradient of the criterion with respect to its own input. This is returned in gradInput. Also, the gradInput state variable is updated accordingly.

    yPred

    input data

    yTrue

    target data / labels

    returns

    gradient of input

    Definition Classes
    CustomLoss → LossFunction → AbstractCriterion

  29. def updateOutput(yPred: Tensor[T], target: Tensor[T]): T

    Permalink

    Computes the loss using input and objective function.

    Computes the loss using input and objective function. This function returns the result which is stored in the output field.

    yPred

    input of the criterion

    target

    target or labels

    returns

    the loss of the criterion

    Definition Classes
    CustomLoss → LossFunction → AbstractCriterion

  30. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  31. final def wait(arg0: Long, arg1: Int): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  32. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from CustomLoss[T]

Inherited from TensorLossFunction[T]

Inherited from LossFunction[Tensor[T], Tensor[T], T]

Inherited from AbstractCriterion[Tensor[T], Tensor[T], T]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped