Class/Object

com.intel.analytics.zoo.pipeline.api.keras.objectives

SquaredHinge

Related Docs: object SquaredHinge | package objectives

Permalink

class SquaredHinge[T] extends TensorLossFunction[T]

Creates a criterion that optimizes a two-class classification squared hinge loss (margin-based loss) between input x (a Tensor of dimension 1) and output y.

Linear Supertypes
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. SquaredHinge
  2. TensorLossFunction
  3. LossFunction
  4. AbstractCriterion
  5. Serializable
  6. Serializable
  7. AnyRef
  8. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new SquaredHinge(margin: Double = 1.0, sizeAverage: Boolean = true)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    Permalink

    margin

    if unspecified, is by default 1.

    sizeAverage

    Boolean. Whether losses are averaged over observations for each mini-batch. Default is true. If false, the losses are instead summed for each mini-batch.

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. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  10. def equals(other: Any): Boolean

    Permalink
    Definition Classes
    AbstractCriterion → AnyRef → Any

  11. def finalize(): Unit

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

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

    Permalink
    Definition Classes
    AbstractCriterion

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

    Permalink
    Definition Classes
    AnyRef → Any

  14. var gradInput: Tensor[T]

    Permalink
    Definition Classes
    AbstractCriterion

  15. def hashCode(): Int

    Permalink
    Definition Classes
    AbstractCriterion → AnyRef → Any

  16. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  17. val loss: AbstractCriterion[Tensor[T], Tensor[T], T]

    Permalink
    Definition Classes
    SquaredHinge → LossFunction

  18. val margin: Double

    Permalink

    if unspecified, is by default 1.

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

    Permalink
    Definition Classes
    AnyRef

  20. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  21. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  22. var output: T

    Permalink
    Definition Classes
    AbstractCriterion

  23. val sizeAverage: Boolean

    Permalink

    Boolean.

    Boolean. Whether losses are averaged over observations for each mini-batch. Default is true. If false, the losses are instead summed for each mini-batch.

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

    Permalink
    Definition Classes
    AnyRef

  25. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  26. def updateGradInput(input: Tensor[T], target: Tensor[T]): Tensor[T]

    Permalink
    Definition Classes
    LossFunction → AbstractCriterion

  27. def updateOutput(input: Tensor[T], target: Tensor[T]): T

    Permalink
    Definition Classes
    LossFunction → AbstractCriterion

  28. final def wait(): Unit

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

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

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

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

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

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