Class

org.apache.mxnet.javaapi

MakeLossParam

Related Doc: package javaapi

Permalink

class MakeLossParam extends AnyRef

This Param Object is specifically used for MakeLoss

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. MakeLossParam
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new MakeLossParam(data: NDArray)

    Permalink

    data

    Input array.

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 clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  6. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  7. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  8. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  9. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  10. def getData(): NDArray

    Permalink
  11. def getGrad_scale(): Float

    Permalink
  12. def getNormalization(): String

    Permalink
  13. def getOut(): mxnet.NDArray

    Permalink
  14. def getValid_thresh(): Float

    Permalink
  15. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  16. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  17. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  18. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  19. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  20. def setGrad_scale(grad_scale: Float): MakeLossParam

    Permalink

    grad_scale

    Gradient scale as a supplement to unary and binary operators

  21. def setNormalization(normalization: String): MakeLossParam

    Permalink

    normalization

    If this is set to null, the output gradient will not be normalized. If this is set to batch, the output gradient will be divided by the batch size. If this is set to valid, the output gradient will be divided by the number of valid input elements.

  22. def setOut(out: NDArray): MakeLossParam

    Permalink
  23. def setValid_thresh(valid_thresh: Float): MakeLossParam

    Permalink

    valid_thresh

    clip each element in the array to 0 when it is less than valid_thresh. This is used when normalization is set to 'valid'.

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

    Permalink
    Definition Classes
    AnyRef
  25. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any
  26. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  27. final def wait(arg0: Long, arg1: Int): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  28. final def wait(arg0: Long): Unit

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

Inherited from AnyRef

Inherited from Any

Ungrouped