Class/Object

com.intel.analytics.bigdl.nn

TimeDistributedCriterion

Related Docs: object TimeDistributedCriterion | package nn

Permalink

class TimeDistributedCriterion[T] extends TensorCriterion[T]

This class is intended to support inputs with 3 or more dimensions. Apply Any Provided Criterion to every temporal slice of an input.

Linear Supertypes
TensorCriterion[T], AbstractCriterion[Tensor[T], Tensor[T], T], Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. TimeDistributedCriterion
  2. TensorCriterion
  3. AbstractCriterion
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new TimeDistributedCriterion(critrn: TensorCriterion[T], sizeAverage: Boolean = false, dimension: Int = 2)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    Permalink

    critrn

    embedded criterion

    sizeAverage

    whether to divide the length of input along dimension.

    dimension

    to compute criterion loss along the input and target dimension if sizeAverage=true, and dimension=1, it means to divide the batch size; if sizeAverage=true, and dimension=2, it means to divide the sequence length

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

    Performs a back-propagation step through the criterion, with respect to the given input.

    Performs a back-propagation step through the criterion, with respect to the given input.

    input

    input data

    target

    target

    returns

    gradient corresponding to input data

    Definition Classes
    AbstractCriterion
  6. def canEqual(other: Any): Boolean

    Permalink
  7. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  8. def cloneCriterion(): AbstractCriterion[Tensor[T], Tensor[T], T]

    Permalink

    Deep copy this criterion

    Deep copy this criterion

    returns

    a deep copied criterion

    Definition Classes
    AbstractCriterion
  9. val critrn: TensorCriterion[T]

    Permalink

    embedded criterion

  10. val dimension: Int

    Permalink

    to compute criterion loss along the input and target dimension if sizeAverage=true, and dimension=1, it means to divide the batch size; if sizeAverage=true, and dimension=2, it means to divide the sequence length

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

    Permalink
    Definition Classes
    AnyRef
  12. def equals(other: Any): Boolean

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

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  14. def forward(input: Tensor[T], target: Tensor[T]): T

    Permalink

    Takes an input object, and computes the corresponding loss of the criterion, compared with target.

    Takes an input object, and computes the corresponding loss of the criterion, compared with target.

    input

    input data

    target

    target

    returns

    the loss of criterion

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

    Permalink
    Definition Classes
    AnyRef → Any
  16. var gradInput: Tensor[T]

    Permalink
    Definition Classes
    AbstractCriterion
  17. def hashCode(): Int

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

    Permalink
    Definition Classes
    Any
  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. var results: Array[Future[Unit]]

    Permalink
    Attributes
    protected
  24. val sizeAverage: Boolean

    Permalink

    whether to divide the length of input along dimension.

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

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

    Permalink
    Definition Classes
    AnyRef → Any
  27. def updateGradInput(input: Tensor[T], target: 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.

    input

    input data

    target

    target data / labels

    returns

    gradient of input

    Definition Classes
    TimeDistributedCriterionAbstractCriterion
  28. def updateOutput(input: 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.

    input

    input of the criterion

    target

    target or labels

    returns

    the loss of the criterion

    Definition Classes
    TimeDistributedCriterionAbstractCriterion
  29. final def wait(): Unit

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

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

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

Inherited from TensorCriterion[T]

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

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped