Object

com.intel.analytics.bigdl.nn

Utils

Related Doc: package nn

Permalink

object Utils

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

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 calculateFwdBwdTime[T](times: Array[(AbstractModule[_ <: Activity, _ <: Activity, T], Long, Long)])(implicit arg0: ClassTag[T]): (Long, Long)

    Permalink

    Calculate forward time and backward time.

  6. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  7. def copyModule[T](src: Module[T], dst: Module[T]): Module[T]

    Permalink

    copy src's parameters and running status to dst

    copy src's parameters and running status to dst

    src

    source model

    dst

    destination model

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

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

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

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

    Permalink
    Definition Classes
    AnyRef → Any
  12. def getNamedModules[T](model: Module[T]): Map[String, Module[T]]

    Permalink

    get all modules and map by name

  13. def hashCode(): Int

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

    Permalink
    Definition Classes
    Any
  15. def isLayerwiseScaled[T](model: Module[T]): Boolean

    Permalink

    get whether the module is layerwise scaled

    get whether the module is layerwise scaled

    model

    input module

    returns

    whether the module is layerwise scaled

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

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

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

    Permalink
    Definition Classes
    AnyRef
  19. def recursiveAdd[T](y: Activity, alpha: Double = 1.0, x: Activity)(implicit ev: TensorNumeric[T]): Activity

    Permalink

    Apply a add operation on table x and table y one by one.

    Apply a add operation on table x and table y one by one. y := y + alpha * x

    Table x should have the same size with y.

    returns

    y

  20. def recursiveCopy[T](y: Activity, x: Activity)(implicit ev: TensorNumeric[T]): Activity

    Permalink

    copy table x's tensor to table y.

    copy table x's tensor to table y.

    Table x should have the same size with y.

    returns

    y

  21. def recursiveFill[T](x: Activity, value: Double)(implicit ev: TensorNumeric[T]): Unit

    Permalink

    Fill the value to each Tensor in the table recursively

  22. def recursiveResizeAs[T](target: Activity, src: Activity)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Activity

    Permalink

    Resize table target as table src.

  23. def recursiveTensorApply1[T](x: Activity, func: (Tensor[T]) ⇒ Tensor[T])(implicit ev: TensorNumeric[T]): Unit

    Permalink

    Apply function 'func' on all tensor in the table.

  24. def recursiveTensorApply2[T](x: Activity, y: Activity, func: (Tensor[T], Tensor[T]) ⇒ Tensor[T])(implicit ev: TensorNumeric[T]): Activity

    Permalink

    Apply function 'func' on each tensor in table x and table y recursively.

    Apply function 'func' on each tensor in table x and table y recursively.

    Table x should have the same size with table y.

  25. def shuffle[T](src: Tensor[T], permutation: Array[Int], buffer: Tensor[T] = null)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Tensor[T]

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

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

    Permalink
    Definition Classes
    AnyRef → Any
  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( ... )
  31. def zeroTableCopy[T](t1: Table, t2: Table)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Table

    Permalink

    This method recursively keep the shape of the source table t2 and set the elements of each tensor to zero, saving the result on the destination table t1 Notice that t1 and t2 can only contain tables or tensors

    This method recursively keep the shape of the source table t2 and set the elements of each tensor to zero, saving the result on the destination table t1 Notice that t1 and t2 can only contain tables or tensors

    t1

    is the destination table

    t2

    is the source table

Inherited from AnyRef

Inherited from Any

Ungrouped