com.intel.analytics.bigdl.nn

SmoothL1CriterionWithWeights

class SmoothL1CriterionWithWeights[T] extends AbstractCriterion[Tensor[T], Table, T]

a smooth version of the AbsCriterion It uses a squared term if the absolute element-wise error falls below 1. It is less sensitive to outliers than the MSECriterion and in some cases prevents exploding gradients (e.g. see "Fast R-CNN" paper by Ross Girshick).

d = (x - y) * w_in loss(x, y, w_in, w_out) | 0.5 * (sigma * d_i)^2 * w_out if |d_i| < 1 / sigma / sigma

1/n \sum | | (|d_i| - 0.5 / sigma / sigma) * w_out otherwise

T

Linear Supertypes
AbstractCriterion[Tensor[T], Table, T], Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. SmoothL1CriterionWithWeights
  2. AbstractCriterion
  3. Serializable
  4. Serializable
  5. AnyRef
  6. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new SmoothL1CriterionWithWeights(sigma: Double, num: Int = 0)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

Value Members

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

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

    Definition Classes
    AnyRef → Any
  4. final def ==(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  5. final def ==(arg0: Any): Boolean

    Definition Classes
    Any
  6. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  7. def backward(input: Tensor[T], target: Table): Tensor[T]

    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
  8. var buffer: Tensor[T]

  9. def canEqual(other: Any): Boolean

    Definition Classes
    AbstractCriterion
  10. def clone(): AnyRef

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

    Deep copy this criterion

    Deep copy this criterion

    returns

    a deep copied criterion

    Definition Classes
    AbstractCriterion
  12. var diff: Tensor[T]

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

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

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

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

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

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

    Definition Classes
    AbstractCriterion
  19. var hasWeights: Boolean

  20. def hashCode(): Int

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

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

    Definition Classes
    AnyRef
  23. final def notify(): Unit

    Definition Classes
    AnyRef
  24. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  25. val num: Int

  26. var output: T

    Definition Classes
    AbstractCriterion
  27. val sigma: Double

  28. val sigma2: Double

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

    Definition Classes
    AnyRef
  30. def toString(): String

    Definition Classes
    SmoothL1CriterionWithWeights → AnyRef → Any
  31. def updateGradInput(input: Tensor[T], target: Table): Tensor[T]

    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
    SmoothL1CriterionWithWeightsAbstractCriterion
  32. def updateOutput(input: Tensor[T], target: Table): T

    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
    SmoothL1CriterionWithWeightsAbstractCriterion
  33. final def wait(): Unit

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

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped