lamp-core
API
Generated with
lamp-core/lamp/lamp.nn/LossFunctions

LossFunctions

lamp.nn.LossFunctions
object LossFunctions

Attributes

Graph
Supertypes
class Object
trait Matchable
class Any
Self type

Members list

Type members

Classlikes

case class BCEWithLogits(posWeights: Option[STen], reduction: Reduction, ignore: Long) extends LossFunction

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
trait LossFunction
class Object
trait Matchable
class Any
Show all
case object Identity extends LossFunction

Attributes

Supertypes
trait Singleton
trait Product
trait Mirror
trait Serializable
trait Product
trait Equals
trait LossFunction
class Object
trait Matchable
class Any
Show all
Self type
Identity.type
case object MSE extends LossFunction

Attributes

Supertypes
trait Singleton
trait Product
trait Mirror
trait Serializable
trait Product
trait Equals
trait LossFunction
class Object
trait Matchable
class Any
Show all
Self type
MSE.type
case class NLL(numClasses: Int, classWeights: STen, reduction: Reduction, ignore: Long) extends LossFunction

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
trait LossFunction
class Object
trait Matchable
class Any
Show all
case class SequenceNLL(numClasses: Int, classWeights: STen, ignore: Long) extends LossFunction

Return a loss function which takes outputs of time step x batch x classes and targets of time step x batch The returned loss is averaged over the batch and the time steps

Return a loss function which takes outputs of time step x batch x classes and targets of time step x batch The returned loss is averaged over the batch and the time steps

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
trait LossFunction
class Object
trait Matchable
class Any
Show all
case class SmoothL1Loss(reduction: Reduction, beta: Double) extends LossFunction

Attributes

Supertypes
trait Serializable
trait Product
trait Equals
trait LossFunction
class Object
trait Matchable
class Any
Show all
Generated with