lamp-core/lamp.nn/AttentionDecoder

AttentionDecoder

case class AttentionDecoder[T, M <: StatefulModule[Variable, Variable, T], M0 <: Module](decoder: M & StatefulModule[Variable, Variable, T], embedding: M0 & Module, stateToKey: T => Variable, keyValue: Variable, tokens: Variable, padToken: Long) extends StatefulModule[Variable, Variable, T]
trait Serializable
trait Product
trait Equals
trait GenericModule[(Variable, T), (Variable, T)]
class Object
trait Matchable
class Any

Value members

Concrete methods

def forward[S : Sc](x: (Variable, T)): (Variable, T)
def forward1[S : Sc](x: Variable, state: T): (Variable, T)
override def state: Seq[(Constant, PTag)]
Definition Classes

Inherited methods

def apply[S : Sc](a: (Variable, T)): (Variable, T)

Alias of forward

Alias of forward

Inherited from:
GenericModule
final def gradients(loss: Variable, zeroGrad: Boolean): Seq[Option[STen]]

Computes the gradient of loss with respect to the parameters.

Computes the gradient of loss with respect to the parameters.

Inherited from:
GenericModule
final def learnableParameters: Long

Returns the total number of optimizable parameters.

Returns the total number of optimizable parameters.

Inherited from:
GenericModule
final def parameters: Seq[(Constant, PTag)]

Returns the state variables which need gradient computation.

Returns the state variables which need gradient computation.

Inherited from:
GenericModule
def productElementNames: Iterator[String]
Inherited from:
Product
def productIterator: Iterator[Any]
Inherited from:
Product
final def zeroGrad(): Unit
Inherited from:
GenericModule