Generated with

GenericModule

lamp.nn.GenericModule

See theGenericModule companion object

Base type of modules

Modules are functions of type (Seq[lamp.autograd.Constant],A) => B, where the Seq[lamp.autograd.Constant] arguments are optimizable parameters and A is a non-optimizable input.

Modules provide a way to build composite functions while also keep track of the parameter list of the composite function.

===Example===

case object Weights extends LeafTag
case object Bias extends LeafTag
case class Linear(weights: Constant, bias: Option[Constant]) extends Module {

 override val state = List(
   weights -> Weights
 ) ++ bias.toList.map(b => (b, Bias))

 def forward[S: Sc](x: Variable): Variable = {
   val v = x.mm(weights)
   bias.map(_ + v).getOrElse(v)

 }
}

Some other attributes of modules are attached by type classes e.g. with the nn.TrainingMode, nn.Load type classes.

Type parameters

A: the argument type of the module
B: the value type of the module

Attributes

See also: nn.Module is an alias for simple Variable => Variable modules
Companion: object
Graph
Supertypes: class Object

trait Matchable

class Any
Known subtypes: class BertEncoder

class BertLoss

class BertPretrainModule

class MaskedLanguageModelModule

class GraphAttention

class LanguageModelLoss

class LanguageModelModule

class EitherModule[A, B, M1, M2]

class GenericFun[A, B]

class MultiheadAttention

class Recursive[A, M]

class Seq2[T1, T2, T3, M1, M2]

class Seq3[T1, T2, T3, T4, M1, M2, M3]

class Seq4[T1, T2, T3, T4, T5, M1, M2, M3, M4]

class Seq5[T1, T2, T3, T4, T5, T6, M1, M2, M3, M4, M5]

class Seq6[T1, T2, T3, T4, T5, T6, T7, M1, M2, M3, M4, M5, M6]

class Sequential[A, M]

class Transformer

class TransformerDecoder

class TransformerDecoderBlock

class TransformerEmbedding

class TransformerEncoder

class TransformerEncoderBlock

class UnliftedModule[A, B, C, D, M]
Show all

Members list

Value members

Abstract methods

The implementation of the function.

In addition of x it can also use all the `state to compute its value.

Attributes

List of optimizable, or non-optimizable, but stateful parameters

Stateful means that the state is carried over the repeated forward calls.

Attributes

Concrete methods

Alias of forward

Attributes

Computes the gradient of loss with respect to the parameters.

Attributes

Returns the total number of optimizable parameters.

Attributes

Returns the state variables which need gradient computation.

Attributes

In this article

Generated with