BertPretrainModule

lamp.nn.bert.BertPretrainModule
See theBertPretrainModule companion object
case class BertPretrainModule(encoder: BertEncoder, mlm: MaskedLanguageModelModule, wholeSentenceBinaryClassifier: MLP) extends GenericModule[BertPretrainInput, BertPretrainOutput]

Attributes

Companion
object
Graph
Supertypes
trait Serializable
trait Product
trait Equals
class Object
trait Matchable
class Any
Show all

Members list

Value members

Concrete methods

The implementation of the function.

The implementation of the function.

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

Attributes

def state: Seq[(Constant, PTag)]

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

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

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

Attributes

Inherited methods

def apply[S : Sc](a: BertPretrainInput): B

Alias of forward

Alias of forward

Attributes

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.

Attributes

Inherited from:
GenericModule
final def learnableParameters: Long

Returns the total number of optimizable parameters.

Returns the total number of optimizable parameters.

Attributes

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.

Attributes

Inherited from:
GenericModule
def productElementNames: Iterator[String]

Attributes

Inherited from:
Product
def productIterator: Iterator[Any]

Attributes

Inherited from:
Product
final def zeroGrad(): Unit

Attributes

Inherited from:
GenericModule