object BertEncoder extends Serializable
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- BertEncoder
- Serializable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- Protected
Value Members
- final def !=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def ##: Int
- Definition Classes
- AnyRef → Any
- final def ==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- def apply[S](maxLength: Int, vocabularySize: Int, segmentVocabularySize: Int, numBlocks: Int, embeddingDim: Int, attentionHiddenPerHeadDim: Int, attentionNumHeads: Int, mlpHiddenDim: Int, dropout: Double, tOpt: STenOptions, linearized: Boolean, positionEmbedding: Option[STen])(implicit arg0: Sc[S]): BertEncoder
Factory for the encoder module of Bert
Factory for the encoder module of Bert
Input is
(tokens, segments)wheretokensandsegmentsare both (batch,num tokens) long tensor.- maxLength
maximum num token length
- vocabularySize
vocabulary size
- numBlocks
number of transformer blocks to create
- embeddingDim
input embedding dimension
- attentionHiddenPerHeadDim
size of hidden attention dimension of each attention head
- attentionNumHeads
number of attention heads
- mlpHiddenDim
size of hidden dimension of the two layer perceptron
- dropout
dropout rate
- tOpt
tensor options
- positionEmbedding
optional float tensor of size (sequence length, embedding dimension) if missing the absolute positional embeddings from Vaswani et al 2017 is used Following the Bert paper the position embeddings are summed
- returns
a module
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @IntrinsicCandidate() @native()
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def equals(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef → Any
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- def hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- implicit val load: Load[BertEncoder]
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def toString(): String
- Definition Classes
- AnyRef → Any
- implicit val trainingMode: TrainingMode[BertEncoder]
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- object PositionalEmbeddingWeight extends LeafTag
Deprecated Value Members
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable]) @Deprecated
- Deprecated
(Since version 9)