lamp.nn.bert.BertPretrainInput
See theBertPretrainInput companion object
case class BertPretrainInput(tokens: Constant, segments: Constant, positions: STen, maxLength: Option[STen])
Input for BERT pretrain module
- Tokens: Long tensor of size (batch, sequence length). Sequence length includes cls and sep tokens. Values are tokens of the input vocabulary and 4 additional control tokens: cls, sep, pad, mask. First token must be cls.
- Segments: Long tensor of size (batch, sequence length). Values are segment tokens.
- Positions: Long tensor of size (batch, mask size (variable)). Values are indices in [0,sequence length) selecting masked sequence positions. They never select positions of cls, sep, pad.
- maxLength: 1D long tensor of size (sequence length). Values are in [0,sequence_length]. Tokens at positions higher or equal than the sequence length are ignored.
Attributes
- Companion
- object
- Graph
-
- Supertypes
-
trait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass Any
Members list
In this article