Skip to content

feedforward_encoder

allennlp.modules.seq2seq_encoders.feedforward_encoder

[SOURCE]


FeedForwardEncoder

@Seq2SeqEncoder.register("feedforward")
class FeedForwardEncoder(Seq2SeqEncoder):
 | def __init__(self, feedforward: FeedForward) -> None

This class applies the FeedForward to each item in sequences.

Registered as a Seq2SeqEncoder with name "feedforward".

get_input_dim

class FeedForwardEncoder(Seq2SeqEncoder):
 | ...
 | def get_input_dim(self) -> int

get_output_dim

class FeedForwardEncoder(Seq2SeqEncoder):
 | ...
 | def get_output_dim(self) -> int

is_bidirectional

class FeedForwardEncoder(Seq2SeqEncoder):
 | ...
 | def is_bidirectional(self) -> bool

forward

class FeedForwardEncoder(Seq2SeqEncoder):
 | ...
 | def forward(
 |     self,
 |     inputs: torch.Tensor,
 |     mask: torch.BoolTensor = None
 | ) -> torch.Tensor

Parameters

  • inputs : torch.Tensor
    A tensor of shape (batch_size, timesteps, input_dim)
  • mask : torch.BoolTensor, optional (default = None)
    A tensor of shape (batch_size, timesteps).

Returns

  • A tensor of shape (batch_size, timesteps, output_dim).