Skip to content

lstm_cell

allennlp_models.generation.modules.decoder_nets.lstm_cell

[SOURCE]

LstmCellDecoderNet#

@DecoderNet.register("lstm_cell")
class LstmCellDecoderNet(DecoderNet):
 | def __init__(
 |     self,
 |     decoding_dim: int,
 |     target_embedding_dim: int,
 |     attention: Optional[Attention] = None,
 |     bidirectional_input: bool = False
 | ) -> None

This decoder net implements simple decoding network with LSTMCell and Attention.

Parameters

  • decoding_dim : int
    Defines dimensionality of output vectors.
  • target_embedding_dim : int
    Defines dimensionality of input target embeddings. Since this model takes it's output on a previous step as input of following step, this is also an input dimensionality.
  • attention : Attention, optional (default = None)
    If you want to use attention to get a dynamic summary of the encoder outputs at each step of decoding, this is the function used to compute similarity between the decoder hidden state and encoder outputs.

init_decoder_state#

class LstmCellDecoderNet(DecoderNet):
 | ...
 | def init_decoder_state(
 |     self,
 |     encoder_out: Dict[str, torch.LongTensor]
 | ) -> Dict[str, torch.Tensor]

forward#

class LstmCellDecoderNet(DecoderNet):
 | ...
 | @overrides
 | def forward(
 |     self,
 |     previous_state: Dict[str, torch.Tensor],
 |     encoder_outputs: torch.Tensor,
 |     source_mask: torch.BoolTensor,
 |     previous_steps_predictions: torch.Tensor,
 |     previous_steps_mask: Optional[torch.BoolTensor] = None
 | ) -> Tuple[Dict[str, torch.Tensor], torch.Tensor]