DecoderRNN¶
-
class
DecoderRNN(input_size, hidden_size, rnn_layers=6, dropout=0.2)[source]¶ DecoderRNN model to be used in the decoder of the RST Parser network.
-
forward(input_hidden_states: torch.Tensor, last_hidden: torch.Tensor) → Tuple[torch.Tensor, torch.Tensor][source]¶ Forward pass for decoder RNN.
- Parameters
input_hidden_states (torch.Tensor) – input hidden tensor from encoder RNN output.
last_hidden (torch.Tensor) – last hidden state from encoder RNN.
- Returns
return the output and final hidden state.
- Return type
Tuple[torch.Tensor, torch.Tensor]
-