espnet2.enh.layers.dpmulcat.MulCatBlock

source

class espnet2.enh.layers.dpmulcat.MulCatBlock(input_size: int, hidden_size: int, dropout: float = 0.0, bidirectional: bool = True)

Bases: Module

The MulCat block.

• Parameters:
  • input_size – int, dimension of the input feature. The input should have shape (batch, seq_len, input_size).
  • hidden_size – int, dimension of the hidden state.
  • dropout – float, the dropout rate in the LSTM layer. (Default: 0.0)
  • bidirectional – bool, whether the RNN layers are bidirectional. (Default: True)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(input)

Compute output after MulCatBlock.

• Parameters:input (torch.Tensor) – The input feature. Tensor of shape (batch, time, feature_dim)
• Returns: The output feature after MulCatBlock. : Tensor of shape (batch, time, feature_dim)
• Return type: (torch.Tensor)