espnet2.legacy.nets.pytorch_backend.transformer.multi_layer_conv.Conv1dLinear

source

class espnet2.legacy.nets.pytorch_backend.transformer.multi_layer_conv.Conv1dLinear(in_chans, hidden_chans, kernel_size, dropout_rate)

Bases: Module

Conv1D + Linear for Transformer block.

A variant of MultiLayeredConv1d, which replaces second conv-layer to linear.

Initialize Conv1dLinear module.

• Parameters:
  • in_chans (int) – Number of input channels.
  • hidden_chans (int) – Number of hidden channels.
  • kernel_size (int) – Kernel size of conv1d.
  • dropout_rate (float) – Dropout rate.

forward(x)

Calculate forward propagation.

• Parameters:x (torch.Tensor) – Batch of input tensors (B, T, in_chans).
• Returns: Batch of output tensors (B, T, hidden_chans).
• Return type: torch.Tensor