espnet.nets.pytorch_backend.conformer.encoder_layer.EncoderLayer

source

class espnet.nets.pytorch_backend.conformer.encoder_layer.EncoderLayer(size, self_attn, feed_forward, feed_forward_macaron, conv_module, dropout_rate, normalize_before=True, concat_after=False, stochastic_depth_rate=0.0)

Bases: Module

Encoder layer module.

• Parameters:
  • size (int) – Input dimension.
  • self_attn (torch.nn.Module) – Self-attention module instance. MultiHeadedAttention or RelPositionMultiHeadedAttention instance can be used as the argument.
  • feed_forward (torch.nn.Module) – Feed-forward module instance. PositionwiseFeedForward, MultiLayeredConv1d, or Conv1dLinear instance can be used as the argument.
  • feed_forward_macaron (torch.nn.Module) – Additional feed-forward module instance. PositionwiseFeedForward, MultiLayeredConv1d, or Conv1dLinear instance can be used as the argument.
  • conv_module (torch.nn.Module) – Convolution module instance. ConvlutionModule instance can be used as the argument.
  • dropout_rate (float) – Dropout rate.
  • normalize_before (bool) – Whether to use layer_norm before the first block.
  • concat_after (bool) – Whether to concat attention layer’s input and output. if True, additional linear will be applied. i.e. x -> x + linear(concat(x, att(x))) if False, no additional linear will be applied. i.e. x -> x + att(x)
  • stochastic_depth_rate (float) – Proability to skip this layer. During training, the layer may skip residual computation and return input as-is with given probability.

Construct an EncoderLayer object.

forward(x_input, mask, cache=None)

Compute encoded features.

• Parameters:
  • x_input (Union *[*Tuple , torch.Tensor ]) – Input tensor w/ or w/o pos emb.
    • w/ pos emb: Tuple of tensors [(#batch, time, size), (1, time, size)].
    • w/o pos emb: Tensor (#batch, time, size).
  • mask (torch.Tensor) – Mask tensor for the input (#batch, 1, time).
  • cache (torch.Tensor) – Cache tensor of the input (#batch, time - 1, size).
• Returns: Output tensor (#batch, time, size). torch.Tensor: Mask tensor (#batch, 1, time).
• Return type: torch.Tensor