Spaces:
Build error
Build error
| #!/usr/bin/env python3 | |
| # -*- coding: utf-8 -*- | |
| # Copyright 2020 Johns Hopkins University (Shinji Watanabe) | |
| # Northwestern Polytechnical University (Pengcheng Guo) | |
| # Apache 2.0 (http://www.apache.org/licenses/LICENSE-2.0) | |
| """Encoder self-attention layer definition.""" | |
| import torch | |
| from torch import nn | |
| from vec2wav2.models.conformer.layer_norm import LayerNorm | |
| class DecoderLayer(nn.Module): | |
| """Encoder layer module. | |
| Args: | |
| 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) | |
| """ | |
| def __init__( | |
| self, | |
| size, | |
| self_attn, | |
| src_attn, | |
| feed_forward, | |
| feed_forward_macaron, | |
| conv_module, | |
| dropout_rate, | |
| normalize_before=True, | |
| concat_after=False, | |
| ): | |
| """Construct an EncoderLayer object.""" | |
| super(DecoderLayer, self).__init__() | |
| self.self_attn = self_attn | |
| self.src_attn = src_attn | |
| self.feed_forward = feed_forward | |
| self.feed_forward_macaron = feed_forward_macaron | |
| self.conv_module = conv_module | |
| self.norm_ff = LayerNorm(size) # for the FNN module | |
| self.norm_mha = LayerNorm(size) # for the MHA module | |
| self.norm2 = LayerNorm(size) # for the MHA module | |
| if feed_forward_macaron is not None: | |
| self.norm_ff_macaron = LayerNorm(size) | |
| self.ff_scale = 0.5 | |
| else: | |
| self.ff_scale = 1.0 | |
| if self.conv_module is not None: | |
| self.norm_conv = LayerNorm(size) # for the CNN module | |
| self.norm_final = LayerNorm(size) # for the final output of the block | |
| self.dropout = nn.Dropout(dropout_rate) | |
| self.size = size | |
| self.normalize_before = normalize_before | |
| self.concat_after = concat_after | |
| if self.concat_after: | |
| self.concat_linear = nn.Linear(size + size, size) | |
| self.concat_linear2 = nn.Linear(size + size, size) | |
| def forward(self, x_input, mask, memory, memory_mask, cache=None): | |
| """Compute encoded features. | |
| Args: | |
| 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, time). | |
| cache (torch.Tensor): Cache tensor of the input (#batch, time - 1, size). | |
| Returns: | |
| torch.Tensor: Output tensor (#batch, time, size). | |
| torch.Tensor: Mask tensor (#batch, time). | |
| """ | |
| if isinstance(x_input, tuple): | |
| x, pos_emb = x_input[0], x_input[1] | |
| else: | |
| x, pos_emb = x_input, None | |
| # whether to use macaron style | |
| if self.feed_forward_macaron is not None: | |
| residual = x | |
| if self.normalize_before: | |
| x = self.norm_ff_macaron(x) | |
| x = residual + self.ff_scale * self.dropout(self.feed_forward_macaron(x)) | |
| if not self.normalize_before: | |
| x = self.norm_ff_macaron(x) | |
| # multi-headed self-attention module | |
| residual = x | |
| if self.normalize_before: | |
| x = self.norm_mha(x) | |
| if cache is None: | |
| x_q = x | |
| else: | |
| assert cache.shape == (x.shape[0], x.shape[1] - 1, self.size) | |
| x_q = x[:, -1:, :] | |
| residual = residual[:, -1:, :] | |
| mask = None if mask is None else mask[:, -1:, :] | |
| if pos_emb is not None: | |
| x_att = self.self_attn(x_q, x, x, pos_emb, mask) | |
| else: | |
| x_att = self.self_attn(x_q, x, x, mask) | |
| if self.concat_after: | |
| x_concat = torch.cat((x, x_att), dim=-1) | |
| x = residual + self.concat_linear(x_concat) | |
| else: | |
| x = residual + self.dropout(x_att) | |
| if not self.normalize_before: | |
| x = self.norm_mha(x) | |
| # cross attention | |
| residual = x | |
| if self.normalize_before: | |
| x = self.norm2(x) | |
| if self.concat_after: | |
| x_concat = torch.cat( | |
| (x, self.src_attn(x, memory, memory, memory_mask)), dim=-1 | |
| ) | |
| x = residual + self.concat_linear2(x_concat) | |
| else: | |
| x = residual + self.dropout(self.src_attn(x, memory, memory, memory_mask)) | |
| if not self.normalize_before: | |
| x = self.norm2(x) | |
| # convolution module | |
| if self.conv_module is not None: | |
| residual = x | |
| if self.normalize_before: | |
| x = self.norm_conv(x) | |
| x = residual + self.dropout(self.conv_module(x)) | |
| if not self.normalize_before: | |
| x = self.norm_conv(x) | |
| # feed forward module | |
| residual = x | |
| if self.normalize_before: | |
| x = self.norm_ff(x) | |
| x = residual + self.ff_scale * self.dropout(self.feed_forward(x)) | |
| if not self.normalize_before: | |
| x = self.norm_ff(x) | |
| if self.conv_module is not None: | |
| x = self.norm_final(x) | |
| if cache is not None: | |
| x = torch.cat([cache, x], dim=1) | |
| if pos_emb is not None: | |
| return (x, pos_emb), mask, memory, memory_mask | |
| return x, mask, memory, memory_mask | |