Method forward

modules/commons/common_layers.py:564–588

(self, x, encoder_padding_mask=None, **kwargs)

            c, 4 * c, kernel_size=kernel_size, dropout=relu_dropout, padding=padding, act=act)

    def forward(self, x, encoder_padding_mask=None, **kwargs):
        layer_norm_training = kwargs.get('layer_norm_training', None)
        if layer_norm_training is not None:
            self.layer_norm1.training = layer_norm_training
            self.layer_norm2.training = layer_norm_training
        if self.num_heads > 0:
            residual = x
            x = self.layer_norm1(x)
            x, _, = self.self_attn(
                query=x,
                key=x,
                value=x,
                key_padding_mask=encoder_padding_mask
            )
            x = F.dropout(x, self.dropout, training=self.training)
            x = residual + x
            x = x * (1 - encoder_padding_mask.float()).transpose(0, 1)[..., None]

        residual = x
        x = self.layer_norm2(x)
        x = self.ffn(x)
        x = F.dropout(x, self.dropout, training=self.training)
        x = residual + x
        x = x * (1 - encoder_padding_mask.float()).transpose(0, 1)[..., None]
        return x


class DecSALayer(nn.Module):