fairseq/models/bert_seq2seq.py [323:339]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self.project_in_dim is not None:
            x = self.project_in_dim(x)

        if positions is not None:
            x += positions
        x = F.dropout(x, p=self.dropout, training=self.training)
        # B x T x C -> T x B x C
        x = x.transpose(0, 1)
        attn = None
        inner_states = [x]

        # decoder layers
        for layer in self.layers:
            x, attn = layer(
                x,
                encoder_out['encoder_out'] if encoder_out is not None else None,
                encoder_out['encoder_padding_mask'] if encoder_out is not None else None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



fairseq/models/transformer.py [411:429]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self.project_in_dim is not None:
            x = self.project_in_dim(x)

        if positions is not None:
            x += positions
        x = F.dropout(x, p=self.dropout, training=self.training)

        # B x T x C -> T x B x C
        x = x.transpose(0, 1)
        attn = None

        inner_states = [x]

        # decoder layers
        for layer in self.layers:
            x, attn = layer(
                x,
                encoder_out['encoder_out'] if encoder_out is not None else None,
                encoder_out['encoder_padding_mask'] if encoder_out is not None else None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -