def relative_positional_encoding()

in src/modeling/dummy_modeling_xlnet.py [0:0]

• 29 lines of code
• 7 McCabe index (conditional complexity)

    def relative_positional_encoding(self, qlen, klen, bsz=None):
        # create relative positional encoding.
        freq_seq = torch.arange(0, self.d_model, 2.0, dtype=torch.float)
        inv_freq = 1 / torch.pow(10000, (freq_seq / self.d_model))

        if self.attn_type == "bi":
            # beg, end = klen - 1, -qlen
            beg, end = klen, -qlen
        elif self.attn_type == "uni":
            # beg, end = klen - 1, -1
            beg, end = klen, -1
        else:
            raise ValueError("Unknown `attn_type` {}.".format(self.attn_type))

        if self.bi_data:
            fwd_pos_seq = torch.arange(beg, end, -1.0, dtype=torch.float)
            bwd_pos_seq = torch.arange(-beg, -end, 1.0, dtype=torch.float)

            if self.clamp_len > 0:
                fwd_pos_seq = fwd_pos_seq.clamp(-self.clamp_len, self.clamp_len)
                bwd_pos_seq = bwd_pos_seq.clamp(-self.clamp_len, self.clamp_len)

            if bsz is not None:
                fwd_pos_emb = self.positional_embedding(fwd_pos_seq, inv_freq, bsz // 2)
                bwd_pos_emb = self.positional_embedding(bwd_pos_seq, inv_freq, bsz // 2)
            else:
                fwd_pos_emb = self.positional_embedding(fwd_pos_seq, inv_freq)
                bwd_pos_emb = self.positional_embedding(bwd_pos_seq, inv_freq)

            pos_emb = torch.cat([fwd_pos_emb, bwd_pos_emb], dim=1)
        else:
            fwd_pos_seq = torch.arange(beg, end, -1.0)
            if self.clamp_len > 0:
                fwd_pos_seq = fwd_pos_seq.clamp(-self.clamp_len, self.clamp_len)
            pos_emb = self.positional_embedding(fwd_pos_seq, inv_freq, bsz)

        pos_emb = pos_emb.to(self.device)
        return pos_emb