pytorch_translate/beam_decode.py [511:563]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                    num_remaining_sent -= finalize_hypos(
                        step, eos_bbsz_idx, eos_scores, cand_scores
                    )

            assert num_remaining_sent >= 0
            if num_remaining_sent == 0:
                break
            assert step < maxlen

            # set active_mask so that values > cand_size indicate eos hypos
            # and values < cand_size indicate candidate active hypos.
            # After, the min values per row are the top candidate active hypos
            active_mask = buffer("active_mask")
            torch.add(
                eos_mask.type_as(cand_offsets) * cand_size,
                cand_offsets[: eos_mask.size(1)],
                out=active_mask,
            )

            # get the top beam_size active hypotheses, which are just the hypos
            # with the smallest values in active_mask
            active_hypos, _ignore = buffer("active_hypos"), buffer("_ignore")
            torch.topk(
                active_mask,
                k=beam_size,
                dim=1,
                largest=False,
                out=(_ignore, active_hypos),
            )
            active_bbsz_idx = buffer("active_bbsz_idx")
            torch.gather(cand_bbsz_idx, dim=1, index=active_hypos, out=active_bbsz_idx)
            active_scores = torch.gather(
                cand_scores,
                dim=1,
                index=active_hypos,
                out=scores[:, step].view(bsz, beam_size),
            )
            active_bbsz_idx = active_bbsz_idx.view(-1)
            active_scores = active_scores.view(-1)

            # copy tokens and scores for active hypotheses
            torch.index_select(
                tokens[:, : step + 1],
                dim=0,
                index=active_bbsz_idx,
                out=tokens_buf[:, : step + 1],
            )
            torch.gather(
                cand_indices,
                dim=1,
                index=active_hypos,
                out=tokens_buf.view(bsz, beam_size, -1)[:, :, step + 1],
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



pytorch_translate/research/multisource/multisource_decode.py [433:485]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                    num_remaining_sent -= finalize_hypos(
                        step, eos_bbsz_idx, eos_scores, cand_scores
                    )

            assert num_remaining_sent >= 0
            if num_remaining_sent == 0:
                break
            assert step < maxlen

            # set active_mask so that values > cand_size indicate eos hypos
            # and values < cand_size indicate candidate active hypos.
            # After, the min values per row are the top candidate active hypos
            active_mask = buffer("active_mask")
            torch.add(
                eos_mask.type_as(cand_offsets) * cand_size,
                cand_offsets[: eos_mask.size(1)],
                out=active_mask,
            )

            # get the top beam_size active hypotheses, which are just the hypos
            # with the smallest values in active_mask
            active_hypos, _ignore = buffer("active_hypos"), buffer("_ignore")
            torch.topk(
                active_mask,
                k=beam_size,
                dim=1,
                largest=False,
                out=(_ignore, active_hypos),
            )
            active_bbsz_idx = buffer("active_bbsz_idx")
            torch.gather(cand_bbsz_idx, dim=1, index=active_hypos, out=active_bbsz_idx)
            active_scores = torch.gather(
                cand_scores,
                dim=1,
                index=active_hypos,
                out=scores[:, step].view(bsz, beam_size),
            )
            active_bbsz_idx = active_bbsz_idx.view(-1)
            active_scores = active_scores.view(-1)

            # copy tokens and scores for active hypotheses
            torch.index_select(
                tokens[:, : step + 1],
                dim=0,
                index=active_bbsz_idx,
                out=tokens_buf[:, : step + 1],
            )
            torch.gather(
                cand_indices,
                dim=1,
                index=active_hypos,
                out=tokens_buf.view(bsz, beam_size, -1)[:, :, step + 1],
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -