058c2e6963c597d8c613d85646e200c38c059971,allennlp/modules/conditional_random_field.py,ConditionalRandomField,viterbi_tags,#ConditionalRandomField#Any#Any#Any#,333

Before Change

            // At timestep 0 we must have the START_TAG
            tag_sequence[0, start_tag] = 0.0
            // At steps 1, ..., sequence_length we just use the incoming prediction
            tag_sequence[1 : (sequence_length + 1), :num_tags] = prediction[:sequence_length]
            // And at the last timestep we must have the END_TAG
            tag_sequence[sequence_length + 1, end_tag] = 0.0

            // We pass the tags and the transitions to ``viterbi_decode``.

After Change

        tag sequences (the top tag sequence for each batch item).
        
        if mask is None:
            mask = torch.ones(*logits.shape[:2], dtype=torch.long, device=logits.device)

        if top_k is None:
            top_k = 1
            flatten_output = True

Instances