tf.contrib.crf.crf_sequence_score(
inputs,
tag_indices,
sequence_lengths,
transition_params
)
Defined in tensorflow/contrib/crf/python/ops/crf.py
.
Computes the unnormalized score for a tag sequence.
Args:
inputs
: A [batch_size, max_seq_len, num_tags] tensor of unary potentials to use as input to the CRF layer.tag_indices
: A [batch_size, max_seq_len] matrix of tag indices for which we compute the unnormalized score.sequence_lengths
: A [batch_size] vector of true sequence lengths.transition_params
: A [num_tags, num_tags] transition matrix.
Returns:
sequence_scores
: A [batch_size] vector of unnormalized sequence scores.