tf.contrib.crf.crf_log_norm(inputs, sequence_lengths, transition_params)

tf.contrib.crf.crf_log_norm(inputs, sequence_lengths, transition_params)

See the guide: CRF (contrib)

Computes the normalization for a CRF.

Args:

  • inputs: A [batch_size, max_seq_len, num_tags] tensor of unary potentials to use as input to the CRF layer.
  • sequence_lengths: A [batch_size] vector of true sequence lengths.
  • transition_params: A [num_tags, num_tags] transition matrix. Returns:
  • log_norm: A [batch_size] vector of normalizers for a CRF.

Defined in tensorflow/contrib/crf/python/ops/crf.py.