Module: tf.contrib.crf

Module tf.contrib.crf

Linear-chain CRF layer. See the CRF (contrib) guide.

Members

class CrfForwardRnnCell: Computes the alpha values in a linear-chain CRF.

crf_binary_score(...): Computes the binary scores of tag sequences.

crf_log_likelihood(...): Computes the log-likelihood of tag sequences in a CRF.

crf_log_norm(...): Computes the normalization for a CRF.

crf_sequence_score(...): Computes the unnormalized score for a tag sequence.

crf_unary_score(...): Computes the unary scores of tag sequences.

viterbi_decode(...): Decode the highest scoring sequence of tags outside of TensorFlow.

Defined in tensorflow/contrib/crf/__init__.py.