Module: tf.contrib.crf

Linear-chain CRF layer.

See the CRF (contrib) guide.

Classes

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.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 3.0 License, and code samples are licensed under the Apache 2.0 License. For details, see our Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated June 15, 2017.