# tf.contrib.crf.crf_decode

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/crf/python/ops/crf.py#L519-L596) |

Decode the highest scoring sequence of tags in TensorFlow.

    tf.contrib.crf.crf_decode(
        potentials, transition_params, sequence_length
    )

This is a function for tensor.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `potentials` | A \[batch_size, max_seq_len, num_tags\] tensor of unary potentials. |
| `transition_params` | A \[num_tags, num_tags\] matrix of binary potentials. |
| `sequence_length` | A \[batch_size\] vector of true sequence lengths. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| `decode_tags` | A \[batch_size, max_seq_len\] matrix, with dtype [`tf.int32`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf#int32). Contains the highest scoring tag indices. |
| `best_score` | A \[batch_size\] vector, containing the score of `decode_tags`. |

<br />