Warning: This project is deprecated. TensorFlow Addons has stopped development,
The project will only be providing minimal maintenance releases until May 2024. See the full
announcement here or on
github.
tfa.text.crf_sequence_score
Stay organized with collections
Save and categorize content based on your preferences.
Computes the unnormalized score for a tag sequence.
tfa.text.crf_sequence_score(
inputs: tfa.types.TensorLike,
tag_indices: tfa.types.TensorLike,
sequence_lengths: tfa.types.TensorLike,
transition_params: tfa.types.TensorLike
) -> tf.Tensor
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.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-05-25 UTC.
[null,null,["Last updated 2023-05-25 UTC."],[],[],null,["# tfa.text.crf_sequence_score\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/addons/blob/v0.20.0/tensorflow_addons/text/crf.py#L54-L104) |\n\nComputes the unnormalized score for a tag sequence.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tfa.text.crf.crf_sequence_score`](https://www.tensorflow.org/addons/api_docs/python/tfa/text/crf_sequence_score)\n\n\u003cbr /\u003e\n\n tfa.text.crf_sequence_score(\n inputs: ../../tfa/types/TensorLike,\n tag_indices: ../../tfa/types/TensorLike,\n sequence_lengths: ../../tfa/types/TensorLike,\n transition_params: ../../tfa/types/TensorLike\n ) -\u003e tf.Tensor\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------------------|------------------------------------------------------------------------------------------------------|\n| `inputs` | A \\[batch_size, max_seq_len, num_tags\\] tensor of unary potentials to use as input to the CRF layer. |\n| `tag_indices` | A \\[batch_size, max_seq_len\\] matrix of tag indices for which we compute the unnormalized score. |\n| `sequence_lengths` | A \\[batch_size\\] vector of true sequence lengths. |\n| `transition_params` | A \\[num_tags, num_tags\\] transition matrix. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|-------------------|----------------------------------------------------------|\n| `sequence_scores` | A \\[batch_size\\] vector of unnormalized sequence scores. |\n\n\u003cbr /\u003e"]]
View source on GitHub