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_forward
Stay organized with collections
Save and categorize content based on your preferences.
Computes the alpha values in a linear-chain CRF.
tfa.text.crf_forward(
inputs: tfa.types.TensorLike,
state: tfa.types.TensorLike,
transition_params: tfa.types.TensorLike,
sequence_lengths: tfa.types.TensorLike
) -> tf.Tensor
See http://www.cs.columbia.edu/~mcollins/fb.pdf for reference.
Args |
|---|
inputs
|
A [batch_size, num_tags] matrix of unary potentials.
|
state
|
A [batch_size, num_tags] matrix containing the previous alpha
values.
|
transition_params
|
A [num_tags, num_tags] matrix of binary potentials.
This matrix is expanded into a [1, num_tags, num_tags] in preparation
for the broadcast summation occurring within the cell.
|
sequence_lengths
|
A [batch_size] vector of true sequence lengths.
|
Returns |
|---|
new_alphas
|
A [batch_size, num_tags] matrix containing the
new alpha values.
|
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_forward\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#L329-L371) |\n\nComputes the alpha values in a linear-chain CRF.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tfa.text.crf.crf_forward`](https://www.tensorflow.org/addons/api_docs/python/tfa/text/crf_forward)\n\n\u003cbr /\u003e\n\n tfa.text.crf_forward(\n inputs: ../../tfa/types/TensorLike,\n state: ../../tfa/types/TensorLike,\n transition_params: ../../tfa/types/TensorLike,\n sequence_lengths: ../../tfa/types/TensorLike\n ) -\u003e tf.Tensor\n\nSee [http://www.cs.columbia.edu/\\~mcollins/fb.pdf](http://www.cs.columbia.edu/~mcollins/fb.pdf) for reference.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `inputs` | A \\[batch_size, num_tags\\] matrix of unary potentials. |\n| `state` | A \\[batch_size, num_tags\\] matrix containing the previous alpha values. |\n| `transition_params` | A \\[num_tags, num_tags\\] matrix of binary potentials. This matrix is expanded into a \\[1, num_tags, num_tags\\] in preparation for the broadcast summation occurring within the cell. |\n| `sequence_lengths` | A \\[batch_size\\] vector of true sequence lengths. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|--------------|--------------------------------------------------------------------|\n| `new_alphas` | A \\[batch_size, num_tags\\] matrix containing the new alpha values. |\n\n\u003cbr /\u003e"]]
View source on GitHub