CRF for keras 2.0 #6226
Closed
CRF for keras 2.0 #6226
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
This is a very large change adding a brand new feature. Typically the process for such a change would be to first ship it in Keras contrib and have users try it out for a couple of months. After this trial period, if a sufficient large group of users want it, include it as part of core Keras. This is designed to:
|
nzw0301
reviewed
Apr 15, 2017
| x = [[w[0].lower() for w in s] for s in data] | ||
| y = [[w[1] for w in s] for s in data] | ||
| x = pad_sequences([[word2idx.get(w[0].lower(), 1) for w in s] for s in data], maxlen=maxlen) | ||
| y = pad_sequences([[class_labels.index(w[1])for w in s] for s in data], maxlen=maxlen) |
nzw0301
reviewed
Apr 15, 2017
| @@ -0,0 +1,540 @@ | |||
| import keras | |||
nzw0301
reviewed
Apr 15, 2017
| self.built = True | ||
|
|
||
| def call(self, X, mask=None): | ||
| input_length = K.int_shape(X)[1] |
There was a problem hiding this comment.
unused variable input_length
|
How can I use this CRF layer in image segmentation, can I set units to be an array? |
|
https://github.com/farizrahman4u/keras-contrib also see CONTRIBUTING.md |
|
Closing since expecting it to go to |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
An Implementation of linear chain conditional random field (CRF), modified for keras 2.0 from previous PR #4646.