Changed the code structure into more efficient way to separate graphs building of prediction process #5
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
…hs (elmos & clinical concepts extraction) can be builded globally and used to predict multiple times without need to build the graph every time.
…to segments/sentences
…oken, span, label]
…t conatains the start and the end of each label in given text
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Outdated suggestions cannot be applied.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.
the following are the main updates:
created the ClinicalConceptExtraction class who contains the elmo model graph and clinical concept graph built and loaded in initiate time to avoid building them with every prediction process.
edited the build input method to work in a direct way by get embeddings and labels by the same batch size in one forward pass, instead of looping over sentences and get embeddings for each sentence and use tf.dataset to create padded iterator by the given batch size.