Feature extraction - ESM embeddings #13
Merged
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
Storing Esm embeddings wont work since they are 320-d vectors PER amino acid... Instead the better approach is to just store the sequence strings and leave the esm emb calc to be done on the model side of things. See #8 for more
Esm embedding now works
Not too great, outliers ruining training?
This has to be done since argparse doesnt handle boolean choices well through the cli.
… into feature_extraction
… into feature_extraction
Main thing is to freeze ESM layers since its too large to train.
This is useful since epochs would be cluttered with transformer tokenizer warning logs
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Outdated suggestions cannot be applied.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.
This development line leads to the successful introduction of esm embeddings to my feature set for the graph convolutions
This fixes #8!