-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Bert extractor class #4
Conversation
To clarify: further work on this feature may be performed by anybody, not necessarily by @homomorfism |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
@implausibleDeniability please check my changes |
Tests are failing, do not merge |
Now tests are ok Please, do not merge changes: today l am planning to train classifier, based on (untrained) bert features and handcrafted features. And then we will push changes to develop branch. |
Shamil, reviewing many unrelated changes is not that easy =( Why do you add text features extractor to the branch with bert features extractor? That confuses the review greatly. If it's possible, I would suggest to split the changes to several branches:
You may do this several times if it seems you can decompose the current branch to many brances |
Good Spellchecking btw! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Indeed, big commit. Everything seems fine to me!
Заебись, Шамиль =) |
Implementation of bert feature extractor, followed by our discussion idea.
Didn't tried train model, based on the proposed hypothesis, only implementation