-
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
Optional relabelling of nodes & edges with Annotation.UNKNOWN
label
#200
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
I'm trying to run the code, but I get a fail with the following error:
I think it is due to the embeddings variable in this line not being defined is the condition in line 66 is not met. grace/grace/models/classifier.py Line 69 in a4d98ef
|
Temporarily fixed now, proper fix for option to train a linear-only classifier upcoming in #183 🚀 |
Annotation.UNKNOWN
labelAnnotation.UNKNOWN
label
Cool, it runs now without issues. |
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.
I've run the code with the relabelling annotation on and off and seems to run well. My only comment left is on making the relabeling a configurable option for the user, but besides that I think is ready to merge.
If the user decides to do so, relabel all GT annotations from
Annotation.UNKNOWN
toAnnotation.TRUE_NEGATIVE
, to increase the number of data points to train the GCN on. Particularly good for exhaustive annotation.Annotation.UNKNOWN
label #185logging
rather thanprint
for user feedback #204