-
Notifications
You must be signed in to change notification settings - Fork 12
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
Help #4
Comments
We will check it out and update the code this week, which includes the minor bug fix |
We have tried many ways to run your program, but this seems to be very difficult to succeed. Hope to see a working version. |
@zqy396 have you solved the error? it seems that the root_dir should be contains the files from both original and superpatch |
I am a beginner. I would like to ask, the article says that distance d and Angle a are embedded as edge features. Take the length,d ={d11,d12,... dNN}, where d11 and patch feature dimensions are consistent, what is the specific calculation method for distance d? Are the corresponding elements of two node eigenvectors subtracted? |
1 similar comment
I am a beginner. I would like to ask, the article says that distance d and Angle a are embedded as edge features. Take the length,d ={d11,d12,... dNN}, where d11 and patch feature dimensions are consistent, what is the specific calculation method for distance d? Are the corresponding elements of two node eigenvectors subtracted? |
i can`t run the whole program,if i run main.py,i will take an error--ZeroDivisionError: No admissable pairs in the dataset. |
superpatch_network_constrution.py doesn't seem to work, are you sure root_dir is /Graph_test/?
The text was updated successfully, but these errors were encountered: