Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[DEVELOPMENT] Consider splitting all classifier options into individual torch.nn.Module objects #279

Open
KristinaUlicna opened this issue Sep 29, 2023 · 0 comments
Open

[DEVELOPMENT] Consider splitting all classifier options into individual torch.nn.Module objects #279

KristinaUlicna opened this issue Sep 29, 2023 · 0 comments
Labels
methodology Building functional & diverse pipeline

Comments

@KristinaUlicna
Copy link
Collaborator

KristinaUlicna commented Sep 29, 2023 •
edited
Loading

The current implementation uses a single GNNModel and based on the classifier_type & hidden_channels arguments builds an appropriate model. Consider breaking this down into separate objects for LinearModel, GCNModel, GATModel, etc.

Potential drawback: load of code duplication, esp. in self.forward() and when calling the model for prediction.
@KristinaUlicna KristinaUlicna added the methodology Building functional & diverse pipeline label Sep 29, 2023
@KristinaUlicna KristinaUlicna self-assigned this Sep 29, 2023
@KristinaUlicna KristinaUlicna changed the title [DEVELOPMENT] Split Linear classifier from GCN [DEVELOPMENT] Consider splitting all classifier options into individual torch.nn.Module objects Oct 12, 2023
@KristinaUlicna KristinaUlicna removed their assignment Oct 12, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
methodology Building functional & diverse pipeline
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@KristinaUlicna