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.

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

Add extra condition to GraphUNet edge weights assert #9742

Merged
merged 3 commits into from
Oct 31, 2024

Conversation

eurunuela
Copy link
Contributor

Closes #9741.

This PR adds an extra condition to the assert to ensure that the user-given edge weights are a 1D vector. 2D matrices make the adjacency matrix multiplication fail as described in the issue above.

torch_geometric/nn/models/graph_unet.py Outdated Show resolved Hide resolved
@rusty1s rusty1s changed the title Add extra condition to GraphUNet edge weights assert Add extra condition to GraphUNet edge weights assert Oct 31, 2024
@rusty1s rusty1s merged commit f5c8293 into pyg-team:master Oct 31, 2024
17 of 20 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

GraphUNet adjacency - matrix RuntimeError: expand is unsupported for SparseCsr tensors
2 participants