Skip to content
Discussion options

You must be logged in to vote

How about

unique = data.edge_index.view(-1).unique()

mask = torch.ones(data.num_nodes, dtype=torch.bool)
mask[unique] = False

print(mask.nonzero())  # The indices of all isolated nodes.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by BodyCSoulN
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants