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

Time to generate graphs #8

Open
han-liu opened this issue Nov 4, 2020 · 3 comments
Open

Time to generate graphs #8

han-liu opened this issue Nov 4, 2020 · 3 comments

Comments

@han-liu
Copy link

han-liu commented Nov 4, 2020

Hi, I'm wondering how long it takes to generate one graph from probability map/ground truth map (e.g., for DRIVE dataset)? It seems to take quite a long time with the parameters provided in the paper. Thanks.

@syshin1014
Copy link
Owner

Hi, I can't remember how long it took exactly.
But, I remember it took a long time for a dense graph.
That's why I used the 'multiprocessing' module to generate multiple graphs from multiple prob. maps at the same time.
You can try to make a sparser graph by controlling the vertex sampling sparsity (in our paper) if it is ok to you.

@han-liu
Copy link
Author

han-liu commented Nov 8, 2020

Thanks for the clarification. Here's another question. In the file make_graph_db.py line 133, can you clarify why the node labels as added as the node indices? I thought that would be binary value 0/1 obtained from the ground truth map. Thanks!

@syshin1014
Copy link
Owner

In the line, 'node_idx' is irrelevant with the label indicating whether it is vessel or not.
It's a general index for nodes in a graph, e.g. 0~N-1 for a graph having N nodes.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants