You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
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.
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!
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.
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.
The text was updated successfully, but these errors were encountered: