syshin1014

Hi, You can download the pre-trained model (weights) for the HRF dataset using the hyperlink provided in 'Testing a Model' [https://github.com/syshin1014/VGN](url). We've used all three subsets, namely healthy, diabetic retinopathy,...

Hi, You can check #3 for the relevant information.

Two lines below the line are for preparing the arguments for the function. Each of them would be a list, and it is passed to the function by 'pool.map'

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...

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...

Hi, Did you use a right checkpoint path for 'args.model_path'?

Hi, as noted, this code was developed with Python2.7, so you need to modify it if you find any syntax error when you run it using Python3. I don't have...

Hi, let me quote the relevant description on that from our paper. We note that: 1) FoV masks are originally not available for STARE and CHASE_DB1, 2) we used ones...

Hi, As you've already noticed, the current code was developed with public datasets that include GT labels, and it loads the GT label as well as an input image for...