Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- def calculate_iogts(region_associations, img1_props, img2_props): # one image
- iogts = []
- for a in region_associations:
- set_region1_coords = set(tuple(i) for i in img1_props[a[0]].coords)
- set_region2_coords = set(tuple(i) for i in img2_props[a[1]].coords)
- intersection = set_region1_coords.intersection(set_region2_coords)
- union = set_region1_coords.union(set_region2_coords)
- iogts.append(len(intersection)/len(union))
- return iogts
- centroid-matching
- avg: 0.548 | max: 0.903 | min: 0.000 | median: 0.610 | q1: 0.395 | q3: 0.770
- avg: 0.581 | max: 0.873 | min: 0.000 | median: 0.629 | q1: 0.466 | q3: 0.763
- avg: 0.499 | max: 0.874 | min: 0.000 | median: 0.575 | q1: 0.177 | q3: 0.775
- avg: 0.638 | max: 0.886 | min: 0.000 | median: 0.716 | q1: 0.524 | q3: 0.815
- avg: 0.614 | max: 0.910 | min: 0.000 | median: 0.706 | q1: 0.504 | q3: 0.808
- avg: 0.489 | max: 0.925 | min: 0.000 | median: 0.609 | q1: 0.073 | q3: 0.789
- avg: 0.662 | max: 0.905 | min: 0.000 | median: 0.790 | q1: 0.487 | q3: 0.841
- avg: 0.422 | max: 0.861 | min: 0.000 | median: 0.508 | q1: 0.179 | q3: 0.639
- avg: 0.285 | max: 0.719 | min: 0.019 | median: 0.241 | q1: 0.163 | q3: 0.392
- avg: 0.682 | max: 0.939 | min: 0.000 | median: 0.839 | q1: 0.514 | q3: 0.883
- avg: 0.476 | max: 0.889 | min: 0.000 | median: 0.510 | q1: 0.245 | q3: 0.705
- avg: 0.448 | max: 0.799 | min: 0.000 | median: 0.512 | q1: 0.262 | q3: 0.647
- avg: 0.535 | max: 0.904 | min: 0.000 | median: 0.618 | q1: 0.378 | q3: 0.729
- avg: 0.626 | max: 0.920 | min: 0.000 | median: 0.731 | q1: 0.493 | q3: 0.819
- avg: 0.387 | max: 0.871 | min: 0.000 | median: 0.408 | q1: 0.110 | q3: 0.628
- avg: 0.546 | max: 0.847 | min: 0.000 | median: 0.616 | q1: 0.381 | q3: 0.722
- avg: 0.423 | max: 0.897 | min: 0.000 | median: 0.438 | q1: 0.156 | q3: 0.700
- avg: 0.453 | max: 0.874 | min: 0.000 | median: 0.493 | q1: 0.269 | q3: 0.668
- avg: 0.482 | max: 0.880 | min: 0.000 | median: 0.580 | q1: 0.249 | q3: 0.708
- avg: 0.644 | max: 0.902 | min: 0.000 | median: 0.722 | q1: 0.532 | q3: 0.815
- mostpixels-matching
- avg: 0.564 | max: 0.903 | min: 0.000 | median: 0.610 | q1: 0.421 | q3: 0.770
- avg: 0.582 | max: 0.873 | min: 0.000 | median: 0.629 | q1: 0.469 | q3: 0.763
- avg: 0.512 | max: 0.874 | min: 0.000 | median: 0.575 | q1: 0.244 | q3: 0.775
- avg: 0.649 | max: 0.886 | min: 0.000 | median: 0.716 | q1: 0.524 | q3: 0.815
- avg: 0.621 | max: 0.910 | min: 0.000 | median: 0.706 | q1: 0.504 | q3: 0.808
- avg: 0.500 | max: 0.925 | min: 0.000 | median: 0.609 | q1: 0.190 | q3: 0.789
- avg: 0.679 | max: 0.905 | min: 0.003 | median: 0.790 | q1: 0.487 | q3: 0.841
- avg: 0.426 | max: 0.861 | min: 0.000 | median: 0.508 | q1: 0.188 | q3: 0.639
- avg: 0.252 | max: 0.719 | min: 0.000 | median: 0.273 | q1: 0.000 | q3: 0.388
- avg: 0.702 | max: 0.939 | min: 0.000 | median: 0.839 | q1: 0.514 | q3: 0.883
- avg: 0.486 | max: 0.889 | min: 0.000 | median: 0.510 | q1: 0.273 | q3: 0.705
- avg: 0.396 | max: 0.799 | min: 0.000 | median: 0.512 | q1: 0.004 | q3: 0.647
- avg: 0.522 | max: 0.904 | min: 0.000 | median: 0.618 | q1: 0.377 | q3: 0.729
- avg: 0.627 | max: 0.920 | min: 0.000 | median: 0.731 | q1: 0.493 | q3: 0.819
- avg: 0.396 | max: 0.871 | min: 0.000 | median: 0.408 | q1: 0.155 | q3: 0.628
- avg: 0.538 | max: 0.847 | min: 0.000 | median: 0.616 | q1: 0.381 | q3: 0.722
- avg: 0.436 | max: 0.897 | min: 0.000 | median: 0.438 | q1: 0.174 | q3: 0.700
- avg: 0.466 | max: 0.874 | min: 0.000 | median: 0.493 | q1: 0.294 | q3: 0.668
- avg: 0.486 | max: 0.880 | min: 0.000 | median: 0.580 | q1: 0.255 | q3: 0.708
- avg: 0.648 | max: 0.902 | min: 0.000 | median: 0.722 | q1: 0.532 | q3: 0.815
Advertisement
Add Comment
Please, Sign In to add comment
