I am trying on your work to produce topdown semantic map for each scene in gibson dataset. However, some topdown map looks weird, can you help me to know what's the problem? I have no idea if it is the problem with my env or it is just normal.
for example, this image has a large area labeled as out-of-bound, but actually seems like a potential room

This image has a really large area marked as out of bound

This sample also has some confusing area.
