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
Originally in the next-prediction repo, we use ADE20K model and only these most common 10 classes are used in preprocessing, which does not include "person" class since person features are covered in another module. See here. Since in the ActEV dataset these are the most common classes except for person class and to keep the same preprocessing, I put the person class into the background (id 0). This is a bit hacky. You can easily change this by adding an entry in the scene36_64_id2name_top10.json file ("13" is person class for ADE20K) for training and testing but may not see a performance difference.
JunweiLiang
changed the title
Test input questions
"Person" class in semantic segmentation input
May 12, 2021
Why do the ten categories of semantic segmentation results not include pedestrians? Do they serve as background?
The text was updated successfully, but these errors were encountered: