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
I used the coco slicing utility to slice my coco-format dataset into 512x512px patches with an overlap of 0.25. I then used a custom object detector to perform inference on these patches and have the results as a coco-style results json for the patches.
Is there a utility to combine the results, so that the result patches of an image are merged into detection results on a single and can be evaluated against the original coco annotations? I didn't find a direct utility for this in the repository.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I used the coco slicing utility to slice my coco-format dataset into 512x512px patches with an overlap of 0.25. I then used a custom object detector to perform inference on these patches and have the results as a coco-style results json for the patches.
Is there a utility to combine the results, so that the result patches of an image are merged into detection results on a single and can be evaluated against the original coco annotations? I didn't find a direct utility for this in the repository.
Thank you!
Beta Was this translation helpful? Give feedback.
All reactions