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 am using RTMDet segmentation model on a custom dataset consisting of cca. 20 classes. I need segmentation masks only for 2 classes, for the rest only bboxes are needed. In order to improve inference speed, I am thinking it could help to have segmentation head only doing the segmentation for the required 2 classes.
Does my hypotheses makes. any sense at all?
Can this maybe be achieved via configuration file solely or is code update needed?
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 am using RTMDet segmentation model on a custom dataset consisting of cca. 20 classes. I need segmentation masks only for 2 classes, for the rest only bboxes are needed. In order to improve inference speed, I am thinking it could help to have segmentation head only doing the segmentation for the required 2 classes.
Does my hypotheses makes. any sense at all?
Can this maybe be achieved via configuration file solely or is code update needed?
Beta Was this translation helpful? Give feedback.
All reactions