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 read the tutorial, and I want to ask a question about the generating a eigencam for yolov5. Why doesn't yolov5 need to write the target function when generating eigencam, but faster-rcnn needs it? Can I use the method of faster-rcnn to generate eigencam for yolov5? Which method is more accurate?
By the way, Can I use gradcam's method on yolov5? If used, whether a boundingbox can only correspond to a cam, can it only generate one cam like eigencam.
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 read the tutorial, and I want to ask a question about the generating a eigencam for yolov5. Why doesn't yolov5 need to write the target function when generating eigencam, but faster-rcnn needs it? Can I use the method of faster-rcnn to generate eigencam for yolov5? Which method is more accurate?
By the way, Can I use gradcam's method on yolov5? If used, whether a boundingbox can only correspond to a cam, can it only generate one cam like eigencam.
Beta Was this translation helpful? Give feedback.
All reactions