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
When I trained in mnist, I added deformable conv layer, the experimental accuracy did not increase, and become very low, what is the reason for this phenomenon, how about your results thank you very much @kanuore@unsky
In mnist network given,why used dilation convolution in offset layer? For the offset have a lager search area in feature map or not?
The text was updated successfully, but these errors were encountered: