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
In the deformable attention, the spatial shapes represented by height (H) and width (W). Why is it necessary to exchange the offset_normalizer to the witdh(W) height(H) order here?
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
-
Hi @jshilong, sorry to disturb you.
In the deformable attention, the spatial shapes represented by height (H) and width (W). Why is it necessary to exchange the
offset_normalizer
to the witdh(W) height(H) order here?mmcv/mmcv/ops/multi_scale_deform_attn.py
Lines 352 to 353 in c46684c
Beta Was this translation helpful? Give feedback.
All reactions