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
replacing out = torch.einsum('bnchwk,bnchwk -> bnchw', out, v_out)
with out = (out*v_out).sum(dim=5)
made running time more than 2x faster while training on IMAGENET (2 min vs 53s per 100 step, batchsize 25) which is still 3.5x slower than training normal ResNet on IMAGENET
(Not sure whether this model works for IMAGENET or not)
The text was updated successfully, but these errors were encountered:
in attention.py, class AttentionConv
replacing out = torch.einsum('bnchwk,bnchwk -> bnchw', out, v_out)
with out = (out*v_out).sum(dim=5)
made running time more than 2x faster while training on IMAGENET (2 min vs 53s per 100 step, batchsize 25) which is still 3.5x slower than training normal ResNet on IMAGENET
(Not sure whether this model works for IMAGENET or not)
The text was updated successfully, but these errors were encountered: