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
First, nice work. But I found something wrong when calculating flops in torch.nn.Conv2d, in count_hooks.py file, the out_w = y.size(2) // m.stride[0] is wrong, it must be out_w = y.size(2). The same as out_h.
So the flops result is less than standard ones.
The text was updated successfully, but these errors were encountered:
First, nice work. But I found something wrong when calculating flops in torch.nn.Conv2d, in count_hooks.py file, the
out_w = y.size(2) // m.stride[0]
is wrong, it must beout_w = y.size(2)
. The same asout_h
.So the flops result is less than standard ones.
The text was updated successfully, but these errors were encountered: