Kevin Zhu
Kevin Zhu
1. padding is set to "same" because of the dialation, otherwise `res=res.expand_as(x)` in line 49 will fail. 2. removed unnecessary `b, c, _, _ = x.size()` since it's never used....
Changing the "width_multiple" will result in an error. For example changing "width_multiple" to 0.5 in yolov9.yaml will yield `RuntimeError: stack expects each tensor to be equal size, but got [1,...