Sorry for the late reply. I’ve reproduced the timing issue, profiled your code using torch.utils.bottleneck
, and it seems run with random weights just performs a lot more calls to layers/box_utils.py
.
It’s a guess as I’m not familiar with the code, but I think the random weights just might create a lot of more detection candidates which are evaluated one after the other.
Could you confirm the assumption?
1 Like