upsample = nn.Upsample(scale_factor = 2, mode = "nearest") should be upsample = nn.Upsample(scale_factor = stride, mode = "nearest")
This bug is silent since stride=2 in the cfg file. But if someone changed the value it would not be applied. The value 2 would be used since it is hard coded in create_modules.
There is an error in
darknet.py
line 118 in https://github.com/ayooshkathuria/YOLO_v3_tutorial_from_scratch/commit/0057114edfa1522e089dc5f379a1ebd4282f0ff3upsample = nn.Upsample(scale_factor = 2, mode = "nearest")
should beupsample = nn.Upsample(scale_factor = stride, mode = "nearest")
This bug is silent since
stride=2
in thecfg
file. But if someone changed the value it would not be applied. The value2
would be used since it is hard coded increate_modules
.