search

DeNA / PyTorch_YOLOv3

Implementation of YOLOv3 in PyTorch
Other
436 stars 147 forks source link

Why BCELoss for xy? #65

Open ccqu opened 4 years ago

ccqu commented 4 years ago

Hi, I think the original loss for xy is L2, so why in your code is BCELoss used? https://github.com/DeNA/PyTorch_YOLOv3/blob/master/models/yolo_layer.py#L192 Thanks in advance!

LukasStruppek commented 4 years ago

Hi, I am having the same question. The paper just mentioned BCE Loss for class prediction.

YHRen commented 4 years ago

add me to the list :D same question here.