Does ScaledYOLOv4 use the same encoding of bounding box coordinates as YOLOv3

[songyuc]

Hi, guys,
I want to know whether ScaledYOLOv4 uses the same encoding of bounding box coordinates as YOLOv3, like,

Any answer or idea will be appreciated!

[WongKinYiu]

No, the encoding/decoding method is changed in yolov4.
yolov4-tiny used same encoding/decoding method as yolov4.
the encoding/decoding method is proposed by glenn, which solved the grid sensitivity problem.
glenn further replaced exponential function by sigmoid function to avoid nan problem in training process.
yolov4-csp and yolov4-large models use this new encoding/decoding method.

reference: AlexeyAB/darknet#3293 AlexeyAB/darknet#6987 (comment)

[songyuc]

Hi, @WongKinYiu
Today I read the code of ScaledYOLOv4, and translate the decoding as these formulas,

I hope you can give me more correction advices.

[WongKinYiu]

yes, the formulas are totally same as AlexeyAB/darknet#6987 (comment)

[songyuc]

@WongKinYiu , I am not sure about why there is a factor of 2. Is this factor of 2 would help mitigate the issue of sigmoid's gradiet vanishing?

[saikrishnadas]

So, Is it possible to use the same yolo annotations(.txt) as YOLOv4 darknet in Scaled-Yolov4?