Open songyuc opened 3 years ago
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: https://github.com/AlexeyAB/darknet/issues/3293 https://github.com/AlexeyAB/darknet/issues/6987#issuecomment-729218069
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.
yes, the formulas are totally same as https://github.com/AlexeyAB/darknet/issues/6987#issuecomment-729218069
@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?
So, Is it possible to use the same yolo annotations(.txt) as YOLOv4 darknet in Scaled-Yolov4?
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!