zengwz

Results 2 comments of zengwz
trafficstars

When training the ByteTrack using BDD100K dataset, detection accuracy downs to nearly zero after adding L1 Loss of YOLOX

According to my understanding, it should depend on "YOLOXModeSwitchHook". It will close the mosaic and mixup in the last num epochs and add L1 LOSS. the concrete implementation depends on...

When training the ByteTrack using BDD100K dataset, detection accuracy downs to nearly zero after adding L1 Loss of YOLOX

> Could you share how you processed the BDD100K dataset in mmtracking and where did you download the BDD100K dataset? Thank you very much! I processed BDD100K dataset follow QDTrack(https://github.com/SysCV/qdtrack)....