清晨的雾

Hello, You need to use the provided corresponding weights to get the results. For hyperparameters, you can just use the default values in https://github.com/MCG-NJU/MixSort/blob/main/tools/track_mixsort_oc.py

Hi @sky-creater , I recommend you add breakpoints to code to see what caused the unexpected stop at 13% progress. May be there are some corrupted data?

Hello, In our SportsMOT dataset, we only focus on all the players, so the referees are not annotated.

Hello @sky-creater, The error you encountered seems to be the same as #2 , you can refer to it.

Hello @realsazzad, You can try changing the line to `from yolox.byte_tracker.byte_tracker import BYTETracker`. This should resolve the import issue. This file is a demo from [ByteTrack](https://github.com/ifzhang/ByteTrack). Since we haven't made...

Hi @arthur-andre , It seems like the program quits without any error output, so I recommend you to add some breakpoints and run the program step by step to see...

Hello @arthur-andre , I think this is the problem within the yolox. I directly import `YOLOPAFPN` module from `yolox.models`, and this error would occur regardless of the shape of the...

Hello @Qweqwem3m3m3 , Thanks for your interest in our dataset! I'm afraid that I couldn't help you solve this problem because this repo is not related to the codalab competition.

Hello @Xiyu-AI , You could refer to following functions: https://github.com/MCG-NJU/MixSort/blob/a078f5bf6ae9fbeecbc1384479d5f02ab8b9e7f6/yolox/evaluators/mot_evaluator.py#L322-L340 While encountering a new video (L334), `tracker.re_init` is called to reset the variables. https://github.com/MCG-NJU/MixSort/blob/a078f5bf6ae9fbeecbc1384479d5f02ab8b9e7f6/yolox/mixsort_tracker/mixsort_tracker.py#L217-L221 To use our tracker, you need...

Hello @MintMAO , I'm afraid that we don't provide detection files. For the weird detection results you posted, I recommend you to check your configuration of YOLOX detector according to...