Han GuangXin

I will run more tests on different settings, and maybe provide my results to discuss.

 Here are my results, using pretrained model to run evaluation in **MOT17_val_half** and **DanceTrack_val**. For each metric, **red > blue > green**. There are observations which **does not make...

Thanks a lot for your detailed and enlightening explanation, truly! It deepened my understanding of the algorithms and the task of MOT. I will review the DanceTrack paper more thoroughly....

And I can provide the code using JDE kalman filter in ocsort, if needed. Maybe there is something I missed out.

Thanks! You convinced me again. There is a lot things I have to do and to learn. I will make a fork or PR as soon as possible, after I...

@noahcao Sorry for the delay! I make a PR which combine OC-SORT and BYTE, getting both higher MOTA and HOTA. Maybe you can check it or merge it? It is...

@Zhongdao Hi, can you share the code for converting CUHKSYSU dataset format?

@AmanGoyal99 , @Xiaofei-Kevin-Yang This command can be used as the reference: `pip install mmcv-full==1.3.10 -f https://download.openmmlab.com/mmcv/dist/cu102/torch1.7.0/index.html`

There are some reasons I can't use `ex.run_commandline()` and `ex.run()`. For `ex.run_commandline()`, It can't work with an existing `argparse`. And for `ex.run()`, it can't work with multiple GPU training (for...

Nice work! Really appreciate it! ---Original--- From: "Antoine ***@***.***> Date: Sun, Jun 19, 2022 16:37 PM To: ***@***.***>; Cc: "Han ***@***.******@***.***>; Subject: Re: [WeiChengTseng/Pytorch-PCGrad] support for amp? (Issue #15) I...