OC_SORT

OC_SORT copied to clipboard

AssertionError in train MOT20

3

I can successfully run evaluation code for MOT17 and MOT20 and video demo. But I got an error in training for MOT20, using 'python tools/train.py -f exps/example/mot/yolox_x_mix_mot20_ch.py -d 1 -b...

iTruffle

Hi, first of all thank you for this repo. I am doing an project where I am using 7 different object detectors and I would like to use their detectons...

JovanBosic

Just want to confirm: **MOT17-half-val** --> **ocsort_mot17_ablation.pth.tar**, same as **bytetrack_ablation.pth.tar** (based on ByteTrack: Train on CrowdHuman and MOT17 half train, evaluate on MOT17 half val) **MOT17-test** --> **ocsort_x_mot17.pth.tar**, same as...

jerichosu

Customized Detector -- Example

2

Hi, I added a Predictor class to work with any `yolov5` detector. I saw on the Roadmap that adding customizable Predictor objects is helpful, so I am leaving it here...

jpoberhauser

when Train on DanceTrack train set ,I can't find the exps/example/dancetrack/yolox_x.py？

1

Lisi911

How to get the score of the boxes after tracking? I don't think it can be simply set as 1.0

1

floveqq

Where is the post-processing code in this repository?

1

Hi, thanks for the interesting points in your paper and the code you provided. Could you help me to find where is the linear interpolation post-processing code described in Table...

LingyvKong

Performance improvement with Online smoothing (OOS)

1

First of all, thank you for providing a valuable contribution to the Computer Vision community. It was interesting to read your paper and also thank you for providing your implementation....

AbinayaKumar25

OCSORT + ByteTrack?

14

Thanks for the amazing work again! After replacing the SORT kalman filter in `ocsort.py` with the JDE kalman filter, I got higher HOTA and faster speed, which may indicates that...

HanGuangXin

How about C++ version ?

3

uyolo1314