SysCV / qdtrack

Quasi-Dense Similarity Learning for Multiple Object Tracking, CVPR 2021 (Oral)
Apache License 2.0
384 stars 61 forks source link

Using detector only #141

Open Raspberry-beans opened 1 year ago

Raspberry-beans commented 1 year ago

Hi, I hope everyone will be fine.

Is it possible to first use detector only and calculate the evaluation metrics e.g. mAP ? I actually want to conduct an experiment showing that tracker also improves detection results. So I need to run only the detection part first and then detection + tracking part.

also the detection evaluations we get from test.py script (see figure below), are they before applying tracker or after?

qdtrack_bbox

Any kind of suggestions will be helpful for me.

Regards, Rehman