Only using detector

[Raspberry-beans]

Hi,
Firstly thanks a lot for great work.

I have performed steps mentioned in GET_STARTED.md and everything is working fine.

I actually want to show that tracking also improves detection results. For this is it possible if I only use the detector first, calculate evaluation metrics and then apply detector along with tracker and see whether the detection results have been improved or not?

Any help would be appreciated. I really need to show this experiment as it is basis for my research internship, so I am looking for any kind of suggestions.

Best Regards,
Rehman

[dccdcc7]

hello, have you encoutered
ModuleNotFoundError: No module named 'mmcv._ext'
when you performed steps mentioned in GET_STARTED.md?
thank u

[Raspberry-beans]

Hi
For me only mmcv version 1.6.1 was working as mentioned in qdtrack (a MOT model similar to PCAN)

Even I faced several issues like yours when installing this version via pip. Hence I build it from source as mentioned here

Using different mmcv version than mentioned in PCAN might generate few errors while running their python scripts. But I remember that I somehow managed to correct those errors manually :-)

I hope my answer helps!

Regards,
Rehman