Run demo with batch with other model than Yolox-s

[sodi16]

I want to run detection and choose the batch size, I try to change the path yolox_s.pth.tar to l, x models but it doesn't work.
Should I run eval.py for this task in place of demo.py?
Thanks in advance

[GOATmessi8]

For demo, we didn't support batch inferencing. You may have to revise the eval.py for your task.

[sodi16]

@ruinmessi Thanks a lot for your help, I just don't find wich argparse should I give to change to my Video path?

[Joker316701882]

python tools/demo.py video -n yolox-s -c /path/to/your/yolox_s.pth.tar --path /path/to/your/video --conf 0.3 --nms 0.65 --tsize 640 --save_result --device [cpu/gpu]

Modify --path to change your video path, modify -n and -c to change a different model.

[sodi16]

@Joker316701882 Thanks for your help, but I mean the video path argument in eval.py