Segmentation Fault while running demo

[ifzhang]

Segmentation Fault while running demo

[jamessmith123456]

i got it too..Segmentation fault(core dumped). Have you solve it?

[ifzhang]

Have you successfully built DCNv2？I think the error is caused by "You're using a third-party extension module written in C, and that extension module has crashed." You can try to build DCNv2 again or use our HRNetW18 model which does not need DCNv2 to run the demo (don't forget to comment the lines with 'dcn' in src/lib/models/model.py).

[toyal]

i got it too..Segmentation fault(core dumped). Have you solve it?

have you solve this problem,i locate the problem caused by dcnv2,but how to solve it

[ZhangYuef]

Have you successfully built DCNv2？I think the error is caused by "You're using a third-party extension module written in C, and that extension module has crashed." You can try to build DCNv2 again or use our HRNetW18 model which does not need DCNv2 to run the demo (don't forget to comment the lines with 'dcn' in src/lib/models/model.py).

@ifzhang How to use HRNetW18 model correctly? I use following command:

python track.py mot --load_model ../models/hrnetv2_w18_imagenet_pretrained.pth --conf_thres 0.6 --val_mot16 False

Got following warning:

No param reg.2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
No param reg.2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.

and all NaN value ...