Should I reduce the model osnet_x0_25_market1501.pt as Yolov5n-strongsort-osnet tracking process Killed after loading osnet_x0_25_market1501?

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano
1

Hi, I am using Jetson nano with Jetpack 4.6 installed with PyTorch 1.10.0 and torchvision 0.11.0. I use a yolov5n.pt as the detector and osnet_x0_25_market1501.pt weight for tracker. I am running the tracker using GPU. Until it loads osnet_x0_25_market1501.pt , everything runs in normal speed. once the osnet_x0_25_market1501.pt the process gets killed. I would like to know how I can solve this issue. I exported the reid model to onnx, but it is not helping.

2

Moved to Nano forum for better support, thanks.

1 Like
4

Hi,

Is osnet_x0_25_market1501.pt a complicated model?
Could you monitor the system status with tegrastats to confirm if you run out of memory first?

$ sudo tegrastats

Thanks.

6

I was able to run the tracker with osnet and yolov5n model in cpu successfully. Thanks for the reply.

7

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.