Dashcam Deepstream 6.0 source code

Accelerated Computing Intelligent Video Analytics DeepStream SDK
#1

Can someone guide me to run the Dashcamnet Tao Pretrained model card in a jetson nano please?

i tried to run it but since the jetpack, docker and deepstream had been updated, i cant figure out how to run de pruned model, but everytime i try i just got an error.

im trying with this comands modified from the documentation but i cant find a apropiated way to do it, im trying to run it for real time vision on a webcam via usb:

sudo docker run -it --rm --net=host --runtime nvidia -e DISPLAY=$DISPLAY -v $HOME:/opt/nvidia/deepstream/deepstream-6.0/samples/models/tao_pretrained_models/dashcamnet
-w /opt/nvidia/deepstream/deepstream-6.0 --device /dev/video0 -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/deepstream-l4t:6.0-samples/configs/tao_pretrained_models \

deepstream-app -c /opt/nvidia/deepstream/deepstream-6.0/samples/configs/tao_pretrained_models/deepstream_app_source1_dashcamnet_vehiclemakenet_vehicletypenet.txt

but i always got a docker error and just the deepstream-app tutorial video but i need to do it on the web cam

#3

Any error you met?

#4

an error from the docker

docker: Error response from daemon: failed to create shim: OCI runtime create failed: container_linux.go:380: starting container process caused: error adding seccomp filter rule for syscall clone3: permission denied: unknown.

#5

Try this
sudo usermod -aG nvidia docker // if you are using nvidia user name, or change it accordingly.

#6

it just says usermod: group ‘nvidia’ does not exist

#7

Sorry, this one.
sudo usermod -aG docker nvidia

#9

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