Hardware Platform (Jetson / GPU)
Jetson NX
• DeepStream Version
5.1
• JetPack Version (valid for Jetson only)
4.5-b129
• TensorRT Version
7.1.3
• Issue Type( questions, new requirements, bugs)
When I tried to deploy a usb deepstream app container in a k3s pod, after successfully creating the pod, I tried to run
$ deepstream-app -c samples/configs/deepstream-app/source1_usb_dec_infer_resnet_int8.txt
got
deepstream-app: error while loading shared libraries: /usr/lib/aarch64-linux-gnu/libnvinfer.so.7: file too short
The following is my .yaml for the deployment
apiVersion: v1
kind: Pod
metadata:
name: demo-pod
labels:
name: demo-pod
spec:
hostNetwork: true
containers:
- name: demo-stream
image: nvcr.io/nvidia/deepstream-l4t:5.1-21.02-samples
securityContext:
privileged: true
allowPrivilegeEscalation: true
command:
- sleep
- "150000"
workingDir: /opt/nvidia/deepstream/deepstream-5.1
volumeMounts:
- mountPath: /tmp/.X11-unix/
name: x11
- mountPath: /dev/video0
name: cam
volumes:
- name: x11
hostPath:
path: /tmp/.X11-unix/
- name: cam
hostPath:
path: /dev/video0
Does there anyone have some related experiences, please share some advice with me.