Hi all,
I’m trying to run the Helm chart install of the Intelligent Video Analytics Demo on my Jetson Nano. Details:
Package: nvidia-jetpack
Version: 4.6-b199
Priority: standard
Section: metapackages
Maintainer: NVIDIA Corporation
Installed-Size: 199 kB
Depends: nvidia-cuda (= 4.6-b199), nvidia-opencv (= 4.6-b199), nvidia-cudnn8 (= 4.6-b199), nvidia-tensorrt (= 4.6-b199), nvidia-visionworks (= 4.6-b199), nvidia-container (= 4.6-b199), nvidia-vpi (= 4.6-b199), nvidia-l4t-jetson-multimedia-api (>> 32.6-0), nvidia-l4t-jetson-multimedia-api (<< 32.7-0)
Homepage: http://developer.nvidia.com/jetson
Download-Size: 29.4 kB
APT-Sources: https://repo.download.nvidia.com/jetson/t210 r32.6/main arm64 Packages
Description: NVIDIA Jetpack Meta Package
Docker runtime set to Nvidia
sudo docker info | grep Runtime
Runtimes: nvidia runc io.containerd.runc.v2 io.containerd.runtime.v1.linux
Default Runtime: nvidia
Logs from the container generated by the helm chart:
2022-03-01 18:30:19 (2.59 MB/s) - 'tlt_trafficcamnet_pruned_v1.0.zip' saved [5452023/5452023]
Archive: tlt_trafficcamnet_pruned_v1.0.zip
inflating: labels.txt
inflating: resnet18_trafficcamnet_pruned.etlt
inflating: trafficnet_int8.txt
deepstream-app: error while loading shared libraries: libnvinfer.so.7: cannot open shared object file: No such file or directory
[]
0
/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/run.txt
I would have thought this would be covered by the nvidia-tensorrt package, but I could be wrong.
Anyone got any ideas of what to try?
Thanks