Deepstream 5 in Docker on Jetson Nano : yolov3 not working

AI & Data Science Deep Learning (Training & Inference) DIGITS (Locked)
1

Hi,

I’m using the docker container provide by nvidia for Jetson Nano :

docker pull nvcr.io/nvidia/deepstream-l4t:5.0.1-20.09-samples

As it is written, this container have a lot of package already installed :

the DeepStream base container contains the plugins and libraries that are part of the DeepStream SDK along with dependencies such as CUDA, TensorRT, Gstreamer etc

When I try to run the deep-stream sample for yolov3 :

deepstream-app -c deepstream_app_config_yoloV3.txt

, it raised the error :

deepstream-app: error while loading shared libraries: libnvinfer.so.7: cannot open shared object file: No such file or directory

Does this mean that TensorRT is not installed in the container ?

1 Like
2

I have the same problem.

3

Not sure because it was a long time ago but I remenber that the problem was with the TensorRT version on the Host. The container has just a link with the file on the host nano and I remember I solved this with updating or downgrading the host image with the good jetpack.

4

The problem was that I was running yolo compilation inside the Dockerfile. If you run the build already in a ready-made container, then everything is fine.