Nvcr.io/nvidia/l4t-pytorch:r34.1.1-pth1.12-py3 run arenot available on jetson nano

Autonomous Machines Jetson & Embedded Systems Jetson Nano
,
1

Hi, I pulled the docker image nvcr.io/nvidia/l4t-pytorch:r32.6.1-pth1.8-py3, because I installed my Jetpack 4.6 at Jetson Nano. After the pulling, I tried to run that image and this just happened.

insung@insung-desktop:~/MotuS-ML$ sudo docker run -it --rm --runtime nvidia --network host nvcr.io/nvidia/l4t-pytorch:r34.1.1-pth1.12-py3
docker: Error response from daemon: failed to create shim: OCI runtime create failed: container_linux.go:380: starting container process caused: process_linux.go:545: container init caused: Running hook #0:: error running hook: exit status 1, stdout: , stderr: nvidia-container-cli: initialization error: driver error: failed to process request: unknown.

I think the problem is that -runtime nvidia is a problem because we don’t have any errors without that command.

3

Hi,

r34/r25 doesn’t support Jetson Nano.
It looks like you are using a r34 container.
Please use the r32 container (ex. nvcr.io/nvidia/l4t-pytorch:r32.7.1-pth1.10-py3) instead.

Thanks.

1 Like
4

Thanks for your reply!

I reflashed the SD card and installed jetpack 4.6.1 on my jetson nano. I have additional questions…

  1. You must deploy AI services using Nvidia Jetson. Containers that run and use CUDA via a Docker image build a fastapi server. Is there a way to run it automatically without logging in?
  2. How do I find the correct Nvidia NGC version?
5

Hi,

You will need to use our container that supports the l4t system to use iGPU.

Usually, our container has the tag specified in the branch version.
For example, nvcr.io/nvidia/l4t-pytorch:r32.7.1-pth1.10-py3

Then compare to the OS returns by the following command:

$ cat /etc/nv_tegra_release

Thanks.

7

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