How to build Docker container for Jetson Nano

Hi,

Could you let us know how to build a docker container for Tensorflow model on an x86 architecture machine and deploy that container on Jetson Nano. Any links or tutorials would be highly appreciated.

Also we are getting this warning -
WARNING: The requested image’s platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested

Thanks

Hi,

You will need an l4t-based container for compatibility.

Below is a tutorial for your reference:
Please noted that you need to change the tag to the corresponding JetPack version. (ex. nvcr.io/nvidia/l4t-base:r32.5.0)

Thanks.

I recommend to try the l4t-tensorflow or l4t-ml container. Then copy your TensorFlow model from your PC to your Jetson. Then you can mount the folder containing your model into the container by using the --volume command shown in the links above.

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.