Training models on a dedicated gpu then importing into jetson nano

I’m able to train models with transfer learning on the Jetson Nano 2GB but its painfully slow. I’ve tried copy pasting the code from jetson inference after cloning the repo into a my pc running ubuntu to train a fruit object detection model shown in the jetson inference GitHub page but it isn’t working.

Training on a dedicated gpu will certainly reduce the time needed to train models.

Are there any guides that can help out?


Jetson_inference configure is by default setup for Jetson platform.
Some update is required to deploy it on an x86 machine.

Please check the following topic for the details:


Thank you for the help! I’ll try it and let you know the results.

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