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 work…

Training models on a dedicated gpu then importing into jetson nano

AastaLLL October 18, 2021, 2:14am 3

Hi,

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:

Thanks.