I have met power down when run pytorch transfer learning using Jetson nano.

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano
1

Hi, All

I have met power down when run pytorch transfer learning using Jetson nano.

code: Transfer Learning for Computer Vision Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation

In that moment, memory is near to 2.2GB of total 3.87GB.

So, I think that is not memory problems, but power problems …

I’m using usb 5pin power.

Is that right ?

Thanks in advance …

2

Hi bemore, it is recommended to either use 4A DC barrel jack adapter power supply, or to change your Nano to 5W power mode with this command to avoid over-taxing your USB power supply:

$ sudo nvpmodel -m 1