The GPU is not used when running detection with YOLOv5

[angelinpurba99]

When I run the YOLOv5 detection code, it still uses CPU. And it causes the detection process to be slow, I get fps = 0.4. For installation, CUDA has been activated but the CUDA on the Jetson nano is still not used. Please give me an explanation why it happened and what is the solution?

[AastaLLL]

Hi,

Are you using Jetson Nano with a custom Python version?
If yes, please build Pytorch from the source to get the CUDA support.

Thanks.

[angelinpurba99]

The following are the versions of CUDA 10.2.300 and pytorch 2.3.1 that I have installed.
I use the virtual environment Python 3.8.0. Please tell which version of Pytorch and CUDA suits my python virtual environment. Please help me

[AastaLLL]

Hi,

We only provide the Python 3.6 package for JetPack 4.

If you want a custom Python version, please build it from the source.
You can find the building command and info below:

https://forums.developer.nvidia.com/t/pytorch-for-jetson/72048

Instructions → Build from Source

Thanks.