How to cuda cores while using pytorch models ? only in cpu mode i can run my program which takes more time

I am running my model over jetson tx2 board while I am using GPU ids=0 or 1 it’s not supported asking to install a new driver for Nvidia while I am using CPU only its working but speed is very slow, I installed cuda 10.2 using SDK and torch 1.7.0


May I know how do you install the PyTorch first?
You will need a package with the Jetson GPU architecture support.

Below is our prebuilt package, and you can also find a container in our NGC page: l4t-pytorch.


yes installed the packages using this link, trying to install them again hope it will work