DG-Net icon indicating copy to clipboard operation
DG-Net copied to clipboard

Published 20 hours ago • verified publisher icon NVlabs

Run DG-Net on Nvidia Jetson Nano

Open pablovicentem opened this issue 5 years ago • 2 comments

Hi,

I was wondering if I can implement this DG-Net in the Nvidia Jetson Nano and I have the followinmg questions:

It is posswible to apply TensorRT to the NN in order to first create an UFF model an the apply TensorRT? It is possible to add this NN to a deep stream pipeline?

Best regards.

pablovicentem avatar Feb 13 '20 12:02 pablovicentem

Hi @pablovicentem Sorry for the late response. We have not tested the code on the Jetson Nano. I am not sure whether it is feasible or not. Memory may be the bottleneck. But, you are right. TensorRT may be helpful. You also may test the apex(for float16 inference).

Thanks a lot.

layumi avatar Feb 23 '20 23:02 layumi

Hi @pablovicentem Sorry for the late response. We have not tested the code on the Jetson Nano. I am not sure whether it is feasible or not. Memory may be the bottleneck. But, you are right. TensorRT may be helpful. You also may test the apex(for float16 inference).

Thanks a lot.

hey man whats the min GPU hardware you would suggest for running DG-Net?

lakshaydulani avatar Apr 23 '22 11:04 lakshaydulani