Jetson Nanon 2gb

[vladimirjankov]

When I follow the steps I just get "Killed" after I run inference.
The model crashed first at tlt-converter with output killed, which I fixed by adding -w 1000000.

Is this model able to run on Jetson Nano 2gb?

[vladimirjankov]

If someone can give me clarification I would appreciate it. Thanks in advance

[atoaster]

Hi @vladimirjankov

It's been a while, but I can pretty much say that no, this won't run on a 2GB Nano. The Killed message means you've run out of RAM.

In fact, barely any tensorrt/cuda/gstreamer based stuff can run on a 2GB Nano, because the OS/nvargus-daemon/tensorrt consume so much RAM by default.

You could use heaps of swap, but swap is so unbelievably slow, it makes it seem pointless. Using swap is also a good way to destroy your SD card, as I have done many times.