I just purchased a jetson nano 2gb and tested the system using the face detection script from GitHub - JetsonHacksNano/CSI-Camera: Simple example of using a CSI-Camera (like the Raspberry Pi Version 2 camera) with the NVIDIA Jetson Developer Kit with a LI-IMX219-MIPI-FF-NANO-H136 camera. I noticed that there is some lag that happens when using the face detection script, I was wondering if upgrading to a 4gb nano will increase the speed of inference significantly and if there is a significant performance upgrade with a 4gb nano (other than more io ports).
Would appreciate some input, thanks.