Jetson Nano 2GB, Ram problem

[lewowe]

Hi,

I am trying to run the trt_pose model on Jetson Nano 2GB, but the application freezes due to low ram and prints “Segmentation fault(Core dumped)”. What does it mean?
How to achieve 10-15 FPS? I followed the exact installation instructions mentioned here - GitHub - NVIDIA-AI-IOT/trt_pose: Real-time pose estimation accelerated with NVIDIA TensorRT

Swap memory is set to 5GB.
1.2GB ram is already being used without running anything - Any suggestions on how to reduce this?

Any help would be appreciated, Thank you

[AastaLLL]

Hi,

Please noted swap memory is not a GPU-accessible memory so TensorRT cannot use it.

The fps is tested on the standard Nano 4GB platform.
It might not able to reproduce on a 2GB device which is much limited in resources.

Please check the memory status with the below command first:

$ sudo tegrastats

Thanks.