CUDA support in Jetson Orin Nano (Jetpack 6.2)

[fasatejayesh909]

Hello Nvidia,

Im really frusted with Nvidia Jetson Orin nano board. I want to have CUDA support to work on OpenCV. I used SD card method to get started. I flash using (JetPack SDK | NVIDIA Developer) and I install jtop to check the system info and you can see in attach image. I try enabling CUDA using: (JEP/script/install_opencv4.9.0_Jetpack6.0.sh at master · AastaNV/JEP · GitHub)

Can anyone help me fix this?

[SivaRamaKrishnaNV]

Dear @fasatejayesh909 ,
I dont see any issue with JEP/script/install_opencv4.10.0_Jetpack6.1.sh at master · AastaNV/JEP · GitHub on Jetpack 6.2

nvidia@tegra-ubuntu:~$ head -1 /etc/nv_tegra_release
# R36 (release), REVISION: 4.3, GCID: 38968081, BOARD: generic, EABI: aarch64, DATE: Wed Jan  8 01:49:37 UTC 2025

Noticed below message in the end.

-- Set runtime path of "/usr/local/bin/opencv_annotation" to "/usr/local/lib:/usr/local/cuda/lib64"
-- Installing: /usr/local/bin/opencv_visualisation
-- Set runtime path of "/usr/local/bin/opencv_visualisation" to "/usr/local/lib:/usr/local/cuda/lib64"
-- Installing: /usr/local/bin/opencv_interactive-calibration
-- Set runtime path of "/usr/local/bin/opencv_interactive-calibration" to "/usr/local/lib:/usr/local/cuda/lib64"
-- Installing: /usr/local/bin/opencv_version
-- Set runtime path of "/usr/local/bin/opencv_version" to "/usr/local/lib:/usr/local/cuda/lib64"
-- Installing: /usr/local/bin/opencv_model_diagnostics
-- Set runtime path of "/usr/local/bin/opencv_model_diagnostics" to "/usr/local/lib:/usr/local/cuda/lib64"
** Install opencv 4.10.0 successfully
** Bye :)

[fasatejayesh909]

Thank You @SivaRamaKrishnaNV 4.10.0 worked.