Compiling OpenCV with CUDA

Hi everyone,

I configured my AGX Orin Dev Kit with SDK Manager-Jetpack 5.1.
I am coding OpenCV projects with Python. So as soon as I know Cuda should be compiled with opencv. The exist version of OpenCV is not compile with CUDA and has no make file in folder to do flag section.

How can I do it ?
Reflashing without CUDA and OpenCV by SDK Manager ? or easier way ?

Hi,
You wound need to manually enable CUDA filters and build OpenCV. A user has shared a script:
GitHub - mdegans/nano_build_opencv: Build OpenCV on Nvidia Jetson Nano

Please give it a try.

2 Likes

Thank you sir.
It solved the problem with a little change in setup file.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.