I'm trying to use OpenCV 3.1 with CUDA8.0 (statically linked). However, whenever I try to use any CUDA functionality, an exception is thrown during allocation . I have the exact same setup with CUDA 7.5 that works perfectly, and my installations are mirrors of each other. The nvidia CUDA samples do work, and the initialization of the cudev tests does show my hardware, but none of the cuda related tests run. Has anyone else seen anything like this?
This forum is disabled, please visit https://forum.opencv.org