Attention! This forum will be made read-only by Dec-20. Please migrate to https://forum.opencv.org. Most of existing active users should've received invitation by e-mail.
Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

CUDA 10.0 added native vector arithmetic operators for the __half2 datatype. The CUDA backend for OpenCV DNN has merged a few weeks ago and makes use of the aforementioned builtin operators.

You will either have to upgrade to CUDA 10.0 to use the CUDA backend of OpenCV DNN or disable it by unmarking OPENCV_DNN_CUDA in CMake options.

CUDA 10.0 added native vector arithmetic operators for the __half2 __half2 datatype. The CUDA backend for OpenCV DNN has merged a few weeks ago and makes use of the aforementioned builtin built-in operators.

You will either have to upgrade to CUDA 10.0 to use the CUDA backend of OpenCV DNN or disable it by unmarking OPENCV_DNN_CUDA OPENCV_DNN_CUDA in CMake options.

Note: The CUDA backend for OpenCV DNN was merged into master a few weeks ago and is not in any release yet. I suspect you have built the master branch instead of OpenCV 4.1.2.