OpenCV with OpenCL/CUDA oclMat/GpuMat doesn't work
Hello to everyone,
I'm trying to run OpenCVs calcOpticalFlowPyrLK on my GPU. I'm using Visual Studio 2012 and OpenCL 2.4.10 because OpenCV 3.0 doesn't work fine. I tried it one one PC with a AMD Radeon and also on a Laptop with an NVIDIA Geforce.
At first i tried it with OpenCL. Included this: #include "<"opencv2\ocl\ocl.hpp">" When I try to declare the oclMat Variable and scroll the mouse over it, it says: computes element-wise minimum of the two arrays (dst=min(src1,src2))
It also says: ";" expected when i scroll over the name I wanted to give my oclMat Object.
Then I tried everything with CUDA and it was nearly the same.
Does someone have an idea? Which Versions of what do I have to install?
Thank you for your help! PS: Sorry for the bad formatting
Does your GPU support CUDA ? Did you install CUDA tool kit and test CUDA sample programs like deviceQuery?
Do you mean something like this https://devblogs.nvidia.com/parallelf... I'm sorry I don't have any experience with CUDA