cenit
commented
5 years ago OpenCV with CUDA support requires building it from source. For it, I suggest the vcpkg route. Anyway maybe it's not even necessary for you. That message should be clear enough that "Darknet is fine"... detection from webcam works anyway even without a CUDA-enabled OpenCV
hi i followed the git page and downloaded the necessary requirements, i am wanting to run detection with webcam/video. i have compiled darknet successfully without opencv in visual studio 2019. i am stuck on opencv because it asks about PATH and that i install the correct opencv, by building with sources with CUDA support (i dont know how to go about these 2 things). also, i am unsure what boxes to check here https://i.imgur.com/knhkzzi.png
this is what CMake shows when i configure:
Selecting Windows SDK version 10.0.17763.0 to target Windows 10.0.17134. Autodetected CUDA architecture(s): 6.1 Building with CUDA flags: -gencode;arch=compute_61,code=sm_61 OpenCV ARCH: x64 OpenCV RUNTIME: vc15 OpenCV STATIC: OFF Found OpenCV 4.1.0 in C:/opencv/build/x64/vc15/lib You might need to add C:\opencv\build\x64\vc15\bin to your PATH to be able to run your applications. -> darknet is fine for now, but uselib_track has been disabled! -> Please rebuild OpenCV from sources with CUDA support to enable it Found cuDNN: v7.6.0 (include: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v10.1/include, library: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v10.1/lib/x64/cudnn.lib) CMAKE_CUDA_FLAGS: -gencode arch=compute_61,code=sm_61 -Wno-deprecated-declarations -Xcompiler="/wd4013,/wd4018,/wd4028,/wd4047,/wd4068,/wd4090,/wd4101,/wd4113,/wd4133,/wd4190,/wd4244,/wd4267,/wd4305,/wd4477,/wd4996,/wd4819,/fp:fast,/DGPU,/DCUDNN,/DOPENCV" -D_WINDOWS -Xcompiler="/W3 /GR /EHsc" Configuring done