Prabindh Sundareson

It cannot, but can be done with trivial modifications to the code. Please raise a separate issue.

Which version of CUDA8.0 is this ?

I strongly feel it may not be related to CUDNN. Did you stop the training in both of them after reasonable accuracies have been obtained in training ? Can you...

@bobeo Have you ensured your wrapper application (that uses the .so) also has the same options that are used for building the darknet shared lib ?

@kidapu Does inference work with CUDNN=1, with the shared lib ?

Is this behaviour seen with the latest master as well ? Please check the latest master and confirm

@ooobelix please confirm - that you are building Arapaho, and darknet with same options (for GPU, CUDNN) in both the Makefiles.

Could you confirm, what cfg is being used ?

I think you already tried with GPU=1, but I observed that in the last comment GPU is not defined. > my application with CFLAGS "-DCUDNN"

I tried the Arapaho build (Windows build from darknet-cpp-windows) with latest code, and the config:- Yolo-tinyv3 cfg, and CUDA91. I am able to see detections with the default yolov3 weights.