How to run yolo 3 object detector on a NVidia GPU

asked 2019-01-21 15:43:50 -0600

pouya.1991
81 ●3 ●9

updated 2019-01-21 15:56:28 -0600

Hi,

I've written a program which uses OpenCV (v 4.0.1) dnn module for object detection. Now I wanna to use my GPU (Geforce 1070) to accelerate my computation, but I found that at the moment OpenCV dnn module doesn't support Nvidia GPUs, so what is the best way to accelerate my program? I must use another framework like darknet to achieve this purpose or is there any other solution?

(I'm using Windows 10, CUDA 10 and CuDNN 7.4, MSVC 2017 64)

edit retag flag offensive close merge delete

add a comment

1 answer

Sort by » oldest newest most voted

answered 2019-01-22 04:50:49 -0600

cudawarped
869 ●3 ●10 http://jamesbowley.co.uk

Unfortunately yes. That said the windows fork of darknet uses OpenCV in its demo, so everything is already there for you. You can even use the CUDA version of OpenCV if you have additional image processing to perform which would benefit from GPU acceleration.