How to train haar cascade on gpu

Question

I am trying to train a cascade using opencv's opencv_traincascade method. But the program is very slow as it run on the CPU. Is there any way I can the program on a GPU for faster training. I tried following this link

https://www.cerebrumedge.com/single-post/2017/12/26/Compiling-OpenCV-with-CUDA-and-FFMpeg-on-Ubuntu-1604, but later realized that it does not work for python, atleast according to this link OpenCV 3.2 CUDA support python. But the person has also mentioned that one can use opencl with python.

Is there anyway I can use opencl to train the cascade on a GPU?

Thanks in advance

Answer 1

I don't know how to use GPU computing, but I used parallel computing on the CPU and the speed was increased by 4 times.