Revision history [back]

Good Day!

My question would be, that i'm currently trying to optimize my C++ program for GPU. My PC (relevant part):

• Geforce GTX 780
• I5-6600K
• Corsair vengeance 2.6GHZ memory 16GB

My code is pretty big, because it's connected with an AI, and i also use Landmark detection aswell, so now i will post only the relevant part of the code. Basictly my problem is, then every settings how i try gives slower results on GPU then CPU.

My code:

double cascade_ScaleFactor=1.2;
 cascade_MinNumberNeighbor=3;


    void facedetector(cv::Mat& frame, BufferFaceGPU& b)
    {   

        double processT,processT_total;

        /****************************/
        /***********GPU**************/
        /****************************/

        if (GPUx==1){   
            /***********VERSION 1.0 OLD*************/
            cascade_gpu->setMinObjectSize(cascadeMinSize);
            cascade_gpu->setMaxObjectSize(cascadeMaxSize);

            processT_total = (double)cv::getTickCount();

            std::vector<Rect> faces;
            cv::Mat cpu_frame_gray;

            processT = (double)cv::getTickCount();
            b.gpu_frame.upload(frame);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("GPU_data_upload.txt", processT);

            processT = (double)cv::getTickCount();
            cv::cuda::cvtColor(b.gpu_frame, b.gpu_frame, CV_BGR2GRAY);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("GPU_data_cvtColor.txt", processT);

            processT = (double)cv::getTickCount();
            cv::cuda::equalizeHist(b.gpu_frame, b.gpu_frame);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("GPU_data_equalizeHist.txt", processT);

            processT = (double)cv::getTickCount();
            cascade_gpu->detectMultiScale(b.gpu_frame, b.gpu_faces);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("GPU_data_detectMultiScale.txt", processT);


            processT = (double)cv::getTickCount();
            cascade_gpu->convert(b.gpu_faces, faces);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("GPU_data_convert.txt", processT);


            processT = (double)cv::getTickCount();
            b.gpu_frame.download(cpu_frame_gray);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("GPU_data_download.txt", processT);

            if (!faces.empty())
            {
                processT = (double)cv::getTickCount();
                get_landmarks(faces, cpu_frame_gray, frame);
                processT = (double)cv::getTickCount() - processT;
                processT /= (double)cv::getTickFrequency();
                read_write_data_tofile("GPU_data_getLandmarks.txt", processT);
            }


            processT_total = (double)cv::getTickCount() - processT_total;
            processT_total /= (double)cv::getTickFrequency();
            read_write_data_tofile("GPU_data_total.txt", processT_total);

        }

        /****************************/
        /***********CPU**************/
        /****************************/
        else if(GPUx==2){
            cv::Mat frame_gray;
            std::vector<Rect> faces;
            processT_total = (double)cv::getTickCount();

            processT = (double)cv::getTickCount();
            cv::cvtColor(frame, frame_gray, CV_BGR2GRAY);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("CPU_data_cvtColor.txt", processT);

            processT = (double)cv::getTickCount();
            cv::equalizeHist(frame_gray, frame_gray);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("CPU_data_equalizeHist.txt", processT);

            processT = (double)cv::getTickCount();
            face_cascade.detectMultiScale(frame_gray, faces, cascade_ScaleFactor, cascade_MinNumberNeighbor, 0 | CV_HAAR_SCALE_IMAGE, cascadeMinSize,cascadeMaxSize);
            processT = (double)cv::getTickCount() - processT;
            processT /= (double)cv::getTickFrequency();
            read_write_data_tofile("CPU_data_detecetMultiScale.txt", processT);

            if (!faces.empty())
            {
                processT = (double)cv::getTickCount();
                get_landmarks(faces, frame_gray, frame);
                processT = (double)cv::getTickCount() - processT;
                processT /= (double)cv::getTickFrequency();
                read_write_data_tofile("CPU_data_getLandmarks.txt", processT);
            }


            processT_total = (double)cv::getTickCount() - processT_total;
            processT_total /= (double)cv::getTickFrequency();
            read_write_data_tofile("CPU_data_total.txt", processT_total);
        }
        else{
            errormsg("Something went wrong!\nEXIT");
        }

    }

Sorry for the long code. I tried a bunch of optimalization (e.g. the max and min size is in a PID controller, and it's alwasy have to search for just a reasenable size of faces).

I'm monitoring the FPS and the process times also, and get almost a 1/4 of the CPU processed FPS. My results in monitoring is just like that:

On the last picture you can clearly see that the most difference is between the detectMultiScale function. I also use structure for the GPU aswell:

struct BufferFaceGPU{
    cv::cuda::GpuMat gpu_frame, gpu_faces;
};

My current idea is maybe on Visual Studio 2013 i built my solution wrong perhalps? I don't actually know, that do i need to set for example In the Build Customization CUDA on?

.. or did i forget something in the preferences maybe?

I'm not sure, what im doing wrong. Can you help, or any suggestion?

Thanks in advance.