Jackal's profile - activity

Hi All,

when trying to load a cascade classifier into cv::gpu::CascadeClassifier_GPU my application thread memory is jumping high over 1GB.

Is just in my machine ?

CascadeLoaded = cascade_gpu.load(cascadeName);

I've started to debug the above line and found that inside the file:cascadeclasifier.cpp (Line 626)

stage_mat.upload(cv::Mat(1, (int) (stages.size() * sizeof(Stage)), CV_8UC1, (uchar*)&(stages[0]) ));

The Memory is bloated.

I'm loading this classifier (LBP) https://raw.github.com/Itseez/opencv/master/data/lbpcascades/lbpcascade_frontalface.xml

Hope it helps you to help me.

Regards, Jackal.

Thank you ... :)

Thanks StevenPuttemans,

Well i don't know what I've change (maybe with the initialization) but it start to pass the function with no error. but in general it still works slowly ? is there any chance to make it work faster ?

Thanks for your answer, I've tried that like you wrote just to be sure, but it returns the same error. It seems like i have something missing.

1. Does this function worked to anyone with GPU ?
2. Do i need something special to be installed ?

Thanks in advance, Jackal.

I'm initiate it like this: cv::gpu::GpuMat ColorSRC = cv::gpu::GpuMat(myImageHIGHT,myImageWIDTH,CV_8UC4,&myColorImageMat);

is it ok ?

(I've the same error in it's inside path to 8UC4 and 8UC1)

I don't know if it's the same. mine is calling the HogDescriptor::detectMultiScale and yours calling the CascadeClassifier::detectMultiScale ..

But this is the exception i get ...

This is the call : hog.detectMultiScale(ColorSRC, found);

This is the exception: Unhandled exception at at 0x7543C41F in OnysusPlayer.exe: Microsoft C++ exception: cv::Exception at memory location 0x665AE388.

Hello , I've compile the opencv 2.4.5 with Cuda5 and trying to implement the detectMultiScale Call. since i've got an error i started to debug it. and found that in hog.cu the error raised.

if (correct_gamma) compute_gradients_8UC1_kernel<nthreads, 1=""><<<gdim, bdim="">>>(height, width, img, angle_scale, grad, qangle); else compute_gradients_8UC1_kernel<nthreads, 0=""><<<gdim, bdim="">>>(height, width, img, angle_scale, grad, qangle);

        cudaSafeCall( cudaGetLastError() );

        cudaSafeCall( cudaDeviceSynchronize() );

also i can't debug into the compute_gradients_8UC1_kernel does anyone has any idea ?

Regards, Jackal.