2017-11-19 23:25:15 -0600 | asked a question | 15 seconds to start up UMat OpenCV3.1 15 seconds to start up UMat OpenCV3.1 Hi, I tested on my computer: Intel i7-6700, the GPU is HD Graphics 530. When I us |
2017-08-01 21:21:15 -0600 | received badge | ● Famous Question (source) |
2017-01-10 23:10:45 -0600 | commented question | opencl for image sequence The version I used is opencv3.0.0. |
2017-01-09 19:58:25 -0600 | asked a question | opencl for image sequence Hi, I have a confusion that, when the image sequence to be processed using opencl, the context of opencl will be initialized many times, the initialization may make efficiency lower. The question is that, is it possible to initialize the openCL context ONCE during the image sequence process? |
2016-07-27 07:40:52 -0600 | received badge | ● Notable Question (source) |
2016-03-11 08:19:32 -0600 | received badge | ● Popular Question (source) |
2015-12-13 23:35:01 -0600 | asked a question | Are there versions 2.XX available on Centos7? Are there versions 2.XX available on Centos7? Because the projects are compeleted using C. |
2015-08-24 22:36:13 -0600 | commented question | efficiency of Filter2D and sepFilter2D The radius of the kernel is 3 for both cases. And I've tested both CPU and GPU. |
2015-08-21 00:19:55 -0600 | received badge | ● Student (source) |
2015-08-19 20:31:24 -0600 | asked a question | efficiency of Filter2D and sepFilter2D Theoretically, the sepFilter is faster than Filter. But, the results in my tests show that the Filter2D is about 4 times faster than the sepFilter2D. I tested the two functions in CPU,with the same kernel radius size. |
2015-07-26 03:46:55 -0600 | answered a question | OpenCL in OpenCV 3.0.0 Have you tested other filter algorithms, are they still slower down? In my project the GaussianBlur is slower in GPU than CUP, but the other algorithms are more faster in GPU. Maybe the GaussianBlur is suitbale computing in CPU because of its theory. |
2015-07-26 03:19:41 -0600 | answered a question | Is there any reason not to use UMat? The data member in UMat is hidden and there is no constructor with user data. And some functions can not be carried on OpenCL. So some Mat should be remained. |
2015-07-22 05:30:56 -0600 | commented question | Heap corruption using opencv3.0 Yeah, but both the possibility of errors are ruled out.And the problem is still existing. |
2015-07-21 21:33:52 -0600 | asked a question | Heap corruption using opencv3.0 Hi, The bilateralFilter is used in the video image processing, and after a period of time, a dump happens. That's memory Free or Allocator breakpoint. The call stack reports the location is in ocl_bilateralFilter_8u. |
2015-07-20 20:49:12 -0600 | asked a question | memory leaks when using ocl_bilateralFilter_8u opencv3.0 Hi, The bilateralFilter is used in the video image processing, and after a period of time, a dump happens. That's memory Free or Allocator breakpoint. The call stack reports the location is in ocl_bilateralFilter_8u. |
2015-07-17 03:36:10 -0600 | asked a question | bug in ocl_bilateralFilter_8u Hi, The bilateralFilter is used in the video image processing, and after a period of time, a dump happens. That's memory Free or Allocator breakpoint. The call stack reports the location is in ocl_bilateralFilter_8u. |
2015-06-18 03:34:17 -0600 | received badge | ● Necromancer (source) |
2015-06-17 21:48:51 -0600 | asked a question | location of data_ in oclMat initialization function? Hi, the question is that wher is the data in oclMat initialization function, in host or device? |
2015-06-13 21:22:34 -0600 | asked a question | Performance of data transfer of OpenCL in Intel HD Graphics? Hi, I'm trying to use OpenCL to accelerate the imgproc module. The test results show that the time costed by data transfering is nearly the same as the computing time, and that's a lager number. I use funcs getUMat and copyTo to do the data transfer. The GPU platform in my computer is Intel HD Graphics 4600, and that's the only GPU device.So I want to konw how does the data transfer between the device and host in OpenCV? Is the transfer mode suitable for Intel Graphics? |
2015-06-12 04:14:04 -0600 | received badge | ● Enthusiast |
2015-06-12 01:18:48 -0600 | marked best answer | OpenCV 3.0 ,the performance of UMat Hi, I'm trying to compare the performance of facedetect computing with OpenCL and without. So I use the Mat and UMat for the two cases. But the UMat is more slow than Mat. The OpenCL runtime is OK on my computer. The question is how can I start the GPU device? |
2015-06-11 21:21:48 -0600 | received badge | ● Scholar (source) |
2015-06-11 21:09:38 -0600 | received badge | ● Critic (source) |
2015-06-11 21:00:30 -0600 | received badge | ● Editor |
2015-06-10 03:14:08 -0600 | answered a question | openCV 3.0 beta and OpenCL setDevice How about trying following code: - current_device.set(current_device.ptr()); BTW, you'd beeter set the environment variables to set up the OpenCL device. |
2015-06-09 19:48:28 -0600 | commented answer | OpenCV 3.0 ,the performance of UMat Yes, I've set the flag as true. But the result is the same as false when I use the haarcascade to do the facedetect. Then I change the cascade file as lbpcascade, and get a double FPS. |
2015-06-09 04:35:13 -0600 | commented answer | OpenCV 3.0 ,the performance of UMat I've done some tests refer to http://answers.opencv.org/question/58.... For the filtering and Soble cases, I have got some good results. But the results of the facedetect demo are still bad. The GPU has seemingly not started up, because the GPU load(tested by GPU-Z) is 1%~2%. And I have not check out the reason until now. |