opencv

Commit Graph

Author	SHA1	Message	Date
Firat Kalaycilar	0a16d93e1d	Fixed an issue with weight assignment causing the resulting GMM weights to be unsorted in the CUDA and OCL versions of BackgroundSubtractorMOG2	11 years ago
Ilya Lavrenov	3940b6163b	remove intel guard since the code is 2 times faster on AMD too	11 years ago
Ilya Lavrenov	61c347fb76	typos	11 years ago
Ilya Lavrenov	6f76e7b42d	improved performance of bitwise ops	11 years ago
Ilya Lavrenov	adc15c2bba	improved performance of cv::ocl::sum	11 years ago
Ilya Lavrenov	3ebfe60008	improved performance of cv::ocl::countNonZero	11 years ago
Ilya Lavrenov	8e79de35a8	changes for GFTT	11 years ago
Ilya Lavrenov	a5afcd9f11	improved performance of cv::ocl::minMax	11 years ago
Ilya Lavrenov	3eff05e3eb	added performance tests for cv::ocl::calcHist	11 years ago
Alexander Karsakov	806e9241a6	Clarifying comments	11 years ago
Ilya Lavrenov	f7a474180b	tuned some tests	11 years ago
Alexander Karsakov	4aa891e773	Remove clReleaseDevice call (workaround for pure virtual call on Windows)	11 years ago
Ilya Lavrenov	099ea91823	typos	11 years ago
Ilya Lavrenov	767b28f2e3	tests	11 years ago
Ilya Lavrenov	c1c3139368	master-like performance tests	11 years ago
Alexander Karsakov	e6f6707558	OCL: Fix for Haar classifier (thanks to Konstantin Rodyushkin).	11 years ago
Ilya Lavrenov	e1a598c5b3	disabled ABF tests	11 years ago
Ilya Lavrenov	aa5311ea9f	backport of master-based perf tests for matchTemplate to 2.4	11 years ago
Alexander Alekhin	d1606b4aa3	ocl: added SVM perf test	11 years ago
Zhigang Gong	9aef26e2ad	Workaround a LLVM/Clang 3.3 bug. The LLVM/Clang 3.3 has a bug when compile a cl kernel with assignment of a scalar to a vector data type. This patch could work around this bug. Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>	11 years ago
Konstantin Matskevich	435615ba2e	update test CascadeClassifier	11 years ago
Andrey Pavlenko	0a4a1d7526	temporary disabling hanging test	11 years ago
ahb	49dfa5a17f	Fix the following error for ocl::getOpenCLPlatforms() on Ubuntu 12.04 with gcc 4.8 OpenCV Error: Unknown error code -6 (OpenCL function is not available: [clGetPlatformIDs]) in opencl_check_fn, file /home/ahb/software/opencv/modules/ocl/src/cl_runtime/cl_runtime.cpp, line 83 The issue results from modules/ocl/src/cl_runtime/cl_runtime.cpp checking for "linux" instead of "__linux__" (cp. http://sourceforge.net/p/predef/wiki/OperatingSystems/) Adjust all other occurrences of "defined(linux)" as well.	11 years ago
Andrey Pavlenko	4c99196399	adding `finish()` to flush CL queue, renaming the test to match 'master' branch	11 years ago
Andrey Pavlenko	a7821c60e5	refactoring the test as it should be in 2.4	11 years ago
Andrey Pavlenko	4d28e8243c	'master'-like Haar perf test	11 years ago
Ilya Lavrenov	6b9ebcbf3d	deleted extra semicolons	11 years ago
Ilya Lavrenov	d014cb8fb4	fixed warning [-Wempty-body]	11 years ago
Peng Xiao	0ccc903647	fixed a buffer overrun of ocl canny the `map` buffer does not have the same size with CUDA and index starts at [1, 1] instead of [0, 0].	11 years ago
Alexander Smorkalov	4f6f6e8cac	static function qualifier replaced on inline to enable kernel compilation with OpenCL 1.1 embedded profile.	11 years ago
krodyush	e8dd31aacd	change code according reviewer suggesions	11 years ago
krodyush	27c1bd2762	Improve ocl cvt_color performance for the following conversions: RGB<->BGR, RGB->Gray, RGB<->XYZ, RGB<->YCrCb, RGB<->YUV, and mRGBA<->RGBA. The improvement was done basically by processing more than 1 pixel by each work-item and using vector's operations. new performance tests were added	11 years ago
krodyush	1ae71fe205	intel device guard was added because of perf degradation on some non intel platform.	11 years ago
krodyush	34c630faf4	update doc to be consisted with headers	11 years ago
krodyush	ea0c9b7f5c	GFFT fix for linux build	11 years ago
krodyush	dfe7c98090	optimize separable filter by Added "sep_filter_singlepass" kernel that performs separable filtering in one kernel call Added appropriate host part - sepFilter2D_SinglePass function and SingleStepSeparableFilterEngine_GPU class Changed function declarations to enable their usage	11 years ago
krodyush	f3ee1c3d2f	Changes the datatype of the angle of the gradient for Intel platforms.	11 years ago
krodyush	917b883cf0	remove extra calculations from haar to be consistent with native implementation	11 years ago
krodyush	a63576e76d	HOST side optimization for GFFT	11 years ago
krodyush	de431609db	optimize Dx and Dy calcualtion to make it as single opencl kernel	11 years ago
Matthias Bady	b7c97f6e30	fixed init of clCxt	11 years ago
Alexander Alekhin	17ca7f9545	ocl: add support for initialization from user-provided OpenCL handles	11 years ago
Alexander Alekhin	740b1f235e	ocl: implemented per-thread OpenCL command queue	11 years ago
Peter Andreas Entschev	def17f2baa	Removing ocl::oclMat::ptr() method. The method ocl::oclMat::ptr() is being removed because it returns a pointer to a row of oclMat::data. The data attribute is a cl_mem structure and cannot be iterated outside an OpenCL kernel.	11 years ago
Peter Andreas Entschev	3bc952ed34	ocl::BruteForceMatcher fix wrong use of oclMat::ptr(). The oclMat::ptr() method was mistakenly used in ocl::BruteForceMatcher to pass a pointer to a oclMat object. The ptr() method returns a uchar pointer to the cl_mem data structure and this method will be removed.	11 years ago
Alexander Alekhin	3dcddad88a	ocl: added workaround into Haar kernels	11 years ago
Zhigang Gong	6ce03b0484	Fixed some implicitly type conversions between vector and scalar data type. There are some mixed implicitly/explicitly type conversion between scalar and vector. Although the spec allows those conversion, I prefer to make them consistent and use explicitly all the cases. Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>	11 years ago
Alexander Alekhin	7b551af424	ocl: try to disable clFinish workaround	11 years ago
Alexander Alekhin	c962a9d61c	ocl:perf: fix moments test for plain impl	11 years ago
Alexander Smorkalov	eab7603096	Warning fixes and suppression in ocl module for gcc 4.6 from Android NDK.	11 years ago

1 2 3 4 5 ...

864 Commits (46d39aff68e466ab563d8c26869d3b76fea84de6)