mirror of
https://github.com/opencv/opencv.git
synced 2026-07-28 14:53:03 +04:00
60b806f9b8
Added cv::hasNonZero() #22947 `cv::hasNonZero()` is semantically equivalent to (`cv::countNonZero()>0`) but stops parsing the image when a non-zero value is found, for a performance gain - [X] I agree to contribute to the project under Apache 2 License. - [X] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [X] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake This pull request might be refused, but I submit it to know if further work is needed or if I just stop working on it. The idea is only a performance gain vs `countNonZero()>0` at the cost of more code. Reasons why it might be refused : - this is just more code - the execution time is "unfair"/"unpredictable" since it depends on the position of the first non-zero value - the user must be aware that default search is from first row/col to last row/col and has no way to customize that, even if his use case lets him know where a non zero could be found - the PR in its current state is using, for the ocl implementation, a mere `countNonZero()>0` ; there is not much sense in trying to break early the ocl kernel call when non-zero is encountered. So the ocl implementation does not bring any improvement. - there is no IPP function that can help (`countNonZero()` is based in `ippCountInRange`) - the PR in its current state might be slower than a call to `countNonZero()>0` in some cases (see "challenges" below) Reasons why it might be accepted : - the performance gain is huge on average, if we consider that "on average" means "non zero in the middle of the image" - the "missing" IPP implementation is replaced by an "Open-CV universal intrinsics" implementation - the PR in its current state is almost always faster than a call to `countNonZero()>0`, is only slightly slower in the worst cases, and not even for all matrices **Challenges** The worst case is either an all-zero matrix, or a non-zero at the very last position. In such a case, the `hasNonZero()` implementation will parse the whole matrix like `countNonZero()` would do. But we expect the performance to be the same in this case. And `ippCountInRange` is hard to beat ! There is also the case of very small matrices (<=32x32...) in 8b, where the SIMD can be hard to feed. For all cases but the worse, my custom `hasNonZero()` performs better than `ippCountInRange()` For the worst case, my custom `hasNonZero()` performs better than `ippCountInRange()` *except for large matrices of type CV_32S or CV_64F* (but surprisingly, not CV_32F). The difference is small, but it exists (and I don't understand why). For very small CV_8U matrices `ippCountInRange()` seems unbeatable. Here is the code that I use to check timings ``` //test cv::hasNonZero() vs (cv::countNonZero()>0) for different matrices sizes, types, strides... { cv::setRNGSeed(1234); const std::vector<cv::Size> sizes = {{32, 32}, {64, 64}, {128, 128}, {320, 240}, {512, 512}, {640, 480}, {1024, 768}, {2048, 2048}, {1031, 1000}}; const std::vector<int> types = {CV_8U, CV_16U, CV_32S, CV_32F, CV_64F}; const size_t iterations = 1000; for(const cv::Size& size : sizes) { for(const int type : types) { for(int c = 0 ; c<2 ; ++c) { const bool continuous = !c; for(int i = 0 ; i<4 ; ++i) { cv::Mat m = continuous ? cv::Mat::zeros(size, type) : cv::Mat(cv::Mat::zeros(cv::Size(2*size.width, size.height), type), cv::Rect(cv::Point(0, 0), size)); const bool nz = (i <= 2); const unsigned int nzOffsetRange = 10; const unsigned int nzOffset = cv::randu<unsigned int>()%nzOffsetRange; const cv::Point pos = (i == 0) ? cv::Point(nzOffset, 0) : (i == 1) ? cv::Point(size.width/2-nzOffsetRange/2+nzOffset, size.height/2) : (i == 2) ? cv::Point(size.width-1-nzOffset, size.height-1) : cv::Point(0, 0); std::cout << "============================================================" << std::endl; std::cout << "size:" << size << " type:" << type << " continuous = " << (continuous ? "true" : "false") << " iterations:" << iterations << " nz=" << (nz ? "true" : "false"); std::cout << " pos=" << ((i == 0) ? "begin" : (i == 1) ? "middle" : (i == 2) ? "end" : "none"); std::cout << std::endl; cv::Mat mask = cv::Mat::zeros(size, CV_8UC1); mask.at<unsigned char>(pos) = 0xFF; m.setTo(cv::Scalar::all(0)); m.setTo(cv::Scalar::all(nz ? 1 : 0), mask); std::vector<bool> results; std::vector<double> timings; { bool res = false; auto ref = cv::getTickCount(); for(size_t k = 0 ; k<iterations ; ++k) res = cv::hasNonZero(m); auto now = cv::getTickCount(); const bool error = (res != nz); if (error) printf("!!ERROR!!\r\n"); results.push_back(res); timings.push_back(1000.*(now-ref)/cv::getTickFrequency()); } { bool res = false; auto ref = cv::getTickCount(); for(size_t k = 0 ; k<iterations ; ++k) res = (cv::countNonZero(m)>0); auto now = cv::getTickCount(); const bool error = (res != nz); if (error) printf("!!ERROR!!\r\n"); results.push_back(res); timings.push_back(1000.*(now-ref)/cv::getTickFrequency()); } const size_t bestTimingIndex = (std::min_element(timings.begin(), timings.end())-timings.begin()); if ((bestTimingIndex != 0) || (std::find_if_not(results.begin(), results.end(), [&](bool r) {return (r == nz);}) != results.end())) { std::cout << "cv::hasNonZero\t\t=>" << results[0] << ((results[0] != nz) ? " ERROR" : "") << " perf:" << timings[0] << "ms => " << (iterations/timings[0]*1000) << " im/s" << ((bestTimingIndex == 0) ? " * " : "") << std::endl; std::cout << "cv::countNonZero\t=>" << results[1] << ((results[1] != nz) ? " ERROR" : "") << " perf:" << timings[1] << "ms => " << (iterations/timings[1]*1000) << " im/s" << ((bestTimingIndex == 1) ? " * " : "") << std::endl; } } } } } } ``` Here is a report of this benchmark (it only reports timings when `cv::countNonZero()` is faster) My CPU is an Intel Core I7 4790 @ 3.60Ghz ``` ============================================================ size:[32 x 32] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[32 x 32] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:0 continuous = false iterations:1000 nz=true pos=middle cv::hasNonZero =>1 perf:0.353764ms => 2.82674e+06 im/s cv::countNonZero =>1 perf:0.282044ms => 3.54555e+06 im/s * ============================================================ size:[32 x 32] type:0 continuous = false iterations:1000 nz=true pos=end cv::hasNonZero =>1 perf:0.610478ms => 1.63806e+06 im/s cv::countNonZero =>1 perf:0.283182ms => 3.5313e+06 im/s * ============================================================ size:[32 x 32] type:0 continuous = false iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:0.630115ms => 1.58701e+06 im/s cv::countNonZero =>0 perf:0.282044ms => 3.54555e+06 im/s * ============================================================ size:[32 x 32] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[32 x 32] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[32 x 32] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[32 x 32] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[32 x 32] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[32 x 32] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:5 continuous = false iterations:1000 nz=true pos=end cv::hasNonZero =>1 perf:0.607347ms => 1.64651e+06 im/s cv::countNonZero =>1 perf:0.467037ms => 2.14116e+06 im/s * ============================================================ size:[32 x 32] type:5 continuous = false iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:0.618162ms => 1.6177e+06 im/s cv::countNonZero =>0 perf:0.468175ms => 2.13595e+06 im/s * ============================================================ size:[32 x 32] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[32 x 32] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[32 x 32] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[32 x 32] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[32 x 32] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[64 x 64] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[64 x 64] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[64 x 64] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[64 x 64] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[128 x 128] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[128 x 128] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[128 x 128] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[128 x 128] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[320 x 240] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[320 x 240] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[320 x 240] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[320 x 240] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[512 x 512] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[512 x 512] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[512 x 512] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[512 x 512] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[640 x 480] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[640 x 480] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[640 x 480] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[640 x 480] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1024 x 768] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1024 x 768] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1024 x 768] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1024 x 768] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:4 continuous = true iterations:1000 nz=true pos=end cv::hasNonZero =>1 perf:895.381ms => 1116.84 im/s cv::countNonZero =>1 perf:882.569ms => 1133.06 im/s * ============================================================ size:[2048 x 2048] type:4 continuous = true iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:899.53ms => 1111.69 im/s cv::countNonZero =>0 perf:870.894ms => 1148.24 im/s * ============================================================ size:[2048 x 2048] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[2048 x 2048] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:6 continuous = true iterations:1000 nz=true pos=end cv::hasNonZero =>1 perf:2018.92ms => 495.313 im/s cv::countNonZero =>1 perf:1966.37ms => 508.552 im/s * ============================================================ size:[2048 x 2048] type:6 continuous = true iterations:1000 nz=false pos=none cv::hasNonZero =>0 perf:2005.87ms => 498.537 im/s cv::countNonZero =>0 perf:1992.78ms => 501.812 im/s * ============================================================ size:[2048 x 2048] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[2048 x 2048] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[2048 x 2048] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[2048 x 2048] type:6 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:0 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:0 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:0 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:0 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:0 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:0 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:0 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:0 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:2 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:2 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:2 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:2 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:2 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:2 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:2 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:2 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:4 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:4 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:4 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:4 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:4 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:4 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:4 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:4 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:5 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:5 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:5 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:5 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:5 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:5 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:5 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:5 continuous = false iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:6 continuous = true iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:6 continuous = true iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:6 continuous = true iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:6 continuous = true iterations:1000 nz=false pos=none ============================================================ size:[1031 x 1000] type:6 continuous = false iterations:1000 nz=true pos=begin ============================================================ size:[1031 x 1000] type:6 continuous = false iterations:1000 nz=true pos=middle ============================================================ size:[1031 x 1000] type:6 continuous = false iterations:1000 nz=true pos=end ============================================================ size:[1031 x 1000] type:6 continuous = false iterations:1000 nz=false pos=none done ```
108 lines
3.4 KiB
C++
108 lines
3.4 KiB
C++
// This file is part of OpenCV project.
|
|
// It is subject to the license terms in the LICENSE file found in the top-level directory
|
|
// of this distribution and at http://opencv.org/license.html
|
|
|
|
|
|
#include "precomp.hpp"
|
|
#include "opencl_kernels_core.hpp"
|
|
#include "stat.hpp"
|
|
|
|
#include "has_non_zero.simd.hpp"
|
|
#include "has_non_zero.simd_declarations.hpp" // defines CV_CPU_DISPATCH_MODES_ALL=AVX2,...,BASELINE based on CMakeLists.txt content
|
|
|
|
namespace cv {
|
|
|
|
static HasNonZeroFunc getHasNonZeroTab(int depth)
|
|
{
|
|
CV_INSTRUMENT_REGION();
|
|
CV_CPU_DISPATCH(getHasNonZeroTab, (depth),
|
|
CV_CPU_DISPATCH_MODES_ALL);
|
|
}
|
|
|
|
#ifdef HAVE_OPENCL
|
|
static bool ocl_hasNonZero( InputArray _src, bool & res )
|
|
{
|
|
int type = _src.type(), depth = CV_MAT_DEPTH(type), kercn = ocl::predictOptimalVectorWidth(_src);
|
|
bool doubleSupport = ocl::Device::getDefault().doubleFPConfig() > 0;
|
|
|
|
if (depth == CV_64F && !doubleSupport)
|
|
return false;
|
|
|
|
int dbsize = ocl::Device::getDefault().maxComputeUnits();
|
|
size_t wgs = ocl::Device::getDefault().maxWorkGroupSize();
|
|
|
|
int wgs2_aligned = 1;
|
|
while (wgs2_aligned < (int)wgs)
|
|
wgs2_aligned <<= 1;
|
|
wgs2_aligned >>= 1;
|
|
|
|
ocl::Kernel k("reduce", ocl::core::reduce_oclsrc,
|
|
format("-D srcT=%s -D srcT1=%s -D cn=1 -D OP_COUNT_NON_ZERO"
|
|
" -D WGS=%d -D kercn=%d -D WGS2_ALIGNED=%d%s%s",
|
|
ocl::typeToStr(CV_MAKE_TYPE(depth, kercn)),
|
|
ocl::typeToStr(depth), (int)wgs, kercn,
|
|
wgs2_aligned, doubleSupport ? " -D DOUBLE_SUPPORT" : "",
|
|
_src.isContinuous() ? " -D HAVE_SRC_CONT" : ""));
|
|
if (k.empty())
|
|
return false;
|
|
|
|
UMat src = _src.getUMat(), db(1, dbsize, CV_32SC1);
|
|
k.args(ocl::KernelArg::ReadOnlyNoSize(src), src.cols, (int)src.total(),
|
|
dbsize, ocl::KernelArg::PtrWriteOnly(db));
|
|
|
|
size_t globalsize = dbsize * wgs;
|
|
if (k.run(1, &globalsize, &wgs, true))
|
|
return res = (saturate_cast<int>(cv::sum(db.getMat(ACCESS_READ))[0])>0), true;
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
bool hasNonZero(InputArray _src)
|
|
{
|
|
CV_INSTRUMENT_REGION();
|
|
|
|
int type = _src.type(), cn = CV_MAT_CN(type);
|
|
CV_Assert( cn == 1 );
|
|
|
|
bool res = false;
|
|
|
|
#ifdef HAVE_OPENCL
|
|
CV_OCL_RUN_(OCL_PERFORMANCE_CHECK(_src.isUMat()) && _src.dims() <= 2,
|
|
ocl_hasNonZero(_src, res),
|
|
res)
|
|
#endif
|
|
|
|
Mat src = _src.getMat();
|
|
|
|
HasNonZeroFunc func = getHasNonZeroTab(src.depth());
|
|
CV_Assert( func != 0 );
|
|
|
|
if (src.dims == 2)//fast path to avoid creating planes of single rows
|
|
{
|
|
if (src.isContinuous())
|
|
res |= func(src.ptr<uchar>(0), src.total());
|
|
else
|
|
for(int row = 0, rowsCount = src.rows ; !res && (row<rowsCount) ; ++row)
|
|
res |= func(src.ptr<uchar>(row), src.cols);
|
|
}
|
|
else//if (src.dims != 2)
|
|
{
|
|
const Mat* arrays[] = {&src, nullptr};
|
|
Mat planes[1];
|
|
NAryMatIterator itNAry(arrays, planes, 1);
|
|
for(size_t p = 0 ; !res && (p<itNAry.nplanes) ; ++p, ++itNAry)
|
|
{
|
|
const Mat& plane = itNAry.planes[0];
|
|
if (plane.isContinuous())
|
|
res |= func(plane.ptr<uchar>(0), plane.total());
|
|
else
|
|
for(int row = 0, rowsCount = plane.rows ; !res && (row<rowsCount) ; ++row)
|
|
res |= func(plane.ptr<uchar>(row), plane.cols);
|
|
}
|
|
}
|
|
|
|
return res;
|
|
}
|
|
|
|
} // namespace
|