CARVIEW |
Navigation Menu
-
-
Notifications
You must be signed in to change notification settings - Fork 56.2k
added cv::hasNonZero() #22947
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
added cv::hasNonZero() #22947
Conversation
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
{ | ||
const size_t N = 1500; | ||
|
||
for (int k = 1; k <= 3; ++k) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why do you need loop, if all k are handled in swtch?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- I propose to reduce switch and extract common part. No need to repeat the same several times.
- No need to handle results and print status manually. Use it parameter and call the function with particular k in dedicated test instance. Result will be obvious from GTest output.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I just took the code from test_countnonzero, this is the exact same scheme.
What is the best option : make that scheme evolve for cv_hasNonZero(), or keep homogeneity between those two unit tests ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
test_countnonzero was written in pre-GTest epoch. No need to do the same. Feel free to use Gtest in more efficient way.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ok, I will refactor the whole hasNonZero tests to modern code (within a few days )
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done (and it exposed a bug that I could fix)
{ | ||
bool result = false; | ||
|
||
for (int i = 0; i < src.rows; ++i) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
{}
for (int j = 0; j < size.width; ++j) | ||
for (int i = 0; i < size.height; ++i) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
{}
|
||
v0 |= v2; | ||
v4 |= v6; | ||
res = v_check_any(((v0 | v4) != v_zero)); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the code does not handle -0 properly
|
||
v0 |= v4; | ||
v8 |= v12; | ||
res = v_check_any(((v0 | v8) != v_zero)); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
-0 is not handled properly
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@chacha21 Friendly reminder.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
AFAIK, my last commit does support -0 correctly. The buildbot just reports failure because of perf_test not runnable (no reference data).
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I just double-checked that v_check_any(((v0 | v8) != v_zero));
will be correct on a x64 target :
typedef v_float64 v_type;
const v_type v_zero = vx_setzero_f64();
const v_type v_poszero = vx_setall_f64(0);
const v_type v_negzero = vx_setall_f64(-0);
const v_type v_one = vx_setall_f64(1);
bool b1 = v_check_any((v_poszero != v_zero));//reports FALSE, as expected
bool b2 = v_check_any((v_negzero != v_zero));//reports FALSE, as expected, because the _mm256_cmp_pd seems to handle -0 correctly
bool b3 = v_check_any((v_one != v_zero));//reports TRUE, as expected
But I don't know if it behaves the same on NEON
@chacha21, thanks for the contribution! the function may probably be useful for some applications (not sure which though). I see that -0 is not handled properly in f32 and f64 cases |
-0 is supported by recasting to floating type before comparing to floating 0
Some examples of use cases for me :
|
This PR is definitely useful to speed-up tests that compare to a golden image, or when investigating if there is any problem with a mask. Thx ! |
strict aliasing rules are violated if trying to use bitwise logic when gathering several floats before comparing to 0.0
for performance, use unrolling+bitwise logic for floating case. instead of recasting to float before comparing to +/-0, just get rid of the sign bit by SHL
|
No regression data for hnz argument means that you need to add SANITY_CHECK_NOTHING() at the end of all performance tests instead of SANITY_CHECK(). SANITY_CHECK expects some sanity data in opencv_extra that is not provided.
unused variable hnz after switching to SANITY_CHECK_NOTHING()
|
unused variable "result" after switching to SANITY_CHECK_NOTHING()
if (src.isContinuous()) | ||
res = func(src.ptr<uchar>(0), src.total()); | ||
else | ||
for(int row = 0, rowsCount = src.rows ; !res && (row<rowsCount) ; ++row) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the non-continuous case does not handle multi-dimensional arrays. It should not be difficult to add for this function, use NAryMatIterator
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ok, It will just take me the time to figure out how NAryMatIterator is supposed to be used (I am not familiar with it yet)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
at least add the check for src.dims <= 2, otherwise in the case of non-contiguous 3D, 4D etc. arrays the function will always return 'false', since rows=cols=-1 in this case.
use NAryMatIterator to support multi-dimensionnal arrays
For information, the doc https://docs.opencv.org/4.x/d5/dd2/classcv_1_1NAryMatIterator.html should be fixed as well
`res |= ...` instead of `res = ...` to accumulate the non zero state
the old tests were copycat from test_countNonZero new tests are modern Gtests, and are more relevant for hasNonZero
totalBytes *= steps[dim]*static_cast<size_t>(sizes[dim]); | ||
} | ||
|
||
void* data = fastMalloc(totalBytes); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
std::vector or other container is better here. No memory leaks in case of exception.
|
||
RNG& rng = theRNG(); | ||
|
||
const size_t N = 1000; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The same here.
SIMD returns false for (NaN != v_zero), it should be rewritten as !(NaN == v_zero)
|
I was not able to understand where this warning comes from |
Complete warning messages from stdout:
|
tentatively use EXPECT_TRUE() and EXPECT_FALSE() instead of EXPECT_EQ(true/false, ...)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 Thanks a lot for the contribution!
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 ? "carview.php?tsp=true" : "false") << " iterations:" << iterations << " nz=" << (nz ? "carview.php?tsp=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 ```
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 ? "carview.php?tsp=true" : "false") << " iterations:" << iterations << " nz=" << (nz ? "carview.php?tsp=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 ```
cv::hasNonZero()
is semantically equivalent to (cv::countNonZero()>0
) but stops parsing the image when a non-zero value is found, for a performance gainPatch to opencv_extra has the same branch name.
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 :
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.countNonZero()
is based inippCountInRange
)countNonZero()>0
in some cases (see "challenges" below)Reasons why it might be accepted :
countNonZero()>0
, is only slightly slower in the worst cases, and not even for all matricesChallenges
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 likecountNonZero()
would do. But we expect the performance to be the same in this case. AndippCountInRange
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 thanippCountInRange()
For the worst case, my custom
hasNonZero()
performs better thanippCountInRange()
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
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