potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 15:23:05 +04:00
Code Packages Releases Wiki Activity

Merge pull request #23098 from savuor:nanMask

Browse Source 
finiteMask() and doubles for patchNaNs() #23098

Related to #22826
Connected PR in extra: [#1037@extra](https://github.com/opencv/opencv_extra/pull/1037)

### TODOs:
- [ ] Vectorize `finiteMask()` for 64FC3 and 64FC4

### Changes

This PR:
* adds a new function `finiteMask()`
* extends `patchNaNs()` by CV_64F support
* moves `patchNaNs()` and `finiteMask()` to a separate file

**NOTE:** now the function is called `finiteMask()` as discussed with the OpenCV core team

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [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
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Rostislav Vasilikhin
2023-11-09 08:32:47 +01:00
committed by GitHub
parent 34f34f6227
commit 53aad98a1a
15 changed files with 1190 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/src/mathfuncs.cpp
+1 -69
View File
@@ -1574,75 +1574,7 @@ bool checkRange(InputArray _src, bool quiet, Point* pt, double minVal, double ma
return true;
}
#ifdef HAVE_OPENCL
static bool ocl_patchNaNs( InputOutputArray _a, float value )
{
int rowsPerWI = ocl::Device::getDefault().isIntel() ? 4 : 1;
ocl::Kernel k("KF", ocl::core::arithm_oclsrc,
format("-D UNARY_OP -D OP_PATCH_NANS -D dstT=float -D DEPTH_dst=%d -D rowsPerWI=%d",
CV_32F, rowsPerWI));
if (k.empty())
return false;
UMat a = _a.getUMat();
int cn = a.channels();
k.args(ocl::KernelArg::ReadOnlyNoSize(a),
ocl::KernelArg::WriteOnly(a, cn), (float)value);
size_t globalsize[2] = { (size_t)a.cols * cn, ((size_t)a.rows + rowsPerWI - 1) / rowsPerWI };
return k.run(2, globalsize, NULL, false);
}
#endif
void patchNaNs( InputOutputArray _a, double _val )
{
CV_INSTRUMENT_REGION();
CV_Assert( _a.depth() == CV_32F );
CV_OCL_RUN(_a.isUMat() && _a.dims() <= 2,
ocl_patchNaNs(_a, (float)_val))
Mat a = _a.getMat();
const Mat* arrays[] = {&a, 0};
int* ptrs[1] = {};
NAryMatIterator it(arrays, (uchar**)ptrs);
size_t len = it.size*a.channels();
Cv32suf val;
val.f = (float)_val;
#if (CV_SIMD || CV_SIMD_SCALABLE)
v_int32 v_mask1 = vx_setall_s32(0x7fffffff), v_mask2 = vx_setall_s32(0x7f800000);
v_int32 v_val = vx_setall_s32(val.i);
#endif
for( size_t i = 0; i < it.nplanes; i++, ++it )
{
int* tptr = ptrs[0];
size_t j = 0;
#if (CV_SIMD || CV_SIMD_SCALABLE)
size_t cWidth = (size_t)VTraits<v_int32>::vlanes();
for ( ; j + cWidth <= len; j += cWidth)
{
v_int32 v_src = vx_load(tptr + j);
v_int32 v_cmp_mask = v_lt(v_mask2, v_and(v_src, v_mask1));
v_int32 v_dst = v_select(v_cmp_mask, v_val, v_src);
v_store(tptr + j, v_dst);
}
vx_cleanup();
#endif
for( ; j < len; j++ )
if( (tptr[j] & 0x7fffffff) > 0x7f800000 )
tptr[j] = val.i;
}
}
}
} // namespace cv
#ifndef OPENCV_EXCLUDE_C_API