Tonu Samuel a015333f04 ml: SIMD for SVM kernel reductions ...

SVM::predict is dominated by the per-feature kernel reduction over the
support vectors. Vectorize the four reduction kernels in svm.cpp with
universal intrinsics (two independent accumulators + scalar tail):
calc_non_rbf_base (dot product), calc_rbf (squared distance),
calc_intersec (min-sum) and calc_chi2. Same approach as the KNN
findNearest reduction in #29380. Adds modules/ml/perf/perf_svm.cpp
covering the RBF/POLY/INTER/CHI2 kernels.

2026-06-28 18:09:05 +03:00

..

doc

Fix modules/ typos

2019-08-16 17:34:29 +03:00

include/opencv2

Merge pull request #27338 from omahs:patch-1

2025-05-21 12:13:50 +03:00

misc

replace tostring() with tobytes

2025-02-18 12:25:01 +05:30

perf

ml: SIMD for SVM kernel reductions

2026-06-28 18:09:05 +03:00

src

ml: SIMD for SVM kernel reductions

2026-06-28 18:09:05 +03:00

test

Fix ml::KDTree::findNearest

2025-10-16 22:58:55 +03:00

CMakeLists.txt

Revert "suppress warning on GCC 7 and later"

2022-08-07 15:43:10 +03:00