Intrinsics must be effective, so don't declare FP16 type/operations if there is no native support. - CV_FP16: supports load/store into/from float32 - CV_SIMD_FP16: declares FP16 types and native FP16 operations |
||
|---|---|---|
| .. | ||
| 3rdparty/SoftFloat | ||
| doc | ||
| include/opencv2 | ||
| misc/java | ||
| perf | ||
| src | ||
| test | ||
| CMakeLists.txt | ||