diff options
| author | Giorgio Arena <giorgio.arena@arm.com> | 2021-05-12 12:28:58 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-05-17 09:02:15 +0000 |
| commit | ed4b8a07e67c7802207c8954a88ad7a91aec79e0 (patch) | |
| tree | 771cb0867fa675cf02286006f7fafa2f66a814e2 /src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp | |
| parent | 186fe683da63dea2dac06e46a412e354d33cd9c2 (diff) | |
| download | ComputeLibrary-ed4b8a07e67c7802207c8954a88ad7a91aec79e0.tar.gz | |
Fix MeanStdDevNormalizationLayer reference outputting nan for FP16
- Bring the epsilon up to 1e-3 for FP16 (both backends) since it was causing the reference's variance being negative and its square root being NaN
- Bring the epsilon up to 1e-7 for FP16 NEON test for the same problem on the NEON kernel
- Adjust the CL kernel's vec_size when input tensor's width < 16 and use macros agnostic of vector size for sum reduction
- Add previously mismatching tensor shapes
Resolve COMPMID-4354
Change-Id: I823c871aacb72326f90c86b24cb16c3e2d4bd15e
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5630
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp')
0 files changed, 0 insertions, 0 deletions