diff options
author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-02-19 15:55:01 +0000 |
---|---|---|
committer | Giuseppe Rossini <giuseppe.rossini@arm.com> | 2020-02-20 10:09:14 +0000 |
commit | d42c1f37be18e716dff7705d38e66222d975114c (patch) | |
tree | 1c0b623a271d8bbeffac64ba81f00d2ab0349989 /src/core/CL/kernels/CLPoolingLayerKernel.cpp | |
parent | 5979b217ee887c4442e1affa7dc4378a4a642b95 (diff) | |
download | ComputeLibrary-d42c1f37be18e716dff7705d38e66222d975114c.tar.gz |
COMPMID-3209: Failing VTS/NN Tests on CpuAcc for avg_pool_quant and mobilenet quant
Rounding-to-nearest is already taken into account by adding 0.5f to the
result, so no need to use vcvtnq.
Change-Id: I2ee78d0abd5d1fb2c7d3133c316cb48d59d2497b
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2751
Reviewed-by: James Conroy <james.conroy@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/kernels/CLPoolingLayerKernel.cpp')
0 files changed, 0 insertions, 0 deletions