diff options
author | Michalis Spyrou <michalis.spyrou@arm.com> | 2017-12-20 15:50:55 +0000 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:42:33 +0000 |
commit | b91e34c9837756c9ee45917e13fb6a6cb901f795 (patch) | |
tree | 6f5dd4c2ec527f2a188ac940a081206810ec4d44 /arm_compute/core/NEON/NEKernels.h | |
parent | aa1209a1bfc9fa24a24c1b47d309e27ba2cd90a7 (diff) | |
download | ComputeLibrary-b91e34c9837756c9ee45917e13fb6a6cb901f795.tar.gz |
COMPMID-746 Allow NEDirectConvolution to work without biases for QS.
Renamed BiasAccumulateKernel to OutputStage. If no bias is provided
when the input is quantized, the kernel simply downscales the input.
Throw error if no bias is provided and input is floating point.
Change-Id: I645a4ee9c6014b0547778fdd92c9ec72ef2f0aab
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114158
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/NEKernels.h')
-rw-r--r-- | arm_compute/core/NEON/NEKernels.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arm_compute/core/NEON/NEKernels.h b/arm_compute/core/NEON/NEKernels.h index 6c31fa4fb1..8a4cf7abeb 100644 --- a/arm_compute/core/NEON/NEKernels.h +++ b/arm_compute/core/NEON/NEKernels.h @@ -53,8 +53,8 @@ #include "arm_compute/core/NEON/kernels/NEDequantizationLayerKernel.h" #include "arm_compute/core/NEON/kernels/NEDerivativeKernel.h" #include "arm_compute/core/NEON/kernels/NEDilateKernel.h" -#include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerBiasAccumulateKernel.h" #include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerKernel.h" +#include "arm_compute/core/NEON/kernels/NEDirectConvolutionLayerOutputStageKernel.h" #include "arm_compute/core/NEON/kernels/NEErodeKernel.h" #include "arm_compute/core/NEON/kernels/NEFastCornersKernel.h" #include "arm_compute/core/NEON/kernels/NEFillArrayKernel.h" |