diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2017-11-16 14:37:08 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:35:24 +0000 |
| commit | 41caa625231c24533a514606bbf2683f7d4964ad (patch) | |
| tree | 4e897dfbcc77d57c996f15bab014b20e4cb4868d /src/core/NEON/kernels/NENormalizationLayerKernel.cpp | |
| parent | 181e65145d153210ec5587a42d2938e27e1d5b01 (diff) | |
| download | ComputeLibrary-41caa625231c24533a514606bbf2683f7d4964ad.tar.gz | |
COMPMID-683: Normalization layer API clarification.
Adds a is_scaled parameter in the NormalizationLayerInfo that flags if
the alpha parameter should be scaled by the normalization size of not.
Unscaled parameter is used by [Krichevksy 2012] which is used in
AndroidNN and TensorFlow LRN layer.
Change-Id: Iad2aa5e688cf4dcd6cc77a6e28c0663764f34ccb
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/96102
Reviewed-by: Diego Lopez Recas <diego.lopezrecas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/NENormalizationLayerKernel.cpp')
| -rw-r--r-- | src/core/NEON/kernels/NENormalizationLayerKernel.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/core/NEON/kernels/NENormalizationLayerKernel.cpp b/src/core/NEON/kernels/NENormalizationLayerKernel.cpp index a409519114..b983609e49 100644 --- a/src/core/NEON/kernels/NENormalizationLayerKernel.cpp +++ b/src/core/NEON/kernels/NENormalizationLayerKernel.cpp @@ -61,7 +61,7 @@ void NENormalizationLayerKernel::configure(const ITensor *input, const ITensor * ARM_COMPUTE_ERROR_ON_VALUE_NOT_REPRESENTABLE_IN_FIXED_POINT(norm_info.scale_coeff(), input); } - const unsigned int border_width = (norm_info.type() == NormType::CROSS_MAP) ? 0 : std::min<unsigned int>(norm_info.norm_size() / 2, 3U); + const unsigned int border_width = (norm_info.is_cross_map()) ? 0 : std::min<unsigned int>(norm_info.norm_size() / 2, 3U); _input = input; _input_squared = input_squared; |