Add an option to use lowest for max-pooling
- Add a parameter in PoolingLayerInfo class to pick which value to use as min for max-pooling.
Resolves: [ONCPUML-1166]
Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com>
Change-Id: I34e1cccc15176bbf31523c61e99f3188ddca23e1
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8989
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/tests/validation/reference/PoolingLayer.cpp b/tests/validation/reference/PoolingLayer.cpp
index 378d91d..6a358ce 100644
--- a/tests/validation/reference/PoolingLayer.cpp
+++ b/tests/validation/reference/PoolingLayer.cpp
@@ -87,7 +87,7 @@
int hend = std::min(hstart + pool_size_y, h_src);
wstart = std::max(wstart, 0);
hstart = std::max(hstart, 0);
- auto max_val = -std::numeric_limits<ACC_T>::infinity();
+ auto max_val = info.use_inf_as_limit ? -std::numeric_limits<ACC_T>::infinity() : std::numeric_limits<ACC_T>::lowest();
int max_index{ 0 };
for(int y = hstart; y < hend; ++y)
{