COMPMID-906: Use fused activation in NEON Batch normalization

Change-Id: I5a6413548b2c9b8972c91ddba57395509dffd87e
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120656
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
diff --git a/arm_compute/core/NEON/wrapper/intrinsics/load.h b/arm_compute/core/NEON/wrapper/intrinsics/load.h
index 9629f2b..442d857 100644
--- a/arm_compute/core/NEON/wrapper/intrinsics/load.h
+++ b/arm_compute/core/NEON/wrapper/intrinsics/load.h
@@ -24,8 +24,6 @@
 #ifndef __ARM_COMPUTE_WRAPPER_LOAD_H__
 #define __ARM_COMPUTE_WRAPPER_LOAD_H__
 
-#include "arm_compute/core/NEON/wrapper/traits.h"
-
 #include <arm_neon.h>
 
 namespace arm_compute
@@ -63,6 +61,8 @@
 //VLOAD_IMPL(uint64_t, uint64x1_t, u64)
 //VLOAD_IMPL(int64_t, int64x1_t, s64)
 VLOADQ_IMPL(float, float32x4_t, f32)
-}
-}
+
+#undef VLOAD_IMPL
+} // namespace wrapper
+} // namespace arm_compute
 #endif /* __ARM_COMPUTE_WRAPPER_LOAD_H__ */