From: kevmay01 <kevin.may@arm.com>
Date: Mon, 17 Dec 2018 15:32:45 +0000 (+0000)
Subject: IVGCVSW-2399 Margin of error too severe for ValidateBiasTensorQuantisation
X-Git-Tag: submit/tizen/20200316.035456~992
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=6c46dd3e126410e7abff1cb4b2a8e1f753a3ca47;p=platform%2Fupstream%2Farmnn.git

IVGCVSW-2399 Margin of error too severe for ValidateBiasTensorQuantisation

Change-Id: I56f56398e7c2c2ac57a96952237e7f1bc0ced208
---

diff --git a/src/backends/backendsCommon/WorkloadData.cpp b/src/backends/backendsCommon/WorkloadData.cpp
index bc25415..47d5364 100644
--- a/src/backends/backendsCommon/WorkloadData.cpp
+++ b/src/backends/backendsCommon/WorkloadData.cpp
@@ -153,7 +153,7 @@ void ValidateBiasTensorQuantization(const TensorInfo& biasTensor, const TensorIn
             to_string(biasTensor.GetQuantizationOffset()));
     }
     const float expectedScale = inputTensorInfo.GetQuantizationScale() * weightsTensorInfo.GetQuantizationScale();
-    if (std::abs(biasTensor.GetQuantizationScale() - expectedScale) > 0.000000001f)
+    if (std::abs(biasTensor.GetQuantizationScale() - expectedScale) > 0.00000001f)
     {
         // Print the float values with extra precision to see very small differences
         std::stringstream msg;