diff options
| author | Teresa Charlin <teresa.charlinreyes@arm.com> | 2023-04-03 19:57:00 +0100 |
|---|---|---|
| committer | Colm Donelan <colm.donelan@arm.com> | 2023-04-18 17:27:41 +0000 |
| commit | acb3ec51e51542d3011ed87842f87c2261abaaff (patch) | |
| tree | b1ed73756c1db4a8e71b18a5a8256f42bb49341b /include | |
| parent | 8294e96a2f0f4ad3f5cd261079a6f90eee40142c (diff) | |
| download | armnn-acb3ec51e51542d3011ed87842f87c2261abaaff.tar.gz | |
GitHub #719 Set quantization parameter scale to 1.0, instead of 0.0.
* Arm NN does not account for int8 or uint8 not quantized types, Tensorflow does.
Not quantized int8 and uint8 is the same as quantized int8 and uint8 with scale = 1.0 and offset= 0
Default offset/zero_point was already 0, this review sets the default scale to 1.0.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibc3eecc281de516c2cc706e17bde01c64ff9556e
Diffstat (limited to 'include')
| -rw-r--r-- | include/armnn/Tensor.hpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/include/armnn/Tensor.hpp b/include/armnn/Tensor.hpp index 46859c4887..1bbc19f2f1 100644 --- a/include/armnn/Tensor.hpp +++ b/include/armnn/Tensor.hpp @@ -1,5 +1,5 @@ // -// Copyright © 2017,2022 Arm Ltd and Contributors. All rights reserved. +// Copyright © 2017,2022-2023 Arm Ltd and Contributors. All rights reserved. // SPDX-License-Identifier: MIT // #pragma once @@ -157,14 +157,14 @@ public: TensorInfo(const TensorShape& shape, DataType dataType, - float quantizationScale = 0.0f, + float quantizationScale = 1.0f, int32_t quantizationOffset = 0, bool isConstant = false); TensorInfo(unsigned int numDimensions, const unsigned int* dimensionSizes, DataType dataType, - float quantizationScale = 0.0f, + float quantizationScale = 1.0f, int32_t quantizationOffset = 0, bool isConstant = false); |