diff options
| author | Mike Kelly <mike.kelly@arm.com> | 2021-04-06 12:25:55 +0100 |
|---|---|---|
| committer | Matthew Sloyan <matthew.sloyan@arm.com> | 2021-04-09 12:38:48 +0100 |
| commit | 1f140f7226c4ed7bc5cbaf2ce09654eee452f4bf (patch) | |
| tree | 044d491d429b6da4d85530afd4ea2a310cdbb827 /src/armnn | |
| parent | 7c67fabc86b6647855beebac9f6cfe92341357cb (diff) | |
| download | armnn-1f140f7226c4ed7bc5cbaf2ce09654eee452f4bf.tar.gz | |
MLCE-328 Serializer/Deserializer does not support Signed64
* Added support for Signed64 to flatbuffer's schema & updated source tree
* Added support for Signed64 to TFLite Delegate
* Added support for Signed64 to Serializer
* Added support for Signed64 to Deserializer
* Added unit test for ArgMinMax to Deserializer
* Deprecated m_Output_Type from the ArgMinMaxDescriptor: the output type
is solely determined by the DataType of the output Tensor
* Fixed issue where RefArgMinMaxWorkload could output data using
the wrong DataType
* Added Signed64 to RefLayerSupport::IsArgMinMaxSupported as a supported
type
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib622c052a1f8aa3e658262f8bde5a6881a8cbe10
Diffstat (limited to 'src/armnn')
| -rw-r--r-- | src/armnn/ResolveType.hpp | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/src/armnn/ResolveType.hpp b/src/armnn/ResolveType.hpp index e1bea42d3c..5355091169 100644 --- a/src/armnn/ResolveType.hpp +++ b/src/armnn/ResolveType.hpp @@ -1,5 +1,5 @@ // -// Copyright © 2017 Arm Ltd. All rights reserved. +// Copyright © 2017 Arm Ltd and Contributors. All rights reserved. // SPDX-License-Identifier: MIT // @@ -58,6 +58,12 @@ struct ResolveTypeImpl<DataType::Signed32> }; template<> +struct ResolveTypeImpl<DataType::Signed64> +{ + using Type = int64_t; +}; + +template<> struct ResolveTypeImpl<DataType::Boolean> { using Type = uint8_t; |