diff options
| author | Mike Kelly <mike.kelly@arm.com> | 2023-01-03 16:29:44 +0000 |
|---|---|---|
| committer | mike.kelly <mike.kelly@arm.com> | 2023-01-05 11:48:13 +0000 |
| commit | 0506ef0a099f5ba564af5e110e6857a68f462080 (patch) | |
| tree | 2ff1a15e435c41916a7f93f14766456759dd20b1 /src/armnn/TypesUtils.cpp | |
| parent | 8b4a483e0e2fee508c23be2248ba0409789f1a74 (diff) | |
| download | armnn-0506ef0a099f5ba564af5e110e6857a68f462080.tar.gz | |
GitHub #543 Problem Parsing Mixed-Precision Model
* Fixed bug when converting Constants with Per-Axis Quantization
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ifbea23e60483746ec987da491dae96e74cb33af4
Diffstat (limited to 'src/armnn/TypesUtils.cpp')
| -rw-r--r-- | src/armnn/TypesUtils.cpp | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/src/armnn/TypesUtils.cpp b/src/armnn/TypesUtils.cpp index 4ba9ed19e1..74ac231bc9 100644 --- a/src/armnn/TypesUtils.cpp +++ b/src/armnn/TypesUtils.cpp @@ -81,4 +81,8 @@ float armnn::Dequantize<int16_t>(int16_t value, float scale, int32_t offset); /// Explicit specialization of Dequantize for int32_t template -float armnn::Dequantize<int32_t>(int32_t value, float scale, int32_t offset);
\ No newline at end of file +float armnn::Dequantize<int32_t>(int32_t value, float scale, int32_t offset); + +/// Explicit specialization of Dequantize for int64_t +template +float armnn::Dequantize<int64_t>(int64_t value, float scale, int32_t offset); |