diff options
| author | Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> | 2019-11-26 14:04:54 +0000 |
|---|---|---|
| committer | Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> | 2019-11-26 15:00:28 +0000 |
| commit | 21fc28bb68d7a6232eea3a0e8cfd800d95346ea4 (patch) | |
| tree | 5eca96ac31e3f8c62da3ad7742834180a0f7eeac /src/backends/neon/workloads/NeonWorkloadUtils.hpp | |
| parent | 9b6d4246804d39e5b7570992d63e31a044442385 (diff) | |
| download | armnn-21fc28bb68d7a6232eea3a0e8cfd800d95346ea4.tar.gz | |
IVGCVSW-3866 Add support for per-channel QSymm8 Convolution2d to Neon backend
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: If7d366b2894050c53a651016165f34be1a2ce7a6
Diffstat (limited to 'src/backends/neon/workloads/NeonWorkloadUtils.hpp')
| -rw-r--r-- | src/backends/neon/workloads/NeonWorkloadUtils.hpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/src/backends/neon/workloads/NeonWorkloadUtils.hpp b/src/backends/neon/workloads/NeonWorkloadUtils.hpp index f63946ec07..e9edc8901e 100644 --- a/src/backends/neon/workloads/NeonWorkloadUtils.hpp +++ b/src/backends/neon/workloads/NeonWorkloadUtils.hpp @@ -46,6 +46,9 @@ inline void InitializeArmComputeTensorData(arm_compute::Tensor& tensor, case DataType::QuantisedAsymm8: CopyArmComputeTensorData(tensor, handle->GetConstTensor<uint8_t>()); break; + case DataType::QuantizedSymm8PerAxis: + CopyArmComputeTensorData(tensor, handle->GetConstTensor<int8_t>()); + break; case DataType::Signed32: CopyArmComputeTensorData(tensor, handle->GetConstTensor<int32_t>()); break; |