diff options
| author | Cathal Corbett <cathal.corbett@arm.com> | 2022-05-13 09:55:59 +0100 |
|---|---|---|
| committer | Cathal Corbett <cathal.corbett@arm.com> | 2022-05-13 15:09:18 +0000 |
| commit | 4452baf3d295164877c5810a3867b1d2d79b04f3 (patch) | |
| tree | 861b248dd0a603140eb384e48cd9ef97603a296b /src/backends/neon/workloads/NeonFullyConnectedWorkload.hpp | |
| parent | c46b90ef031a8041fe25a7191de799eca9eff8e5 (diff) | |
| download | armnn-4452baf3d295164877c5810a3867b1d2d79b04f3.tar.gz | |
IVGCVSW-6260 ConstTensorsAsInput: Fully Connected Cl and Neon support.
* IVGCVSW-6940 ConstTensorsAsInput: DepthwiseConvolution2d - Complete Neon and Cl Bug Fix
* Bug fix to enable Cl and Neon Backend Compatibility ConstantTensorsAsInputs
* Updated Cl and Neon FullyConnected workloads to handle constant
weights and bias as inputs rather than reading from member variables.
* Prevent non const weights and biases passing CL and NEON validate
for Depthwise Convolution.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I0f505ff5998a183152f843d0f6cc74327ba920e7
Diffstat (limited to 'src/backends/neon/workloads/NeonFullyConnectedWorkload.hpp')
| -rw-r--r-- | src/backends/neon/workloads/NeonFullyConnectedWorkload.hpp | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/src/backends/neon/workloads/NeonFullyConnectedWorkload.hpp b/src/backends/neon/workloads/NeonFullyConnectedWorkload.hpp index 419a3299f2..944731d7bd 100644 --- a/src/backends/neon/workloads/NeonFullyConnectedWorkload.hpp +++ b/src/backends/neon/workloads/NeonFullyConnectedWorkload.hpp @@ -33,11 +33,9 @@ public: private: std::unique_ptr<arm_compute::IFunction> m_FullyConnectedLayer; - std::unique_ptr<arm_compute::Tensor> m_WeightsTensor; std::unique_ptr<arm_compute::Tensor> m_BiasesTensor; - void FreeUnusedTensors(); }; } //namespace armnn |