diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-07-22 12:11:20 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-07-24 13:36:11 +0000 |
| commit | 09cad7253cc75f67bf428ceef196cfbec7f8c357 (patch) | |
| tree | c60bd15e82c1e01fa688bfb8ddb426fc7be419c9 /arm_compute/runtime/NEON/functions/NEConcatenateLayer.h | |
| parent | 318c9f40770b2d1c06f8c0fe3f7929812503733e (diff) | |
| download | ComputeLibrary-09cad7253cc75f67bf428ceef196cfbec7f8c357.tar.gz | |
COMPMID-3393: Minor tweaks on memory injection interface
* Avoid the need to overload workspace() everytime
* Remove the Layer suffix from the operators
* Clean interface by removing default arguments when unsupported
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I7710ecd485cae13e9c2d45216debbd8103bc5a0f
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3610
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEConcatenateLayer.h')
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NEConcatenateLayer.h | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEConcatenateLayer.h b/arm_compute/runtime/NEON/functions/NEConcatenateLayer.h index 02c27e20e6..73c62330c5 100644 --- a/arm_compute/runtime/NEON/functions/NEConcatenateLayer.h +++ b/arm_compute/runtime/NEON/functions/NEConcatenateLayer.h @@ -103,11 +103,11 @@ namespace experimental * -# @ref NEDepthConcatenateLayerKernel (if underlying concatenation axis is 2). * -# @ref NEBatchConcatenateLayerKernel (if underlying concatenation axis is 3). */ -class NEConcatenateLayer : public INEOperator +class NEConcatenation : public INEOperator { public: /** Default constructor */ - NEConcatenateLayer(); + NEConcatenation(); /** Initialise the kernel's inputs vector and output. * * @note Input and output tensor dimensions preconditions defer depending on the concatenation axis. @@ -132,7 +132,6 @@ public: static Status validate(const std::vector<const ITensorInfo *> &inputs_vector, const ITensorInfo *output, size_t axis); // Inherited methods overridden: - MemoryRequirements workspace() const override; void run(InputTensorMap inputs, OutputTensorMap outputs, OperatorTensorMap workspace) override; private: |