blob: 45c646aa44d60961d77679990ee04a4b382f0370 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
|
//
// Copyright © 2017 Arm Ltd and Contributors. All rights reserved.
// SPDX-License-Identifier: MIT
//
#pragma once
#include "NeonBaseWorkload.hpp"
#include <arm_compute/runtime/IFunction.h>
#include <arm_compute/runtime/Tensor.h>
#include <memory>
namespace armnn
{
arm_compute::Status NeonDepthwiseConvolutionWorkloadValidate(const TensorInfo& input,
const TensorInfo& output,
const DepthwiseConvolution2dDescriptor& descriptor,
const TensorInfo& weights,
const Optional<TensorInfo>& biases,
const ActivationDescriptor* activationDescriptor
= nullptr);
class NeonDepthwiseConvolutionWorkload : public NeonBaseWorkload<DepthwiseConvolution2dQueueDescriptor>
{
public:
NeonDepthwiseConvolutionWorkload(const DepthwiseConvolution2dQueueDescriptor& descriptor,
const WorkloadInfo& info);
virtual void Execute() const override;
private:
mutable std::unique_ptr<arm_compute::IFunction> m_pDepthwiseConvolutionLayer;
std::unique_ptr<arm_compute::Tensor> m_KernelTensor;
std::unique_ptr<arm_compute::Tensor> m_BiasTensor;
void FreeUnusedTensors();
};
} // namespace armnn
|
