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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
|
/*
* Copyright (c) 2019 Samsung Electronics Co., Ltd. All Rights Reserved
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#ifndef __ONERT_KERNEL_CPU_DEPTHWISECONVOLUTIONLAYER_H__
#define __ONERT_KERNEL_CPU_DEPTHWISECONVOLUTIONLAYER_H__
#include <backend/IPortableTensor.h>
#include "OperationUtils.h"
#include "../ExternalContext.h"
#include <exec/IFunction.h>
namespace onert
{
namespace backend
{
namespace cpu
{
namespace ops
{
class DepthwiseConvolutionLayer : public ::onert::exec::IFunction
{
public:
DepthwiseConvolutionLayer() = default;
public:
void convFloat32();
void convQ8uPerTensor();
void convQ8uPerChannel();
void convQ8i();
void configure(const IPortableTensor *input, const IPortableTensor *kernel,
const IPortableTensor *bias, const uint32_t paddingLeft,
const uint32_t paddingRight, const uint32_t paddingTop,
const uint32_t paddingBottom, const uint32_t strideW, const uint32_t strideH,
const uint32_t multiplier, const uint32_t dilationWidth,
const uint32_t dilationHeight, const ir::Activation activation,
IPortableTensor *output, const std::shared_ptr<ExternalContext> &external_context);
void run() override;
private:
void prepareQ8i();
void prepareQ8uPerChannel();
private:
const IPortableTensor *_input{nullptr};
const IPortableTensor *_kernel{nullptr};
const IPortableTensor *_bias{nullptr};
IPortableTensor *_output{nullptr};
uint32_t _paddingLeft{0};
uint32_t _paddingTop{0};
uint32_t _paddingRight{0};
uint32_t _paddingBottom{0};
uint32_t _strideWidth{0};
uint32_t _strideHeight{0};
uint32_t _multiplier{0};
uint32_t _dilationWidth{1};
uint32_t _dilationHeight{1};
ir::Activation _activation{ir::Activation::NONE};
std::shared_ptr<ExternalContext> _external_context;
bool _prepared{false};
// Per channel output multiplier and shift.
std::vector<int32_t> _per_channel_output_multiplier;
std::vector<int> _per_channel_output_shift;
};
} // namespace ops
} // namespace cpu
} // namespace backend
} // namespace onert
#endif // __ONERT_KERNEL_CPU_DEPTHWISECONVOLUTIONLAYER_H__
|