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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
|
/*
* Copyright (c) 2017-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef ARM_COMPUTE_NEGEMMCONVOLUTIONLAYER_H
#define ARM_COMPUTE_NEGEMMCONVOLUTIONLAYER_H
#include "arm_compute/runtime/IFunction.h"
#include "arm_compute/core/Types.h"
#include "arm_compute/runtime/IFunction.h"
#include "arm_compute/runtime/IMemoryManager.h"
#include "arm_compute/runtime/IWeightsManager.h"
#include "arm_compute/runtime/MemoryGroup.h"
#include <memory>
namespace arm_compute
{
class ITensor;
class ITensorInfo;
/** Basic function to compute the convolution layer. This function calls the following kernels/functions:
*
* -# @ref cpu::CpuGemmConv2d
*
*/
class NEGEMMConvolutionLayer : public IFunction
{
public:
/** Constructor */
NEGEMMConvolutionLayer(const std::shared_ptr<IMemoryManager> &memory_manager = nullptr, IWeightsManager *weights_manager = nullptr);
/** Prevent instances of this class from being copied (As this class contains pointers) */
NEGEMMConvolutionLayer(const NEGEMMConvolutionLayer &) = delete;
/** Prevent instances of this class from being moved (As this class contains non movable objects) */
NEGEMMConvolutionLayer(NEGEMMConvolutionLayer &&) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers) */
NEGEMMConvolutionLayer &operator=(const NEGEMMConvolutionLayer &) = delete;
/** Prevent instances of this class from being moved (As this class contains non movable objects) */
NEGEMMConvolutionLayer &operator=(NEGEMMConvolutionLayer &&) = delete;
/** Default destructor */
~NEGEMMConvolutionLayer();
/** Set the input and output tensors.
*
* Valid data layouts:
* - NHWC
* - NCHW
*
* Valid data type configurations:
* |src0 |src1 |src2 |dst |
* |:--------------|:------------------|:--------|:--------------|
* |F16 |F16 |F16 |F16 |
* |F32 |F32 |F32 |F32 |
* |BFLOAT16 |BFLOAT16 |BFLOAT16 |BFLOAT16 |
* |QASYMM8 |QASYMM8 |S32 |QASYMM8 |
* |QASYMM8 |QSYMM8_PER_CHANNEL |S32 |QASYMM8 |
* |QASYMM8_SIGNED |QASYMM8_SIGNED |S32 |QASYMM8_SIGNED |
* |QASYMM8_SIGNED |QSYMM8_PER_CHANNEL |S32 |QASYMM8_SIGNED |
*
* @param[in] input Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
* while every optional dimension from 4 and above represent a batch of inputs.
* Data types supported: QASYMM8/QASYMM8_SIGNED/BFLOAT16/F16/F32.
* @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
* Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32.
* @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
* Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type.
* @param[out] output Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
* Data types supported: Same as @p input.
* @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo.
* @param[in] weights_info Specifies if the weights tensor has been reshaped with NEWeightsReshapeKernel. If this is not part of the fully connected layer the weights
* tensor has also been transposed with cpu::kernels::CpuGemmTranspose1xWKernel. Data type supported: Same as @p input.
* @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
* @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.
* @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
* available which may introduce a drop of accuracy as well. Default is false
* @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is not supported
*/
void configure(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output, const PadStrideInfo &conv_info, const WeightsInfo &weights_info = WeightsInfo(),
const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false, unsigned int num_groups = 1);
/** Static function to check if given info will lead to a valid configuration of @ref NEGEMMConvolutionLayer
*
* @param[in] input Source tensor info. 3 lower dimensions represent a single input [width, height, IFM],
* while every optional dimension from 4 and above represent a batch of inputs.
* Data types supported: QASYMM8/QASYMM8_SIGNED/BFLOAT16/F16/F32.
* @param[in] weights Weights tensor info. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
* Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32.
* @param[in] biases Biases tensor info. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
* Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type.
* @param[in] output Destination tensor info. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
* Data types supported: Same as @p input.
* @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo.
* @param[in] weights_info Specifies if the weights tensor has been reshaped with NEWeightsReshapeKernel. If this is not part of the fully connected layer the weights
* tensor has also been transposed with cpu::kernels::CpuGemmTranspose1xWKernel. Data type supported: Same as @p input.
* @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
* @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.
* @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
* available which may introduce a drop of accuracy as well. Default is false
* @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is not supported
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info,
const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(),
bool enable_fast_math = false, unsigned int num_groups = 1);
// Inherited methods overridden:
void run() override;
void prepare() override;
private:
struct Impl;
std::unique_ptr<Impl> _impl;
};
} // namespace arm_compute
#endif /* ARM_COMPUTE_NEGEMMCONVOLUTIONLAYER_H */
|
