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
|
/*
* Copyright (c) 2017-2019 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_NELOCALLYCONNECTEDLAYER_H
#define ARM_COMPUTE_NELOCALLYCONNECTEDLAYER_H
#include "arm_compute/runtime/IFunction.h"
#include "arm_compute/core/NEON/kernels/NECol2ImKernel.h"
#include "arm_compute/core/NEON/kernels/NEIm2ColKernel.h"
#include "arm_compute/core/NEON/kernels/NELocallyConnectedMatrixMultiplyKernel.h"
#include "arm_compute/core/NEON/kernels/NEWeightsReshapeKernel.h"
#include "arm_compute/core/Types.h"
#include "arm_compute/runtime/IMemoryManager.h"
#include "arm_compute/runtime/MemoryGroup.h"
#include "arm_compute/runtime/Tensor.h"
#include <memory>
namespace arm_compute
{
class INETensor;
/** Basic function to compute the locally connected layer. This function calls the following NEON kernels:
*
* -# @ref NEWeightsReshapeKernel (executed only once for each configuration)
* -# @ref NEIm2ColKernel
* -# @ref NELocallyConnectedMatrixMultiplyKernel
* -# @ref NECol2ImKernel
*/
class NELocallyConnectedLayer : public IFunction
{
public:
/** Default constructor */
NELocallyConnectedLayer(std::shared_ptr<IMemoryManager> memory_manager = nullptr);
/** Prevent instances of this class from being copied (As this class contains pointers) */
NELocallyConnectedLayer(const NELocallyConnectedLayer &) = delete;
/** Default move constructor */
NELocallyConnectedLayer(NELocallyConnectedLayer &&) = default;
/** Prevent instances of this class from being copied (As this class contains pointers) */
NELocallyConnectedLayer &operator=(const NELocallyConnectedLayer &) = delete;
/** Default move assignment operator */
NELocallyConnectedLayer &operator=(NELocallyConnectedLayer &&) = default;
/** Set the input and output tensors.
*
* @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: F16, F32.
* @param[in] weights Weights tensor. Weights are 5D tensor with dimensions [kernel_x, kernel_y, IFM, OFM, num_patches]. Data type supported:Same as @p input.
* @param[in] biases Biases tensor. Shared biases supported. Biases are 2D tensor with dimensions [OFM, num_patches]. Data type supported:Same as @p input.
* @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.
*/
void configure(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output, const PadStrideInfo &conv_info);
/** Static function to check if given info will lead to a valid configuration of @ref NELocallyConnectedLayer
*
* @param[in] input Input 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: F16, F32.
* @param[in] weights Weights tensor info. Weights are 5D tensor with dimensions [kernel_x, kernel_y, IFM, OFM, num_patches]. Data type supported:Same as @p input.
* @param[in] biases Biases tensor info. Shared biases supported. Biases are 2D tensor with dimensions [OFM, num_patches]. Data type supported:Same as @p input.
* @param[in] output Output 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.
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info);
// Inherited methods overridden:
void run() override;
void prepare() override;
private:
MemoryGroup _memory_group;
NEIm2ColKernel _input_im2col_kernel;
NEWeightsReshapeKernel _weights_reshape_kernel;
NELocallyConnectedMatrixMultiplyKernel _mm_kernel;
NECol2ImKernel _output_col2im_kernel;
Tensor _input_im2col_reshaped;
Tensor _weights_reshaped;
Tensor _gemm_output;
bool _is_prepared;
const ITensor *_original_weights;
};
}
#endif /* ARM_COMPUTE_NELOCALLYCONNECTEDLAYER_H */
|
