summaryrefslogtreecommitdiff
path: root/compute/ARMComputeEx/arm_compute/runtime/CL/functions/CLTransposeConvLayer.h
blob: 5fb102e478880c45556291e04cdf6a3966f5f6e8 (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
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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
/*
 * 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.
 */

/*
 * Copyright (c) 2017-2020 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_CLTRANSPOSECONVLAYER_H__
#define __ARM_COMPUTE_CLTRANSPOSECONVLAYER_H__

#include "arm_compute/runtime/CL/functions/CLDirectTransposeConvLayer.h"
#include "arm_compute/runtime/CL/functions/CLGEMMDeconvolutionLayer.h"
#include "arm_compute/runtime/IFunction.h"
#include "arm_compute/runtime/IMemoryManager.h"

#include <memory>

namespace arm_compute
{
/** Basic function to compute the deconvolution layer. This function calls the following OpenCL
 * kernels/functions:
 *
 * -# @ref CLGEMMDeconvolutionLayer
 * -# @ref CLDirectTransposeConvLayer
 */
class CLTransposeConvLayer : public IFunction
{
public:
  /** Default constructor */
  CLTransposeConvLayer(std::shared_ptr<IMemoryManager> memory_manager = nullptr);

  /** Set the input, weights, biases and output tensors.
   *
   * @param[in,out] input        Input tensor. 3 lower dimensions represent a single input, and an
 * optional 4th dimension for batch of inputs. Data types supported: QASYMM8_SIGNED/QASYMM8/F16/F32.
   * @param[in]     weights      The 4d weights with dimensions [width, height, IFM, OFM]. Data type
 * supported: Same as @p input.
   * @param[in]     bias         (Optional) The biases have one dimension. Data type supported: Same
 * as @p input.
   * @param[out]    output       Output tensor. The output has the same number of dimensions as the
 * @p input.
   * @param[in]     deconv_info  Contains padding and policies to be used in the deconvolution, this
 * is described in @ref PadStrideInfo.
 * @param[in] invalid_right  The number of zeros added to right edge of the output.
 * @param[in] invalid_bottom  The number of zeros added to bottom edge of the output.
   * @param[in]     weights_info (Optional) Weights information needed for @ref CLConvolutionLayer,
 * specifies if the weights tensor has been reshaped with @ref CLWeightsReshapeKernel.
   *
   */
  void configure(ICLTensor *input, ICLTensor *weights, const ICLTensor *bias, ICLTensor *output,
                 const PadStrideInfo &deconv_info, unsigned int invalid_right,
                 unsigned int invalid_bottom, const WeightsInfo &weights_info = WeightsInfo());
  /** Set the input, weights, biases and output tensors.
   *
   * @param[in]     compile_context The compile context to be used.
   * @param[in,out] input           Input tensor. 3 lower dimensions represent a single input, and
 * an optional 4th dimension for batch of inputs. Data types supported:
 * QASYMM8_SIGNED/QASYMM8/F16/F32.
   * @param[in]     weights         The 4d weights with dimensions [width, height, IFM, OFM]. Data
 * type supported: Same as @p input.
   * @param[in]     bias            (Optional) The biases have one dimension. Data type supported:
 * Same as @p input.
   * @param[out]    output          Output tensor. The output has the same number of dimensions as
 * the @p input.
   * @param[in]     deconv_info     Contains padding and policies to be used in the deconvolution,
 * this is described in @ref PadStrideInfo.
 * @param[in] invalid_right  The number of zeros added to right edge of the output.
 * @param[in] invalid_bottom  The number of zeros added to bottom edge of the output.
   * @param[in]     weights_info    (Optional) Weights information needed for @ref
 * CLConvolutionLayer, specifies if the weights tensor has been reshaped with @ref
 * CLWeightsReshapeKernel.
   *
   */
  void configure(const CLCompileContext &compile_context, ICLTensor *input, ICLTensor *weights,
                 const ICLTensor *bias, ICLTensor *output, const PadStrideInfo &deconv_info,
                 unsigned int invalid_right, unsigned int invalid_bottom,
                 const WeightsInfo &weights_info = WeightsInfo());
  /** Static function to check if given info will lead to a valid configuration of @ref
 * CLTransposeConvLayer
   *
   * @param[in] input        Input tensor info. 3 lower dimensions represent a single input, and an
 * optional 4th dimension for batch of inputs. Data types supported: QASYMM8_SIGNED/QASYMM8/F16/F32.
   * @param[in] weights      The 4d weights info with dimensions [width, height, IFM, OFM]. Data
 * type supported: Same as @p input.
   * @param[in] bias         (Optional) The biases have one dimension. Data type supported: Same as
 * @p input.
   * @param[in] output       Output tensor info. The output has the same number of dimensions as the
 * @p input.
   * @param[in] deconv_info  Contains padding and policies to be used in the deconvolution, this is
 * described in @ref PadStrideInfo.
 * @param[in] invalid_right  The number of zeros added to right edge of the output.
 * @param[in] invalid_bottom  The number of zeros added to bottom edge of the output.
   * @param[in] weights_info (Optional) Weights information needed for @ref CLConvolutionLayer,
 * specifies if the weights tensor has been reshaped with @ref CLWeightsReshapeKernel.
   *
   * @return a status
   */
  static Status validate(const ITensorInfo *input, const ITensorInfo *weights,
                         const ITensorInfo *bias, ITensorInfo *output,
                         const PadStrideInfo &deconv_info, unsigned int invalid_right,
                         unsigned int invalid_bottom,
                         const WeightsInfo &weights_info = WeightsInfo());

  static DeconvolutionMethod
  get_deconvolution_method(const ITensorInfo *input, const ITensorInfo *weights,
                           const ITensorInfo *bias, ITensorInfo *output,
                           const PadStrideInfo &deconv_info, unsigned int invalid_right,
                           unsigned int invalid_bottom, const WeightsInfo &weights_info);
  // Inherited methods overridden:
  void run() override;
  void prepare() override;

private:
  std::shared_ptr<IMemoryManager> _memory_manager;
  std::unique_ptr<IFunction> _function;
};
} // namespace arm_compute
#endif /* __ARM_COMPUTE_CLTRANSPOSECONVLAYER_H__ */