summaryrefslogtreecommitdiff
path: root/libs/ARMComputeEx/arm_compute/runtime/NEON/functions/NENormalizationLayerEx.h
blob: fa7408ecd639de715a690aa462a3454b4b0c4bec (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
/*
 * Copyright (c) 2018 Samsung Electronics Co., Ltd. All Rights Reserved
 * Copyright (c) 2016-2018 ARM Limited.
 *
 * 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 __ARM_COMPUTE_NENORMALIZATIONLAYEREX_H__
#define __ARM_COMPUTE_NENORMALIZATIONLAYEREX_H__

#include "arm_compute/runtime/IFunction.h"

#include "arm_compute/core/NEON/kernels/NEFillBorderKernel.h"
#include "arm_compute/core/NEON/kernels/NENormalizationLayerExKernel.h"
#include "arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h"
#include "arm_compute/runtime/MemoryGroup.h"

namespace arm_compute
{
class ITensor;

/** Basic function to compute a normalization layer. This function calls the following NEON kernels:
 *
 * -# @ref NEPixelWiseMultiplicationKernel
 * -# @ref NEFillBorderKernel
 * -# @ref NENormalizationLayerKernelEx
 *
 */
class NENormalizationLayerEx : public IFunction
{
public:
  /** Default constructor */
  NENormalizationLayerEx(std::shared_ptr<IMemoryManager> memory_manager = nullptr);
  /** Set the input and output tensors.
   *
   * @param[in]  input     Source tensor. 3 lower dims represent a single input with dimensions
   * [width, height, IFM],
   *                       and an optional 4th dimension for batch of inputs. Data type supported:
   * F16/F32
   * @param[out] output    Destination with the same dimensions, data type and number of channels of
   * @p input
   * @param[in]  norm_info Normalization layer information like the normalization type,
   * normalization size and other parameters.
   */
  void configure(const ITensor *input, ITensor *output, const NormalizationLayerInfo &norm_info);
  /** Static function to check if given info will lead to a valid configuration of @ref
   * NENormalizationLayer
   *
   * @param[in] input     Source tensor. 3 lower dims represent a single input with dimensions
   * [width, height, IFM],
   *                      and an optional 4th dimension for batch of inputs. Data type supported:
   * F16/F32
   * @param[in] output    Destination with the same dimensions, data type and number of channels of
   * @p input
   * @param[in] norm_info Normalization layer information like the normalization type, normalization
   * size and other parameters.
   *
   * @return a status
   */
  static Status validate(const ITensorInfo *input, const ITensorInfo *output,
                         const NormalizationLayerInfo &norm_info);

  // Inherited methods overridden:
  void run() override;

private:
  MemoryGroup _memory_group;                        /**< Function memory group */
  NENormalizationLayerExKernel _norm_kernel;        /**< Normalization layer kernel */
  NEPixelWiseMultiplicationKernel _multiply_kernel; /**< Pixel multiplication kernel */
  NEFillBorderKernel _border_handler;               /**< Kernel to handle  borders */
  Tensor _input_squared; /**< The intermediate buffer which stores results of squaring input */
};
}
#endif /* __ARM_COMPUTE_NENORMALIZATIONLAYEREX_H__ */