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
|
/*
* Copyright (c) 2016-2021 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_CPU_SCALEKERNEL_H
#define ARM_COMPUTE_CPU_SCALEKERNEL_H
#include "arm_compute/core/KernelDescriptors.h"
#include "src/core/common/Macros.h"
#include "src/core/cpu/ICpuKernel.h"
namespace arm_compute
{
namespace cpu
{
namespace kernels
{
/** Arm(R) Neon(TM) kernel to perform scaling on a tensor */
class CpuScaleKernel : public ICpuKernel
{
public:
/** Default constructor */
CpuScaleKernel();
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuScaleKernel);
/** Initialise the kernel's inputs, output and interpolation policy
*
* @note dx, dy and offsets have the same dimensions (width and height) of the output tensor
* @note Using @p policy Area only supports data layout NCHW and input data type U8.
*
* @param[in] src Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/U8/S16/F16/F32.
* @param[in] dx Distance x tensor info. Pixel's distance between the X real coordinate and the smallest X following integer. Data type supported: F32
* @param[in] dy Distance y tensor info. Pixel's distance between the Y real coordinate and the smallest Y following integer. Data type supported: F32
* @param[in] offsets Offset tensor info. Offset to access the pixel with NEAREST interpolation or the top-left pixel with BILINEAR interpolation in the input tensor. Data type supported: S32.
* @param[out] dst Destination tensor info. Data types supported: Same as @p input. All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
* @param[in] info @ref ScaleKernelInfo to use for configuration
*/
void configure(const ITensorInfo *src, const ITensorInfo *dx, const ITensorInfo *dy, const ITensorInfo *offsets, ITensorInfo *dst,
const ScaleKernelInfo &info);
/** Static function to check if given info will lead to a valid configuration of @ref CpuScaleKernel
*
* @note dx, dy and offsets have the same dimensions (width and height) of the output tensor
* @note Using @p policy Area only supports data layout NCHW and input data type U8.
*
* @param[in] src Source tensor. Data types supported: QASYMM8/QASYMM8_SIGNED/U8/S16/F16/F32.
* @param[in] dx Distance x tensor info. Pixel's distance between the X real coordinate and the smallest X following integer. Data type supported: F32
* @param[in] dy Distance y tensor info. Pixel's distance between the Y real coordinate and the smallest Y following integer. Data type supported: F32
* @param[in] offsets Offset tensor info. Offset to access the pixel with NEAREST interpolation or the top-left pixel with BILINEAR interpolation in the input tensor. Data type supported: S32.
* @param[in] dst Destination tensor info. Data types supported: Same as @p input. All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
* @param[in] info @ref ScaleKernelInfo to use for validation
*/
static Status validate(const ITensorInfo *src, const ITensorInfo *dx, const ITensorInfo *dy, const ITensorInfo *offsets, ITensorInfo *dst,
const ScaleKernelInfo &info);
// Inherited methods overridden:
void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override;
const char *name() const override;
private:
#ifdef ENABLE_NCHW_KERNELS
/** function to perform scale using area interpolation on the given window
*
* @note Used only in case down-sampling.
*/
void scale_area_nchw_u8(const ITensor *src, ITensor *dst, const ITensor *dx, const ITensor *dy, const ITensor *offsets, const Window &window);
/** function to perform scale using bilinear interpolation on the given window */
template <typename T>
void scale_bilinear_nchw(const ITensor *src, ITensor *dst, const ITensor *dx, const ITensor *dy, const ITensor *offsets, const Window &window);
/** function to perform scale using bilinear interpolation on the given window */
template <typename T>
void scale_bilinear_qasymm(const ITensor *src, ITensor *dst, const ITensor *dx, const ITensor *dy, const ITensor *offsets, const Window &window);
/** function to perform scale using nearest neighbour on the given window */
template <typename T>
void scale_nearest_nchw(const ITensor *src, ITensor *dst, const ITensor *dx, const ITensor *dy, const ITensor *offsets, const Window &window);
#endif // ENABLE_NCHW_KERNELS
/** Scale function to use for the particular function to use */
using ScaleFunctionPtr = void (CpuScaleKernel::*)(const ITensor *, ITensor *, const ITensor *, const ITensor *, const ITensor *, const Window &window);
ScaleFunctionPtr _func;
InterpolationPolicy _policy;
BorderMode _border_mode;
PixelValue _constant_border_value;
float _sampling_offset;
bool _align_corners;
DataLayout _data_layout;
};
} // namespace kernels
} // namespace cpu
} // namespace arm_compute
#endif /*ARM_COMPUTE_CPU_SCALEKERNEL_H */
|
