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
|
/*
* Copyright (c) 2017 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_CLSOFTMAXLAYER_H__
#define __ARM_COMPUTE_CLSOFTMAXLAYER_H__
#include "arm_compute/core/CL/kernels/CLSoftmaxLayerKernel.h"
#include "arm_compute/runtime/CL/CLTensor.h"
#include "arm_compute/runtime/IFunction.h"
namespace arm_compute
{
class ICLTensor;
/** Basic function to compute a SoftmaxLayer.
*
* Softmax is calculated by :
* @f[ out = exp(x - max(x)) / sum(exp(x - max(x))) @f]
*
* This function runs the following kernels:
* -# @ref CLLogits1DMaxKernel
* -# @ref CLLogits1DShiftExpSumKernel
* -# @ref CLLogits1DNormKernel
*/
class CLSoftmaxLayer : public IFunction
{
public:
/** Constructor */
CLSoftmaxLayer();
/** Set the input and output tensors.
*
* @param[in] input Source tensor. Data types supported: F16, F32. Number of channels must be 1.
* @param[out] output Destination tensor. Matching input type and channel number.
*/
void configure(const ICLTensor *input, ICLTensor *output);
// Inherited methods overridden:
void run() override;
private:
CLLogits1DMaxKernel _max_kernel;
CLLogits1DShiftExpSumKernel _shift_exp_sum_kernel;
CLLogits1DNormKernel _norm_kernel;
CLTensor _max;
CLTensor _sum;
CLTensor _tmp;
};
}
#endif /* __ARM_COMPUTE_CLSOFTMAXLAYER_H__ */
|
