aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/GLES_COMPUTE/kernels/GCWeightsReshapeKernel.h
blob: bf535229ffe30e2343b7ef94e3630e406e4c1585 (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
/*
 * Copyright (c) 2017-2018 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_GCWEIGHTSRESHAPEKERNEL_H__
#define __ARM_COMPUTE_GCWEIGHTSRESHAPEKERNEL_H__

#include "arm_compute/core/GLES_COMPUTE/IGCKernel.h"

namespace arm_compute
{
/** GLES Compute kernel to perform reshaping on the weights used by convolution and locally connected layer
 *
 * Rearranges each 3-dimensional kernel to a single row leading to a matrix with linearized kernels.
 * In combination with the @ref GCIm2ColKernel can transform a convolution to a matrix multiplication.
 *
 * For example assuming a 3D weight kernel of 3x3 dimensions and depth of 2 we have:
 * @f[
 * \left( \begin{array}{ccc}
 * a000 & a001 & a002 \\
 * a010 & a011 & a012 \\
 * a020 & a021 & a022 \\
 * \end{array} \right)
 * \left( \begin{array}{ccc}
 * a100 & a101 & a102 \\
 * a110 & a111 & a112 \\
 * a120 & a121 & a122 \\
 * \end{array} \right)
 * \rightarrow
 * \left( \begin{array}{ccccccccc}
 * a000 & a001 & a002 & a010 & a011 & a012 & a020 & a021 & a022 & a100 & a101 & a102 & a110 & a111 & a112 & a120 & a121 & a122 \\
 * \end{array} \right)
 * @f]
 */
class GCWeightsReshapeKernel : public IGCKernel
{
public:
    /** Constructor.*/
    GCWeightsReshapeKernel();
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    GCWeightsReshapeKernel(const GCWeightsReshapeKernel &) = delete;
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    GCWeightsReshapeKernel &operator=(const GCWeightsReshapeKernel &) = delete;
    /** Allow instances of this class to be moved */
    GCWeightsReshapeKernel(GCWeightsReshapeKernel &&) = default;
    /** Allow instances of this class to be moved */
    GCWeightsReshapeKernel &operator=(GCWeightsReshapeKernel &&) = default;
    /** Default destructor */
    ~GCWeightsReshapeKernel() = default;

    /** Set the input and output of the kernel.
     *
     * @param[in]  input  The input tensor to convert. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] if shared,
     *                    and 5D tensor with dimensions [kernel_x, kernel_y, IFM, OFM,  batches] if unshared. Data types supported: F16, F32
     * @param[in]  biases The shared biases tensor to append.  Bias is 1D tensor with dimensions [OFM] if shared and 2D tensor with
     *                    dimensions [OFM, batches] if unshared. Data types supported: Same as @p input
     *                    @warning Appending biases to weights reshaped matrix is not supported for quantized asymmetric types.
     * @param[out] output The output tensor. Should be a 2D Tensor. Data types supported: Same as @p input
     */
    void configure(const IGCTensor *input, const IGCTensor *biases, IGCTensor *output);

    // Inherited methods overridden:
    void run(const Window &window) override;

private:
    const IGCTensor *_input;
    const IGCTensor *_biases;
    IGCTensor       *_output;
};
} // namespace arm_compute
#endif /*__ARM_COMPUTE_GCWEIGHTSRESHAPEKERNEL_H__ */