tiny_dnn 1.0.0
A header only, dependency-free deep learning framework in C++11
Loading...
Searching...
No Matches
arithmetic_layer.h
1/*
2 Copyright (c) 2013, Taiga Nomi
3 All rights reserved.
4
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions are met:
7 * Redistributions of source code must retain the above copyright
8 notice, this list of conditions and the following disclaimer.
9 * Redistributions in binary form must reproduce the above copyright
10 notice, this list of conditions and the following disclaimer in the
11 documentation and/or other materials provided with the distribution.
12 * Neither the name of the <organization> nor the
13 names of its contributors may be used to endorse or promote products
14 derived from this software without specific prior written permission.
15
16 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
17 EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18 WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19 DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY
20 DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21 (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26*/
27#pragma once
28#include "tiny_dnn/util/util.h"
29#include "tiny_dnn/layers/layer.h"
30
31namespace tiny_dnn {
32
37public:
42 elementwise_add_layer(serial_size_t num_args, serial_size_t dim)
43 : layer(std::vector<vector_type>(num_args, vector_type::data), {vector_type::data}), num_args_(num_args), dim_(dim) {}
44
45 std::string layer_type() const override {
46 return "elementwise-add";
47 }
48
49 std::vector<shape3d> in_shape() const override {
50 return std::vector<shape3d>(num_args_, shape3d(dim_,1,1));
51 }
52
53 std::vector<shape3d> out_shape() const override {
54 return{ shape3d(dim_,1,1) };
55 }
56
57 void forward_propagation(const std::vector<tensor_t*>& in_data,
58 std::vector<tensor_t*>& out_data) override {
59 const tensor_t& in1 = *in_data[0];
60 tensor_t& out = *out_data[0];
61
62 out = in1;
63
64 // @todo parallelize
65 for (size_t sample = 0; sample < in1.size(); ++sample) {
66 for (serial_size_t i = 1; i < num_args_; i++) {
67 std::transform((*in_data[i])[sample].begin(),
68 (*in_data[i])[sample].end(),
69 out[sample].begin(),
70 out[sample].begin(),
71 [](float_t x, float_t y){ return x + y; });
72 }
73 }
74 }
75
76 void back_propagation(const std::vector<tensor_t*>& in_data,
77 const std::vector<tensor_t*>& out_data,
78 std::vector<tensor_t*>& out_grad,
79 std::vector<tensor_t*>& in_grad) override {
80 CNN_UNREFERENCED_PARAMETER(in_data);
81 CNN_UNREFERENCED_PARAMETER(out_data);
82 for (serial_size_t i = 0; i < num_args_; i++)
83 *in_grad[i] = *out_grad[0];
84 }
85
86 template <class Archive>
87 static void load_and_construct(Archive & ar, cereal::construct<elementwise_add_layer> & construct) {
88 serial_size_t num_args, dim;
89
90 ar(cereal::make_nvp("num_args", num_args), cereal::make_nvp("dim", dim));
91 construct(num_args, dim);
92 }
93
94 template <class Archive>
95 void serialize(Archive & ar) {
96 layer::serialize_prolog(ar);
97 ar(cereal::make_nvp("num_args", num_args_), cereal::make_nvp("dim", dim_));
98 }
99private:
100 serial_size_t num_args_;
101 serial_size_t dim_;
102};
103
104} // namespace tiny_dnn
105
element-wise add N vectors y_i = x0_i + x1_i + ... + xnum_i
Definition arithmetic_layer.h:36
std::vector< shape3d > in_shape() const override
array of input shapes (width x height x depth)
Definition arithmetic_layer.h:49
void back_propagation(const std::vector< tensor_t * > &in_data, const std::vector< tensor_t * > &out_data, std::vector< tensor_t * > &out_grad, std::vector< tensor_t * > &in_grad) override
return delta of previous layer (delta=\frac{dE}{da}, a=wx in fully-connected layer)
Definition arithmetic_layer.h:76
std::vector< shape3d > out_shape() const override
array of output shapes (width x height x depth)
Definition arithmetic_layer.h:53
elementwise_add_layer(serial_size_t num_args, serial_size_t dim)
Definition arithmetic_layer.h:42
std::string layer_type() const override
name of layer, should be unique for each concrete class
Definition arithmetic_layer.h:45
void forward_propagation(const std::vector< tensor_t * > &in_data, std::vector< tensor_t * > &out_data) override
Definition arithmetic_layer.h:57
Simple image utility class.
Definition image.h:94
base class of all kind of NN layers
Definition layer.h:62