tiny_dnn  1.0.0
A header only, dependency-free deep learning framework in C++11
input_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/layers/layer.h"
29 
30 namespace tiny_dnn {
31 
32 class input_layer : public layer {
33 public:
34  explicit input_layer(const shape3d& shape)
35  : layer({vector_type::data}, {vector_type::data}), shape_(shape) {}
36 
37  explicit input_layer(serial_size_t in_dim)
38  : layer({ vector_type::data }, { vector_type::data }), shape_(shape3d(in_dim,1,1)) {}
39 
40  std::vector<shape3d> in_shape() const override { return { shape_ }; }
41  std::vector<shape3d> out_shape() const override { return { shape_ }; }
42  std::string layer_type() const override { return "input"; }
43 
44 
45 
46  void forward_propagation(const std::vector<tensor_t*>& in_data,
47  std::vector<tensor_t*>& out_data) override {
48  *out_data[0] = *in_data[0];
49  }
50 
51  void back_propagation(const std::vector<tensor_t*>& in_data,
52  const std::vector<tensor_t*>& out_data,
53  std::vector<tensor_t*>& out_grad,
54  std::vector<tensor_t*>& in_grad) override {
55  // do nothing
56  CNN_UNREFERENCED_PARAMETER(in_data);
57  CNN_UNREFERENCED_PARAMETER(out_data);
58  CNN_UNREFERENCED_PARAMETER(out_grad);
59  CNN_UNREFERENCED_PARAMETER(in_grad);
60  }
61 
62 private:
63  shape3d shape_;
64 };
65 
66 } // namespace tiny_dnn
Definition: input_layer.h:32
void forward_propagation(const std::vector< tensor_t * > &in_data, std::vector< tensor_t * > &out_data) override
Definition: input_layer.h:46
std::vector< shape3d > in_shape() const override
array of input shapes (width x height x depth)
Definition: input_layer.h:40
std::vector< shape3d > out_shape() const override
array of output shapes (width x height x depth)
Definition: input_layer.h:41
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: input_layer.h:51
std::string layer_type() const override
name of layer, should be unique for each concrete class
Definition: input_layer.h:42
base class of all kind of NN layers
Definition: layer.h:62
layer(const std::vector< vector_type > &in_type, const std::vector< vector_type > &out_type)
Defaul layer constructor that instantiates a N-input, M-output layer.
Definition: layer.h:76