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
|
#ifndef CAFFE_DROPOUT_LAYER_HPP_
#define CAFFE_DROPOUT_LAYER_HPP_
#include <vector>
#include "caffe/blob.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/layers/neuron_layer.hpp"
namespace caffe {
/**
* @brief During training only, sets a random portion of @f$x@f$ to 0, adjusting
* the rest of the vector magnitude accordingly.
*
* @param bottom input Blob vector (length 1)
* -# @f$ (N \times C \times H \times W) @f$
* the inputs @f$ x @f$
* @param top output Blob vector (length 1)
* -# @f$ (N \times C \times H \times W) @f$
* the computed outputs @f$ y = |x| @f$
*/
template <typename Dtype>
class DropoutLayer : public NeuronLayer<Dtype> {
public:
/**
* @param param provides DropoutParameter dropout_param,
* with DropoutLayer options:
* - dropout_ratio (\b optional, default 0.5).
* Sets the probability @f$ p @f$ that any given unit is dropped.
*/
explicit DropoutLayer(const LayerParameter& param)
: NeuronLayer<Dtype>(param) {}
virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual inline const char* type() const { return "Dropout"; }
protected:
/**
* @param bottom input Blob vector (length 1)
* -# @f$ (N \times C \times H \times W) @f$
* the inputs @f$ x @f$
* @param top output Blob vector (length 1)
* -# @f$ (N \times C \times H \times W) @f$
* the computed outputs. At training time, we have @f$
* y_{\mbox{train}} = \left\{
* \begin{array}{ll}
* \frac{x}{1 - p} & \mbox{if } u > p \\
* 0 & \mbox{otherwise}
* \end{array} \right.
* @f$, where @f$ u \sim U(0, 1)@f$ is generated independently for each
* input at each iteration. At test time, we simply have
* @f$ y_{\mbox{test}} = \mathbb{E}[y_{\mbox{train}}] = x @f$.
*/
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
/// when divided by UINT_MAX, the randomly generated values @f$u\sim U(0,1)@f$
Blob<unsigned int> rand_vec_;
/// the probability @f$ p @f$ of dropping any input
Dtype threshold_;
/// the scale for undropped inputs at train time @f$ 1 / (1 - p) @f$
Dtype scale_;
unsigned int uint_thres_;
};
} // namespace caffe
#endif // CAFFE_DROPOUT_LAYER_HPP_
|
