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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
|
#include <algorithm>
#include <cfloat>
#include <cmath>
#include <vector>
#include "caffe/layer.hpp"
#include "caffe/util/io.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/vision_layers.hpp"
namespace caffe {
template <typename Dtype>
void InfogainLossLayer<Dtype>::LayerSetUp(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
LossLayer<Dtype>::LayerSetUp(bottom, top);
if (bottom.size() < 3) {
CHECK(this->layer_param_.infogain_loss_param().has_source())
<< "Infogain matrix source must be specified.";
BlobProto blob_proto;
ReadProtoFromBinaryFile(
this->layer_param_.infogain_loss_param().source(), &blob_proto);
infogain_.FromProto(blob_proto);
}
}
template <typename Dtype>
void InfogainLossLayer<Dtype>::Reshape(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
LossLayer<Dtype>::Reshape(bottom, top);
Blob<Dtype>* infogain = NULL;
if (bottom.size() < 3) {
infogain = &infogain_;
} else {
infogain = bottom[2];
}
CHECK_EQ(bottom[1]->channels(), 1);
CHECK_EQ(bottom[1]->height(), 1);
CHECK_EQ(bottom[1]->width(), 1);
const int num = bottom[0]->num();
const int dim = bottom[0]->count() / num;
CHECK_EQ(infogain->num(), 1);
CHECK_EQ(infogain->channels(), 1);
CHECK_EQ(infogain->height(), dim);
CHECK_EQ(infogain->width(), dim);
}
template <typename Dtype>
void InfogainLossLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
const Dtype* bottom_data = bottom[0]->cpu_data();
const Dtype* bottom_label = bottom[1]->cpu_data();
const Dtype* infogain_mat = NULL;
if (bottom.size() < 3) {
infogain_mat = infogain_.cpu_data();
} else {
infogain_mat = bottom[2]->cpu_data();
}
int num = bottom[0]->num();
int dim = bottom[0]->count() / bottom[0]->num();
Dtype loss = 0;
for (int i = 0; i < num; ++i) {
int label = static_cast<int>(bottom_label[i]);
for (int j = 0; j < dim; ++j) {
Dtype prob = std::max(bottom_data[i * dim + j], Dtype(kLOG_THRESHOLD));
loss -= infogain_mat[label * dim + j] * log(prob);
}
}
top[0]->mutable_cpu_data()[0] = loss / num;
}
template <typename Dtype>
void InfogainLossLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down,
const vector<Blob<Dtype>*>& bottom) {
if (propagate_down[1]) {
LOG(FATAL) << this->type()
<< " Layer cannot backpropagate to label inputs.";
}
if (propagate_down.size() > 2 && propagate_down[2]) {
LOG(FATAL) << this->type()
<< " Layer cannot backpropagate to infogain inputs.";
}
if (propagate_down[0]) {
const Dtype* bottom_data = bottom[0]->cpu_data();
const Dtype* bottom_label = bottom[1]->cpu_data();
const Dtype* infogain_mat = NULL;
if (bottom.size() < 3) {
infogain_mat = infogain_.cpu_data();
} else {
infogain_mat = bottom[2]->cpu_data();
}
Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
int num = bottom[0]->num();
int dim = bottom[0]->count() / bottom[0]->num();
const Dtype scale = - top[0]->cpu_diff()[0] / num;
for (int i = 0; i < num; ++i) {
const int label = static_cast<int>(bottom_label[i]);
for (int j = 0; j < dim; ++j) {
Dtype prob = std::max(bottom_data[i * dim + j], Dtype(kLOG_THRESHOLD));
bottom_diff[i * dim + j] = scale * infogain_mat[label * dim + j] / prob;
}
}
}
}
INSTANTIATE_CLASS(InfogainLossLayer);
REGISTER_LAYER_CLASS(InfogainLoss);
} // namespace caffe
|