blob: 0fa83ccddac90886513c2300742fd234d64d3303 (
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
|
#include <algorithm>
#include <cfloat>
#include <vector>
#include "caffe/layer.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/vision_layers.hpp"
namespace caffe {
template <typename Dtype>
void SoftmaxWithLossLayer<Dtype>::LayerSetUp(
const vector<Blob<Dtype>*>& bottom, vector<Blob<Dtype>*>* top) {
LossLayer<Dtype>::LayerSetUp(bottom, top);
softmax_bottom_vec_.clear();
softmax_bottom_vec_.push_back(bottom[0]);
softmax_top_vec_.clear();
softmax_top_vec_.push_back(&prob_);
softmax_layer_->SetUp(softmax_bottom_vec_, &softmax_top_vec_);
if (top->size() >= 2) {
// softmax output
(*top)[1]->ReshapeLike(*bottom[0]);
}
}
template <typename Dtype>
void SoftmaxWithLossLayer<Dtype>::Forward_cpu(
const vector<Blob<Dtype>*>& bottom, vector<Blob<Dtype>*>* top) {
// The forward pass computes the softmax prob values.
softmax_bottom_vec_[0] = bottom[0];
softmax_layer_->Forward(softmax_bottom_vec_, &softmax_top_vec_);
const Dtype* prob_data = prob_.cpu_data();
const Dtype* label = bottom[1]->cpu_data();
int num = prob_.num();
int dim = prob_.count() / num;
Dtype loss = 0;
for (int i = 0; i < num; ++i) {
loss += -log(std::max(prob_data[i * dim + static_cast<int>(label[i])],
Dtype(FLT_MIN)));
}
(*top)[0]->mutable_cpu_data()[0] = loss / num;
if (top->size() == 2) {
(*top)[1]->ShareData(prob_);
}
}
template <typename Dtype>
void SoftmaxWithLossLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down,
vector<Blob<Dtype>*>* bottom) {
if (propagate_down[1]) {
LOG(FATAL) << this->type_name()
<< " Layer cannot backpropagate to label inputs.";
}
if (propagate_down[0]) {
Dtype* bottom_diff = (*bottom)[0]->mutable_cpu_diff();
const Dtype* prob_data = prob_.cpu_data();
caffe_copy(prob_.count(), prob_data, bottom_diff);
const Dtype* label = (*bottom)[1]->cpu_data();
int num = prob_.num();
int dim = prob_.count() / num;
for (int i = 0; i < num; ++i) {
bottom_diff[i * dim + static_cast<int>(label[i])] -= 1;
}
// Scale gradient
const Dtype loss_weight = top[0]->cpu_diff()[0];
caffe_scal(prob_.count(), loss_weight / num, bottom_diff);
}
}
#ifdef CPU_ONLY
STUB_GPU(SoftmaxWithLossLayer);
#endif
INSTANTIATE_CLASS(SoftmaxWithLossLayer);
} // namespace caffe
|