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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
|
#include <algorithm>
#include <cfloat>
#include <vector>
#include "caffe/layers/softmax_loss_layer.hpp"
#include "caffe/util/math_functions.hpp"
namespace caffe {
template <typename Dtype>
__global__ void SoftmaxLossForwardGPU(const int nthreads,
const Dtype* prob_data, const Dtype* label, Dtype* loss,
const int num, const int dim, const int spatial_dim,
const bool has_ignore_label_, const int ignore_label_,
Dtype* counts) {
CUDA_KERNEL_LOOP(index, nthreads) {
const int n = index / spatial_dim;
const int s = index % spatial_dim;
const int label_value = static_cast<int>(label[n * spatial_dim + s]);
if (has_ignore_label_ && label_value == ignore_label_) {
loss[index] = 0;
counts[index] = 0;
} else {
loss[index] = -log(max(prob_data[n * dim + label_value * spatial_dim + s],
Dtype(FLT_MIN)));
counts[index] = 1;
}
}
}
template <typename Dtype>
void SoftmaxWithLossLayer<Dtype>::Forward_gpu(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
softmax_layer_->Forward(softmax_bottom_vec_, softmax_top_vec_);
const Dtype* prob_data = prob_.gpu_data();
const Dtype* label = bottom[1]->gpu_data();
const int dim = prob_.count() / outer_num_;
const int nthreads = outer_num_ * inner_num_;
// Since this memory is not used for anything until it is overwritten
// on the backward pass, we use it here to avoid having to allocate new GPU
// memory to accumulate intermediate results in the kernel.
Dtype* loss_data = bottom[0]->mutable_gpu_diff();
// Similarly, this memory is never used elsewhere, and thus we can use it
// to avoid having to allocate additional GPU memory.
Dtype* counts = prob_.mutable_gpu_diff();
// NOLINT_NEXT_LINE(whitespace/operators)
SoftmaxLossForwardGPU<Dtype><<<CAFFE_GET_BLOCKS(nthreads),
CAFFE_CUDA_NUM_THREADS>>>(nthreads, prob_data, label, loss_data,
outer_num_, dim, inner_num_, has_ignore_label_, ignore_label_, counts);
Dtype loss;
caffe_gpu_asum(nthreads, loss_data, &loss);
Dtype valid_count = -1;
// Only launch another CUDA kernel if we actually need the count of valid
// outputs.
if (normalization_ == LossParameter_NormalizationMode_VALID &&
has_ignore_label_) {
caffe_gpu_asum(nthreads, counts, &valid_count);
}
top[0]->mutable_cpu_data()[0] = loss / get_normalizer(normalization_,
valid_count);
if (top.size() == 2) {
top[1]->ShareData(prob_);
}
caffe_gpu_set(bottom[0]->count(), Dtype(0), bottom[0]->mutable_gpu_diff());
}
template <typename Dtype>
__global__ void SoftmaxLossBackwardGPU(const int nthreads, const Dtype* top,
const Dtype* label, Dtype* bottom_diff, const int num, const int dim,
const int spatial_dim, const bool has_ignore_label_,
const int ignore_label_, Dtype* counts) {
const int channels = dim / spatial_dim;
CUDA_KERNEL_LOOP(index, nthreads) {
const int n = index / spatial_dim;
const int s = index % spatial_dim;
const int label_value = static_cast<int>(label[n * spatial_dim + s]);
if (has_ignore_label_ && label_value == ignore_label_) {
for (int c = 0; c < channels; ++c) {
bottom_diff[n * dim + c * spatial_dim + s] = 0;
}
counts[index] = 0;
} else {
bottom_diff[n * dim + label_value * spatial_dim + s] -= 1;
counts[index] = 1;
}
}
}
template <typename Dtype>
void SoftmaxWithLossLayer<Dtype>::Backward_gpu(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[0]) {
Dtype* bottom_diff = bottom[0]->mutable_gpu_diff();
const Dtype* prob_data = prob_.gpu_data();
const Dtype* top_data = top[0]->gpu_data();
caffe_gpu_memcpy(prob_.count() * sizeof(Dtype), prob_data, bottom_diff);
const Dtype* label = bottom[1]->gpu_data();
const int dim = prob_.count() / outer_num_;
const int nthreads = outer_num_ * inner_num_;
// Since this memory is never used for anything else,
// we use to to avoid allocating new GPU memory.
Dtype* counts = prob_.mutable_gpu_diff();
// NOLINT_NEXT_LINE(whitespace/operators)
SoftmaxLossBackwardGPU<Dtype><<<CAFFE_GET_BLOCKS(nthreads),
CAFFE_CUDA_NUM_THREADS>>>(nthreads, top_data, label, bottom_diff,
outer_num_, dim, inner_num_, has_ignore_label_, ignore_label_, counts);
Dtype valid_count = -1;
// Only launch another CUDA kernel if we actually need the count of valid
// outputs.
if (normalization_ == LossParameter_NormalizationMode_VALID &&
has_ignore_label_) {
caffe_gpu_asum(nthreads, counts, &valid_count);
}
const Dtype loss_weight = top[0]->cpu_diff()[0] /
get_normalizer(normalization_, valid_count);
caffe_gpu_scal(prob_.count(), loss_weight , bottom_diff);
}
}
INSTANTIATE_LAYER_GPU_FUNCS(SoftmaxWithLossLayer);
} // namespace caffe
|
