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
|
#include <vector>
#include "caffe/layer.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/vision_layers.hpp"
namespace caffe {
template <typename Dtype>
__global__ void Slice(const int nthreads, const Dtype* in_data,
const bool forward, const int num_slices, const int slice_size,
const int bottom_slice_axis, const int top_slice_axis,
const int offset_slice_axis, Dtype* out_data) {
CUDA_KERNEL_LOOP(index, nthreads) {
const int total_slice_size = slice_size * top_slice_axis;
const int slice_num = index / total_slice_size;
const int slice_index = index % total_slice_size;
const int bottom_index = slice_index +
(slice_num * bottom_slice_axis + offset_slice_axis) * slice_size;
if (forward) {
out_data[index] = in_data[bottom_index];
} else {
out_data[bottom_index] = in_data[index];
}
}
}
template <typename Dtype>
void SliceLayer<Dtype>::Forward_gpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
if (top.size() == 1) { return; }
int offset_slice_axis = 0;
const Dtype* bottom_data = bottom[0]->gpu_data();
const int bottom_slice_axis = bottom[0]->shape(slice_axis_);
const bool kForward = true;
for (int i = 0; i < top.size(); ++i) {
Dtype* top_data = top[i]->mutable_gpu_data();
const int top_slice_axis = top[i]->shape(slice_axis_);
const int top_slice_size = top_slice_axis * slice_size_;
const int nthreads = top_slice_size * num_slices_;
Slice<Dtype> // NOLINT_NEXT_LINE(whitespace/operators)
<<<CAFFE_GET_BLOCKS(nthreads), CAFFE_CUDA_NUM_THREADS>>>(
nthreads, bottom_data, kForward, num_slices_, slice_size_,
bottom_slice_axis, top_slice_axis, offset_slice_axis, top_data);
offset_slice_axis += top_slice_axis;
}
}
template <typename Dtype>
void SliceLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
if (!propagate_down[0] || top.size() == 1) { return; }
int offset_slice_axis = 0;
Dtype* bottom_diff = bottom[0]->mutable_gpu_diff();
const int bottom_slice_axis = bottom[0]->shape(slice_axis_);
const bool kForward = false;
for (int i = 0; i < top.size(); ++i) {
const Dtype* top_diff = top[i]->gpu_diff();
const int top_slice_axis = top[i]->shape(slice_axis_);
const int top_slice_size = top_slice_axis * slice_size_;
const int nthreads = top_slice_size * num_slices_;
Slice<Dtype> // NOLINT_NEXT_LINE(whitespace/operators)
<<<CAFFE_GET_BLOCKS(nthreads), CAFFE_CUDA_NUM_THREADS>>>(
nthreads, top_diff, kForward, num_slices_, slice_size_,
bottom_slice_axis, top_slice_axis, offset_slice_axis, bottom_diff);
offset_slice_axis += top_slice_axis;
}
}
INSTANTIATE_LAYER_GPU_FUNCS(SliceLayer);
} // namespace caffe
|
