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
|
#include <string>
#include <vector>
#include "caffe/data_layers.hpp"
#include "caffe/util/io.hpp"
namespace caffe {
template <typename Dtype>
BaseDataLayer<Dtype>::BaseDataLayer(const LayerParameter& param)
: Layer<Dtype>(param),
transform_param_(param.transform_param()) {
}
template <typename Dtype>
void BaseDataLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
if (top.size() == 1) {
output_labels_ = false;
} else {
output_labels_ = true;
}
data_transformer_.reset(
new DataTransformer<Dtype>(transform_param_, this->phase_));
data_transformer_->InitRand();
// The subclasses should setup the size of bottom and top
DataLayerSetUp(bottom, top);
}
template <typename Dtype>
void BasePrefetchingDataLayer<Dtype>::LayerSetUp(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
BaseDataLayer<Dtype>::LayerSetUp(bottom, top);
// Now, start the prefetch thread. Before calling prefetch, we make two
// cpu_data calls so that the prefetch thread does not accidentally make
// simultaneous cudaMalloc calls when the main thread is running. In some
// GPUs this seems to cause failures if we do not so.
this->prefetch_data_.mutable_cpu_data();
if (this->output_labels_) {
this->prefetch_label_.mutable_cpu_data();
}
DLOG(INFO) << "Initializing prefetch";
this->CreatePrefetchThread();
DLOG(INFO) << "Prefetch initialized.";
}
template <typename Dtype>
void BasePrefetchingDataLayer<Dtype>::CreatePrefetchThread() {
this->data_transformer_->InitRand();
CHECK(StartInternalThread()) << "Thread execution failed";
}
template <typename Dtype>
void BasePrefetchingDataLayer<Dtype>::JoinPrefetchThread() {
CHECK(WaitForInternalThreadToExit()) << "Thread joining failed";
}
template <typename Dtype>
void BasePrefetchingDataLayer<Dtype>::Forward_cpu(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
// First, join the thread
JoinPrefetchThread();
DLOG(INFO) << "Thread joined";
// Reshape to loaded data.
top[0]->ReshapeLike(prefetch_data_);
// Copy the data
caffe_copy(prefetch_data_.count(), prefetch_data_.cpu_data(),
top[0]->mutable_cpu_data());
DLOG(INFO) << "Prefetch copied";
if (this->output_labels_) {
// Reshape to loaded labels.
top[1]->ReshapeLike(prefetch_label_);
// Copy the labels.
caffe_copy(prefetch_label_.count(), prefetch_label_.cpu_data(),
top[1]->mutable_cpu_data());
}
// Start a new prefetch thread
DLOG(INFO) << "CreatePrefetchThread";
CreatePrefetchThread();
}
#ifdef CPU_ONLY
STUB_GPU_FORWARD(BasePrefetchingDataLayer, Forward);
#endif
INSTANTIATE_CLASS(BaseDataLayer);
INSTANTIATE_CLASS(BasePrefetchingDataLayer);
} // namespace caffe
|
