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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
|
#ifndef CAFFE_NET_HPP_
#define CAFFE_NET_HPP_
#include <map>
#include <set>
#include <string>
#include <utility>
#include <vector>
#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
namespace caffe {
/**
* @brief Connects Layer%s together into a directed acyclic graph (DAG)
* specified by a NetParameter.
*
* TODO(dox): more thorough description.
*/
template <typename Dtype>
class Net {
public:
explicit Net(const NetParameter& param);
explicit Net(const string& param_file);
virtual ~Net() {}
/// @brief Initialize a network with a NetParameter.
void Init(const NetParameter& param);
/**
* @brief Run Forward with the input Blob%s already fed separately.
*
* You can get the input blobs using input_blobs().
*/
const vector<Blob<Dtype>*>& ForwardPrefilled(Dtype* loss = NULL);
/**
* The From and To variants of Forward and Backward operate on the
* (topological) ordering by which the net is specified. For general DAG
* networks, note that (1) computing from one layer to another might entail
* extra computation on unrelated branches, and (2) computation starting in
* the middle may be incorrect if all of the layers of a fan-in are not
* included.
*/
Dtype ForwardFromTo(int start, int end);
Dtype ForwardFrom(int start);
Dtype ForwardTo(int end);
/// @brief Run forward using a set of bottom blobs, and return the result.
const vector<Blob<Dtype>*>& Forward(const vector<Blob<Dtype>* > & bottom,
Dtype* loss = NULL);
/**
* @brief Run forward using a serialized BlobProtoVector and return the
* result as a serialized BlobProtoVector
*/
string Forward(const string& input_blob_protos, Dtype* loss = NULL);
/**
* The network backward should take no input and output, since it solely
* computes the gradient w.r.t the parameters, and the data has already been
* provided during the forward pass.
*/
void Backward();
void BackwardFromTo(int start, int end);
void BackwardFrom(int start);
void BackwardTo(int end);
/**
* @brief Reshape all layers from bottom to top.
*
* This is useful to propagate changes to layer sizes without running
* a forward pass, e.g. to compute output feature size.
*/
void Reshape();
Dtype ForwardBackward(const vector<Blob<Dtype>* > & bottom) {
Dtype loss;
Forward(bottom, &loss);
Backward();
return loss;
}
/// @brief Updates the network weights based on the diff values computed.
void Update();
/**
* @brief For an already initialized net, implicitly copies (i.e., using no
* additional memory) the pre-trained layers from another Net.
*/
void ShareTrainedLayersWith(const Net* other);
// For an already initialized net, CopyTrainedLayersFrom() copies the already
// trained layers from another net parameter instance.
/**
* @brief For an already initialized net, copies the pre-trained layers from
* another Net.
*/
void CopyTrainedLayersFrom(const NetParameter& param);
void CopyTrainedLayersFrom(const string trained_filename);
/// @brief Writes the net to a proto.
void ToProto(NetParameter* param, bool write_diff = false) const;
/// @brief returns the network name.
inline const string& name() const { return name_; }
/// @brief returns the layer names
inline const vector<string>& layer_names() const { return layer_names_; }
/// @brief returns the blob names
inline const vector<string>& blob_names() const { return blob_names_; }
/// @brief returns the blobs
inline const vector<shared_ptr<Blob<Dtype> > >& blobs() const {
return blobs_;
}
/// @brief returns the layers
inline const vector<shared_ptr<Layer<Dtype> > >& layers() const {
return layers_;
}
/**
* @brief returns the bottom vecs for each layer -- usually you won't
* need this unless you do per-layer checks such as gradients.
*/
inline const vector<vector<Blob<Dtype>*> >& bottom_vecs() const {
return bottom_vecs_;
}
/**
* @brief returns the top vecs for each layer -- usually you won't
* need this unless you do per-layer checks such as gradients.
*/
inline const vector<vector<Blob<Dtype>*> >& top_vecs() const {
return top_vecs_;
}
inline const vector<vector<bool> >& bottom_need_backward() const {
return bottom_need_backward_;
}
inline const vector<Dtype>& blob_loss_weights() const {
return blob_loss_weights_;
}
/// @brief returns the parameters
inline const vector<shared_ptr<Blob<Dtype> > >& params() const {
return params_;
}
/// @brief returns the parameter learning rate multipliers
inline const vector<float>& params_lr() const { return params_lr_; }
inline const vector<float>& params_weight_decay() const {
return params_weight_decay_;
}
const map<string, int>& param_names_index() const {
return param_names_index_;
}
/// @brief Input and output blob numbers
inline int num_inputs() const { return net_input_blobs_.size(); }
inline int num_outputs() const { return net_output_blobs_.size(); }
inline const vector<Blob<Dtype>*>& input_blobs() const {
return net_input_blobs_;
}
inline const vector<Blob<Dtype>*>& output_blobs() const {
return net_output_blobs_;
}
inline const vector<int>& input_blob_indices() const {
return net_input_blob_indices_;
}
inline const vector<int>& output_blob_indices() const {
return net_output_blob_indices_;
}
bool has_blob(const string& blob_name) const;
const shared_ptr<Blob<Dtype> > blob_by_name(const string& blob_name) const;
bool has_layer(const string& layer_name) const;
const shared_ptr<Layer<Dtype> > layer_by_name(const string& layer_name) const;
void set_debug_info(const bool value) { debug_info_ = value; }
// Helpers for Init.
/**
* @brief Remove layers that the user specified should be excluded given the current
* phase, level, and stage.
*/
static void FilterNet(const NetParameter& param,
NetParameter* param_filtered);
/// @brief return whether NetState state meets NetStateRule rule
static bool StateMeetsRule(const NetState& state, const NetStateRule& rule,
const string& layer_name);
protected:
// Helpers for Init.
/// @brief Append a new input or top blob to the net.
void AppendTop(const NetParameter& param, const int layer_id,
const int top_id, set<string>* available_blobs,
map<string, int>* blob_name_to_idx);
/// @brief Append a new bottom blob to the net.
int AppendBottom(const NetParameter& param, const int layer_id,
const int bottom_id, set<string>* available_blobs,
map<string, int>* blob_name_to_idx);
/// @brief Append a new parameter blob to the net.
void AppendParam(const NetParameter& param, const int layer_id,
const int param_id);
/// @brief Helper for displaying debug info in Forward about input Blobs.
void InputDebugInfo(const int layer_id);
/// @brief Helper for displaying debug info in Forward.
void ForwardDebugInfo(const int layer_id);
/// @brief Helper for displaying debug info in Backward.
void BackwardDebugInfo(const int layer_id);
/// @brief Helper for displaying debug info in Update.
void UpdateDebugInfo(const int param_id);
/// @brief Get misc parameters, e.g. the LR multiplier and weight decay.
void GetLearningRateAndWeightDecay();
/// @brief Individual layers in the net
vector<shared_ptr<Layer<Dtype> > > layers_;
vector<string> layer_names_;
map<string, int> layer_names_index_;
vector<bool> layer_need_backward_;
/// @brief the blobs storing intermediate results between the layer.
vector<shared_ptr<Blob<Dtype> > > blobs_;
vector<string> blob_names_;
map<string, int> blob_names_index_;
vector<bool> blob_need_backward_;
/// bottom_vecs stores the vectors containing the input for each layer.
/// They don't actually host the blobs (blobs_ does), so we simply store
/// pointers.
vector<vector<Blob<Dtype>*> > bottom_vecs_;
vector<vector<int> > bottom_id_vecs_;
vector<vector<bool> > bottom_need_backward_;
/// top_vecs stores the vectors containing the output for each layer
vector<vector<Blob<Dtype>*> > top_vecs_;
vector<vector<int> > top_id_vecs_;
/// Vector of weight in the loss (or objective) function of each net blob,
/// indexed by blob_id.
vector<Dtype> blob_loss_weights_;
vector<vector<int> > param_id_vecs_;
vector<int> param_owners_;
vector<string> param_display_names_;
vector<pair<int, int> > param_layer_indices_;
map<string, int> param_names_index_;
/// blob indices for the input and the output of the net
vector<int> net_input_blob_indices_;
vector<int> net_output_blob_indices_;
vector<Blob<Dtype>*> net_input_blobs_;
vector<Blob<Dtype>*> net_output_blobs_;
string name_;
/// The parameters in the network.
vector<shared_ptr<Blob<Dtype> > > params_;
/// the learning rate multipliers
vector<float> params_lr_;
/// the weight decay multipliers
vector<float> params_weight_decay_;
/// The bytes of memory used by this net
size_t memory_used_;
/// Whether to compute and display debug info for the net.
bool debug_info_;
DISABLE_COPY_AND_ASSIGN(Net);
};
} // namespace caffe
#endif // CAFFE_NET_HPP_
|
