Caffe源码解析8: Net

原创 2017年01月03日 19:48:40



#include <caffe\net.hpp>


std::string proto("deploy.prototxt");
Net<float> nn(proto, caffe::TEST);
vector<string> bn = nn.blob_names();  //获取Net中所有blob对象名
vector<string> ln = nn.layer_names();
for (int i = 0; i < bn.size(); i++)
    cout << "Blob #" << i << ":" << bn[i] << endl;
for (int j = 0; j < ln.size(); j++)
    cout << "Layer #" << j << ":" << ln[j] << endl;
F0103 13:36:44.474290  5904 cudnn_conv_layer.cpp:53] Check failed: status == CUDNN_STATUS_SUCCESS (6 vs. 0)  CUDNN_STATUS_ARCH_MISMATCH
*** Check failure stack trace: ***

由于我的GPU硬件不支持cuda 3.0以上版本,关闭掉预处理器中的USE_CUDNN(修改CommonSettings.props文件相应选项)。可以看到结果如下:

I0103 13:54:55.282647 13792 net.cpp:283] Network initialization done.
Blob #0:data
Blob #1:conv1
Blob #2:pool1
Blob #3:norm1
Blob #4:conv2
Blob #5:pool2
Blob #6:norm2
Blob #7:conv3
Blob #8:conv4
Blob #9:conv5
Blob #10:pool5
Blob #11:fc6
Blob #12:fc7
Blob #13:fc8
Blob #14:prob
Layer #0:data
Layer #1:conv1
Layer #2:relu1
Layer #3:pool1
Layer #4:norm1
Layer #5:conv2
Layer #6:relu2
Layer #7:pool2
Layer #8:norm2
Layer #9:conv3
Layer #10:relu3
Layer #11:conv4
Layer #12:relu4
Layer #13:conv5
Layer #14:relu5
Layer #15:pool5
Layer #16:fc6
Layer #17:relu6
Layer #18:drop6
Layer #19:fc7
Layer #20:relu7
Layer #21:drop7
Layer #22:fc8
Layer #23:prob





message NetParameter {
  optional string name = 1; // consider giving the network a name
  // DEPRECATED. See InputParameter. The input blobs to the network.
  repeated string input = 3;
  // DEPRECATED. See InputParameter. The shape of the input blobs.
  repeated BlobShape input_shape = 8;

  // 4D input dimensions -- deprecated.  Use "input_shape" instead.
  // If specified, for each input blob there should be four
  // values specifying the num, channels, height and width of the input blob.
  // Thus, there should be a total of (4 * #input) numbers.
  repeated int32 input_dim = 4;

  // Whether the network will force every layer to carry out backward operation.
  // If set False, then whether to carry out backward is determined
  // automatically according to the net structure and learning rates.
  optional bool force_backward = 5 [default = false];
  // The current "state" of the network, including the phase, level, and stage.
  // Some layers may be included/excluded depending on this state and the states
  // specified in the layers' include and exclude fields.
  optional NetState state = 6;

  // Print debugging information about results while running Net::Forward,
  // Net::Backward, and Net::Update.
  optional bool debug_info = 7 [default = false];

  // The layers that make up the net.  Each of their configurations, including
  // connectivity and behavior, is specified as a LayerParameter.
  repeated LayerParameter layer = 100;  // ID 100 so layers are printed last.

  // DEPRECATED: use 'layer' instead.
  repeated V1LayerParameter layers = 2;




可以看到上面有两类Blob:以param开头的权值blob和以blob开头的Layer输入/输出blob。 权值blob会随着学习过程而更新,归属于“模型”; Layer输入/输出blob则只会随网络输入变化,属于“数据”。深度学习的目的就是不断从“数据”获得知识,存储到“模型”中,应用于后来的“数据”。


#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 {
  explicit Net(const NetParameter& param, const Net* root_net = NULL);
  explicit Net(const string& param_file, Phase phase,
      const int level = 0, const vector<string>* stages = NULL,
      const Net* root_net = NULL);
  virtual ~Net() {}

  /// @brief Initialize a network with a NetParameter.
  void Init(const NetParameter& param);

   * @brief Run Forward and return the result.
  const vector<Blob<Dtype>*>& Forward(Dtype* loss = NULL);
  /// @brief DEPRECATED; use Forward() instead.
  const vector<Blob<Dtype>*>& ForwardPrefilled(Dtype* loss = NULL) {
    LOG_EVERY_N(WARNING, 1000) << "DEPRECATED: ForwardPrefilled() "
        << "will be removed in a future version. Use Forward().";
    return Forward(loss);

   * 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 DEPRECATED; set input blobs then use Forward() instead.
  const vector<Blob<Dtype>*>& Forward(const vector<Blob<Dtype>* > & bottom,
      Dtype* loss = NULL);

   * @brief Zeroes out the diffs of all net parameters.
   *        Should be run before Backward.
  void ClearParamDiffs();

   * 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() {
    Dtype loss;
    return loss;

  /// @brief Updates the network weights based on the diff values computed.
  void Update();
   * @brief Shares weight data of owner blobs with shared blobs.
   * Note: this is called by Net::Init, and thus should normally not be
   * called manually.
  void ShareWeights();

   * @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);
  void CopyTrainedLayersFromBinaryProto(const string trained_filename);
  void CopyTrainedLayersFromHDF5(const string trained_filename);
  /// @brief Writes the net to a proto.
  void ToProto(NetParameter* param, bool write_diff = false) const;
  /// @brief Writes the net to an HDF5 file.
  void ToHDF5(const string& filename, 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 phase: TRAIN or TEST
  inline Phase phase() const { return phase_; }
   * @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_;
  /// @brief returns the ids of the top blobs of layer i
  inline const vector<int> & top_ids(int i) const {
    CHECK_GE(i, 0) << "Invalid layer id";
    CHECK_LT(i, top_id_vecs_.size()) << "Invalid layer id";
    return top_id_vecs_[i];
  /// @brief returns the ids of the bottom blobs of layer i
  inline const vector<int> & bottom_ids(int i) const {
    CHECK_GE(i, 0) << "Invalid layer id";
    CHECK_LT(i, bottom_id_vecs_.size()) << "Invalid layer id";
    return bottom_id_vecs_[i];
  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_;
  inline const vector<bool>& layer_need_backward() const {
    return layer_need_backward_;
  /// @brief returns the parameters
  inline const vector<shared_ptr<Blob<Dtype> > >& params() const {
    return params_;
  inline const vector<Blob<Dtype>*>& learnable_params() const {
    return learnable_params_;
  /// @brief returns the learnable parameter learning rate multipliers
  inline const vector<float>& params_lr() const { return params_lr_; }
  inline const vector<bool>& has_params_lr() const { return has_params_lr_; }
  /// @brief returns the learnable parameter decay multipliers
  inline const vector<float>& params_weight_decay() const {
    return params_weight_decay_;
  inline const vector<bool>& has_params_decay() const {
    return has_params_decay_;
  const map<string, int>& param_names_index() const {
    return param_names_index_;
  inline const vector<int>& param_owners() const { return param_owners_; }
  inline const vector<string>& param_display_names() const {
    return param_display_names_;
  /// @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);

  // Helpers for Init.
  /// @brief Append a new 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.
  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 The network name
  string name_;
  /// @brief The phase: TRAIN or TEST
  Phase phase_;
  /// @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_;
  /// The parameters in the network.
  vector<shared_ptr<Blob<Dtype> > > params_;
  vector<Blob<Dtype>*> learnable_params_;
   * The mapping from params_ -> learnable_params_: we have
   * learnable_param_ids_.size() == params_.size(),
   * and learnable_params_[learnable_param_ids_[i]] == params_[i].get()
   * if and only if params_[i] is an "owner"; otherwise, params_[i] is a sharer
   * and learnable_params_[learnable_param_ids_[i]] gives its owner.
  vector<int> learnable_param_ids_;
  /// the learning rate multipliers for learnable_params_
  vector<float> params_lr_;
  vector<bool> has_params_lr_;
  /// the weight decay multipliers for learnable_params_
  vector<float> params_weight_decay_;
  vector<bool> has_params_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_;
  /// The root net that actually holds the shared layers in data parallelism
  const Net* const root_net_;

}  // namespace caffe

#endif  // CAFFE_NET_HPP_



转载自: 这里主要讨论一下ConvolutionLayer相关的Layer: BaseConvo...


参考自: 根据前面一章对Blob的分析,我们看到blob.hpp中封装了#include "caffe/...

Caffe源码解析4: Data_layer

转载自: data_layer应该是网络的最底层,主要是将数据送给blob进入到net中,在data_l...


转载自: layer这个类可以说是里面的一个基本类了,深度网络呢就是一层一层的layer,相互之间通过b...


转载自: Caffe的万丈高楼(Net)是按照我们设计的图纸(prototxt)、用Blob这些砖块筑成...


转载自: Pooling 层一般在网络中是跟在Conv卷积层之后,做采样操作,其实是为了进一步缩小fea...


转载自: NeuronLayer,顾名思义这里就是指神经元,激活函数的相应层。我们知道在blob进入激活...

Caffe傻瓜系列(10):draw_net.py绘制caffe net结构

1、安装pydot $ sudo apt-get install python-pydot2、安装graphviz $ sudo apt-get instll graphviz3、python dra...

caffe python批量抽取图像特征


[caffe笔记004]: caffe添加新层之添加maxout层