caffe code 理解-net.hpp-net.cpp

net.hpp/cpp中主要含有：前向后向传播函数，网络IO函数，每层的参数检测和读取函数，建立和维护每层参数的函数以及vector容器。

caffe支持的网络是有向无环图结构。网络中每一层都是一个节点，网络含有起点和终点，并且起点和终点不一定只有一个，信息在前向传递时在网络中每个节点都会至少会经过一次，并且不一定只有一次。但是只有一个起点时网络每个节点只能经过一次。后向传播时同理。

下面主要用在代码中添加注释的方法来说明。

首先来看net中维护的各种vector以及变量

  /// @brief The network name
  string name_;
  /// @brief The phase: TRAIN or TEST
  Phase phase_;
  /// @brief Individual layers in the net, each indicator specify a layer class.
  vector<shared_ptr<Layer<Dtype> > > layers_;
  // the name of each layer, indexed by layer id.
  vector<string> layer_names_;
  // the map of layer name and layer id.
  map<string, int> layer_names_index_;
  // indicating whether a layer need backword
  vector<bool> layer_need_backward_;
  /// @brief the blobs storing intermediate results between the layer.
  vector<shared_ptr<Blob<Dtype> > > blobs_;
  // the name of each blob, indexed by blob id.
  vector<string> blob_names_;
  // the map of blob name and blob id.
  map<string, int> blob_names_index_;
  // indicating whether a blob need backword
  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 of param id for each param. it is needed because caffe support parameter sharing.
  vector<vector<int> > param_id_vecs_;
  // the number of the onwer of parameter.
  vector<int> param_owners_;
  // the display name of parameter, because the splite algorithm and other reason cause the name of parameter is not the same as specified the prototxt.
  vector<string> param_display_names_;
  // the param and its owner pair, onwer indicates by layer id.
  vector<pair<int, int> > param_layer_indices_;
  //map of param name and param id.
  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_;

下面是构造net相关的函数

	//construct function of Net. Parsed parameter or parameter file name are both available.
	// Netparameter is a class to describe the structure. Sometimes it contains weights of net.
	// it is not a net setted up, but some parameters.
	// it is created by google protobuff project, and the defination of it can be found in caffe.pb.h
	// root_net_ is used for multi-gpu computing, if root_net is not NULL, if will share weight between gpu
template <typename Dtype>
Net<Dtype>::Net(const NetParameter& param, const Net* root_net)
    : root_net_(root_net){
  Init(param);
}

template <typename Dtype>
Net<Dtype>::Net(const string& param_file, Phase phase, const Net* root_net)
    : root_net_(root_net) {
  NetParameter param;
  ReadNetParamsFromTextFileOrDie(param_file, ¶m);
  param.mutable_state()->set_phase(phase);
  Init(param);
}
/// @brief Initialize a network with a NetParameter.
template <typename Dtype>
void Net<Dtype>::Init(const NetParameter& in_param) {
  //if has root_solver, root_net is needed
  CHECK(Caffe::root_solver() || root_net_)
      << "root_net_ needs to be set for all non-root solvers";
  // Set phase from the state. phase is train or test
  phase_ = in_param.state().phase();
  // Filter layers based on their include/exclude rules and
  // the current NetState.
  NetParameter filtered_param;
  // this function is used to check whether the parameter of a layer is legal
  // and then find whether the layer is needed in this phase
  FilterNet(in_param, &filtered_param);
  LOG_IF(INFO, Caffe::root_solver())
      << "Initializing net from parameters: " << std::endl
      << filtered_param.DebugString();
  // Create a copy of filtered_param with splits added where necessary.
  NetParameter param;
  // this function is used when a blob act as the bottom of two or more layers. it will duplicate a bolb and share weights betwwen duplicates.
  // it is needed because caffe assume all blobs can be used only once.
  InsertSplits(filtered_param, ¶m);
  // Basically, build all the layers and set up their connections.
  name_ = param.name();
  map<string, int> blob_name_to_idx;
  set<string> available_blobs;
  memory_used_ = 0;
  // For each layer, set up its input and output
  bottom_vecs_.resize(param.layer_size());
  top_vecs_.resize(param.layer_size());
  bottom_id_vecs_.resize(param.layer_size());
  param_id_vecs_.resize(param.layer_size());
  top_id_vecs_.resize(param.layer_size());
  bottom_need_backward_.resize(param.layer_size());
  // each layer will be setup in following
  for (int layer_id = 0; layer_id < param.layer_size(); ++layer_id) {
    // For non-root solvers, whether this layer is shared from root_net_.
    bool share_from_root = !Caffe::root_solver()
        && root_net_->layers_[layer_id]->ShareInParallel();
    // Inherit phase from net if unset.
    if (!param.layer(layer_id).has_phase()) {
      param.mutable_layer(layer_id)->set_phase(phase_);
    }
    // Setup layer.
    const LayerParameter& layer_param = param.layer(layer_id);
    if (layer_param.propagate_down_size() > 0) {
      CHECK_EQ(layer_param.propagate_down_size(),
          layer_param.bottom_size())
          << "propagate_down param must be specified "
          << "either 0 or bottom_size times ";
    }
	//if the net shared form root, this layer will be shared too or it will be created.
    if (share_from_root) {
      LOG(INFO) << "Sharing layer " << layer_param.name() << " from root net";
      layers_.push_back(root_net_->layers_[layer_id]);
      layers_[layer_id]->SetShared(true);
    } else {
      layers_.push_back(LayerRegistry<Dtype>::CreateLayer(layer_param));
    }
	//push layer name
    layer_names_.push_back(layer_param.name());
    LOG_IF(INFO, Caffe::root_solver())
        << "Creating Layer " << layer_param.name();
    bool need_backward = false;

    // Figure out this layer's input and output. caffe net mainten blobs in bottom or top, and other blobs should be taken cared by layer. 
	// each bottom blob should corresponde to one and only one top blob, or error occur.
    for (int bottom_id = 0; bottom_id < layer_param.bottom_size();
         ++bottom_id) {
		// add a new blob to bottom.
      const int blob_id = AppendBottom(param, layer_id, bottom_id,
                                       &available_blobs, &blob_name_to_idx);
      // If a blob needs backward, this layer should provide it.
      need_backward |= blob_need_backward_[blob_id];
    }
    int num_top = layer_param.top_size();
    for (int top_id = 0; top_id < num_top; ++top_id) {
		// add a new blob to top.
      AppendTop(param, layer_id, top_id, &available_blobs, &blob_name_to_idx);
      // Collect Input layer tops as Net inputs.
      if (layer_param.type() == "Input") {
        const int blob_id = blobs_.size() - 1;
        net_input_blob_indices_.push_back(blob_id);
        net_input_blobs_.push_back(blobs_[blob_id].get());
      }
    }
    // If the layer specifies that AutoTopBlobs() -> true and the LayerParameter
    // specified fewer than the required number (as specified by
    // ExactNumTopBlobs() or MinTopBlobs()), allocate them here.
    Layer<Dtype>* layer = layers_[layer_id].get();
    if (layer->AutoTopBlobs()) {
      const int needed_num_top =
          std::max(layer->MinTopBlobs(), layer->ExactNumTopBlobs());
      for (; num_top < needed_num_top; ++num_top) {
        // Add "anonymous" top blobs -- do not modify available_blobs or
        // blob_name_to_idx as we don't want these blobs to be usable as input
        // to other layers.
        AppendTop(param, layer_id, num_top, NULL, NULL);
      }
    }
    // After this layer is connected, set it up.
    if (share_from_root) {
      // Set up size of top blobs using root_net_
      const vector<Blob<Dtype>*>& base_top = root_net_->top_vecs_[layer_id];
      const vector<Blob<Dtype>*>& this_top = this->top_vecs_[layer_id];
      for (int top_id = 0; top_id < base_top.size(); ++top_id) {
        this_top[top_id]->ReshapeLike(*base_top[top_id]);
        LOG(INFO) << "Created top blob " << top_id << " (shape: "
            << this_top[top_id]->shape_string() <<  ") for shared layer "
            << layer_param.name();
      }
    } else {
      layers_[layer_id]->SetUp(bottom_vecs_[layer_id], top_vecs_[layer_id]);
    }
    LOG_IF(INFO, Caffe::root_solver())
        << "Setting up " << layer_names_[layer_id];
	//add the blob id to blob_loss_weights_ vector and check wether the blob is associated with loss
    for (int top_id = 0; top_id < top_vecs_[layer_id].size(); ++top_id) {
      if (blob_loss_weights_.size() <= top_id_vecs_[layer_id][top_id]) {
        blob_loss_weights_.resize(top_id_vecs_[layer_id][top_id] + 1, Dtype(0));
      }
      blob_loss_weights_[top_id_vecs_[layer_id][top_id]] = layer->loss(top_id);
      LOG_IF(INFO, Caffe::root_solver())
          << "Top shape: " << top_vecs_[layer_id][top_id]->shape_string();
      if (layer->loss(top_id)) {
        LOG_IF(INFO, Caffe::root_solver())
            << "    with loss weight " << layer->loss(top_id);
      }
      memory_used_ += top_vecs_[layer_id][top_id]->count();
    }
    LOG_IF(INFO, Caffe::root_solver())
        << "Memory required for data: " << memory_used_ * sizeof(Dtype);
    const int param_size = layer_param.param_size();
    const int num_param_blobs = layers_[layer_id]->blobs().size();
    CHECK_LE(param_size, num_param_blobs)
        << "Too many params specified for layer " << layer_param.name();
	//ParamSpec is a class to chech wehther a param should backpropagate
	// if ir_mul is not 0, a param should be backpropagate
    ParamSpec default_param_spec;
    for (int param_id = 0; param_id < num_param_blobs; ++param_id) {
      const ParamSpec* param_spec = (param_id < param_size) ?
          &layer_param.param(param_id) : &default_param_spec;
      const bool param_need_backward = param_spec->lr_mult() != 0;
      need_backward |= param_need_backward;
      layers_[layer_id]->set_param_propagate_down(param_id,
                                                  param_need_backward);
    }
	//add new param blob
    for (int param_id = 0; param_id < num_param_blobs; ++param_id) {
      AppendParam(param, layer_id, param_id);
    }
    // Finally, set the backward flag
    layer_need_backward_.push_back(need_backward);
    if (need_backward) {
      for (int top_id = 0; top_id < top_id_vecs_[layer_id].size(); ++top_id) {
        blob_need_backward_[top_id_vecs_[layer_id][top_id]] = true;
      }
    }
  }//layer setup done
  
  // Go through the net backwards to determine which blobs contribute to the
  // loss.  We can skip backward computation for blobs that don't contribute
  // to the loss.
  // Also checks if all bottom blobs don't need backward computation (possible
  // because the skip_propagate_down param) and so we can skip bacward
  // computation for the entire layer
  set<string> blobs_under_loss;
  set<string> blobs_skip_backp;
  // in the following we figure out whether a layer needs backpropagate
  for (int layer_id = layers_.size() - 1; layer_id >= 0; --layer_id) {
    bool layer_contributes_loss = false;
    bool layer_skip_propagate_down = true;
    for (int top_id = 0; top_id < top_vecs_[layer_id].size(); ++top_id) {
      const string& blob_name = blob_names_[top_id_vecs_[layer_id][top_id]];
	  //if one of the top blobs of layer contribute to loss, this layer contribute to loss.
      if (layers_[layer_id]->loss(top_id) ||
          (blobs_under_loss.find(blob_name) != blobs_under_loss.end())) {
        layer_contributes_loss = true;
      }
	  //if one of the top blobs is not skipped from backpropogate, this layer should not skip.
      if (blobs_skip_backp.find(blob_name) == blobs_skip_backp.end()) {
        layer_skip_propagate_down = false;
      }
      if (layer_contributes_loss && !layer_skip_propagate_down)
        break;
    }
    // If this layer can skip backward computation, also all his bottom blobs
    // don't need backpropagation
    if (layer_need_backward_[layer_id] && layer_skip_propagate_down) {
      layer_need_backward_[layer_id] = false;
      for (int bottom_id = 0; bottom_id < bottom_vecs_[layer_id].size();
               ++bottom_id) {
        bottom_need_backward_[layer_id][bottom_id] = false;
      }
    }
	// if the layer do not contribute to loss, it need not bakpropagate.
    if (!layer_contributes_loss) { layer_need_backward_[layer_id] = false; }
	// if this net is not a root net, all setting should be the same as root net.
    if (Caffe::root_solver()) {
      if (layer_need_backward_[layer_id]) {
        LOG(INFO) << layer_names_[layer_id] << " needs backward computation.";
      } else {
        LOG(INFO) << layer_names_[layer_id]
            << " does not need backward computation.";
      }
    }

    for (int bottom_id = 0; bottom_id < bottom_vecs_[layer_id].size();
         ++bottom_id) {
		// if a layer contribute to loss, set all its bottom blob contribute to loss.
      if (layer_contributes_loss) {
        const string& blob_name =
            blob_names_[bottom_id_vecs_[layer_id][bottom_id]];
        blobs_under_loss.insert(blob_name);
      } else {
        bottom_need_backward_[layer_id][bottom_id] = false;
      }
	  //if a bottom blob do not need backpropagate, insert it in skip vector.
      if (!bottom_need_backward_[layer_id][bottom_id]) {
        const string& blob_name =
                   blob_names_[bottom_id_vecs_[layer_id][bottom_id]];
        blobs_skip_backp.insert(blob_name);
      }
    }
  }
  // Handle force_backward if needed.
  if (param.force_backward()) {
    for (int layer_id = 0; layer_id < layers_.size(); ++layer_id) {
      layer_need_backward_[layer_id] = true;
      for (int bottom_id = 0;
           bottom_id < bottom_need_backward_[layer_id].size(); ++bottom_id) {
        bottom_need_backward_[layer_id][bottom_id] =
            bottom_need_backward_[layer_id][bottom_id] ||
            layers_[layer_id]->AllowForceBackward(bottom_id);
        blob_need_backward_[bottom_id_vecs_[layer_id][bottom_id]] =
            blob_need_backward_[bottom_id_vecs_[layer_id][bottom_id]] ||
            bottom_need_backward_[layer_id][bottom_id];
      }
      for (int param_id = 0; param_id < layers_[layer_id]->blobs().size();
           ++param_id) {
        layers_[layer_id]->set_param_propagate_down(param_id, true);
      }
    }
  }
  // In the end, all remaining blobs are considered output blobs.
  for (set<string>::iterator it = available_blobs.begin();
      it != available_blobs.end(); ++it) {
    LOG_IF(INFO, Caffe::root_solver())
        << "This network produces output " << *it;
    net_output_blobs_.push_back(blobs_[blob_name_to_idx[*it]].get());
    net_output_blob_indices_.push_back(blob_name_to_idx[*it]);
  }
  for (size_t blob_id = 0; blob_id < blob_names_.size(); ++blob_id) {
    blob_names_index_[blob_names_[blob_id]] = blob_id;
  }
  for (size_t layer_id = 0; layer_id < layer_names_.size(); ++layer_id) {
    layer_names_index_[layer_names_[layer_id]] = layer_id;
  }
  //handle all of the sharing weights event.
  ShareWeights();
  debug_info_ = param.debug_info();
  LOG_IF(INFO, Caffe::root_solver()) << "Network initialization done.";
}
// Helpers for Init.
/**
* @brief Remove layers that the user specified should be excluded given the current
*        phase, level, and stage.
*/
template <typename Dtype>
void Net<Dtype>::FilterNet(const NetParameter& param,
    NetParameter* param_filtered) {
  NetState net_state(param.state());
  param_filtered->CopyFrom(param);
  param_filtered->clear_layer();
  for (int i = 0; i < param.layer_size(); ++i) {
    const LayerParameter& layer_param = param.layer(i);
    const string& layer_name = layer_param.name();
    CHECK(layer_param.include_size() == 0 || layer_param.exclude_size() == 0)
          << "Specify either include rules or exclude rules; not both.";
    // If no include rules are specified, the layer is included by default and
    // only excluded if it meets one of the exclude rules.
    bool layer_included = (layer_param.include_size() == 0);
    for (int j = 0; layer_included && j < layer_param.exclude_size(); ++j) {
      if (StateMeetsRule(net_state, layer_param.exclude(j), layer_name)) {
        layer_included = false;
      }
    }
    for (int j = 0; !layer_included && j < layer_param.include_size(); ++j) {
      if (StateMeetsRule(net_state, layer_param.include(j), layer_name)) {
        layer_included = true;
      }
    }
    if (layer_included) {
      param_filtered->add_layer()->CopyFrom(layer_param);
    }
  }
}
/// @brief return whether NetState state meets NetStateRule rule
template <typename Dtype>
bool Net<Dtype>::StateMeetsRule(const NetState& state,
    const NetStateRule& rule, const string& layer_name) {
  // Check whether the rule is broken due to phase.
  if (rule.has_phase()) {
      if (rule.phase() != state.phase()) {
        LOG_IF(INFO, Caffe::root_solver())
            << "The NetState phase (" << state.phase()
            << ") differed from the phase (" << rule.phase()
            << ") specified by a rule in layer " << layer_name;
        return false;
      }
  }
  // Check whether the rule is broken due to min level.
  if (rule.has_min_level()) {
    if (state.level() < rule.min_level()) {
      LOG_IF(INFO, Caffe::root_solver())
          << "The NetState level (" << state.level()
          << ") is above the min_level (" << rule.min_level()
          << ") specified by a rule in layer " << layer_name;
      return false;
    }
  }
  // Check whether the rule is broken due to max level.
  if (rule.has_max_level()) {
    if (state.level() > rule.max_level()) {
      LOG_IF(INFO, Caffe::root_solver())
          << "The NetState level (" << state.level()
          << ") is above the max_level (" << rule.max_level()
          << ") specified by a rule in layer " << layer_name;
      return false;
    }
  }
  // Check whether the rule is broken due to stage. The NetState must
  // contain ALL of the rule's stages to meet it.
  for (int i = 0; i < rule.stage_size(); ++i) {
    // Check that the NetState contains the rule's ith stage.
    bool has_stage = false;
    for (int j = 0; !has_stage && j < state.stage_size(); ++j) {
      if (rule.stage(i) == state.stage(j)) { has_stage = true; }
    }
    if (!has_stage) {
      LOG_IF(INFO, Caffe::root_solver())
          << "The NetState did not contain stage '" << rule.stage(i)
          << "' specified by a rule in layer " << layer_name;
      return false;
    }
  }
  // Check whether the rule is broken due to not_stage. The NetState must
  // contain NONE of the rule's not_stages to meet it.
  for (int i = 0; i < rule.not_stage_size(); ++i) {
    // Check that the NetState contains the rule's ith not_stage.
    bool has_stage = false;
    for (int j = 0; !has_stage && j < state.stage_size(); ++j) {
      if (rule.not_stage(i) == state.stage(j)) { has_stage = true; }
    }
    if (has_stage) {
      LOG_IF(INFO, Caffe::root_solver())
          << "The NetState contained a not_stage '" << rule.not_stage(i)
          << "' specified by a rule in layer " << layer_name;
      return false;
    }
  }
  return true;
}

// Helper for Net::Init: add a new top blob to the net.
template <typename Dtype>
void Net<Dtype>::AppendTop(const NetParameter& param, const int layer_id,
                           const int top_id, set<string>* available_blobs,
                           map<string, int>* blob_name_to_idx) {
  shared_ptr<LayerParameter> layer_param(
      new LayerParameter(param.layer(layer_id)));
  const string& blob_name = (layer_param->top_size() > top_id) ?
      layer_param->top(top_id) : "(automatic)";
  // Check if we are doing in-place computation
  if (blob_name_to_idx && layer_param->bottom_size() > top_id &&
      blob_name == layer_param->bottom(top_id)) {
    // In-place computation
    LOG_IF(INFO, Caffe::root_solver())
        << layer_param->name() << " -> " << blob_name << " (in-place)";
    top_vecs_[layer_id].push_back(blobs_[(*blob_name_to_idx)[blob_name]].get());
    top_id_vecs_[layer_id].push_back((*blob_name_to_idx)[blob_name]);
  } else if (blob_name_to_idx &&
             blob_name_to_idx->find(blob_name) != blob_name_to_idx->end()) {
    // If we are not doing in-place computation but have duplicated blobs,
    // raise an error.
    LOG(FATAL) << "Top blob '" << blob_name
               << "' produced by multiple sources.";
  } else {
    // Normal output.
    if (Caffe::root_solver()) {
      LOG(INFO) << layer_param->name() << " -> " << blob_name;
    }
    shared_ptr<Blob<Dtype> > blob_pointer(new Blob<Dtype>());
    const int blob_id = blobs_.size();
    blobs_.push_back(blob_pointer);
    blob_names_.push_back(blob_name);
    blob_need_backward_.push_back(false);
    if (blob_name_to_idx) { (*blob_name_to_idx)[blob_name] = blob_id; }
    top_id_vecs_[layer_id].push_back(blob_id);
    top_vecs_[layer_id].push_back(blob_pointer.get());
  }
  if (available_blobs) { available_blobs->insert(blob_name); }
}

// Helper for Net::Init: add a new bottom blob to the net.
template <typename Dtype>
int Net<Dtype>::AppendBottom(const NetParameter& param, const int layer_id,
    const int bottom_id, set<string>* available_blobs,
    map<string, int>* blob_name_to_idx) {
  const LayerParameter& layer_param = param.layer(layer_id);
  const string& blob_name = layer_param.bottom(bottom_id);
  if (available_blobs->find(blob_name) == available_blobs->end()) {
    LOG(FATAL) << "Unknown bottom blob '" << blob_name << "' (layer '"
               << layer_param.name() << "', bottom index " << bottom_id << ")";
  }
  const int blob_id = (*blob_name_to_idx)[blob_name];
  LOG_IF(INFO, Caffe::root_solver())
      << layer_names_[layer_id] << " <- " << blob_name;
  bottom_vecs_[layer_id].push_back(blobs_[blob_id].get());
  bottom_id_vecs_[layer_id].push_back(blob_id);
  available_blobs->erase(blob_name);
  bool need_backward = blob_need_backward_[blob_id];
  // Check if the backpropagation on bottom_id should be skipped
  if (layer_param.propagate_down_size() > 0) {
    need_backward = layer_param.propagate_down(bottom_id);
  }
  bottom_need_backward_[layer_id].push_back(need_backward);
  return blob_id;
}

template <typename Dtype>
void Net<Dtype>::AppendParam(const NetParameter& param, const int layer_id,
                             const int param_id) {
  const LayerParameter& layer_param = layers_[layer_id]->layer_param();
  const int param_size = layer_param.param_size();
  string param_name =
      (param_size > param_id) ? layer_param.param(param_id).name() : "";
  if (param_name.size()) {
    param_display_names_.push_back(param_name);
  } else {
    ostringstream param_display_name;
    param_display_name << param_id;
    param_display_names_.push_back(param_display_name.str());
  }
  const int net_param_id = params_.size();
  params_.push_back(layers_[layer_id]->blobs()[param_id]);
  param_id_vecs_[layer_id].push_back(net_param_id);
  param_layer_indices_.push_back(make_pair(layer_id, param_id));
  ParamSpec default_param_spec;
  const ParamSpec* param_spec = (layer_param.param_size() > param_id) ?
      &layer_param.param(param_id) : &default_param_spec;
  if (!param_size || !param_name.size() || (param_name.size() &&
      param_names_index_.find(param_name) == param_names_index_.end())) {
    // This layer "owns" this parameter blob -- it is either anonymous
    // (i.e., not given a param_name) or explicitly given a name that we
    // haven't already seen.
    param_owners_.push_back(-1);
    if (param_name.size()) {
      param_names_index_[param_name] = net_param_id;
    }
    const int learnable_param_id = learnable_params_.size();
    learnable_params_.push_back(params_[net_param_id].get());
    learnable_param_ids_.push_back(learnable_param_id);
    has_params_lr_.push_back(param_spec->has_lr_mult());
    has_params_decay_.push_back(param_spec->has_decay_mult());
    params_lr_.push_back(param_spec->lr_mult());
    params_weight_decay_.push_back(param_spec->decay_mult());
  } else {
    // Named param blob with name we've seen before: share params
    const int owner_net_param_id = param_names_index_[param_name];
    param_owners_.push_back(owner_net_param_id);
    const pair<int, int>& owner_index =
        param_layer_indices_[owner_net_param_id];
    const int owner_layer_id = owner_index.first;
    const int owner_param_id = owner_index.second;
    LOG_IF(INFO, Caffe::root_solver()) << "Sharing parameters '" << param_name
        << "' owned by "
        << "layer '" << layer_names_[owner_layer_id] << "', param "
        << "index " << owner_param_id;
    Blob<Dtype>* this_blob = layers_[layer_id]->blobs()[param_id].get();
    Blob<Dtype>* owner_blob =
        layers_[owner_layer_id]->blobs()[owner_param_id].get();
    const int param_size = layer_param.param_size();
    if (param_size > param_id && (layer_param.param(param_id).share_mode() ==
                                  ParamSpec_DimCheckMode_PERMISSIVE)) {
      // Permissive dimension checking -- only check counts are the same.
      CHECK_EQ(this_blob->count(), owner_blob->count())
          << "Cannot share param '" << param_name << "' owned by layer '"
          << layer_names_[owner_layer_id] << "' with layer '"
          << layer_names_[layer_id] << "'; count mismatch.  Owner layer param "
          << "shape is " << owner_blob->shape_string() << "; sharing layer "
          << "shape is " << this_blob->shape_string();
    } else {
      // Strict dimension checking -- all dims must be the same.
      CHECK(this_blob->shape() == owner_blob->shape())
          << "Cannot share param '" << param_name << "' owned by layer '"
          << layer_names_[owner_layer_id] << "' with layer '"
          << layer_names_[layer_id] << "'; shape mismatch.  Owner layer param "
          << "shape is " << owner_blob->shape_string() << "; sharing layer "
          << "expects shape " << this_blob->shape_string();
    }
    const int learnable_param_id = learnable_param_ids_[owner_net_param_id];
    learnable_param_ids_.push_back(learnable_param_id);
    if (param_spec->has_lr_mult()) {
      if (has_params_lr_[learnable_param_id]) {
        CHECK_EQ(param_spec->lr_mult(), params_lr_[learnable_param_id])
            << "Shared param '" << param_name << "' has mismatched lr_mult.";
      } else {
        has_params_lr_[learnable_param_id] = true;
        params_lr_[learnable_param_id] = param_spec->lr_mult();
      }
    }
    if (param_spec->has_decay_mult()) {
      if (has_params_decay_[learnable_param_id]) {
        CHECK_EQ(param_spec->decay_mult(),
                 params_weight_decay_[learnable_param_id])
            << "Shared param '" << param_name << "' has mismatched decay_mult.";
      } else {
        has_params_decay_[learnable_param_id] = true;
        params_weight_decay_[learnable_param_id] = param_spec->decay_mult();
      }
    }
  }
}

其余的函数不在做详尽解释了

/**
   * @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.
   */
  // forword function from a layer and end in another, the start and end specify layer id.
  // if start is not specified, it will start at the beginning of network, usually data layer.
  // if end is not specified, it will end at the last layer, usually loss layer.
  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.
   */
  //generally like forward, and the start and end have same meaning.
  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();
  // forward and then backward. it will return loss.
  Dtype ForwardBackward() {
    Dtype loss;
    Forward(&loss);
    Backward();
    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);
  // the following methods load trained net from special file type.
  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;