Caffe net:init()函数代码详细注解
Caffe 中net的初始化函数init()是整个网络创建的关键函数。在此对此函数做详细的梳理。
一、代码的总体介绍
该init()函数中主要包括以下几个函数：
1. FilterNet(in_param,&filtered_param);
此函数的作用就是模型参数文件（*.prototxt）中的不符合规则的层去掉。例如：在caffe的examples/mnist中的lenet网络中，如果只是用于网络的前向，则需要将包含train的数据层去掉。如下：
layer {
name: "mnist"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
scale: 0.00390625
}
data_param {
source: "examples/mnist/mnist_train_lmdb"
batch_size: 64
backend: LMDB
}
}//在test计算中，此层就会调用函数FilterNet()被过滤掉2、InsertSplits(filtered_param,¶m);
此函数作用是，对于底层一个输出blob对应多个上层的情况，则要在加入分裂层，形成新的网络。这么做的主要原因是多个层反传给该blob的梯度需要累加。
例如：LeNet网络中的数据层的top label blob对应两个输入层，分别是accuracy层和loss层，那么需要在数据层在插入一层。如下图：
数据层之上插入了一个新的层，label_mnist_1_split层，为该层的创建两个top blob分别为，Label_mnist_1_split_0和Label_mnist_1_split_1。
3、layers_.push_back();
该行代码是把当前层的参数转换为shared_ptr<Layer<Dtype>>，创建一个具体的层，并压入到layers_中
4、AppendBottom();
此函数为该层创建bottom blob，由于网络是堆叠而成，即：当前层的输出 bottom是前一层的输出top blob，因此此函数并没没有真正的创建blob，只是在将前一层的指针压入到了bottom_vecs_中。
5、AppendTop();
此函数为该层创建top blob，该函数真正的new的一个blob的对象。并将topblob 的指针压入到top_vecs_中
6、layers_[layer_id]->SetUp();
前面创建了具体的层，并为层创建了输入bottom blob 和输出top blob。改行代码这是启动该层，setup()函数的功能是为创建的blob分配数据内存空间，如有必要还需要调整该层的输入bottom blob 和输出top blob的shape。
7、AppendParam();
对于某些有参数的层，例如：卷基层、全连接层有weight和bias。该函数主要是修改和参数有关的变量，实际的层参数的blob在上面提到的setup()函数中已经创建。如：将层参数blob的指针压入到params_。
二、下面是对函数Net:init()的代码的详细注解。
template <typename Dtype>
void Net<Dtype>::Init(const NetParameter& in_param) {
CHECK(Caffe::root_solver() || root_net_)
<< "root_net_ needs to be set for all non-root solvers";
// Set phase from the state.
phase_ = in_param.state().phase();
// Filter layers based on their include/exclude rules and
// the current NetState.
NetParameter filtered_param;
/*将in_param中的某些不符合规则的层去掉*/
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;
/*
*调用InsertSplits()函数,对于底层的一个输出blob对应多个上层的情况，
*则要在加入分裂层，形成新的网络。
**/
InsertSplits(filtered_param, ¶m);
/*
*以上部分只是根据 *.prototxt文件，确定网络name 和 blob的name的连接情况，
*下面部分是层以及层间的blob的创建，函数ApendTop()中间blob的实例化
*函数layer->SetUp()分配中间层blob的内存空间
*appendparam()
*/
// 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());//存每一层的输入(bottom)blob指针
top_vecs_.resize(param.layer_size());//存每一层输出(top)的blob指针
bottom_id_vecs_.resize(param.layer_size());//存每一层输入(bottom)blob的id
param_id_vecs_.resize(param.layer_size());//存每一层参数blob的id
top_id_vecs_.resize(param.layer_size());//存每一层输出(top)的blob的id
bottom_need_backward_.resize(param.layer_size());//该blob是需要返回的bool值
//（很大的一个for循环）对每一层处理
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.
//如果当前层没有设置phase，则将当前层phase设置为网络net 的phase
if (!param.layer(layer_id).has_phase()) {
param.mutable_layer(layer_id)->set_phase(phase_);
}
// Setup layer.
// param.layers(i)返回的是关于第当前层的参数：
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 (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 {
/*
*把当前层的参数转换为shared_ptr<Layer<Dtype>>，
*创建一个具体的层，并压入到layers_中
*/
layers_.push_back(LayerRegistry<Dtype>::CreateLayer(layer_param));
}
//把当前层的名字压入到layer_names_：vector<string> layer_names_
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
//下面开始产生当前层：分别处理bottom的blob和top的blob两个步骤
//输入bottom blob
for (int bottom_id = 0; bottom_id < layer_param.bottom_size();
++bottom_id) {
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.
/*
*blob_need_backward_,整个网络中，所有非参数blob，是否需要backward。
*注意，这里所说的所有非参数blob其实指的是AppendTop函数中遍历的所有top blob,
*并不是每一层的top+bottom,因为这一层的top就是下一层的bottom,网络是一层一层堆起来的。
*/
need_backward |= blob_need_backward_[blob_id];
}
//输出top blob
int num_top = layer_param.top_size();
for (int top_id = 0; top_id < num_top; ++top_id) {
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 {
// 在 SetUp()中为 appendTop()中创建的Blob分配内存空间
layers_[layer_id]->SetUp(bottom_vecs_[layer_id], top_vecs_[layer_id]);
}
LOG_IF(INFO, Caffe::root_solver())
<< "Setting up " << layer_names_[layer_id];
//每次循环，都会更新向量blob_loss_weights
for (int top_id = 0; top_id < top_vecs_[layer_id].size(); ++top_id) {
//blob_loss_weights_,每次遍历一个layer的时候，都会resize blob_loss_weights_,
//然后调用模板类layer的loss函数返回loss_weight
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));
}
//top_id_vecs_中存储的最基本元素是blob_id -> 每一个新的blob都会赋予其一个blob_id，
//但是这个blob_id可能是会有重复的
blob_loss_weights_[top_id_vecs_[layer_id][top_id]] = layer->loss(top_id);
//loss函数返回loss_weight —> 在模板类的SetUp方法中会调用SetLossWeights来设置其私有数据成员loss_,
//里面存储的其实是loss_weight
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);
}
//计算所需内存
memory_used_ += top_vecs_[layer_id][top_id]->count();
}
LOG_IF(INFO, Caffe::root_solver())
<< "Memory required for data: " << memory_used_ * sizeof(Dtype);
/*
*以下部分是对 每层的param blob 的处理，主要是AppendParam()函数，
*将param blob 以及blob的ID添加到 params_,param_id_vecs_ 等
*/
const int param_size = layer_param.param_size();
// 层内blob_的数量，即该层有几个权重参数，每个blob内有一个参数，例如；cov层和IP层都有两个参数
const int num_param_blobs = layers_[layer_id]->blobs().size();
//param_size是Layermeter类型对象layer_param中ParamSpec param成员的个数,
//num_param_blobs是一个Layer中learnable parameter blob的个数，param_size <= num_param_blobs
CHECK_LE(param_size, num_param_blobs)
<< "Too many params specified for layer " << layer_param.name();
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;
//由param_need_backward来决定need_backward是否为真，
//并且，只要有一次遍历使得need_backward为真，则这个for循环结束后，need_backward也为真
need_backward |= param_need_backward;
layers_[layer_id]->set_param_propagate_down(param_id,
param_need_backward);
}
/*
*添加parameter blob,如果当前layer没有parameter blob(num_param_blobs==0),
*比如ReLU，那么就不进入循环，不添加parameter blob
*AppendParam只是执行为当前layer添加parameter blob的相关工作，
*并不会修改与backward的相关属性
*/
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);
/*
*在上述的AppendTop函数中，在遍历当前层的每一个top blob的时候
*都会将一个false（默认值）压入向量blob_need_backward_。
*在下面的代码中，如果这个layer need backward，则会更新blob_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;
}
}
}
/*至此上面部分各个层被创建并启动，下面部分是按后向顺序修正backward设置 */
// 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
/*
*需要注意的是，上述代码中关于backward设置的部分，是按照前向的顺序设置的，
*而下面的代码是按后向顺序修正前向设置的结果。
* 一个layer是否需要backward computation，主要依据两个方面：
* (1)该layer的top blob 是否参与loss的计算；
* (2)该layer的bottom blob 是否需要backward computation，
* 比如Data层一般就不需要backward computation
*/
set<string> blobs_under_loss;
set<string> blobs_skip_backp;
//反向，从后向前
for (int layer_id = layers_.size() - 1; layer_id >= 0; --layer_id) {
bool layer_contributes_loss = false;
bool layer_skip_propagate_down = true;
/*
*为true，则表示当前layer的bottom blob不需要backward computation
*即该层不需要backward computation。
*这个局部变量所表示的意义与caffe.proto里
*message Layerparameter的propagate_down的定义恰好相反。
*/
for (int top_id = 0; top_id < top_vecs_[layer_id].size(); ++top_id) {
//blob_names_整个网络中，所有非参数blob的name
const string& blob_name = blob_names_[top_id_vecs_[layer_id][top_id]];
if (layers_[layer_id]->loss(top_id) ||
(blobs_under_loss.find(blob_name) != blobs_under_loss.end())) {
layer_contributes_loss = true;
}
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_,整个网络所有网络层的bottom blob是否需要backward
bottom_need_backward_[layer_id][bottom_id] = false;
}
}
if (!layer_contributes_loss) { layer_need_backward_[layer_id] = false; }
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.";
}
}
//修正前向设置的结果
for (int bottom_id = 0; bottom_id < bottom_vecs_[layer_id].size();
++bottom_id) {
if (layer_contributes_loss) {
const string& blob_name =
blob_names_[bottom_id_vecs_[layer_id][bottom_id]];
blobs_under_loss.insert(blob_name);//为blobs_under_loss添加新元素
} else {
bottom_need_backward_[layer_id][bottom_id] = false;
}
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) {
//第一次使用向量blob_names_index_,逐一添加元素，是一个map
blob_names_index_[blob_names_[blob_id]] = blob_id;
}
for (size_t layer_id = 0; layer_id < layer_names_.size(); ++layer_id) {
//第一次使用向量layer_names_index_，逐一添加元素，是一个map
layer_names_index_[layer_names_[layer_id]] = layer_id;
}
ShareWeights();
debug_info_ = param.debug_info();
LOG_IF(INFO, Caffe::root_solver()) << "Network initialization done.";
}
（完）