SoftmaxLayer and SoftmaxwithLossLayer 代码解读

SoftmaxLayer and SoftmaxwithLossLayer 代码解读

Wang Xiao

---

　　先来看看 SoftmaxWithLoss 在prototext文件中的定义：

 layer {
 name: "loss"
 type: "SoftmaxWithLoss"
 bottom: "fc8"
 bottom: "label"
 top: "loss"
 }

　　再看SoftmaxWithLossLayer的.cpp文件：

　　

 #include <algorithm>
 #include <cfloat>
 #include <vector>

 #include "caffe/layers/softmax_loss_layer.hpp"
 #include "caffe/util/math_functions.hpp"

 namespace caffe {

 template <typename Dtype>
void SoftmaxWithLossLayer<Dtype>::LayerSetUp(
     const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
   LossLayer<Dtype>::LayerSetUp(bottom, top);
   LayerParameter softmax_param(this->layer_param_);
   softmax_param.set_type("Softmax");
   softmax_layer_ = LayerRegistry<Dtype>::CreateLayer(softmax_param);
   softmax_bottom_vec_.clear();
softmax_bottom_vec_.push_back(bottom[0]); // 将bottom[0]存入softmax_bottom_vec_;
   softmax_top_vec_.clear();
softmax_top_vec_.push_back(&prob_);  　　// 将 prob_ 存入 softmax_top_vec_;

 softmax_layer_->SetUp(softmax_bottom_vec_, softmax_top_vec_); 

 has_ignore_label_ =   // draw the parameter from layer
 this->layer_param_.loss_param().has_ignore_label(); 
 if (has_ignore_label_) { 
 ignore_label_ = this->layer_param_.loss_param().ignore_label(); 
  } 
 if (!this->layer_param_.loss_param().has_normalization() && 
 this->layer_param_.loss_param().has_normalize()) { 
 normalization_ = this->layer_param_.loss_param().normalize() ? 
  LossParameter_NormalizationMode_VALID : 
  LossParameter_NormalizationMode_BATCH_SIZE; 
 } else { 
 normalization_ = this->layer_param_.loss_param().normalization(); 
  } 
 }

---

　　

　　接下来是对输入数据进行 reshape 操作：

　　

 template <typename Dtype>
 void SoftmaxWithLossLayer<Dtype>::Reshape(
 const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
 LossLayer<Dtype>::Reshape(bottom, top);
 softmax_layer_->Reshape(softmax_bottom_vec_, softmax_top_vec_);
 softmax_axis_ =
 bottom[]->CanonicalAxisIndex(this->layer_param_.softmax_param().axis());
 outer_num_ = bottom[]->count(, softmax_axis_);
 inner_num_ = bottom[]->count(softmax_axis_ + );
 CHECK_EQ(outer_num_ * inner_num_, bottom[]->count())
 << "Number of labels must match number of predictions; "
 << "e.g., if softmax axis == 1 and prediction shape is (N, C, H, W), "
 << "label count (number of labels) must be N*H*W, "
 << "with integer values in {0, 1, ..., C-1}.";
 if (top.size() >= ) {
 // softmax output
 top[]->ReshapeLike(*bottom[]);
 }
 }