caffe——全连接层inner_product_layer

　　在caffe中，全连接层叫做"inner_product_layer"，区别于tensorflow中的fullyconnected_layer。

　

1、prototxt中的定义

layer {
  bottom: "fc7"
  top: "fc8"
  name: "fc8"
  type: "InnerProduct"
  param {  # 权重学习参数 lr_mult: 10 # 学习率 decay_mult: 1 } param { # bias 学习参数 lr_mult: 20 # 一般情况，bias 学习率是权重学习率的两倍. decay_mult: 0 } inner_product_param { num_output: 1000 # 输出单元个数 weight_filler { # 权重初始化方法 type: "gaussian" std: 0.005 } bias_filler { # bias 初始化方法 type: "constant" value: 0.1 } } }


2、caffe.proto中的定义

message LayerParameter {
    optional InnerProductParameter inner_product_param = 117;
}

message InnerProductParameter {
  optional uint32 num_output = 1;   // 网络层输出个数
  optional bool bias_term = 2 [default = true]; // 是否有 bias 项 optional FillerParameter weight_filler = 3; // 权重weight filler optional FillerParameter bias_filler = 4; // 偏置bias filler // 在第一个 axis 进行单个内积计算. // -1 表示最后一个 axis optional int32 axis = 5 [default = 1]; //权重矩阵是否进行转置 optional bool transpose = 6 [default = false]; }

3、inner_product_layer.hpp

#ifndef CAFFE_INNER_PRODUCT_LAYER_HPP_
#define CAFFE_INNER_PRODUCT_LAYER_HPP_

#include <vector> #include "caffe/blob.hpp" #include "caffe/layer.hpp" #include "caffe/proto/caffe.pb.h" namespace caffe { /** * @brief Also known as a "fully-connected" layer, computes an inner product * with a set of learned weights, and (optionally) adds biases. * * TODO(dox): thorough documentation for Forward, Backward, and proto params. */ template <typename Dtype> class InnerProductLayer : public Layer<Dtype> { public: explicit InnerProductLayer(const LayerParameter& param) : Layer<Dtype>(param) {} virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top); virtual void Reshape(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top); virtual inline const char* type() const { return "InnerProduct"; } virtual inline int ExactNumBottomBlobs() const { return 1; } virtual inline int ExactNumTopBlobs() const { return 1; } protected: virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top); virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top); virtual void Backward_cpu(const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom); virtual void Backward_gpu(const vector<Blob<Dtype>*>& top, const

转载于:https://www.cnblogs.com/jianfeifeng/p/11010865.html