C++實現神經BP神經網路
阿新 • • 發佈：2020-05-26
本文例項為大家分享了C++實現神經BP神經網路的具體程式碼，供大家參考，具體內容如下
BP.h
#pragma once
#include<vector>
#include<stdlib.h>
#include<time.h>
#include<cmath>
#include<iostream>
using std::vector;
using std::exp;
using std::cout;
using std::endl;
class BP
{
private:
int studyNum;//允許學習次數
double h;//學習率
double allowError;//允許誤差
vector<int> layerNum;//每層的節點數，不包括常量節點1
vector<vector<vector<double>>> w;//權重
vector<vector<vector<double>>> dw;//權重增量
vector<vector<double>> b;//偏置
vector<vector<double>> db;//偏置增量
vector<vector<vector<double>>> a;//節點值
vector<vector<double>> x;//輸入
vector<vector<double>> y;//期望輸出
void iniwb();//初始化w與b
void inidwdb();//初始化dw與db
double sigmoid(double z);//啟用函式
void forward();//前向傳播
void backward();//後向傳播
double Error();//計算誤差
public:
BP(vector<int>const& layer_num,vector<vector<double>>const & input_a0,vector<vector<double>> const & output_y,double hh = 0.5,double allerror = 0.001,int studynum = 1000);
BP();
void setLayerNumInput(vector<int>const& layer_num,vector<vector<double>> const & input);
void setOutputy(vector<vector<double>> const & output_y);
void setHErrorStudyNum(double hh,double allerror,int studynum);
void run();//執行BP神經網路
vector<double> predict(vector<double>& input);//使用已經學習好的神經網路進行預測
~BP();
};BP.cpp
#include "BP.h"
BP::BP(vector<int>const& layer_num,vector<vector<double>>const & input,double hh,int studynum)
{
layerNum = layer_num;
x = input;//輸入多少個節點的資料，每個節點有多少份資料
y = output_y;
h = hh;
allowError = allerror;
a.resize(layerNum.size());//有這麼多層網路節點
for (int i = 0; i < layerNum.size(); i++)
{
a[i].resize(layerNum[i]);//每層網路節點有這麼多個節點
for (int j = 0; j < layerNum[i]; j++)
a[i][j].resize(input[0].size());
}
a[0] = input;
studyNum = studynum;
}
BP::BP()
{
layerNum = {};
a = {};
y = {};
h = 0;
allowError = 0;
}
BP::~BP()
{
}
void BP::setLayerNumInput(vector<int>const& layer_num,vector<vector<double>> const & input)
{
layerNum = layer_num;
x = input;
a.resize(layerNum.size());//有這麼多層網路節點
for (int i = 0; i < layerNum.size(); i++)
{
a[i].resize(layerNum[i]);//每層網路節點有這麼多個節點
for (int j = 0; j < layerNum[i]; j++)
a[i][j].resize(input[0].size());
}
a[0] = input;
}
void BP::setOutputy(vector<vector<double>> const & output_y)
{
y = output_y;
}
void BP::setHErrorStudyNum(double hh,int studynum)
{
h = hh;
allowError = allerror;
studyNum = studynum;
}
//初始化權重矩陣
void BP::iniwb()
{
w.resize(layerNum.size() - 1);
b.resize(layerNum.size() - 1);
srand((unsigned)time(NULL));
//節點層數層數
for (int l = 0; l < layerNum.size() - 1; l++)
{
w[l].resize(layerNum[l + 1]);
b[l].resize(layerNum[l + 1]);
//對應後層的節點
for (int j = 0; j < layerNum[l + 1]; j++)
{
w[l][j].resize(layerNum[l]);
b[l][j] = -1 + 2 * (rand() / RAND_MAX);
//對應前層的節點
for (int k = 0; k < layerNum[l]; k++)
w[l][j][k] = -1 + 2 * (rand() / RAND_MAX);
}
}
}
void BP::inidwdb()
{
dw.resize(layerNum.size() - 1);
db.resize(layerNum.size() - 1);
//節點層數層數
for (int l = 0; l < layerNum.size() - 1; l++)
{
dw[l].resize(layerNum[l + 1]);
db[l].resize(layerNum[l + 1]);
//對應後層的節點
for (int j = 0; j < layerNum[l + 1]; j++)
{
dw[l][j].resize(layerNum[l]);
db[l][j] = 0;
//對應前層的節點
for (int k = 0; k < layerNum[l]; k++)
w[l][j][k] = 0;
}
}
}
//啟用函式
double BP::sigmoid(double z)
{
return 1.0 / (1 + exp(-z));
}
void BP::forward()
{
for (int l = 1; l < layerNum.size(); l++)
{
for (int i = 0; i < layerNum[l]; i++)
{
for (int j = 0; j < x[0].size(); j++)
{
a[l][i][j] = 0;//第l層第i個節點第j個數據樣本
//計算變數節點乘權值的和
for (int k = 0; k < layerNum[l - 1]; k++)
a[l][i][j] += a[l - 1][k][j] * w[l - 1][i][k];
//加上節點偏置
a[l][i][j] += b[l - 1][i];
a[l][i][j] = sigmoid(a[l][i][j]);
}
}
}
}
void BP::backward()
{
int xNum = x[0].size();//樣本個數
//daP第l層da，daB第l+1層da
vector<double> daP,daB;
for (int j = 0; j < xNum; j++)
{
//處理最後一層的dw
daP.clear();
daP.resize(layerNum[layerNum.size() - 1]);
for (int i = 0,l = layerNum.size() - 1; i < layerNum[l]; i++)
{
daP[i] = a[l][i][j] - y[i][j];
for (int k = 0; k < layerNum[l - 1]; k++)
dw[l - 1][i][k] += daP[i] * a[l][i][j] * (1 - a[l][i][j])*a[l - 1][k][j];
db[l - 1][i] += daP[i] * a[l][i][j] * (1 - a[l][i][j]);
}
//處理剩下層的權重w的增量Dw
for (int l = layerNum.size() - 2; l > 0; l--)
{
daB = daP;
daP.clear();
daP.resize(layerNum[l]);
for (int k = 0; k < layerNum[l]; k++)
{
daP[k] = 0;
for (int i = 0; i < layerNum[l + 1]; i++)
daP[k] += daB[i] * a[l + 1][i][j] * (1 - a[l + 1][i][j])*w[l][i][k];
//dw
for (int i = 0; i < layerNum[l - 1]; i++)
dw[l - 1][k][i] += daP[k] * a[l][k][j] * (1 - a[l][k][j])*a[l - 1][i][j];
//db
db[l-1][k] += daP[k] * a[l][k][j] * (1 - a[l][k][j]);
}
}
}
//計算dw與db平均值
for (int l = 0; l < layerNum.size() - 1; l++)
{
//對應後層的節點
for (int j = 0; j < layerNum[l + 1]; j++)
{
db[l][j] = db[l][j] / xNum;
//對應前層的節點
for (int k = 0; k < layerNum[l]; k++)
w[l][j][k] = w[l][j][k] / xNum;
}
}
//更新引數w與b
for (int l = 0; l < layerNum.size() - 1; l++)
{
for (int j = 0; j < layerNum[l + 1]; j++)
{
b[l][j] = b[l][j] - h * db[l][j];
//對應前層的節點
for (int k = 0; k < layerNum[l]; k++)
w[l][j][k] = w[l][j][k] - h * dw[l][j][k];
}
}
}
double BP::Error()
{
int l = layerNum.size() - 1;
double temp = 0,error = 0;
for (int i = 0; i < layerNum[l]; i++)
for (int j = 0; j < x[0].size(); j++)
{
temp = a[l][i][j] - y[i][j];
error += temp * temp;
}
error = error / x[0].size();//求對每一組樣本的誤差平均
error = error / 2;
cout << error << endl;
return error;
}
//執行神經網路
void BP::run()
{
iniwb();
inidwdb();
int i = 0;
for (; i < studyNum; i++)
{
forward();
if (Error() <= allowError)
{
cout << "Study Success!" << endl;
break;
}
backward();
}
if (i == 10000)
cout << "Study Failed!" << endl;
}
vector<double> BP::predict(vector<double>& input)
{
vector<vector<double>> a1;
a1.resize(layerNum.size());
for (int l = 0; l < layerNum.size(); l++)
a1[l].resize(layerNum[l]);
a1[0] = input;
for (int l = 1; l < layerNum.size(); l++)
for (int i = 0; i < layerNum[l]; i++)
{
a1[l][i] = 0;//第l層第i個節點第j個數據樣本
//計算變數節點乘權值的和
for (int k = 0; k < layerNum[l - 1]; k++)
a1[l][i] += a1[l - 1][k] * w[l - 1][i][k];
//加上節點偏置
a1[l][i] += b[l - 1][i];
a1[l][i] = sigmoid(a1[l][i]);
}
return a1[layerNum.size() - 1];
}驗證程式：
#include"BP.h"
int main()
{
vector<int> layer_num = { 1,10,1 };
vector<vector<double>> input_a0 = { { 1,2,3,4,5,6,7,8,9,10 } };
vector<vector<double>> output_y = { {0,1,1} };
BP bp(layer_num,input_a0,output_y,0.6,0.001,2000);
bp.run();
for (int j = 0; j < 30; j++)
{
vector<double> input = { 0.5*j };
vector<double> output = bp.predict(input);
for (auto i : output)
cout << "j:" << 0.5*j <<" pridict:" << i << " ";
cout << endl;
}
system("pause");
return 0;
}輸出：
以上就是本文的全部內容，希望對大家的學習有所幫助，也希望大家多多支援我們。