本文實例為大家分享了C++實現神經BP神經網絡的具體代碼,供大家參考,具體內容如下
BP.h
#pragma once #include#include#include#include#includeusing 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 vectorlayerNum;//每層的節點數,不包括常量節點1 vector<vector<vector>> w;//權重 vector<vector<vector>> dw;//權重增量 vector<vector> b;//偏置 vector<vector> db;//偏置增量 vector<vector<vector>> a;//節點值 vector<vector> x;//輸入 vector<vector> 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);//激活函數 void forward();//前向傳播 void backward();//後向傳播 double Error();//計算誤差 public: BP(vectorconst& layer_num, vector<vector>const & input_a0, vector<vector> const & output_y, double hh = 0.5, double allerror = 0.001, int studynum = 1000); BP(); void setLayerNumInput(vectorconst& layer_num, vector<vector> const & input); void setOutputy(vector<vector> const & output_y); void setHErrorStudyNum(double hh, double allerror,int studynum); void run();//運行BP神經網絡 vectorpredict(vector& input);//使用已經學習好的神經網絡進行預測 ~BP(); };
BP.cpp
#include "BP.h" BP::BP(vectorconst& layer_num, vector<vector>const & input, vector<vector> const & output_y, double hh, double allerror,int studynum) { layerNum = layer_num; x = input;//輸入多少個節點的數據,每個節點有多少份數據 y = output_y; h = hh; allowError = allerror; a.resize(layerNum.size());//有這麼多層網絡節點 for (int i = 0; i < layerNum.size(); i++) { a[i].resize(layerNum[i]);//每層網絡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(vectorconst& layer_num, vector<vector> const & input) { layerNum = layer_num; x = input; a.resize(layerNum.size());//有這麼多層網絡節點 for (int i = 0; i < layerNum.size(); i++) { a[i].resize(layerNum[i]);//每層網絡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> const & output_y) { y = output_y; } void BP::setHErrorStudyNum(double hh, double allerror,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; } } } //激活函數 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 //計算變量節點乘權值的和 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 vectordaP, 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; } } //更新參數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; } //運行神經網絡 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; } vectorBP::predict(vector& input) { vector<vector> 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 //計算變量節點乘權值的和 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]; }
驗證程序:
#include"BP.h" int main() { vectorlayer_num = { 1, 10, 1 }; vector<vector> input_a0 = { { 1,2,3,4,5,6,7,8,9,10 } }; vector<vector> output_y = { {0,0,0,0,1,1,1,1,1,1} }; BP bp(layer_num, input_a0,output_y,0.6,0.001, 2000); bp.run(); for (int j = 0; j < 30; j++) { vectorinput = { 0.5*j }; vectoroutput = bp.predict(input); for (auto i : output) cout << "j:" << 0.5*j <<" pridict:" << i << " "; cout << endl; } system("pause"); return 0; }
輸出:
[月球人 ] C++實現神經BP神經網絡已經有245次圍觀