神经网络/BP（反向传播）代码示例

#include <iostream>
#include <cstdlib>
#include <cmath>
#include <vector>
using namespace std;const int NX = 784, NB = 500, NY = 10;//输入层X，隐藏层B，输出层Y节点数
const double eta = 0.06;//学习率struct Node {double val{};double bias{};vector<double> weight;
} x[NX], b[NB], y[NY];//输入层X，隐藏层B，输出层Y
double g[NY], e[NB];//用于反向传播
double trainx[NX], trainy[NY];//训练数据double sigmoid(double x) { return 1.0 / (1.0 + exp(-x)); }double get_rand_weight() { return rand() % 10 / 5.0 - 1; } //生成(-1,1)随机数
double get_rand_bias() { return rand() % 10 / 500.0 - 0.01; } //生成(-0.01,0.01)随机数//网络初始化
void init() {for (int i = 0; i < NX; i++) {//x[i].bias = get_rand_bias();for (int j = 0; j < NB; j++) {x[i].weight.push_back(get_rand_weight());}}for (int i = 0; i < NB; i++) {b[i].bias = get_rand_bias();for (int j = 0; j < NY; j++) {b[i].weight.push_back(get_rand_weight());}}for (int i = 0; i < NY; i++) {y[i].bias = get_rand_bias();}
};//前向传播
void forward() {//首先需要清空隐藏层和输出层原有的非参数数据！！！for (int i = 0; i < NB; i++) b[i].val = 0;for (int i = 0; i < NY; i++) y[i].val = 0;//输入层读取数据for (int i = 0; i < NX; i++) x[i].val = trainx[i];//输入层->隐藏层for (int i = 0; i < NX; i++) {for (int j = 0; j < NB; j++) {b[j].val += x[i].val * x[i].weight[j];}}//隐藏层求值for (int i = 0; i < NB; i++) {b[i].val = sigmoid(b[i].val - b[i].bias);}//隐藏层->输出层for (int i = 0; i < NB; i++) {for (int j = 0; j < NY; j++) {y[j].val += b[i].val * b[i].weight[j];}}//输出层求值for (int i = 0; i < NY; i++) {y[i].val = sigmoid(y[i].val - y[i].bias);}
}//反向传播
void back() {//计算g和efor (int i = 0; i < NY; i++) {g[i] = y[i].val * (1 - y[i].val) * (trainy[i] - y[i].val);}for (int i = 0; i < NB; i++) {double res = 0;for (int j = 0; j < NY; j++) {res += b[i].weight[j] * g[j];}e[i] = b[i].val * (1 - b[i].val) * res;}//更新w, theta, v, gammafor (int i = 0; i < NB; i++)for (int j = 0; j < NY; j++)b[i].weight[j] += eta * b[i].val * g[j];for (int i = 0; i < NY; i++)y[i].bias -= eta * g[i];for (int i = 0; i < NX; i++)for (int j = 0; j < NB; j++)x[i].weight[j] += eta * x[i].val * e[j];for (int i = 0; i < NB; i++)b[i].bias -= eta * e[i];
}FILE *fImg, *fAns;
int result[1000000] = {0}; //每次训练的结果，正确为1，错误为0
void train(int Case) {//读入一张新的图片//除了前16字节，接下来的信息都是一张一张的图片//每张图片大小为28*28 = 784 = NX，每个char表示该像素对应的灰度，范围为0至255unsigned char img[NX], ans;fread(img, 1, NX, fImg);for (int i = 0; i < NX; i++) trainx[i] = (double)img[i] / 255.0;//读入该图片对应的答案//除了前8字节，第k个字节对应第k张图片的正确答案fread(&ans,1,1,fAns);for(int i = 0; i < NY; i++) trainy[i] = (i == ans) ? 1 : 0;//前向传播，计算答案是否正确forward();int res = 0;for (int i = 0; i <= 9; i++)if (y[i].val > y[res].val)res = i;result[Case] = (res == ans) ? 1 : 0;for (int i = 0; i < 28; i++) {for (int j = 0; j < 28; j++) {if (trainx[i * 28 + j] != 0) cout << 'X';else cout << ' ';}cout << endl;}cout << "Test Case #" << Case <<", result is " << res << ", answer is " << (int)ans << endl;//反向传播back();//输出最近100局的正确率int P = 100, cnt = 0;if(Case % P == 0) {for(int i = 0; i < P; i++)cnt += result[Case - i];cout << Case << " " << cnt << endl;}
}int main() {fImg=fopen("train-images.idx3-ubyte","rb");fseek(fImg, 16, SEEK_SET);fAns=fopen("train-labels.idx1-ubyte","rb");fseek(fAns, 8, SEEK_SET);freopen("result.txt", "w", stdout);init();for (int Case = 1; Case <= 60000; Case++) {train(Case);}return 0;
}