rbm C++程式碼理解
阿新 • • 發佈:2019-02-12
#include <iostream> #include <math.h> #include "RBM.h" using namespace std; double uniform(double min, double max) { //在max與min之間隨機一個數 return rand() / (RAND_MAX + 1.0) * (max - min) + min; } int binomial(int n, double p) { //二值化 if(p < 0 || p > 1) return 0; int c = 0; double r; for(int i=0; i<n; i++) { r = rand() / (RAND_MAX + 1.0); if (r < p) c++; } return c; } double sigmoid(double x) { return 1.0 / (1.0 + exp(-x)); } RBM::RBM(int size, int n_v, int n_h, double **w, double *hb, double *vb) { //初始化RBM:W,hbias,vbias N = size; n_visible = n_v; n_hidden = n_h; if(w == NULL) { W = new double*[n_hidden]; for(int i=0; i<n_hidden; i++) W[i] = new double[n_visible]; double a = 1.0 / n_visible; for(int i=0; i<n_hidden; i++) { for(int j=0; j<n_visible; j++) { W[i][j] = uniform(-a, a); } } } else { W = w; } if(hb == NULL) { hbias = new double[n_hidden]; for(int i=0; i<n_hidden; i++) hbias[i] = 0; } else { hbias = hb; } if(vb == NULL) { vbias = new double[n_visible]; for(int i=0; i<n_visible; i++) vbias[i] = 0; } else { vbias = vb; } } RBM::~RBM() { //解構函式 for(int i=0; i<n_hidden; i++) delete[] W[i]; delete[] W; delete[] hbias; delete[] vbias; } void RBM::contrastive_divergence(int *input, double lr, int k) { //cd-k input為輸入資料,lr為學習率, double *ph_mean = new double[n_hidden]; //通過計算得到的h0隱含節點的輸入值 int *ph_sample = new int[n_hidden]; //二值化後得到的h0 double *nv_means = new double[n_visible]; //通過計算得到的v1重構節點的輸入值 int *nv_samples = new int[n_visible]; //二值化後得到的v1 double *nh_means = new double[n_hidden]; //通過計算得到的h1重構隱含節點的輸入值 int *nh_samples = new int[n_hidden]; //二值化後得到的h0 /* CD-k */ sample_h_given_v(input, ph_mean, ph_sample); //首先計算h0 for(int step=0; step<k; step++) { if(step == 0) { gibbs_hvh(ph_sample, nv_means, nv_samples, nh_means, nh_samples); //一般k等於1。重構v1和h1 } else { gibbs_hvh(nh_samples, nv_means, nv_samples, nh_means, nh_samples); } } for(int i=0; i<n_hidden; i++) { //更新W,hbias,vbias for(int j=0; j<n_visible; j++) { // W[i][j] += lr * (ph_sample[i] * input[j] - nh_means[i] * nv_samples[j]) / N; W[i][j] += lr * (ph_mean[i] * input[j] - nh_means[i] * nv_samples[j]) / N; //△Wij=lr * (ph_mean[i] * input[j] - nh_means[i] * nv_samples[j]) / N } hbias[i] += lr * (ph_sample[i] - nh_means[i]) / N; //△hbias=lr * (ph_sample[i] - nh_means[i]) / N; } for(int i=0; i<n_visible; i++) { vbias[i] += lr * (input[i] - nv_samples[i]) / N; //△vbias=lr * (input[i] - nv_samples[i]) / N,和hitton的更新不太一樣。 } delete[] ph_mean; delete[] ph_sample; delete[] nv_means; delete[] nv_samples; delete[] nh_means; delete[] nh_samples; } void RBM::sample_h_given_v(int *v0_sample, double *mean, int *sample) { //已知v取樣h for(int i=0; i<n_hidden; i++) { mean[i] = propup(v0_sample, W[i], hbias[i]); sample[i] = binomial(1, mean[i]); } } void RBM::sample_v_given_h(int *h0_sample, double *mean, int *sample) { //已知h取樣v for(int i=0; i<n_visible; i++) { mean[i] = propdown(h0_sample, i, vbias[i]); sample[i] = binomial(1, mean[i]); } } double RBM::propup(int *v, double *w, double b) { //propup傳入的是要求的隱層節點對應那一行的權值W[i] double pre_sigmoid_activation = 0.0; for(int j=0; j<n_visible; j++) { pre_sigmoid_activation += w[j] * v[j]; } pre_sigmoid_activation += b; return sigmoid(pre_sigmoid_activation); } double RBM::propdown(int *h, int i, double b) { //propdown傳入的是要求的重構可見層節點號i double pre_sigmoid_activation = 0.0; for(int j=0; j<n_hidden; j++) { pre_sigmoid_activation += W[j][i] * h[j]; } pre_sigmoid_activation += b; return sigmoid(pre_sigmoid_activation); } void RBM::gibbs_hvh(int *h0_sample, double *nv_means, int *nv_samples, \ double *nh_means, int *nh_samples) { sample_v_given_h(h0_sample, nv_means, nv_samples); sample_h_given_v(nv_samples, nh_means, nh_samples); } void RBM::reconstruct(int *v, double *reconstructed_v) { //重構,propup一次,propdown一次得到重構值。 double *h = new double[n_hidden]; double pre_sigmoid_activation; for(int i=0; i<n_hidden; i++) { h[i] = propup(v, W[i], hbias[i]); } for(int i=0; i<n_visible; i++) { pre_sigmoid_activation = 0.0; for(int j=0; j<n_hidden; j++) { pre_sigmoid_activation += W[j][i] * h[j]; } pre_sigmoid_activation += vbias[i]; reconstructed_v[i] = sigmoid(pre_sigmoid_activation); } delete[] h; } void test_rbm() { srand(0); double learning_rate = 0.1; int training_epochs = 1000; int k = 1; int train_N = 6; int test_N = 2; int n_visible = 6; int n_hidden = 3; // training data int train_X[6][6] = { {1, 1, 1, 0, 0, 0}, {1, 0, 1, 0, 0, 0}, {1, 1, 1, 0, 0, 0}, {0, 0, 1, 1, 1, 0}, {0, 0, 1, 0, 1, 0}, {0, 0, 1, 1, 1, 0} }; // construct RBM RBM rbm(train_N, n_visible, n_hidden, NULL, NULL, NULL); // train for(int epoch=0; epoch<training_epochs; epoch++) { for(int i=0; i<train_N; i++) { rbm.contrastive_divergence(train_X[i], learning_rate, k); } } // test data int test_X[2][6] = { {1, 1, 0, 0, 0, 0}, {0, 0, 0, 1, 1, 0} }; double reconstructed_X[2][6]; // test for(int i=0; i<test_N; i++) { rbm.reconstruct(test_X[i], reconstructed_X[i]); for(int j=0; j<n_visible; j++) { printf("%.5f ", reconstructed_X[i][j]); } cout << endl; } }
int main() {
test_rbm();
return 0;
}
執行結果即重構結果是: