【deep learning学习笔记】注释yusugomori的LR代码 --- LogisticRegression.cpp

模型实现代码，关键是train函数和predict函数，都很容易。

 

#include <iostream>

#include <string>

#include <math.h>

#include "LogisticRegression.h"

using namespace std;





LogisticRegression::LogisticRegression(

						int size, 	// N

						int in, 	// n_in

						int out		// n_out

							) 

{

  	N = size;

  	n_in = in;

  	n_out = out;



  	// initialize W, b

  	// W[n_out][n_in], b[n_out]

  	W = new double*[n_out];

  	for(int i=0; i<n_out; i++) 

	  	W[i] = new double[n_in];

  	b = new double[n_out];



  	for(int i=0; i<n_out; i++) 

  	{

    	for(int j=0; j<n_in; j++) 

		{

      		W[i][j] = 0;

    	}

    	b[i] = 0;

  	}

}



LogisticRegression::~LogisticRegression() 

{

  	for(int i=0; i<n_out; i++) 

	  	delete[] W[i];

  	delete[] W;

  	delete[] b;

}





void LogisticRegression::train (

				int *x, 	// the input from input nodes in training set

				int *y, 	// the output from output nodes in training set

				double lr	// the learning rate

				) 

{

	// the probability of P(y|x)

  	double *p_y_given_x = new double[n_out];

  	// the tmp variable which is not necessary being an array

  	double *dy = new double[n_out];



	// step 1: calculate the output of softmax given input

  	for(int i=0; i<n_out; i++) 

  	{

  		// initialize

    	p_y_given_x[i] = 0;

    	for(int j=0; j<n_in; j++) 

		{

			// the weight of networks

      		p_y_given_x[i] += W[i][j] * x[j];

    	}

    	// the bias

    	p_y_given_x[i] += b[i];

  	}

  	// the softmax value

  	softmax(p_y_given_x);



	// step 2: update the weight of networks

	// w_new = w_old + learningRate * differential (导数)

	//		 = w_old + learningRate * x (1{y_i=y} - p_yi_given_x) 

	//		 = w_old + learningRate * x * (y - p_y_given_x)

  	for(int i=0; i<n_out; i++) 

  	{

    	dy[i] = y[i] - p_y_given_x[i];

    	for(int j=0; j<n_in; j++) 

		{

      		W[i][j] += lr * dy[i] * x[j] / N;

    	}

    	b[i] += lr * dy[i] / N;

  	}

  	delete[] p_y_given_x;

  	delete[] dy;

}



void LogisticRegression::softmax (double *x) 

{

  	double max = 0.0;

  	double sum = 0.0;

  

  	// step1: get the max in the X vector

  	for(int i=0; i<n_out; i++) 

	  	if(max < x[i]) 

		  	max = x[i];

  	// step 2: normalization and softmax

  	// normalize -- 'x[i]-max', it's not necessary in traditional LR.

  	// I wonder why it appears here? 

  	for(int i=0; i<n_out; i++) 

  	{

    	x[i] = exp(x[i] - max);

    	sum += x[i];

  	} 

  	for(int i=0; i<n_out; i++) 

	  x[i] /= sum;

}



void LogisticRegression::predict(

				int *x, 	// the input from input nodes in testing set

				double *y	// the calculated softmax probability

				) 

{

	// get the softmax output value given the current networks

  	for(int i=0; i<n_out; i++) 

  	{

    	y[i] = 0;

    	for(int j=0; j<n_in; j++) 

		{

      		y[i] += W[i][j] * x[j];

    	}

    	y[i] += b[i];

  	}



  	softmax(y);

}