libsvm代码阅读：关于svm_train函数分析

update:2014-2-27 LinJM @HQU  『 libsvm专栏地址：http://blog.csdn.net/column/details/libsvm.html 』

在svm中，训练是一个十分重要的步骤，下面我们来看看svm的train部分。

在libsvm中的svm_train中分别有回归和分类两部分，我只对其中分类做介绍。

分类的步骤如下：

• 统计类别总数，同时记录类别的标号，统计每个类的样本数目
• 将属于相同类的样本分组，连续存放
• 计算权重C
• 训练n(n-1)/2 个模型
  • 初始化nozero数组，便于统计SV
  • //初始化概率数组
  • 训练过程中，需要重建子数据集，样本的特征不变，但样本的类别要改为+1/-1
  • //如有必要，先调用svm_binary_svc_probability
  • 训练子数据集svm_train_one
  • 统计一下nozero，如果nozero已经是真，就不变，否则改为真
• 输出模型
  • 主要是填充svm_model
• 清除内存

函数中调用过程如下：

svm_train-->svm_train_one-->solve_c_svc(for example)-->s.Solve

//
// Interface functions
//重点函数：svm训练函数
//根据选择的算法，来组织参加训练的分样本，以及进行训练结果的保存。其中会对样本进行初步的统计。
svm_model *svm_train(const svm_problem *prob, const svm_parameter *param)
{
	svm_model *model = Malloc(svm_model,1);//#define Malloc(type,n) (type *)malloc((n)*sizeof(type))
	model->param = *param;
	model->free_sv = 0;	// XXX

	if(param->svm_type == ONE_CLASS ||
	   param->svm_type == EPSILON_SVR ||
	   param->svm_type == NU_SVR)
	{
		// regression or one-class-svm
		model->nr_class = 2;
		model->label = NULL;
		model->nSV = NULL;
		model->probA = NULL; model->probB = NULL;
		model->sv_coef = Malloc(double *,1);

		if(param->probability && 
		   (param->svm_type == EPSILON_SVR ||
		    param->svm_type == NU_SVR))
		{
			model->probA = Malloc(double,1);
			model->probA[0] = svm_svr_probability(prob,param);
		}

		decision_function f = svm_train_one(prob,param,0,0);
		model->rho = Malloc(double,1);
		model->rho[0] = f.rho;

		int nSV = 0;
		int i;
		for(i=0;i<prob->l;i++)
			if(fabs(f.alpha[i]) > 0) ++nSV;
		model->l = nSV;
		model->SV = Malloc(svm_node *,nSV);
		model->sv_coef[0] = Malloc(double,nSV);
		model->sv_indices = Malloc(int,nSV);
		int j = 0;
		for(i=0;i<prob->l;i++)
			if(fabs(f.alpha[i]) > 0)
			{
				model->SV[j] = prob->x[i];
				model->sv_coef[0][j] = f.alpha[i];
				model->sv_indices[j] = i+1;
				++j;
			}		
		free(f.alpha);
	}
	else
	{
		// classification
		int l = prob->l;
		int nr_class;
		int *label = NULL;
		int *start = NULL;
		int *count = NULL;
		int *perm = Malloc(int,l);

		// group training data of the same class对训练样本进行处理,同类整合到一起
		svm_group_classes(prob,&nr_class,&label,&start,&count,perm);
		if(nr_class == 1) 
			info("WARNING: training data in only one class. See README for details.\n");
		
		svm_node **x = Malloc(svm_node *,l);
		int i;
		for(i=0;i<l;i++)
			x[i] = prob->x[perm[i]];

		// calculate weighted C

		double *weighted_C = Malloc(double, nr_class);
		for(i=0;i<nr_class;i++)
			weighted_C[i] = param->C;
		for(i=0;i<param->nr_weight;i++)
		{	
			int j;
			for(j=0;j<nr_class;j++)
				if(param->weight_label[i] == label[j])
					break;
			if(j == nr_class)
				fprintf(stderr,"WARNING: class label %d specified in weight is not found\n", param->weight_label[i]);
			else
				weighted_C[j] *= param->weight[i];
		}

		// train k*(k-1)/2 models
		
		bool *nonzero = Malloc(bool,l);
		for(i=0;i<l;i++)
			nonzero[i] = false;
		decision_function *f = Malloc(decision_function,nr_class*(nr_class-1)/2);

		double *probA=NULL,*probB=NULL;
		if (param->probability)
		{
			probA=Malloc(double,nr_class*(nr_class-1)/2);
			probB=Malloc(double,nr_class*(nr_class-1)/2);
		}

		int p = 0;
		for(i=0;i<nr_class;i++)
			for(int j=i+1;j<nr_class;j++)
			{
				svm_problem sub_prob;
				int si = start[i], sj = start[j];
				int ci = count[i], cj = count[j];
				sub_prob.l = ci+cj;
				sub_prob.x = Malloc(svm_node *,sub_prob.l);
				sub_prob.y = Malloc(double,sub_prob.l);
				int k;
				for(k=0;k<ci;k++)
				{
					sub_prob.x[k] = x[si+k];
					sub_prob.y[k] = +1;
				}
				for(k=0;k<cj;k++)
				{
					sub_prob.x[ci+k] = x[sj+k];
					sub_prob.y[ci+k] = -1;
				}

				if(param->probability)
					svm_binary_svc_probability(&sub_prob,param,weighted_C[i],weighted_C[j],probA[p],probB[p]);

				f[p] = svm_train_one(&sub_prob,param,weighted_C[i],weighted_C[j]);
				for(k=0;k<ci;k++)
					if(!nonzero[si+k] && fabs(f[p].alpha[k]) > 0)
						nonzero[si+k] = true;
				for(k=0;k<cj;k++)
					if(!nonzero[sj+k] && fabs(f[p].alpha[ci+k]) > 0)
						nonzero[sj+k] = true;
				free(sub_prob.x);
				free(sub_prob.y);
				++p;
			}

		// build output

		model->nr_class = nr_class;
		
		model->label = Malloc(int,nr_class);
		for(i=0;i<nr_class;i++)
			model->label[i] = label[i];
		
		model->rho = Malloc(double,nr_class*(nr_class-1)/2);
		for(i=0;i<nr_class*(nr_class-1)/2;i++)
			model->rho[i] = f[i].rho;

		if(param->probability)
		{
			model->probA = Malloc(double,nr_class*(nr_class-1)/2);
			model->probB = Malloc(double,nr_class*(nr_class-1)/2);
			for(i=0;i<nr_class*(nr_class-1)/2;i++)
			{
				model->probA[i] = probA[i];
				model->probB[i] = probB[i];
			}
		}
		else
		{
			model->probA=NULL;
			model->probB=NULL;
		}

		int total_sv = 0;
		int *nz_count = Malloc(int,nr_class);
		model->nSV = Malloc(int,nr_class);
		for(i=0;i<nr_class;i++)
		{
			int nSV = 0;
			for(int j=0;j<count[i];j++)
				if(nonzero[start[i]+j])
				{	
					++nSV;
					++total_sv;
				}
			model->nSV[i] = nSV;
			nz_count[i] = nSV;
		}
		
		info("Total nSV = %d\n",total_sv);

		model->l = total_sv;
		model->SV = Malloc(svm_node *,total_sv);
		model->sv_indices = Malloc(int,total_sv);
		p = 0;
		for(i=0;i<l;i++)
			if(nonzero[i])
			{
				model->SV[p] = x[i];
				model->sv_indices[p++] = perm[i] + 1;
			}

		int *nz_start = Malloc(int,nr_class);
		nz_start[0] = 0;
		for(i=1;i<nr_class;i++)
			nz_start[i] = nz_start[i-1]+nz_count[i-1];

		model->sv_coef = Malloc(double *,nr_class-1);
		for(i=0;i<nr_class-1;i++)
			model->sv_coef[i] = Malloc(double,total_sv);

		p = 0;
		for(i=0;i<nr_class;i++)
			for(int j=i+1;j<nr_class;j++)
			{
				// classifier (i,j): coefficients with
				// i are in sv_coef[j-1][nz_start[i]...],
				// j are in sv_coef[i][nz_start[j]...]

				int si = start[i];
				int sj = start[j];
				int ci = count[i];
				int cj = count[j];
				
				int q = nz_start[i];
				int k;
				for(k=0;k<ci;k++)
					if(nonzero[si+k])
						model->sv_coef[j-1][q++] = f[p].alpha[k];
				q = nz_start[j];
				for(k=0;k<cj;k++)
					if(nonzero[sj+k])
						model->sv_coef[i][q++] = f[p].alpha[ci+k];
				++p;
			}
		
		free(label);
		free(probA);
		free(probB);
		free(count);
		free(perm);
		free(start);
		free(x);
		free(weighted_C);
		free(nonzero);
		for(i=0;i<nr_class*(nr_class-1)/2;i++)
			free(f[i].alpha);
		free(f);
		free(nz_count);
		free(nz_start);
	}
	return model;
}

本文地址：http://blog.csdn.net/linj_m/article/details/19848837

微博：林建民-机器视觉