想用Adaboost分類器對自己的資料分類 而網上一查 好多都是Adaboost+Harr人臉檢測啥啥啥的   所以只能自己寫了 參考http://blog.csdn.net/zhaocj/article/details/50536385的 用Adaboost演算法對自己的資料集分類。特徵和標籤都是csv檔案：特徵矩陣是224X1000維的，類別是2就是二分類，

int main(int argc, char** argv)
{

//打亂順序結果在kuangvec[]和stonevec[]兩個數組裡 影象標號
const int uselesssample = 134, usefulsample = 90, allsample = 224,featurecol=1000;
//打亂順序 前90個為礦  後134個為廢石
int kuangvec[usefulsample], stonevec[uselesssample];
for (int i = 0; i < usefulsample; i++)
kuangvec[i] = i ;
for (int i = 0; i <uselesssample; i++)
stonevec[i] = usefulsample+i;
random_shuffle(kuangvec, kuangvec+usefulsample);
random_shuffle(stonevec, stonevec + uselesssample);
///////////////////////////////////////////////show fixed ranks
//for (int i = 0; i < usefulsample; i++)
//cout << kuangvec[i] << endl;
//cout << endl;
//for (int i = 0; i < uselesssample; i++)
//cout << stonevec[i] << endl;
/////////////////////////////////////////////////////////////////////read features
CvMLData cvmlprimer;
cvmlprimer.read_csv("features.csv");
cv::Mat cvml = cv::Mat(cvmlprimer.get_values(),true);
CvMLData resprimer;
resprimer.read_csv("labels.csv");
cv::Mat res = cv::Mat(resprimer.get_values(), true);
/////////////////////////////////////////////////////////////////////saperate into trainset 
const float rate =0.6;
int trainnum=int(usefulsample*rate)+int(uselesssample*rate), testnum=allsample-trainnum;
Mat traindata=Mat::zeros(trainnum, featurecol, cvml.type()), testdata=Mat::zeros(testnum, featurecol, cvml.type()), trainlabel=Mat::zeros(trainnum, 1, res.type()),      testlabel=Mat::zeros(testnum,1, res.type());
for (int i = 0; i <int(usefulsample*rate); i++) 
{
float* newrow = traindata.ptr<float>(i);
int currentrow = kuangvec[i];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = trainlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);  
newlabelrow[0] = primerlabelrow[0];
}
for (int i = int(usefulsample*rate); i <trainnum; i++)  
{
float* newrow = traindata.ptr<float>(i);
int ii = i - int(usefulsample*rate);
int currentrow = stonevec[ii];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = trainlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);
newlabelrow[0] = primerlabelrow[0];
}
//saperate into testset 
for (int i = 0; i <usefulsample-int(usefulsample*rate); i++)
{
float* newrow = testdata.ptr<float>(i);
int iii = i + int(usefulsample*rate);
int currentrow = kuangvec[iii];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = testlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);
newlabelrow[0] = primerlabelrow[0];
}
for (int i = usefulsample - int(usefulsample*rate); i <testnum; i++)
{
int ii = int(uselesssample*rate) + i - (usefulsample - int(usefulsample*rate));
float* newrow = testdata.ptr<float>(i);
int currentrow = stonevec[ii];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = testlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);
newlabelrow[0] = primerlabelrow[0];
}
//trainset and testset have done!/////////////////////////////////////////////////////////////////
//for (int i = 0; i < trainnum; i++) //check the trainlabel and testlabel
//{
//float* row = trainlabel.ptr<float>(i);
//cout <<row[0]<< endl;
//}
//cout << "trainlabel= "<<trainnum << endl;
//for (int i = 0; i < testnum; i++)
//{
//float* row = testlabel.ptr<float>(i);
//cout << row[0]<<endl;
//}
CvMat traindata2 =traindata, trainlabel2 =trainlabel;
const CvMat* traindata3 = cvCreateMat(traindata2.rows, traindata2.cols, traindata2.type);
const CvMat* trainlabel3 = cvCreateMat(trainlabel2.rows, trainlabel2.cols, trainlabel2.type);
printf("Ready for Training ... ");
float priors[1000] = { 1, 1, 1, };
CvBoostParams params(CvBoost::GENTLE, 10, 0.95, 1, false, priors);
CvBoost boost;
bool update = false;
const CvMat* varIdx = 0;
const CvMat* sampleIdx = 0;
const CvMat* varType = 0;
const CvMat* missingDataMask = 0;
boost.train(traindata3,CV_ROW_SAMPLE, trainlabel3, varIdx, sampleIdx, varType, missingDataMask, params, update);
cout << "training done!" << endl;
// 1. Declare a couple of vectors to save the predictions of each sample
//std::vector train_responses, test_responses;
// 2. Calculate the training error
//float fl1 = boost.calc_error(&cvml, CV_TRAIN_ERROR, &train_responses);
// 3. Calculate the test error
//float fl2 = boost.calc_error(&cvml, CV_TEST_ERROR, &test_responses);
//printf("Error train %f \n", fl1);
//printf("Error test %f \n", fl2);
// Save the trained classifier
//boost.save("./trained_boost.xml", "boost");
//return EXIT_SUCCESS;
return 0;
}

我上面只是train 可是用Adaboost訓練時候就報錯 說只能用來二分類可是我檢查我的標籤結果證明是二分類啊訓練標籤是1和2兩個類都拿出了60%作為訓練集兩個類剩下的40%作為測試集可是為什麼train的時候報這樣的錯呢？

搞了一上午 終於知道為什麼了  從traindata轉成CvMat*時候沒有複製資料 只是複製了資訊頭 所以trian裡面是沒有任何資料的！！！太蠢了

改成了這樣：

#include "opencv2/core/core.hpp"  
#include "opencv2/highgui/highgui.hpp"  
#include "opencv2/imgproc/imgproc.hpp"  
#include "opencv2/ml/ml.hpp"  
#include <iostream>  
#include<algorithm>
#include<opencv2/opencv.hpp>
using namespace cv;
using namespace std;
int main(int argc, char** argv)
{
//打亂順序結果在kuangvec[]和stonevec[]兩個數組裡 影象標號
const int uselesssample = 134, usefulsample = 90, allsample = 224,featurecol=1000;
//打亂順序 前90個為礦  後134個為廢石
int kuangvec[usefulsample], stonevec[uselesssample];
for (int i = 0; i < usefulsample; i++)
kuangvec[i] = i ;
for (int i = 0; i <uselesssample; i++)
stonevec[i] = usefulsample+i;
random_shuffle(kuangvec, kuangvec+usefulsample);
random_shuffle(stonevec, stonevec + uselesssample);
///////////////////////////////////////////////show fixed ranks
//for (int i = 0; i < usefulsample; i++)
//cout << kuangvec[i] << endl;
//cout << endl;
//for (int i = 0; i < uselesssample; i++)
//cout << stonevec[i] << endl;
/////////////////////////////////////////////////////////////////////read features
CvMLData cvmlprimer;
cvmlprimer.read_csv("features.csv");
cv::Mat cvml = cv::Mat(cvmlprimer.get_values(),true);
CvMLData resprimer;
resprimer.read_csv("labels.csv");
cv::Mat res = cv::Mat(resprimer.get_values(), true);
/////////////////////////////////////////////////////////////////////saperate into trainset randomly
const float rate =0.6;
int trainnum=int(usefulsample*rate)+int(uselesssample*rate), testnum=allsample-trainnum;
Mat traindata=Mat::zeros(trainnum, featurecol, cvml.type()), testdata=Mat::zeros(testnum, featurecol, cvml.type()), trainlabel=Mat::zeros(trainnum, 1, res.type()), testlabel=Mat::zeros(testnum,1, res.type());
for (int i = 0; i <int(usefulsample*rate); i++) 
{
float* newrow = traindata.ptr<float>(i);
int currentrow = kuangvec[i];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = trainlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);  
newlabelrow[0] = primerlabelrow[0];
}
for (int i = int(usefulsample*rate); i <trainnum; i++)  
{
float* newrow = traindata.ptr<float>(i);
int ii = i - int(usefulsample*rate);
int currentrow = stonevec[ii];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = trainlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);
newlabelrow[0] = primerlabelrow[0];
}
//saperate into testset 
for (int i = 0; i <usefulsample-int(usefulsample*rate); i++)
{
float* newrow = testdata.ptr<float>(i);
int iii = i + int(usefulsample*rate);
int currentrow = kuangvec[iii];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = testlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);
newlabelrow[0] = primerlabelrow[0];
}
for (int i = usefulsample - int(usefulsample*rate); i <testnum; i++)
{
int ii = int(uselesssample*rate) + i - (usefulsample - int(usefulsample*rate));
float* newrow = testdata.ptr<float>(i);
int currentrow = stonevec[ii];
float* primerow = cvml.ptr<float>(currentrow);
for (int j = 0; j < featurecol; j++)
newrow[j] = primerow[j];
float* newlabelrow = testlabel.ptr<float>(i);
float* primerlabelrow = res.ptr<float>(currentrow);
newlabelrow[0] = primerlabelrow[0];
}
//trainset and testset have done!/////////////////////////////////////////////////////////////////
//for (int i = 0; i < trainnum; i++) //check the trainlabel and testlabel
//{
//float* row = trainlabel.ptr<float>(i);
//cout <<row[0]<< endl;
//}
//cout << "trainlabel= "<<trainnum << endl;
//for (int i = 0; i < testnum; i++)
//{
//float* row = testlabel.ptr<float>(i);
//cout << row[0]<<endl;
//}
//cout << "testlabel= " << testnum << endl;
CvMat traindata2 = traindata, trainlabel2 = trainlabel;
    CvMat* traindata3 = cvCreateMat(traindata2.rows, traindata2.cols, traindata2.type);
cvCopy(&traindata2, traindata3);
CvMat* trainlabel3 = cvCreateMat(trainlabel2.rows, trainlabel2.cols, trainlabel2.type);
cvCopy(&trainlabel2, trainlabel3);
cout<<"Ready for Training ... "<<endl;
float priors[1000];
for (int i = 0; i < 1000; i++)
priors[i] = 1;
CvBoostParams params(CvBoost::GENTLE, 1000, 0.95, 1, false, priors);
CvBoost boost;
bool update = false;
const CvMat* varIdx = 0;
const CvMat* sampleIdx = 0;
const CvMat* varType = 0;
const CvMat* missingDataMask = 0;
boost.train(traindata3,CV_ROW_SAMPLE, trainlabel3, varIdx, sampleIdx, varType, missingDataMask, params, update);
cout << "training done!!!prepare for testing..." << endl<<endl;
////////////////////////////////////////////////////////////////begin test
CvMat testdata2 = testdata, testlabel2 = testlabel;
CvMat* testdata3 = cvCreateMat(testdata2.rows, testdata2.cols, testdata2.type);
cvCopy(&testdata2, testdata3);
CvMat* testlabel3 = cvCreateMat(testlabel2.rows, testlabel2.cols, testlabel2.type);
cvCopy(&testlabel2, testlabel3);
const CvMat* missing = 0;
CvMat* weak_responses = 0;
const int numfortest = testdata.rows;
float  outputs;
outputs=boost.predict(testdata3, missing, weak_responses, CV_WHOLE_SEQ, false);
// 1. Declare a couple of vectors to save the predictions of each sample
//std::vector train_responses, test_responses;
// 2. Calculate the training error
//float fl1 = boost.calc_error(&cvml, CV_TRAIN_ERROR, &train_responses);
// 3. Calculate the test error
//float fl2 = boost.calc_error(&cvml, CV_TEST_ERROR, &test_responses);
//printf("Error train %f \n", fl1);
//printf("Error test %f \n", fl2);
// Save the trained classifier
//boost.save("./trained_boost.xml", "boost");
//return EXIT_SUCCESS;
return 0;
}

我增加了把資料集和標籤隨機分為測試集和訓練集  還改了之前的錯誤  結果證明訓練可以了但測試那裡出錯了？請教公司的大神 大神告訴我predict()測試樣本必須是一個樣本 原來它不能像matlab裡面一樣拿很多個樣本一下去測試得到一個標籤向量。它只能一個個測試 所以我迴圈就行了

這樣就行了啊 哈哈！！！只差計算準確率了。我用了個動態陣列outputlabels把每次的輸出的標籤存進去 我都快忘記動態陣列可以避免普通陣列每次定義時候必須寫大小的煩惱  但一定記得delete  結果這樣就行了呀！！！！！！！！Adaboost用來對自己的資料進行分類 完畢！我用新資料重新測試了下：

和我用MATLAB裡的Adaboost做出來的結果幾乎一致。證明沒有錯誤了。可以直接用了以後。