具体封装函数讲解read_num_class_data()、prepare_train_data()等（OpenCV案例源码letter_recog.cpp解读2）
letter_recog.cpp的整体认识查阅RTrees、Boost、ANN_MLP、KNearest、NormalBayesClassifier、SVM，大写英文字母识别，三目运算符的妙用（OpenCV案例源码letter_recog.cpp解读）
letter-recognition.data，20000*17，前16000行用于训练，后4000行测试。
1、read_num_class_data()函数，把数据的第一列保存到标签集_responses，之后的16列保存到特征集_data。
用到了两个函数，说明如下：
fgets(str,n,fp);
从fp指向的文件中获取n-1个字符，并在最后加一个'\0'字符，共n个字符，放到字符数组str中。
如果在读完n-1个字符之前就遇到了换行符或eof，读入结束。
fgets函数返回值为str的首地址。
float a;
int b;
sscanf(ptr, "%f%n", &a, ,&b);//ptr指向的内容中获取浮点型格式的数据保存到a中（%f的作用），此%n所在位置（在当前浮点型之后1位）之前的字符个数保存到b中（%n的作用）
// 把既有标签又有特征的集合，拆分为标签集_responses、特征集_data，var_count是特征数（_data的列数）
static bool read_num_class_data(const string& filename, int var_count,Mat* _data, Mat* _responses)
{
const int M = 1024;//每行最多读取1024个字符，超过filename中每行字符数即可
char buf[M + 2];//buf的第一个元素用于存放标签，+2防止溢出
Mat el_ptr(1, var_count, CV_32F);//用于存放特征集
vector<int> responses;//用于存放标签，push_back buf的第一个元素
_data->release(); //释放该指向中所存储的内容，不是销毁
_responses->release();
FILE* f = fopen(filename.c_str(), "rt");//r只读,t文本文件（可省略，默认t）
if (!f)
{
cout << "Could not read the database " << filename << endl;
return false;
}
for (;;)
{
char* ptr;
if (!fgets(buf, M, f) )//此处每次读一行，因为每行不够1024个字符，遇到换行符停止读取。
break;//直到最后一行
responses.push_back((int)buf[0]);//每行第1个元素放入responses中（标签）
ptr = buf + 2;//ptr指向第一个逗号之后的数据，即第一个样本的第一个特征值
for (int i = 0; i < var_count; i++)//遍历一行中的每个元素
{
int n = 0;
sscanf(ptr, "%f%n", &el_ptr.at<float>(i), &n);//把一行中的浮点数存放到el_ptr一维行向量中
ptr += n + 1;//跳过逗号
}
_data->push_back(el_ptr);//存到特征集_data，_data指向一片Mat空间
}
fclose(f);
Mat(responses).copyTo(*_responses);//保存到_responses指向的Mat空间
cout << "The database " << filename << " is loaded.\n";
return true;
}
2、prepare_train_data()函数，从特征集data中选取前80%行，所有列作为训练集。下文中有int ntrain_samples = (int)(nsamples_all*0.8);
//特征集data中选取前80%行，所有列作为训练集。下文中有int ntrain_samples = (int)(nsamples_all*0.8);
static Ptr<TrainData> prepare_train_data(const Mat& data, const Mat& responses, int ntrain_samples)
{
Mat sample_idx = Mat::zeros(1, data.rows, CV_8U);
Mat train_samples = sample_idx.colRange(0, ntrain_samples);//80%的样本
train_samples.setTo(Scalar::all(1));//操作train_samples就是操作sample_idx，浅拷贝。sample_idx中前80%变为1
return TrainData::create(data, ROW_SAMPLE, responses,noArray(), sample_idx);//所有特征(列)参与训练，前80%样本(行)参与训练
}
3、训练终止条件
inline TermCriteria TC(int iters, double eps)
{
return TermCriteria(TermCriteria::MAX_ITER + (eps > 0 ? TermCriteria::EPS : 0), iters, eps);
}
4、test_and_save_classifier()函数，测试并保存分类模型，算出训练、测试的准确率
static void test_and_save_classifier(const Ptr<StatModel>& model,const Mat& data, const Mat& responses,int ntrain_samples, int rdelta,const string& filename_to_save)
{
int i, nsamples_all = data.rows;
double train_hr = 0, test_hr = 0;
for (i = 0; i < nsamples_all; i++)
{
Mat sample = data.row(i);
float r = model->predict(sample);//所有样本，逐行预测，返回预测结果，65~90
//除MLP，其他算法rdelta=0，预测结果r-对应标签responses如果为0则预测正确，下方的统计数+1
r = std::abs(r + rdelta - responses.at<int>(i)) <= FLT_EPSILON ? 1.f : 0.f;//FLT_EPSILON非常小的正数
if (i < ntrain_samples)//ntrain_samples是0.8*总样本，即80%用于训练
train_hr += r;//统计训练正确的个数
else
test_hr += r;//统计测试正确的个数
}
//计算准确率
test_hr /= nsamples_all - ntrain_samples;
train_hr = ntrain_samples > 0 ? train_hr / ntrain_samples : 1.;//保证分母不为0
printf("Recognition rate: train = %.1f%%, test = %.1f%%\n", train_hr*100., test_hr*100.);
//保存模型，xml格式
if (!filename_to_save.empty())
{
model->save(filename_to_save);
}
}
5、load_classifier()函数，模板类，提示信息，xml模型文件载入是否成功
template<typename T>
static Ptr<T> load_classifier(const string& filename_to_load)
{
// load classifier from the specified file
Ptr<T> model = StatModel::load<T>(filename_to_load);
if (model.empty())
cout << "Could not read the classifier " << filename_to_load << endl;
else
cout << "The classifier " << filename_to_load << " is loaded.\n";
return model;
}
6、具体的各个训练模型的使用这里不再赘述，上述函数是为了统一方便使用而创建的，我会在其他博客里单独使用模型，精简清晰明确，而不需要这么多代码。
全部代码，有删减。
#include<opencv2\opencv.hpp> #include <iostream> using namespace std; using namespace cv; using namespace cv::ml; // 把既有标签又有特征的集合，拆分为标签集_responses、特征集_data，var_count是特征数（_data的列数） static bool read_num_class_data(const string& filename, int var_count, Mat* _data, Mat* _responses) { const int M = 1024;//每行最多读取1024个字符，超过filename中每行字符数即可 char buf[M + 2];//buf的第一个元素用于存放标签，+2防止溢出 Mat el_ptr(1, var_count, CV_32F);//用于存放特征集 vector<int> responses;//用于存放标签，push_back buf的第一个元素 _data->release(); //释放该指向中所存储的内容，不是销毁 _responses->release(); FILE* f = fopen(filename.c_str(), "rt");//r只读,t文本文件（可省略，默认t） if (!f) { cout << "Could not read the database " << filename << endl; return false; } for (;;) { char* ptr; if (!fgets(buf, M, f))//此处每次读一行，因为每行不够1024个字符，遇到换行符停止读取。 break;//直到最后一行 responses.push_back((int)buf[0]);//每行第1个元素放入responses中（标签） ptr = buf + 2;//ptr指向第一个逗号之后的数据，即第一个样本的第一个特征值 for (int i = 0; i < var_count; i++)//遍历一行中的每个元素 { int n = 0; sscanf(ptr, "%f%n", &el_ptr.at<float>(i), &n);//把一行中的浮点数存放到el_ptr一维行向量中 ptr += n + 1;//跳过逗号 } _data->push_back(el_ptr);//存到特征集_data，_data指向一片Mat空间 } fclose(f); Mat(responses).copyTo(*_responses);//保存到_responses指向的Mat空间 cout << "The database " << filename << " is loaded.\n"; return true; } //特征集data中选取前80%行，所有列作为训练集。下文中有int ntrain_samples = (int)(nsamples_all*0.8); static Ptr<TrainData> prepare_train_data(const Mat& data, const Mat& responses, int ntrain_samples) { Mat sample_idx = Mat::zeros(1, data.rows, CV_8U); Mat train_samples = sample_idx.colRange(0, ntrain_samples);//80%的样本 train_samples.setTo(Scalar::all(1));//操作train_samples就是操作sample_idx，浅拷贝。sample_idx中前80%变为1 return TrainData::create(data, ROW_SAMPLE, responses, noArray(), sample_idx);//所有特征(列)参与训练，前80%样本(行)参与训练 } inline TermCriteria TC(int iters, double eps) { return TermCriteria(TermCriteria::MAX_ITER + (eps > 0 ? TermCriteria::EPS : 0), iters, eps); } //测试并保存分类模型，算出训练、测试的准确率 static void test_and_save_classifier(const Ptr<StatModel>& model, const Mat& data, const Mat& responses, int ntrain_samples, int rdelta, const string& filename_to_save) { int i, nsamples_all = data.rows; double train_hr = 0, test_hr = 0; for (i = 0; i < nsamples_all; i++) { Mat sample = data.row(i); float r = model->predict(sample);//所有样本，逐行预测，返回预测结果，65~90 //除MLP，其他算法rdelta=0，预测结果r-对应标签responses如果为0则预测正确，下方的统计数+1 r = std::abs(r + rdelta - responses.at<int>(i)) <= FLT_EPSILON ? 1.f : 0.f;//FLT_EPSILON非常小的正数 if (i < ntrain_samples)//ntrain_samples是0.8*总样本，即80%用于训练 train_hr += r;//统计训练正确的个数 else test_hr += r;//统计测试正确的个数 } //计算准确率 test_hr /= nsamples_all - ntrain_samples; train_hr = ntrain_samples > 0 ? train_hr / ntrain_samples : 1.;//保证分母不为0 printf("Recognition rate: train = %.1f%%, test = %.1f%%\n", train_hr*100., test_hr*100.); //保存模型，xml格式 if (!filename_to_save.empty()) { model->save(filename_to_save); } } //模板类，提示信息，xml模型文件载入是否成功 template<typename T> static Ptr<T> load_classifier(const string& filename_to_load) { // load classifier from the specified file Ptr<T> model = StatModel::load<T>(filename_to_load); if (model.empty()) cout << "Could not read the classifier " << filename_to_load << endl; else cout << "The classifier " << filename_to_load << " is loaded.\n"; return model; } //************************************以下为具体的模型***************************************************************// static bool build_rtrees_classifier(const string& data_filename, const string& filename_to_save, const string& filename_to_load) { Mat data; Mat responses; bool ok = read_num_class_data(data_filename, 16, &data, &responses);//拆分总集为特征集(16个特征)、标签集 if (!ok) return ok; Ptr<RTrees> model; int nsamples_all = data.rows; int ntrain_samples = (int)(nsamples_all*0.8); // Create or load Random Trees classifier if (!filename_to_load.empty()) { model = load_classifier<RTrees>(filename_to_load); if (model.empty()) return false; ntrain_samples = 0; } else { // create classifier by using <data> and <responses> cout << "Training the classifier ...\n"; // Params( int maxDepth, int minSampleCount, // double regressionAccuracy, bool useSurrogates, // int maxCategories, const Mat& priors, // bool calcVarImportance, int nactiveVars, // TermCriteria termCrit ); Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples); model = RTrees::create(); model->setMaxDepth(10); model->setMinSampleCount(10); model->setRegressionAccuracy(0); model->setUseSurrogates(false); model->setMaxCategories(15); model->setPriors(Mat()); model->setCalculateVarImportance(true); model->setActiveVarCount(4); model->setTermCriteria(TC(100, 0.01f)); model->train(tdata); cout << endl; } test_and_save_classifier(model, data, responses, ntrain_samples, 0, filename_to_save); cout << "Number of trees: " << model->getRoots().size() << endl;//树的个数 //输出每个特征的重要性，越大表明此特征越重要 Mat var_importance = model->getVarImportance(); cout << var_importance << endl; return true; } static bool build_boost_classifier(const string& data_filename, const string& filename_to_save, const string& filename_to_load) { const int class_count = 26; Mat data; Mat responses; Mat weak_responses; bool ok = read_num_class_data(data_filename, 16, &data, &responses); if (!ok) return ok; int i, j, k; Ptr<Boost> model; int nsamples_all = data.rows; int ntrain_samples = (int)(nsamples_all*0.5); int var_count = data.cols; // Create or load Boosted Tree classifier if (!filename_to_load.empty()) { model = load_classifier<Boost>(filename_to_load); if (model.empty()) return false; ntrain_samples = 0; } else { // !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! // // As currently boosted tree classifier in MLL can only be trained // for 2-class problems, we transform the training database by // "unrolling" each training sample as many times as the number of // classes (26) that we have. // // !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! Mat new_data(ntrain_samples*class_count, var_count + 1, CV_32F); Mat new_responses(ntrain_samples*class_count, 1, CV_32S); // 1. unroll the database type mask printf("Unrolling the database...\n"); for (i = 0; i < ntrain_samples; i++) { const float* data_row = data.ptr<float>(i); for (j = 0; j < class_count; j++) { float* new_data_row = (float*)new_data.ptr<float>(i*class_count + j); memcpy(new_data_row, data_row, var_count*sizeof(data_row[0])); new_data_row[var_count] = (float)j; new_responses.at<int>(i*class_count + j) = responses.at<int>(i) == j + 'A'; } } Mat var_type(1, var_count + 2, CV_8U); var_type.setTo(Scalar::all(VAR_ORDERED)); var_type.at<uchar>(var_count) = var_type.at<uchar>(var_count + 1) = VAR_CATEGORICAL; Ptr<TrainData> tdata = TrainData::create(new_data, ROW_SAMPLE, new_responses, noArray(), noArray(), noArray(), var_type); vector<double> priors(2); priors[0] = 1; priors[1] = 26; cout << "Training the classifier (may take a few minutes)...\n"; model = Boost::create(); model->setBoostType(Boost::GENTLE); model->setWeakCount(100); model->setWeightTrimRate(0.95); model->setMaxDepth(5); model->setUseSurrogates(false); model->setPriors(Mat(priors)); model->train(tdata); cout << endl; } Mat temp_sample(1, var_count + 1, CV_32F); float* tptr = temp_sample.ptr<float>(); // compute prediction error on train and test data double train_hr = 0, test_hr = 0; for (i = 0; i < nsamples_all; i++) { int best_class = 0; double max_sum = -DBL_MAX; const float* ptr = data.ptr<float>(i); for (k = 0; k < var_count; k++) tptr[k] = ptr[k]; for (j = 0; j < class_count; j++) { tptr[var_count] = (float)j; float s = model->predict(temp_sample, noArray(), StatModel::RAW_OUTPUT); if (max_sum < s) { max_sum = s; best_class = j + 'A'; } } double r = std::abs(best_class - responses.at<int>(i)) < FLT_EPSILON ? 1 : 0; if (i < ntrain_samples) train_hr += r; else test_hr += r; } test_hr /= nsamples_all - ntrain_samples; train_hr = ntrain_samples > 0 ? train_hr / ntrain_samples : 1.; printf("Recognition rate: train = %.1f%%, test = %.1f%%\n", train_hr*100., test_hr*100.); cout << "Number of trees: " << model->getRoots().size() << endl; // Save classifier to file if needed if (!filename_to_save.empty()) model->save(filename_to_save); return true; } static bool build_mlp_classifier(const string& data_filename, const string& filename_to_save, const string& filename_to_load) { const int class_count = 26; Mat data; Mat responses; bool ok = read_num_class_data(data_filename, 16, &data, &responses); if (!ok) return ok; Ptr<ANN_MLP> model; int nsamples_all = data.rows; //int ntrain_samples = (int)(nsamples_all*0.8); int ntrain_samples = (int)(nsamples_all*0.01); // Create or load MLP classifier if (!filename_to_load.empty()) { model = load_classifier<ANN_MLP>(filename_to_load); if (model.empty()) return false; ntrain_samples = 0; } else { // !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! // // MLP does not support categorical variables by explicitly. // So, instead of the output class label, we will use // a binary vector of <class_count> components for training and, // therefore, MLP will give us a vector of "probabilities" at the // prediction stage // // !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! Mat train_data = data.rowRange(0, ntrain_samples); Mat train_responses = Mat::zeros(ntrain_samples, class_count, CV_32F); // 1. unroll the responses cout << "Unrolling the responses...\n"; for (int i = 0; i < ntrain_samples; i++) { int cls_label = responses.at<int>(i) -'A';//大写英文字母用0~25标识 train_responses.at<float>(i, cls_label) = 1.f; } // 2. train classifier int layer_sz[] = { data.cols, 100, 100, class_count }; int nlayers = (int)(sizeof(layer_sz) / sizeof(layer_sz[0])); Mat layer_sizes(1, nlayers, CV_32S, layer_sz); #if 1 int method = ANN_MLP::BACKPROP; double method_param = 0.001; int max_iter = 300; #else int method = ANN_MLP::RPROP; double method_param = 0.1; int max_iter = 1000; #endif Ptr<TrainData> tdata = TrainData::create(train_data, ROW_SAMPLE, train_responses); cout << "Training the classifier (may take a few minutes)...\n"; model = ANN_MLP::create(); model->setLayerSizes(layer_sizes); model->setActivationFunction(ANN_MLP::SIGMOID_SYM, 0, 0); model->setTermCriteria(TC(max_iter, 0)); model->setTrainMethod(method, method_param); model->train(tdata); cout << endl; } //test_and_save_classifier(model, data, responses, ntrain_samples, 'A', filename_to_save); test_and_save_classifier(model, data, responses, ntrain_samples, 'A', "save.xml"); return true; } static bool build_knearest_classifier(const string& data_filename, int K) { Mat data; Mat responses; bool ok = read_num_class_data(data_filename, 16, &data, &responses); if (!ok) return ok; int nsamples_all = data.rows; int ntrain_samples = (int)(nsamples_all*0.8); // create classifier by using <data> and <responses> cout << "Training the classifier ...\n"; Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples); Ptr<KNearest> model = KNearest::create(); model->setDefaultK(K); model->setIsClassifier(true); model->train(tdata); cout << endl; test_and_save_classifier(model, data, responses, ntrain_samples, 0, string()); return true; } static bool build_nbayes_classifier(const string& data_filename) { Mat data; Mat responses; bool ok = read_num_class_data(data_filename, 16, &data, &responses); if (!ok) return ok; Ptr<NormalBayesClassifier> model; int nsamples_all = data.rows; int ntrain_samples = (int)(nsamples_all*0.8); // create classifier by using <data> and <responses> cout << "Training the classifier ...\n"; Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples); model = NormalBayesClassifier::create(); model->train(tdata); cout << endl; test_and_save_classifier(model, data, responses, ntrain_samples, 0, string()); return true; } static bool build_svm_classifier(const string& data_filename, const string& filename_to_save, const string& filename_to_load) { Mat data; Mat responses; bool ok = read_num_class_data(data_filename, 16, &data, &responses); if (!ok) return ok; Ptr<SVM> model; int nsamples_all = data.rows; int ntrain_samples = (int)(nsamples_all*0.8); // Create or load Random Trees classifier if (!filename_to_load.empty()) { model = load_classifier<SVM>(filename_to_load); if (model.empty()) return false; ntrain_samples = 0; } else { // create classifier by using <data> and <responses> cout << "Training the classifier ...\n"; Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples); model = SVM::create(); model->setType(SVM::C_SVC); model->setKernel(SVM::LINEAR); model->setC(1); model->train(tdata); cout << endl; } test_and_save_classifier(model, data, responses, ntrain_samples, 0, filename_to_save); return true; } int main(int argc, char *argv[]) { string filename_to_save = ""; string filename_to_load = ""; string data_filename; string method = "rtrees"; data_filename = "letter-recognition.data";//数据集 filename_to_save = "model.xml";//保存模型 //filename_to_load = "model.xml";//载入已有模型 //三目运算符，替代if……else if嵌套 if ((method == "rtrees" ? build_rtrees_classifier(data_filename, filename_to_save, filename_to_load) : method == "boost" ? build_boost_classifier(data_filename, filename_to_save, filename_to_load) : method == "mlp" ? build_mlp_classifier(data_filename, filename_to_save, filename_to_load) : method == "knearest" ? build_knearest_classifier(data_filename, 10) : method == "nbayes" ? build_nbayes_classifier(data_filename) : method == "svm" ? build_svm_classifier(data_filename, filename_to_save, filename_to_load) : -1) < 0) return 0; }
