C++ CvRTrees::get_tree_count方法代码示例

/* Examines the values at each leaf node in order to see what the distribution of data
  we put in is doing */
void mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[]) {
	ASSERT_NUM_RHS_ARGS_EQUALS(1);
	
	const mxArray* forest_ptr = prhs[0];
	ASSERT_IS_POINTER(forest_ptr);
	CvRTrees *forest = (CvRTrees *) unpack_pointer(forest_ptr);
	
	// We are going to return a cell array with one cell per tree, so need this number
	int num_trees = forest->get_tree_count();
	mexPrintf("Loaded forest of %d trees, retrieving leave node values.\n", num_trees);

	mxArray *output_cell_array = mxCreateCellMatrix(1, num_trees);
	ASSERT_NON_NULL(output_cell_array);
	
	for (unsigned int t = 0; t < num_trees; t++) {
		mxArray* tree_struct = mxCreateStructArray(num_dims, dims, tree_num_fields, tree_field_names);
		ASSERT_NON_NULL(tree_struct);
		mxSetCell(output_cell_array, t, make_matlab_tree_struct(forest->get_tree(t)));
	}
	plhs[0] = output_cell_array;
}

static
int build_rtrees_classifier( char* data_filename,
    char* filename_to_save, char* filename_to_load )
{
    CvMat* data = 0;
    CvMat* responses = 0;
    CvMat* var_type = 0;
    CvMat* sample_idx = 0;

    int ok = read_num_class_data( data_filename, 16, &data, &responses );
    int nsamples_all = 0, ntrain_samples = 0;
    int i = 0;
    double train_hr = 0, test_hr = 0;
    CvRTrees forest;
    CvMat* var_importance = 0;

    if( !ok )
    {
        printf( "Could not read the database %s\n", data_filename );
        return -1;
    }

    printf( "The database %s is loaded.\n", data_filename );
    nsamples_all = data->rows;
    ntrain_samples = (int)(nsamples_all*0.8);

    // Create or load Random Trees classifier
    if( filename_to_load )
    {
        // load classifier from the specified file
        forest.load( filename_to_load );
        ntrain_samples = 0;
        if( forest.get_tree_count() == 0 )
        {
            printf( "Could not read the classifier %s\n", filename_to_load );
            return -1;
        }
        printf( "The classifier %s is loaded.\n", data_filename );
    }
    else
    {
        // create classifier by using <data> and <responses>
        printf( "Training the classifier ...\n");

        // 1. create type mask
        var_type = cvCreateMat( data->cols + 1, 1, CV_8U );
        cvSet( var_type, cvScalarAll(CV_VAR_ORDERED) );
        cvSetReal1D( var_type, data->cols, CV_VAR_CATEGORICAL );

        // 2. create sample_idx
        sample_idx = cvCreateMat( 1, nsamples_all, CV_8UC1 );
        {
            CvMat mat;
            cvGetCols( sample_idx, &mat, 0, ntrain_samples );
            cvSet( &mat, cvRealScalar(1) );

            cvGetCols( sample_idx, &mat, ntrain_samples, nsamples_all );
            cvSetZero( &mat );
        }

        // 3. train classifier
        forest.train( data, CV_ROW_SAMPLE, responses, 0, sample_idx, var_type, 0,
            CvRTParams(10,10,0,false,15,0,true,4,100,0.01f,CV_TERMCRIT_ITER));
        printf( "\n");
    }

    // compute prediction error on train and test data
    for( i = 0; i < nsamples_all; i++ )
    {
        double r;
        CvMat sample;
        cvGetRow( data, &sample, i );

        r = forest.predict( &sample );
        r = fabs((double)r - responses->data.fl[i]) <= FLT_EPSILON ? 1 : 0;

        if( i < ntrain_samples )
            train_hr += r;
        else
            test_hr += r;
    }

    test_hr /= (double)(nsamples_all-ntrain_samples);
    train_hr /= (double)ntrain_samples;
    printf( "Recognition rate: train = %.1f%%, test = %.1f%%\n",
            train_hr*100., test_hr*100. );

    printf( "Number of trees: %d\n", forest.get_tree_count() );

    // Print variable importance
    var_importance = (CvMat*)forest.get_var_importance();
    if( var_importance )
    {
        double rt_imp_sum = cvSum( var_importance ).val[0];
        printf("var#\timportance (in %%):\n");
        for( i = 0; i < var_importance->cols; i++ )
            printf( "%-2d\t%-4.1f\n", i,
            100.f*var_importance->data.fl[i]/rt_imp_sum);
    }

//.........这里部分代码省略.........

int RandomTrees::train(const char* samples_filename, const char* model_filename, const double ratio, double &train_error, double &test_error)
{
	CvMat* data = 0;
	CvMat* responses = 0;
	CvMat* var_type = 0;
	CvMat* sample_idx = 0;

	this->tree_parameters_.nactive_vars = (int)sqrt(this->number_of_features_);

	int ok = read_num_class_data( samples_filename, this->number_of_features_, &data, &responses );
	int nsamples_all = 0, ntrain_samples = 0;
	int i = 0;
	double train_hr = 0, test_hr = 0;
	CvRTrees forest;
	CvMat* var_importance = 0;

	if( !ok )
	{
		cout << "Could not read the sample in" << samples_filename << endl;;
		return -1;
	}

	cout << "The sample file " << samples_filename << " is loaded." << endl;
	nsamples_all = data->rows;
	ntrain_samples = (int)(nsamples_all * ratio);


	// create classifier by using <data> and <responses>
	cout << "Training the classifier ..." << endl;

	// 1. create type mask
	var_type = cvCreateMat( data->cols + 1, 1, CV_8U );
	cvSet( var_type, cvScalarAll(CV_VAR_ORDERED) );
	cvSetReal1D( var_type, data->cols, CV_VAR_CATEGORICAL );

	// 2. create sample_idx
	sample_idx = cvCreateMat( 1, nsamples_all, CV_8UC1 );
	{
		CvMat mat;
		cvGetCols( sample_idx, &mat, 0, ntrain_samples );
		cvSet( &mat, cvRealScalar(1) );

		cvGetCols( sample_idx, &mat, ntrain_samples, nsamples_all );
		cvSetZero( &mat );
	}

	// 3. train classifier
	forest.train( data, CV_ROW_SAMPLE, responses, 0, sample_idx, var_type, 0, this->tree_parameters_);
	cout << endl;


	// compute prediction error on train and test data
	for( i = 0; i < nsamples_all; i++ )
	{
		double r;
		CvMat sample;
		cvGetRow( data, &sample, i );

		r = forest.predict( &sample );
		r = fabs((double)r - responses->data.fl[i]) <= FLT_EPSILON ? 1 : 0;

		if( i < ntrain_samples )
			train_hr += r;
		else
			test_hr += r;
	}

	test_hr /= (double)(nsamples_all-ntrain_samples);
	train_hr /= (double)ntrain_samples;

	train_error = 1 - train_hr;
	test_error = 1 - test_hr;

	cout << "Recognition rate: train = " << train_hr*100 << ", test = " << test_hr*100 << endl;
	cout << "Number of trees: " << forest.get_tree_count() << endl;

	// Print variable importance
	var_importance = (CvMat*)forest.get_var_importance();
	if( var_importance )
	{
		double rt_imp_sum = cvSum( var_importance ).val[0];
		printf("var#\timportance (in %%):\n");
		for( i = 0; i < var_importance->cols; i++ )
			printf( "%-2d\t%-4.1f\n", i,100.f*var_importance->data.fl[i]/rt_imp_sum);
	}

	// Save Random Trees classifier to file if needed
	if( model_filename )
		forest.save( model_filename );

	//cvReleaseMat( &var_importance );		//causes a segmentation fault
	cvReleaseMat( &sample_idx );
	cvReleaseMat( &var_type );
	cvReleaseMat( &data );
	cvReleaseMat( &responses );

	return 0;
}