generic-library/opencv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

reworked nearly all of the OpenCV tests (except for opencv_gpu tests) - they now use the Google Test engine.

Browse Source
This commit is contained in:
Vadim Pisarevsky
2011-02-09 20:55:11 +00:00
parent 63806c9ab9
commit 061b49e0b2
122 changed files with 39081 additions and 28854 deletions
Download Patch File Download Diff File Expand all files Collapse all files

327
modules/ml/test/test_emknearestkmeans.cpp Normal file
View File

@@ -0,0 +1,327 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// Intel License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2000, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of Intel Corporation may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#include "test_precomp.hpp"
using namespace std;
using namespace cv;
void defaultDistribs( vector<Mat>& means, vector<Mat>& covs )
{
float mp0[] = {0.0f, 0.0f}, cp0[] = {0.67f, 0.0f, 0.0f, 0.67f};
float mp1[] = {5.0f, 0.0f}, cp1[] = {1.0f, 0.0f, 0.0f, 1.0f};
float mp2[] = {1.0f, 5.0f}, cp2[] = {1.0f, 0.0f, 0.0f, 1.0f};
Mat m0( 1, 2, CV_32FC1, mp0 ), c0( 2, 2, CV_32FC1, cp0 );
Mat m1( 1, 2, CV_32FC1, mp1 ), c1( 2, 2, CV_32FC1, cp1 );
Mat m2( 1, 2, CV_32FC1, mp2 ), c2( 2, 2, CV_32FC1, cp2 );
means.resize(3), covs.resize(3);
m0.copyTo(means[0]), c0.copyTo(covs[0]);
m1.copyTo(means[1]), c1.copyTo(covs[1]);
m2.copyTo(means[2]), c2.copyTo(covs[2]);
}
// generate points sets by normal distributions
void generateData( Mat& data, Mat& labels, const vector<int>& sizes, const vector<Mat>& means, const vector<Mat>& covs, int labelType )
{
vector<int>::const_iterator sit = sizes.begin();
int total = 0;
for( ; sit != sizes.end(); ++sit )
total += *sit;
assert( means.size() == sizes.size() && covs.size() == sizes.size() );
assert( !data.empty() && data.rows == total );
assert( data.type() == CV_32FC1 );
labels.create( data.rows, 1, labelType );
randn( data, Scalar::all(0.0), Scalar::all(1.0) );
vector<Mat>::const_iterator mit = means.begin(), cit = covs.begin();
int bi, ei = 0;
sit = sizes.begin();
for( int p = 0, l = 0; sit != sizes.end(); ++sit, ++mit, ++cit, l++ )
{
bi = ei;
ei = bi + *sit;
assert( mit->rows == 1 && mit->cols == data.cols );
assert( cit->rows == data.cols && cit->cols == data.cols );
for( int i = bi; i < ei; i++, p++ )
{
Mat r(1, data.cols, CV_32FC1, data.ptr<float>(i));
r = r * (*cit) + *mit;
if( labelType == CV_32FC1 )
labels.at<float>(p, 0) = (float)l;
else
labels.at<int>(p, 0) = l;
}
}
}
int maxIdx( const vector<int>& count )
{
int idx = -1;
int maxVal = -1;
vector<int>::const_iterator it = count.begin();
for( int i = 0; it != count.end(); ++it, i++ )
{
if( *it > maxVal)
{
maxVal = *it;
idx = i;
}
}
assert( idx >= 0);
return idx;
}
bool getLabelsMap( const Mat& labels, const vector<int>& sizes, vector<int>& labelsMap )
{
int total = 0, setCount = (int)sizes.size();
vector<int>::const_iterator sit = sizes.begin();
for( ; sit != sizes.end(); ++sit )
total += *sit;
assert( !labels.empty() );
assert( labels.rows == total && labels.cols == 1 );
assert( labels.type() == CV_32SC1 || labels.type() == CV_32FC1 );
bool isFlt = labels.type() == CV_32FC1;
labelsMap.resize(setCount);
vector<int>::iterator lmit = labelsMap.begin();
vector<bool> buzy(setCount, false);
int bi, ei = 0;
for( sit = sizes.begin(); sit != sizes.end(); ++sit, ++lmit )
{
vector<int> count( setCount, 0 );
bi = ei;
ei = bi + *sit;
if( isFlt )
{
for( int i = bi; i < ei; i++ )
count[(int)labels.at<float>(i, 0)]++;
}
else
{
for( int i = bi; i < ei; i++ )
count[labels.at<int>(i, 0)]++;
}
*lmit = maxIdx( count );
if( buzy[*lmit] )
return false;
buzy[*lmit] = true;
}
return true;
}
float calcErr( const Mat& labels, const Mat& origLabels, const vector<int>& sizes, bool labelsEquivalent = true )
{
int err = 0;
assert( !labels.empty() && !origLabels.empty() );
assert( labels.cols == 1 && origLabels.cols == 1 );
assert( labels.rows == origLabels.rows );
assert( labels.type() == origLabels.type() );
assert( labels.type() == CV_32SC1 || labels.type() == CV_32FC1 );
vector<int> labelsMap;
bool isFlt = labels.type() == CV_32FC1;
if( !labelsEquivalent )
{
getLabelsMap( labels, sizes, labelsMap );
for( int i = 0; i < labels.rows; i++ )
if( isFlt )
err += labels.at<float>(i, 0) != labelsMap[(int)origLabels.at<float>(i, 0)];
else
err += labels.at<int>(i, 0) != labelsMap[origLabels.at<int>(i, 0)];
}
else
{
for( int i = 0; i < labels.rows; i++ )
if( isFlt )
err += labels.at<float>(i, 0) != origLabels.at<float>(i, 0);
else
err += labels.at<int>(i, 0) != origLabels.at<int>(i, 0);
}
return (float)err / (float)labels.rows;
}
//--------------------------------------------------------------------------------------------
class CV_KMeansTest : public cvtest::BaseTest {
public:
CV_KMeansTest() {}
protected:
virtual void run( int start_from );
};
void CV_KMeansTest::run( int /*start_from*/ )
{
const int iters = 100;
int sizesArr[] = { 5000, 7000, 8000 };
int pointsCount = sizesArr[0]+ sizesArr[1] + sizesArr[2];
Mat data( pointsCount, 2, CV_32FC1 ), labels;
vector<int> sizes( sizesArr, sizesArr + sizeof(sizesArr) / sizeof(sizesArr[0]) );
vector<Mat> means, covs;
defaultDistribs( means, covs );
generateData( data, labels, sizes, means, covs, CV_32SC1 );
int code = cvtest::TS::OK;
Mat bestLabels;
// 1. flag==KMEANS_PP_CENTERS
kmeans( data, 3, bestLabels, TermCriteria( TermCriteria::COUNT, iters, 0.0), 0, KMEANS_PP_CENTERS, 0 );
if( calcErr( bestLabels, labels, sizes, false ) > 0.01f )
{
ts->printf( cvtest::TS::LOG, "bad accuracy if flag==KMEANS_PP_CENTERS" );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
// 2. flag==KMEANS_RANDOM_CENTERS
kmeans( data, 3, bestLabels, TermCriteria( TermCriteria::COUNT, iters, 0.0), 0, KMEANS_RANDOM_CENTERS, 0 );
if( calcErr( bestLabels, labels, sizes, false ) > 0.01f )
{
ts->printf( cvtest::TS::LOG, "bad accuracy if flag==KMEANS_PP_CENTERS" );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
// 3. flag==KMEANS_USE_INITIAL_LABELS
labels.copyTo( bestLabels );
RNG rng;
for( int i = 0; i < 0.5f * pointsCount; i++ )
bestLabels.at<int>( rng.next() % pointsCount, 0 ) = rng.next() % 3;
kmeans( data, 3, bestLabels, TermCriteria( TermCriteria::COUNT, iters, 0.0), 0, KMEANS_USE_INITIAL_LABELS, 0 );
if( calcErr( bestLabels, labels, sizes, false ) > 0.01f )
{
ts->printf( cvtest::TS::LOG, "bad accuracy if flag==KMEANS_PP_CENTERS" );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
ts->set_failed_test_info( code );
}
//--------------------------------------------------------------------------------------------
class CV_KNearestTest : public cvtest::BaseTest {
public:
CV_KNearestTest() {}
protected:
virtual void run( int start_from );
};
void CV_KNearestTest::run( int /*start_from*/ )
{
int sizesArr[] = { 500, 700, 800 };
int pointsCount = sizesArr[0]+ sizesArr[1] + sizesArr[2];
// train data
Mat trainData( pointsCount, 2, CV_32FC1 ), trainLabels;
vector<int> sizes( sizesArr, sizesArr + sizeof(sizesArr) / sizeof(sizesArr[0]) );
vector<Mat> means, covs;
defaultDistribs( means, covs );
generateData( trainData, trainLabels, sizes, means, covs, CV_32FC1 );
// test data
Mat testData( pointsCount, 2, CV_32FC1 ), testLabels, bestLabels;
generateData( testData, testLabels, sizes, means, covs, CV_32FC1 );
int code = cvtest::TS::OK;
KNearest knearest;
knearest.train( trainData, trainLabels );
knearest.find_nearest( testData, 4, &bestLabels );
if( calcErr( bestLabels, testLabels, sizes, true ) > 0.01f )
{
ts->printf( cvtest::TS::LOG, "bad accuracy on test data" );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
ts->set_failed_test_info( code );
}
//--------------------------------------------------------------------------------------------
class CV_EMTest : public cvtest::BaseTest {
public:
CV_EMTest() {}
protected:
virtual void run( int start_from );
};
void CV_EMTest::run( int /*start_from*/ )
{
int sizesArr[] = { 5000, 7000, 8000 };
int pointsCount = sizesArr[0]+ sizesArr[1] + sizesArr[2];
// train data
Mat trainData( pointsCount, 2, CV_32FC1 ), trainLabels;
vector<int> sizes( sizesArr, sizesArr + sizeof(sizesArr) / sizeof(sizesArr[0]) );
vector<Mat> means, covs;
defaultDistribs( means, covs );
generateData( trainData, trainLabels, sizes, means, covs, CV_32SC1 );
// test data
Mat testData( pointsCount, 2, CV_32FC1 ), testLabels, bestLabels;
generateData( testData, testLabels, sizes, means, covs, CV_32SC1 );
int code = cvtest::TS::OK;
ExpectationMaximization em;
CvEMParams params;
params.nclusters = 3;
em.train( trainData, Mat(), params, &bestLabels );
// check train error
if( calcErr( bestLabels, trainLabels, sizes, true ) > 0.002f )
{
ts->printf( cvtest::TS::LOG, "bad accuracy on train data" );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
// check test error
bestLabels.create( testData.rows, 1, CV_32SC1 );
for( int i = 0; i < testData.rows; i++ )
{
Mat sample( 1, testData.cols, CV_32FC1, testData.ptr<float>(i));
bestLabels.at<int>(i,0) = (int)em.predict( sample, 0 );
}
if( calcErr( bestLabels, testLabels, sizes, true ) > 0.005f )
{
ts->printf( cvtest::TS::LOG, "bad accuracy on test data" );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
ts->set_failed_test_info( code );
}
TEST(ML_KMeans, accuracy) { CV_KMeansTest test; test.safe_run(); }
TEST(ML_KNearest, accuracy) { CV_KNearestTest test; test.safe_run(); }
TEST(ML_EMTest, accuracy) { CV_EMTest test; test.safe_run(); }

275
modules/ml/test/test_gbttest.cpp Normal file
View File

@@ -0,0 +1,275 @@
#include "test_precomp.hpp"
#include <string>
#include <fstream>
#include <iostream>
using namespace std;
class CV_GBTreesTest : public cvtest::BaseTest
{
public:
CV_GBTreesTest();
~CV_GBTreesTest();
protected:
void run(int);
int TestTrainPredict(int test_num);
int TestSaveLoad();
int checkPredictError(int test_num);
int checkLoadSave();
//string model_file_name1;
//string model_file_name2;
char model_file_name1[50];
char model_file_name2[50];
string* datasets;
string data_path;
CvMLData* data;
CvGBTrees* gtb;
vector<float> test_resps1;
vector<float> test_resps2;
};
int _get_len(const CvMat* mat)
{
return (mat->cols > mat->rows) ? mat->cols : mat->rows;
}
CV_GBTreesTest::CV_GBTreesTest()
{
datasets = 0;
data = 0;
gtb = 0;
}
CV_GBTreesTest::~CV_GBTreesTest()
{
if (data)
delete data;
delete[] datasets;
}
int CV_GBTreesTest::TestTrainPredict(int test_num)
{
int code = cvtest::TS::OK;
int weak_count = 200;
float shrinkage = 0.1f;
float subsample_portion = 0.5f;
int max_depth = 5;
bool use_surrogates = true;
int loss_function_type = 0;
switch (test_num)
{
case (1) : loss_function_type = CvGBTrees::SQUARED_LOSS; break;
case (2) : loss_function_type = CvGBTrees::ABSOLUTE_LOSS; break;
case (3) : loss_function_type = CvGBTrees::HUBER_LOSS; break;
case (0) : loss_function_type = CvGBTrees::DEVIANCE_LOSS; break;
default :
{
ts->printf( cvtest::TS::LOG, "Bad test_num value in CV_GBTreesTest::TestTrainPredict(..) function." );
return cvtest::TS::FAIL_BAD_ARG_CHECK;
}
}
int dataset_num = test_num == 0 ? 0 : 1;
if (!data)
{
data = new CvMLData();
data->set_delimiter(',');
if (data->read_csv(datasets[dataset_num].c_str()))
{
ts->printf( cvtest::TS::LOG, "File reading error." );
return cvtest::TS::FAIL_INVALID_TEST_DATA;
}
if (test_num == 0)
{
data->set_response_idx(57);
data->set_var_types("ord[0-56],cat[57]");
}
else
{
data->set_response_idx(13);
data->set_var_types("ord[0-2,4-13],cat[3]");
subsample_portion = 0.7f;
}
int train_sample_count = cvFloor(_get_len(data->get_responses())*0.5f);
CvTrainTestSplit spl( train_sample_count );
data->set_train_test_split( &spl );
}
data->mix_train_and_test_idx();
if (gtb) delete gtb;
gtb = new CvGBTrees();
bool tmp_code = true;
tmp_code = gtb->train(data, CvGBTreesParams(loss_function_type, weak_count,
shrinkage, subsample_portion,
max_depth, use_surrogates));
if (!tmp_code)
{
ts->printf( cvtest::TS::LOG, "Model training was failed.");
return cvtest::TS::FAIL_INVALID_OUTPUT;
}
code = checkPredictError(test_num);
return code;
}
int CV_GBTreesTest::checkPredictError(int test_num)
{
if (!gtb)
return cvtest::TS::FAIL_GENERIC;
float mean[] = {5.430247f, 13.5654f, 12.6569f, 13.1661f};
float sigma[] = {0.4162694f, 3.21161f, 3.43297f, 3.00624f};
float current_error = gtb->calc_error(data, CV_TEST_ERROR);
if ( abs( current_error - mean[test_num]) > 6*sigma[test_num] )
{
ts->printf( cvtest::TS::LOG, "Test error is out of range:\n"
"abs(%f/*curEr*/ - %f/*mean*/ > %f/*6*sigma*/",
current_error, mean[test_num], 6*sigma[test_num] );
return cvtest::TS::FAIL_BAD_ACCURACY;
}
return cvtest::TS::OK;
}
int CV_GBTreesTest::TestSaveLoad()
{
if (!gtb)
return cvtest::TS::FAIL_GENERIC;
tmpnam(model_file_name1);
tmpnam(model_file_name2);
if(model_file_name1[0] == '\\')
model_file_name1[0] = '_';
if(model_file_name2[0] == '\\')
model_file_name2[0] = '_';
gtb->save(model_file_name1);
gtb->calc_error(data, CV_TEST_ERROR, &test_resps1);
gtb->load(model_file_name1);
gtb->calc_error(data, CV_TEST_ERROR, &test_resps2);
gtb->save(model_file_name2);
return checkLoadSave();
}
int CV_GBTreesTest::checkLoadSave()
{
int code = cvtest::TS::OK;
// 1. compare files
ifstream f1( model_file_name1 ), f2( model_file_name2 );
string s1, s2;
int lineIdx = 0;
CV_Assert( f1.is_open() && f2.is_open() );
for( ; !f1.eof() && !f2.eof(); lineIdx++ )
{
getline( f1, s1 );
getline( f2, s2 );
if( s1.compare(s2) )
{
ts->printf( cvtest::TS::LOG, "first and second saved files differ in %n-line; first %n line: %s; second %n-line: %s",
lineIdx, lineIdx, s1.c_str(), lineIdx, s2.c_str() );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
}
if( !f1.eof() || !f2.eof() )
{
ts->printf( cvtest::TS::LOG, "First and second saved files differ in %n-line; first %n line: %s; second %n-line: %s",
lineIdx, lineIdx, s1.c_str(), lineIdx, s2.c_str() );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
f1.close();
f2.close();
// delete temporary files
remove( model_file_name1 );
remove( model_file_name2 );
// 2. compare responses
CV_Assert( test_resps1.size() == test_resps2.size() );
vector<float>::const_iterator it1 = test_resps1.begin(), it2 = test_resps2.begin();
for( ; it1 != test_resps1.end(); ++it1, ++it2 )
{
if( fabs(*it1 - *it2) > FLT_EPSILON )
{
ts->printf( cvtest::TS::LOG, "Responses predicted before saving and after loading are different" );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
}
return code;
}
void CV_GBTreesTest::run(int)
{
string data_path = string(ts->get_data_path());
datasets = new string[2];
datasets[0] = data_path + string("spambase.data"); /*string("dataset_classification.csv");*/
datasets[1] = data_path + string("housing_.data"); /*string("dataset_regression.csv");*/
int code = cvtest::TS::OK;
for (int i = 0; i < 4; i++)
{
int temp_code = TestTrainPredict(i);
if (temp_code != cvtest::TS::OK)
{
code = temp_code;
break;
}
else if (i==0)
{
temp_code = TestSaveLoad();
if (temp_code != cvtest::TS::OK)
code = temp_code;
delete data;
data = 0;
}
delete gtb;
gtb = 0;
}
delete data;
data = 0;
ts->set_failed_test_info( code );
}
/////////////////////////////////////////////////////////////////////////////
//////////////////// test registration /////////////////////////////////////
/////////////////////////////////////////////////////////////////////////////
TEST(ML_GBTrees, regression) { CV_GBTreesTest test; test.safe_run(); }

3
modules/ml/test/test_main.cpp Normal file
View File

@@ -0,0 +1,3 @@
#include "test_precomp.hpp"
CV_TEST_MAIN("ml")

130
modules/ml/test/test_mltests.cpp Normal file
View File

@@ -0,0 +1,130 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// Intel License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2000, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of Intel Corporation may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#include "test_precomp.hpp"
using namespace cv;
using namespace std;
CV_AMLTest::CV_AMLTest( const char* _modelName ) : CV_MLBaseTest( _modelName )
{
validationFN = "avalidation.xml";
}
int CV_AMLTest::run_test_case( int testCaseIdx )
{
int code = cvtest::TS::OK;
code = prepare_test_case( testCaseIdx );
if (code == cvtest::TS::OK)
{
//#define GET_STAT
#ifdef GET_STAT
const char* data_name = ((CvFileNode*)cvGetSeqElem( dataSetNames, testCaseIdx ))->data.str.ptr;
printf("%s, %s ", name, data_name);
const int icount = 100;
float res[icount];
for (int k = 0; k < icount; k++)
{
#endif
data.mix_train_and_test_idx();
code = train( testCaseIdx );
#ifdef GET_STAT
float case_result = get_error();
res[k] = case_result;
}
float mean = 0, sigma = 0;
for (int k = 0; k < icount; k++)
{
mean += res[k];
}
mean = mean /icount;
for (int k = 0; k < icount; k++)
{
sigma += (res[k] - mean)*(res[k] - mean);
}
sigma = sqrt(sigma/icount);
printf("%f, %f\n", mean, sigma);
#endif
}
return code;
}
int CV_AMLTest::validate_test_results( int testCaseIdx )
{
int iters;
float mean, sigma;
// read validation params
FileNode resultNode =
validationFS.getFirstTopLevelNode()["validation"][modelName][dataSetNames[testCaseIdx]]["result"];
resultNode["iter_count"] >> iters;
if ( iters > 0)
{
resultNode["mean"] >> mean;
resultNode["sigma"] >> sigma;
float curErr = get_error( testCaseIdx, CV_TEST_ERROR );
const int coeff = 4;
ts->printf( cvtest::TS::LOG, "Test case = %d; test error = %f; mean error = %f (diff=%f), %d*sigma = %f",
testCaseIdx, curErr, mean, abs( curErr - mean), coeff, coeff*sigma );
if ( abs( curErr - mean) > coeff*sigma )
{
ts->printf( cvtest::TS::LOG, "abs(%f - %f) > %f - OUT OF RANGE!\n", curErr, mean, coeff*sigma, coeff );
return cvtest::TS::FAIL_BAD_ACCURACY;
}
else
ts->printf( cvtest::TS::LOG, ".\n" );
}
else
{
ts->printf( cvtest::TS::LOG, "validation info is not suitable" );
return cvtest::TS::FAIL_INVALID_TEST_DATA;
}
return cvtest::TS::OK;
}
TEST(ML_DTree, regression) { CV_AMLTest test( CV_DTREE ); test.safe_run(); }
TEST(ML_Boost, regression) { CV_AMLTest test( CV_BOOST ); test.safe_run(); }
TEST(ML_RTrees, regression) { CV_AMLTest test( CV_RTREES ); test.safe_run(); }
TEST(ML_ERTrees, regression) { CV_AMLTest test( CV_ERTREES ); test.safe_run(); }
/* End of file. */

796
modules/ml/test/test_mltests2.cpp Normal file
View File

@@ -0,0 +1,796 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// Intel License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2000, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of Intel Corporation may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#include "test_precomp.hpp"
using namespace cv;
using namespace std;
// auxiliary functions
// 1. nbayes
void nbayes_check_data( CvMLData* _data )
{
if( _data->get_missing() )
CV_Error( CV_StsBadArg, "missing values are not supported" );
const CvMat* var_types = _data->get_var_types();
bool is_classifier = var_types->data.ptr[var_types->cols-1] == CV_VAR_CATEGORICAL;
if( ( fabs( cvNorm( var_types, 0, CV_L1 ) -
(var_types->rows + var_types->cols - 2)*CV_VAR_ORDERED - CV_VAR_CATEGORICAL ) > FLT_EPSILON ) ||
!is_classifier )
CV_Error( CV_StsBadArg, "incorrect types of predictors or responses" );
}
bool nbayes_train( CvNormalBayesClassifier* nbayes, CvMLData* _data )
{
nbayes_check_data( _data );
const CvMat* values = _data->get_values();
const CvMat* responses = _data->get_responses();
const CvMat* train_sidx = _data->get_train_sample_idx();
const CvMat* var_idx = _data->get_var_idx();
return nbayes->train( values, responses, var_idx, train_sidx );
}
float nbayes_calc_error( CvNormalBayesClassifier* nbayes, CvMLData* _data, int type, vector<float> *resp )
{
float err = 0;
nbayes_check_data( _data );
const CvMat* values = _data->get_values();
const CvMat* response = _data->get_responses();
const CvMat* sample_idx = (type == CV_TEST_ERROR) ? _data->get_test_sample_idx() : _data->get_train_sample_idx();
int* sidx = sample_idx ? sample_idx->data.i : 0;
int r_step = CV_IS_MAT_CONT(response->type) ?
1 : response->step / CV_ELEM_SIZE(response->type);
int sample_count = sample_idx ? sample_idx->cols : 0;
sample_count = (type == CV_TRAIN_ERROR && sample_count == 0) ? values->rows : sample_count;
float* pred_resp = 0;
if( resp && (sample_count > 0) )
{
resp->resize( sample_count );
pred_resp = &((*resp)[0]);
}
for( int i = 0; i < sample_count; i++ )
{
CvMat sample;
int si = sidx ? sidx[i] : i;
cvGetRow( values, &sample, si );
float r = (float)nbayes->predict( &sample, 0 );
if( pred_resp )
pred_resp[i] = r;
int d = fabs((double)r - response->data.fl[si*r_step]) <= FLT_EPSILON ? 0 : 1;
err += d;
}
err = sample_count ? err / (float)sample_count * 100 : -FLT_MAX;
return err;
}
// 2. knearest
void knearest_check_data_and_get_predictors( CvMLData* _data, CvMat* _predictors )
{
const CvMat* values = _data->get_values();
const CvMat* var_idx = _data->get_var_idx();
if( var_idx->cols + var_idx->rows != values->cols )
CV_Error( CV_StsBadArg, "var_idx is not supported" );
if( _data->get_missing() )
CV_Error( CV_StsBadArg, "missing values are not supported" );
int resp_idx = _data->get_response_idx();
if( resp_idx == 0)
cvGetCols( values, _predictors, 1, values->cols );
else if( resp_idx == values->cols - 1 )
cvGetCols( values, _predictors, 0, values->cols - 1 );
else
CV_Error( CV_StsBadArg, "responses must be in the first or last column; other cases are not supported" );
}
bool knearest_train( CvKNearest* knearest, CvMLData* _data )
{
const CvMat* responses = _data->get_responses();
const CvMat* train_sidx = _data->get_train_sample_idx();
bool is_regression = _data->get_var_type( _data->get_response_idx() ) == CV_VAR_ORDERED;
CvMat predictors;
knearest_check_data_and_get_predictors( _data, &predictors );
return knearest->train( &predictors, responses, train_sidx, is_regression );
}
float knearest_calc_error( CvKNearest* knearest, CvMLData* _data, int k, int type, vector<float> *resp )
{
float err = 0;
const CvMat* response = _data->get_responses();
const CvMat* sample_idx = (type == CV_TEST_ERROR) ? _data->get_test_sample_idx() : _data->get_train_sample_idx();
int* sidx = sample_idx ? sample_idx->data.i : 0;
int r_step = CV_IS_MAT_CONT(response->type) ?
1 : response->step / CV_ELEM_SIZE(response->type);
bool is_regression = _data->get_var_type( _data->get_response_idx() ) == CV_VAR_ORDERED;
CvMat predictors;
knearest_check_data_and_get_predictors( _data, &predictors );
int sample_count = sample_idx ? sample_idx->cols : 0;
sample_count = (type == CV_TRAIN_ERROR && sample_count == 0) ? predictors.rows : sample_count;
float* pred_resp = 0;
if( resp && (sample_count > 0) )
{
resp->resize( sample_count );
pred_resp = &((*resp)[0]);
}
if ( !is_regression )
{
for( int i = 0; i < sample_count; i++ )
{
CvMat sample;
int si = sidx ? sidx[i] : i;
cvGetRow( &predictors, &sample, si );
float r = knearest->find_nearest( &sample, k );
if( pred_resp )
pred_resp[i] = r;
int d = fabs((double)r - response->data.fl[si*r_step]) <= FLT_EPSILON ? 0 : 1;
err += d;
}
err = sample_count ? err / (float)sample_count * 100 : -FLT_MAX;
}
else
{
for( int i = 0; i < sample_count; i++ )
{
CvMat sample;
int si = sidx ? sidx[i] : i;
cvGetRow( &predictors, &sample, si );
float r = knearest->find_nearest( &sample, k );
if( pred_resp )
pred_resp[i] = r;
float d = r - response->data.fl[si*r_step];
err += d*d;
}
err = sample_count ? err / (float)sample_count : -FLT_MAX;
}
return err;
}
// 3. svm
int str_to_svm_type(string& str)
{
if( !str.compare("C_SVC") )
return CvSVM::C_SVC;
if( !str.compare("NU_SVC") )
return CvSVM::NU_SVC;
if( !str.compare("ONE_CLASS") )
return CvSVM::ONE_CLASS;
if( !str.compare("EPS_SVR") )
return CvSVM::EPS_SVR;
if( !str.compare("NU_SVR") )
return CvSVM::NU_SVR;
CV_Error( CV_StsBadArg, "incorrect svm type string" );
return -1;
}
int str_to_svm_kernel_type( string& str )
{
if( !str.compare("LINEAR") )
return CvSVM::LINEAR;
if( !str.compare("POLY") )
return CvSVM::POLY;
if( !str.compare("RBF") )
return CvSVM::RBF;
if( !str.compare("SIGMOID") )
return CvSVM::SIGMOID;
CV_Error( CV_StsBadArg, "incorrect svm type string" );
return -1;
}
void svm_check_data( CvMLData* _data )
{
if( _data->get_missing() )
CV_Error( CV_StsBadArg, "missing values are not supported" );
const CvMat* var_types = _data->get_var_types();
for( int i = 0; i < var_types->cols-1; i++ )
if (var_types->data.ptr[i] == CV_VAR_CATEGORICAL)
{
char msg[50];
sprintf( msg, "incorrect type of %d-predictor", i );
CV_Error( CV_StsBadArg, msg );
}
}
bool svm_train( CvSVM* svm, CvMLData* _data, CvSVMParams _params )
{
svm_check_data(_data);
const CvMat* _train_data = _data->get_values();
const CvMat* _responses = _data->get_responses();
const CvMat* _var_idx = _data->get_var_idx();
const CvMat* _sample_idx = _data->get_train_sample_idx();
return svm->train( _train_data, _responses, _var_idx, _sample_idx, _params );
}
bool svm_train_auto( CvSVM* svm, CvMLData* _data, CvSVMParams _params,
int k_fold, CvParamGrid C_grid, CvParamGrid gamma_grid,
CvParamGrid p_grid, CvParamGrid nu_grid, CvParamGrid coef_grid,
CvParamGrid degree_grid )
{
svm_check_data(_data);
const CvMat* _train_data = _data->get_values();
const CvMat* _responses = _data->get_responses();
const CvMat* _var_idx = _data->get_var_idx();
const CvMat* _sample_idx = _data->get_train_sample_idx();
return svm->train_auto( _train_data, _responses, _var_idx,
_sample_idx, _params, k_fold, C_grid, gamma_grid, p_grid, nu_grid, coef_grid, degree_grid );
}
float svm_calc_error( CvSVM* svm, CvMLData* _data, int type, vector<float> *resp )
{
svm_check_data(_data);
float err = 0;
const CvMat* values = _data->get_values();
const CvMat* response = _data->get_responses();
const CvMat* sample_idx = (type == CV_TEST_ERROR) ? _data->get_test_sample_idx() : _data->get_train_sample_idx();
const CvMat* var_types = _data->get_var_types();
int* sidx = sample_idx ? sample_idx->data.i : 0;
int r_step = CV_IS_MAT_CONT(response->type) ?
1 : response->step / CV_ELEM_SIZE(response->type);
bool is_classifier = var_types->data.ptr[var_types->cols-1] == CV_VAR_CATEGORICAL;
int sample_count = sample_idx ? sample_idx->cols : 0;
sample_count = (type == CV_TRAIN_ERROR && sample_count == 0) ? values->rows : sample_count;
float* pred_resp = 0;
if( resp && (sample_count > 0) )
{
resp->resize( sample_count );
pred_resp = &((*resp)[0]);
}
if ( is_classifier )
{
for( int i = 0; i < sample_count; i++ )
{
CvMat sample;
int si = sidx ? sidx[i] : i;
cvGetRow( values, &sample, si );
float r = svm->predict( &sample );
if( pred_resp )
pred_resp[i] = r;
int d = fabs((double)r - response->data.fl[si*r_step]) <= FLT_EPSILON ? 0 : 1;
err += d;
}
err = sample_count ? err / (float)sample_count * 100 : -FLT_MAX;
}
else
{
for( int i = 0; i < sample_count; i++ )
{
CvMat sample;
int si = sidx ? sidx[i] : i;
cvGetRow( values, &sample, si );
float r = svm->predict( &sample );
if( pred_resp )
pred_resp[i] = r;
float d = r - response->data.fl[si*r_step];
err += d*d;
}
err = sample_count ? err / (float)sample_count : -FLT_MAX;
}
return err;
}
// 4. em
// 5. ann
int str_to_ann_train_method( string& str )
{
if( !str.compare("BACKPROP") )
return CvANN_MLP_TrainParams::BACKPROP;
if( !str.compare("RPROP") )
return CvANN_MLP_TrainParams::RPROP;
CV_Error( CV_StsBadArg, "incorrect ann train method string" );
return -1;
}
void ann_check_data_and_get_predictors( CvMLData* _data, CvMat* _inputs )
{
const CvMat* values = _data->get_values();
const CvMat* var_idx = _data->get_var_idx();
if( var_idx->cols + var_idx->rows != values->cols )
CV_Error( CV_StsBadArg, "var_idx is not supported" );
if( _data->get_missing() )
CV_Error( CV_StsBadArg, "missing values are not supported" );
int resp_idx = _data->get_response_idx();
if( resp_idx == 0)
cvGetCols( values, _inputs, 1, values->cols );
else if( resp_idx == values->cols - 1 )
cvGetCols( values, _inputs, 0, values->cols - 1 );
else
CV_Error( CV_StsBadArg, "outputs must be in the first or last column; other cases are not supported" );
}
void ann_get_new_responses( CvMLData* _data, Mat& new_responses, map<int, int>& cls_map )
{
const CvMat* train_sidx = _data->get_train_sample_idx();
int* train_sidx_ptr = train_sidx->data.i;
const CvMat* responses = _data->get_responses();
float* responses_ptr = responses->data.fl;
int r_step = CV_IS_MAT_CONT(responses->type) ?
1 : responses->step / CV_ELEM_SIZE(responses->type);
int cls_count = 0;
// construct cls_map
cls_map.clear();
for( int si = 0; si < train_sidx->cols; si++ )
{
int sidx = train_sidx_ptr[si];
int r = cvRound(responses_ptr[sidx*r_step]);
CV_DbgAssert( fabs(responses_ptr[sidx*r_step]-r) < FLT_EPSILON );
int cls_map_size = (int)cls_map.size();
cls_map[r];
if ( (int)cls_map.size() > cls_map_size )
cls_map[r] = cls_count++;
}
new_responses.create( responses->rows, cls_count, CV_32F );
new_responses.setTo( 0 );
for( int si = 0; si < train_sidx->cols; si++ )
{
int sidx = train_sidx_ptr[si];
int r = cvRound(responses_ptr[sidx*r_step]);
int cidx = cls_map[r];
new_responses.ptr<float>(sidx)[cidx] = 1;
}
}
int ann_train( CvANN_MLP* ann, CvMLData* _data, Mat& new_responses, CvANN_MLP_TrainParams _params, int flags = 0 )
{
const CvMat* train_sidx = _data->get_train_sample_idx();
CvMat predictors;
ann_check_data_and_get_predictors( _data, &predictors );
CvMat _new_responses = CvMat( new_responses );
return ann->train( &predictors, &_new_responses, 0, train_sidx, _params, flags );
}
float ann_calc_error( CvANN_MLP* ann, CvMLData* _data, map<int, int>& cls_map, int type , vector<float> *resp_labels )
{
float err = 0;
const CvMat* responses = _data->get_responses();
const CvMat* sample_idx = (type == CV_TEST_ERROR) ? _data->get_test_sample_idx() : _data->get_train_sample_idx();
int* sidx = sample_idx ? sample_idx->data.i : 0;
int r_step = CV_IS_MAT_CONT(responses->type) ?
1 : responses->step / CV_ELEM_SIZE(responses->type);
CvMat predictors;
ann_check_data_and_get_predictors( _data, &predictors );
int sample_count = sample_idx ? sample_idx->cols : 0;
sample_count = (type == CV_TRAIN_ERROR && sample_count == 0) ? predictors.rows : sample_count;
float* pred_resp = 0;
vector<float> innresp;
if( sample_count > 0 )
{
if( resp_labels )
{
resp_labels->resize( sample_count );
pred_resp = &((*resp_labels)[0]);
}
else
{
innresp.resize( sample_count );
pred_resp = &(innresp[0]);
}
}
int cls_count = (int)cls_map.size();
Mat output( 1, cls_count, CV_32FC1 );
CvMat _output = CvMat(output);
map<int, int>::iterator b_it = cls_map.begin();
for( int i = 0; i < sample_count; i++ )
{
CvMat sample;
int si = sidx ? sidx[i] : i;
cvGetRow( &predictors, &sample, si );
ann->predict( &sample, &_output );
CvPoint best_cls = {0,0};
cvMinMaxLoc( &_output, 0, 0, 0, &best_cls, 0 );
int r = cvRound(responses->data.fl[si*r_step]);
CV_DbgAssert( fabs(responses->data.fl[si*r_step]-r) < FLT_EPSILON );
r = cls_map[r];
int d = best_cls.x == r ? 0 : 1;
err += d;
pred_resp[i] = (float)best_cls.x;
}
err = sample_count ? err / (float)sample_count * 100 : -FLT_MAX;
return err;
}
// 6. dtree
// 7. boost
int str_to_boost_type( string& str )
{
if ( !str.compare("DISCRETE") )
return CvBoost::DISCRETE;
if ( !str.compare("REAL") )
return CvBoost::REAL;
if ( !str.compare("LOGIT") )
return CvBoost::LOGIT;
if ( !str.compare("GENTLE") )
return CvBoost::GENTLE;
CV_Error( CV_StsBadArg, "incorrect boost type string" );
return -1;
}
// 8. rtrees
// 9. ertrees
// ---------------------------------- MLBaseTest ---------------------------------------------------
CV_MLBaseTest::CV_MLBaseTest(const char* _modelName)
{
int64 seeds[] = { CV_BIG_INT(0x00009fff4f9c8d52),
CV_BIG_INT(0x0000a17166072c7c),
CV_BIG_INT(0x0201b32115cd1f9a),
CV_BIG_INT(0x0513cb37abcd1234),
CV_BIG_INT(0x0001a2b3c4d5f678)
};
int seedCount = sizeof(seeds)/sizeof(seeds[0]);
RNG& rng = theRNG();
initSeed = rng.state;
rng.state = seeds[rng(seedCount)];
modelName = _modelName;
nbayes = 0;
knearest = 0;
svm = 0;
em = 0;
ann = 0;
dtree = 0;
boost = 0;
rtrees = 0;
ertrees = 0;
if( !modelName.compare(CV_NBAYES) )
nbayes = new CvNormalBayesClassifier;
else if( !modelName.compare(CV_KNEAREST) )
knearest = new CvKNearest;
else if( !modelName.compare(CV_SVM) )
svm = new CvSVM;
else if( !modelName.compare(CV_EM) )
em = new CvEM;
else if( !modelName.compare(CV_ANN) )
ann = new CvANN_MLP;
else if( !modelName.compare(CV_DTREE) )
dtree = new CvDTree;
else if( !modelName.compare(CV_BOOST) )
boost = new CvBoost;
else if( !modelName.compare(CV_RTREES) )
rtrees = new CvRTrees;
else if( !modelName.compare(CV_ERTREES) )
ertrees = new CvERTrees;
}
CV_MLBaseTest::~CV_MLBaseTest()
{
if( validationFS.isOpened() )
validationFS.release();
if( nbayes )
delete nbayes;
if( knearest )
delete knearest;
if( svm )
delete svm;
if( em )
delete em;
if( ann )
delete ann;
if( dtree )
delete dtree;
if( boost )
delete boost;
if( rtrees )
delete rtrees;
if( ertrees )
delete ertrees;
theRNG().state = initSeed;
}
int CV_MLBaseTest::read_params( CvFileStorage* _fs )
{
if( !_fs )
test_case_count = -1;
else
{
CvFileNode* fn = cvGetRootFileNode( _fs, 0 );
fn = (CvFileNode*)cvGetSeqElem( fn->data.seq, 0 );
fn = cvGetFileNodeByName( _fs, fn, "run_params" );
CvSeq* dataSetNamesSeq = cvGetFileNodeByName( _fs, fn, modelName.c_str() )->data.seq;
test_case_count = dataSetNamesSeq ? dataSetNamesSeq->total : -1;
if( test_case_count > 0 )
{
dataSetNames.resize( test_case_count );
vector<string>::iterator it = dataSetNames.begin();
for( int i = 0; i < test_case_count; i++, it++ )
*it = ((CvFileNode*)cvGetSeqElem( dataSetNamesSeq, i ))->data.str.ptr;
}
}
return cvtest::TS::OK;;
}
void CV_MLBaseTest::run( int start_from )
{
string filename = ts->get_data_path();
filename += get_validation_filename();
validationFS.open( filename, FileStorage::READ );
read_params( *validationFS );
int code = cvtest::TS::OK;
start_from = 0;
for (int i = 0; i < test_case_count; i++)
{
int temp_code = run_test_case( i );
if (temp_code == cvtest::TS::OK)
temp_code = validate_test_results( i );
if (temp_code != cvtest::TS::OK)
code = temp_code;
}
if ( test_case_count <= 0)
{
ts->printf( cvtest::TS::LOG, "validation file is not determined or not correct" );
code = cvtest::TS::FAIL_INVALID_TEST_DATA;
}
ts->set_failed_test_info( code );
}
int CV_MLBaseTest::prepare_test_case( int test_case_idx )
{
int trainSampleCount, respIdx;
string varTypes;
clear();
string dataPath = ts->get_data_path();
if ( dataPath.empty() )
{
ts->printf( cvtest::TS::LOG, "data path is empty" );
return cvtest::TS::FAIL_INVALID_TEST_DATA;
}
string dataName = dataSetNames[test_case_idx],
filename = dataPath + dataName + ".data";
if ( data.read_csv( filename.c_str() ) != 0)
{
char msg[100];
sprintf( msg, "file %s can not be read", filename.c_str() );
ts->printf( cvtest::TS::LOG, msg );
return cvtest::TS::FAIL_INVALID_TEST_DATA;
}
FileNode dataParamsNode = validationFS.getFirstTopLevelNode()["validation"][modelName][dataName]["data_params"];
CV_DbgAssert( !dataParamsNode.empty() );
CV_DbgAssert( !dataParamsNode["LS"].empty() );
dataParamsNode["LS"] >> trainSampleCount;
CvTrainTestSplit spl( trainSampleCount );
data.set_train_test_split( &spl );
CV_DbgAssert( !dataParamsNode["resp_idx"].empty() );
dataParamsNode["resp_idx"] >> respIdx;
data.set_response_idx( respIdx );
CV_DbgAssert( !dataParamsNode["types"].empty() );
dataParamsNode["types"] >> varTypes;
data.set_var_types( varTypes.c_str() );
return cvtest::TS::OK;
}
string& CV_MLBaseTest::get_validation_filename()
{
return validationFN;
}
int CV_MLBaseTest::train( int testCaseIdx )
{
bool is_trained = false;
FileNode modelParamsNode =
validationFS.getFirstTopLevelNode()["validation"][modelName][dataSetNames[testCaseIdx]]["model_params"];
if( !modelName.compare(CV_NBAYES) )
is_trained = nbayes_train( nbayes, &data );
else if( !modelName.compare(CV_KNEAREST) )
{
assert( 0 );
//is_trained = knearest->train( &data );
}
else if( !modelName.compare(CV_SVM) )
{
string svm_type_str, kernel_type_str;
modelParamsNode["svm_type"] >> svm_type_str;
modelParamsNode["kernel_type"] >> kernel_type_str;
CvSVMParams params;
params.svm_type = str_to_svm_type( svm_type_str );
params.kernel_type = str_to_svm_kernel_type( kernel_type_str );
modelParamsNode["degree"] >> params.degree;
modelParamsNode["gamma"] >> params.gamma;
modelParamsNode["coef0"] >> params.coef0;
modelParamsNode["C"] >> params.C;
modelParamsNode["nu"] >> params.nu;
modelParamsNode["p"] >> params.p;
is_trained = svm_train( svm, &data, params );
}
else if( !modelName.compare(CV_EM) )
{
assert( 0 );
}
else if( !modelName.compare(CV_ANN) )
{
string train_method_str;
double param1, param2;
modelParamsNode["train_method"] >> train_method_str;
modelParamsNode["param1"] >> param1;
modelParamsNode["param2"] >> param2;
Mat new_responses;
ann_get_new_responses( &data, new_responses, cls_map );
int layer_sz[] = { data.get_values()->cols - 1, 100, 100, (int)cls_map.size() };
CvMat layer_sizes =
cvMat( 1, (int)(sizeof(layer_sz)/sizeof(layer_sz[0])), CV_32S, layer_sz );
ann->create( &layer_sizes );
is_trained = ann_train( ann, &data, new_responses, CvANN_MLP_TrainParams(cvTermCriteria(CV_TERMCRIT_ITER,300,0.01),
str_to_ann_train_method(train_method_str), param1, param2) ) >= 0;
}
else if( !modelName.compare(CV_DTREE) )
{
int MAX_DEPTH, MIN_SAMPLE_COUNT, MAX_CATEGORIES, CV_FOLDS;
float REG_ACCURACY = 0;
bool USE_SURROGATE, IS_PRUNED;
modelParamsNode["max_depth"] >> MAX_DEPTH;
modelParamsNode["min_sample_count"] >> MIN_SAMPLE_COUNT;
modelParamsNode["use_surrogate"] >> USE_SURROGATE;
modelParamsNode["max_categories"] >> MAX_CATEGORIES;
modelParamsNode["cv_folds"] >> CV_FOLDS;
modelParamsNode["is_pruned"] >> IS_PRUNED;
is_trained = dtree->train( &data,
CvDTreeParams(MAX_DEPTH, MIN_SAMPLE_COUNT, REG_ACCURACY, USE_SURROGATE,
MAX_CATEGORIES, CV_FOLDS, false, IS_PRUNED, 0 )) != 0;
}
else if( !modelName.compare(CV_BOOST) )
{
int BOOST_TYPE, WEAK_COUNT, MAX_DEPTH;
float WEIGHT_TRIM_RATE;
bool USE_SURROGATE;
string typeStr;
modelParamsNode["type"] >> typeStr;
BOOST_TYPE = str_to_boost_type( typeStr );
modelParamsNode["weak_count"] >> WEAK_COUNT;
modelParamsNode["weight_trim_rate"] >> WEIGHT_TRIM_RATE;
modelParamsNode["max_depth"] >> MAX_DEPTH;
modelParamsNode["use_surrogate"] >> USE_SURROGATE;
is_trained = boost->train( &data,
CvBoostParams(BOOST_TYPE, WEAK_COUNT, WEIGHT_TRIM_RATE, MAX_DEPTH, USE_SURROGATE, 0) ) != 0;
}
else if( !modelName.compare(CV_RTREES) )
{
int MAX_DEPTH, MIN_SAMPLE_COUNT, MAX_CATEGORIES, CV_FOLDS, NACTIVE_VARS, MAX_TREES_NUM;
float REG_ACCURACY = 0, OOB_EPS = 0.0;
bool USE_SURROGATE, IS_PRUNED;
modelParamsNode["max_depth"] >> MAX_DEPTH;
modelParamsNode["min_sample_count"] >> MIN_SAMPLE_COUNT;
modelParamsNode["use_surrogate"] >> USE_SURROGATE;
modelParamsNode["max_categories"] >> MAX_CATEGORIES;
modelParamsNode["cv_folds"] >> CV_FOLDS;
modelParamsNode["is_pruned"] >> IS_PRUNED;
modelParamsNode["nactive_vars"] >> NACTIVE_VARS;
modelParamsNode["max_trees_num"] >> MAX_TREES_NUM;
is_trained = rtrees->train( &data, CvRTParams( MAX_DEPTH, MIN_SAMPLE_COUNT, REG_ACCURACY,
USE_SURROGATE, MAX_CATEGORIES, 0, true, // (calc_var_importance == true) <=> RF processes variable importance
NACTIVE_VARS, MAX_TREES_NUM, OOB_EPS, CV_TERMCRIT_ITER)) != 0;
}
else if( !modelName.compare(CV_ERTREES) )
{
int MAX_DEPTH, MIN_SAMPLE_COUNT, MAX_CATEGORIES, CV_FOLDS, NACTIVE_VARS, MAX_TREES_NUM;
float REG_ACCURACY = 0, OOB_EPS = 0.0;
bool USE_SURROGATE, IS_PRUNED;
modelParamsNode["max_depth"] >> MAX_DEPTH;
modelParamsNode["min_sample_count"] >> MIN_SAMPLE_COUNT;
modelParamsNode["use_surrogate"] >> USE_SURROGATE;
modelParamsNode["max_categories"] >> MAX_CATEGORIES;
modelParamsNode["cv_folds"] >> CV_FOLDS;
modelParamsNode["is_pruned"] >> IS_PRUNED;
modelParamsNode["nactive_vars"] >> NACTIVE_VARS;
modelParamsNode["max_trees_num"] >> MAX_TREES_NUM;
is_trained = ertrees->train( &data, CvRTParams( MAX_DEPTH, MIN_SAMPLE_COUNT, REG_ACCURACY,
USE_SURROGATE, MAX_CATEGORIES, 0, false, // (calc_var_importance == true) <=> RF processes variable importance
NACTIVE_VARS, MAX_TREES_NUM, OOB_EPS, CV_TERMCRIT_ITER)) != 0;
}
if( !is_trained )
{
ts->printf( cvtest::TS::LOG, "in test case %d model training was failed", testCaseIdx );
return cvtest::TS::FAIL_INVALID_OUTPUT;
}
return cvtest::TS::OK;
}
float CV_MLBaseTest::get_error( int testCaseIdx, int type, vector<float> *resp )
{
float err = 0;
if( !modelName.compare(CV_NBAYES) )
err = nbayes_calc_error( nbayes, &data, type, resp );
else if( !modelName.compare(CV_KNEAREST) )
{
assert( 0 );
testCaseIdx = 0;
/*int k = 2;
validationFS.getFirstTopLevelNode()["validation"][modelName][dataSetNames[testCaseIdx]]["model_params"]["k"] >> k;
err = knearest->calc_error( &data, k, type, resp );*/
}
else if( !modelName.compare(CV_SVM) )
err = svm_calc_error( svm, &data, type, resp );
else if( !modelName.compare(CV_EM) )
assert( 0 );
else if( !modelName.compare(CV_ANN) )
err = ann_calc_error( ann, &data, cls_map, type, resp );
else if( !modelName.compare(CV_DTREE) )
err = dtree->calc_error( &data, type, resp );
else if( !modelName.compare(CV_BOOST) )
err = boost->calc_error( &data, type, resp );
else if( !modelName.compare(CV_RTREES) )
err = rtrees->calc_error( &data, type, resp );
else if( !modelName.compare(CV_ERTREES) )
err = ertrees->calc_error( &data, type, resp );
return err;
}
void CV_MLBaseTest::save( const char* filename )
{
if( !modelName.compare(CV_NBAYES) )
nbayes->save( filename );
else if( !modelName.compare(CV_KNEAREST) )
knearest->save( filename );
else if( !modelName.compare(CV_SVM) )
svm->save( filename );
else if( !modelName.compare(CV_EM) )
em->save( filename );
else if( !modelName.compare(CV_ANN) )
ann->save( filename );
else if( !modelName.compare(CV_DTREE) )
dtree->save( filename );
else if( !modelName.compare(CV_BOOST) )
boost->save( filename );
else if( !modelName.compare(CV_RTREES) )
rtrees->save( filename );
else if( !modelName.compare(CV_ERTREES) )
ertrees->save( filename );
}
void CV_MLBaseTest::load( const char* filename )
{
if( !modelName.compare(CV_NBAYES) )
nbayes->load( filename );
else if( !modelName.compare(CV_KNEAREST) )
knearest->load( filename );
else if( !modelName.compare(CV_SVM) )
svm->load( filename );
else if( !modelName.compare(CV_EM) )
em->load( filename );
else if( !modelName.compare(CV_ANN) )
ann->load( filename );
else if( !modelName.compare(CV_DTREE) )
dtree->load( filename );
else if( !modelName.compare(CV_BOOST) )
boost->load( filename );
else if( !modelName.compare(CV_RTREES) )
rtrees->load( filename );
else if( !modelName.compare(CV_ERTREES) )
ertrees->load( filename );
}
/* End of file. */

1
modules/ml/test/test_precomp.cpp Normal file
View File

@@ -0,0 +1 @@
#include "test_precomp.hpp"

80
modules/ml/test/test_precomp.hpp Normal file
View File

@@ -0,0 +1,80 @@
#ifndef __OPENCV_TEST_PRECOMP_HPP__
#define __OPENCV_TEST_PRECOMP_HPP__
#include "opencv2/ts/ts.hpp"
#include "opencv2/ml/ml.hpp"
#include "opencv2/core/core_c.h"
#include <iostream>
#include <map>
#define CV_NBAYES "nbayes"
#define CV_KNEAREST "knearest"
#define CV_SVM "svm"
#define CV_EM "em"
#define CV_ANN "ann"
#define CV_DTREE "dtree"
#define CV_BOOST "boost"
#define CV_RTREES "rtrees"
#define CV_ERTREES "ertrees"
class CV_MLBaseTest : public cvtest::BaseTest
{
public:
CV_MLBaseTest( const char* _modelName );
virtual ~CV_MLBaseTest();
protected:
virtual int read_params( CvFileStorage* fs );
virtual void run( int startFrom );
virtual int prepare_test_case( int testCaseIdx );
virtual std::string& get_validation_filename();
virtual int run_test_case( int testCaseIdx ) = 0;
virtual int validate_test_results( int testCaseIdx ) = 0;
int train( int testCaseIdx );
float get_error( int testCaseIdx, int type, std::vector<float> *resp = 0 );
void save( const char* filename );
void load( const char* filename );
CvMLData data;
std::string modelName, validationFN;
std::vector<std::string> dataSetNames;
cv::FileStorage validationFS;
// MLL models
CvNormalBayesClassifier* nbayes;
CvKNearest* knearest;
CvSVM* svm;
CvEM* em;
CvANN_MLP* ann;
CvDTree* dtree;
CvBoost* boost;
CvRTrees* rtrees;
CvERTrees* ertrees;
std::map<int, int> cls_map;
int64 initSeed;
};
class CV_AMLTest : public CV_MLBaseTest
{
public:
CV_AMLTest( const char* _modelName );
protected:
virtual int run_test_case( int testCaseIdx );
virtual int validate_test_results( int testCaseIdx );
};
class CV_SLMLTest : public CV_MLBaseTest
{
public:
CV_SLMLTest( const char* _modelName );
protected:
virtual int run_test_case( int testCaseIdx );
virtual int validate_test_results( int testCaseIdx );
std::vector<float> test_resps1, test_resps2; // predicted responses for test data
char fname1[50], fname2[50];
};
#endif

138
modules/ml/test/test_save_load.cpp Normal file
View File

@@ -0,0 +1,138 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// Intel License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2000, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of Intel Corporation may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#include "test_precomp.hpp"
#include <iostream>
#include <fstream>
using namespace cv;
using namespace std;
CV_SLMLTest::CV_SLMLTest( const char* _modelName ) : CV_MLBaseTest( _modelName )
{
validationFN = "slvalidation.xml";
}
int CV_SLMLTest::run_test_case( int testCaseIdx )
{
int code = cvtest::TS::OK;
code = prepare_test_case( testCaseIdx );
if( code == cvtest::TS::OK )
{
data.mix_train_and_test_idx();
code = train( testCaseIdx );
if( code == cvtest::TS::OK )
{
get_error( testCaseIdx, CV_TEST_ERROR, &test_resps1 );
tmpnam(fname1);
if(fname1[0] == '\\') fname1[0] = '_';
save( fname1 );
load( fname1);
get_error( testCaseIdx, CV_TEST_ERROR, &test_resps2 );
tmpnam(fname2);
if(fname2[0] == '\\') fname2[0] = '_';
save( fname2 );
}
else
ts->printf( cvtest::TS::LOG, "model can not be trained" );
}
return code;
}
int CV_SLMLTest::validate_test_results( int testCaseIdx )
{
int code = cvtest::TS::OK;
// 1. compare files
ifstream f1( fname1 ), f2( fname2 );
string s1, s2;
int lineIdx = 0;
CV_Assert( f1.is_open() && f2.is_open() );
for( ; !f1.eof() && !f2.eof(); lineIdx++ )
{
getline( f1, s1 );
getline( f2, s2 );
if( s1.compare(s2) )
{
ts->printf( cvtest::TS::LOG, "first and second saved files differ in %n-line; first %n line: %s; second %n-line: %s",
lineIdx, lineIdx, s1.c_str(), lineIdx, s2.c_str() );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
}
if( !f1.eof() || !f2.eof() )
{
ts->printf( cvtest::TS::LOG, "in test case %d first and second saved files differ in %n-line; first %n line: %s; second %n-line: %s",
testCaseIdx, lineIdx, lineIdx, s1.c_str(), lineIdx, s2.c_str() );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
f1.close();
f2.close();
// delete temporary files
remove( fname1 );
remove( fname2 );
// 2. compare responses
CV_Assert( test_resps1.size() == test_resps2.size() );
vector<float>::const_iterator it1 = test_resps1.begin(), it2 = test_resps2.begin();
for( ; it1 != test_resps1.end(); ++it1, ++it2 )
{
if( fabs(*it1 - *it2) > FLT_EPSILON )
{
ts->printf( cvtest::TS::LOG, "in test case %d responses predicted before saving and after loading is different", testCaseIdx );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
}
return code;
}
TEST(ML_NaiveBayes, save_load) { CV_SLMLTest test( CV_NBAYES ); test.safe_run(); }
//CV_SLMLTest lsmlknearest( CV_KNEAREST, "slknearest" ); // does not support save!
TEST(ML_SVM, save_load) { CV_SLMLTest test( CV_SVM ); test.safe_run(); }
//CV_SLMLTest lsmlem( CV_EM, "slem" ); // does not support save!
TEST(ML_ANN, save_load) { CV_SLMLTest test( CV_ANN ); test.safe_run(); }
TEST(ML_DTree, save_load) { CV_SLMLTest test( CV_DTREE ); test.safe_run(); }
TEST(ML_Boost, save_load) { CV_SLMLTest test( CV_BOOST ); test.safe_run(); }
TEST(ML_RTrees, save_load) { CV_SLMLTest test( CV_RTREES ); test.safe_run(); }
TEST(ML_ERTrees, save_load) { CV_SLMLTest test( CV_ERTREES ); test.safe_run(); }
/* End of file. */