potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 07:43:03 +04:00
Code Packages Releases Wiki Activity

added cv::EM, moved CvEM to legacy, added/updated tests

Browse Source
This commit is contained in:
Maria Dimashova
2012-04-06 09:26:11 +00:00
parent cdc5bbc0bc
commit 85fa0e7763
13 changed files with 1726 additions and 1449 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/ml/test/test_emknearestkmeans.cpp
+234 -98
View File
@@ -44,34 +44,49 @@
using namespace std;
using namespace cv;
void defaultDistribs( vector<Mat>& means, vector<Mat>& covs )
static
void defaultDistribs( 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};
means.create(3, 2, CV_32FC1);
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]);
Mat mr0 = means.row(0);
m0.copyTo(mr0);
c0.copyTo(covs[0]);
Mat mr1 = means.row(1);
m1.copyTo(mr1);
c1.copyTo(covs[1]);
Mat mr2 = means.row(2);
m2.copyTo(mr2);
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 )
static
void generateData( Mat& data, Mat& labels, const vector<int>& sizes, const 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( _means.rows == (int)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> means(sizes.size());
for(int i = 0; i < _means.rows; i++)
means[i] = _means.row(i);
vector<Mat>::const_iterator mit = means.begin(), cit = covs.begin();
int bi, ei = 0;
sit = sizes.begin();
@@ -95,6 +110,7 @@ void generateData( Mat& data, Mat& labels, const vector<int>& sizes, const vecto
}
}
static
int maxIdx( const vector<int>& count )
{
int idx = -1;
@@ -112,74 +128,83 @@ int maxIdx( const vector<int>& count )
return idx;
}
static
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;
size_t total = 0, nclusters = sizes.size();
for(size_t i = 0; i < sizes.size(); i++)
total += sizes[i];
assert( !labels.empty() );
assert( labels.rows == total && labels.cols == 1 );
assert( labels.total() == total && (labels.cols == 1 || labels.rows == 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 )
labelsMap.resize(nclusters);
vector<bool> buzy(nclusters, false);
int startIndex = 0;
for( size_t clusterIndex = 0; clusterIndex < sizes.size(); clusterIndex++ )
{
vector<int> count( setCount, 0 );
bi = ei;
ei = bi + *sit;
if( isFlt )
vector<int> count( nclusters, 0 );
for( int i = startIndex; i < startIndex + sizes[clusterIndex]; i++)
{
for( int i = bi; i < ei; i++ )
count[(int)labels.at<float>(i, 0)]++;
int lbl = isFlt ? (int)labels.at<float>(i) : labels.at<int>(i);
CV_Assert(lbl < (int)nclusters);
count[lbl]++;
CV_Assert(count[lbl] < (int)total);
}
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;
startIndex += sizes[clusterIndex];
int cls = maxIdx( count );
CV_Assert( !buzy[cls] );
labelsMap[clusterIndex] = cls;
buzy[cls] = true;
}
return true;
for(size_t i = 0; i < buzy.size(); i++)
if(!buzy[i])
return false;
return true;
}
float calcErr( const Mat& labels, const Mat& origLabels, const vector<int>& sizes, bool labelsEquivalent = true )
static
bool calcErr( const Mat& labels, const Mat& origLabels, const vector<int>& sizes, float& err, 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 );
err = 0;
CV_Assert( !labels.empty() && !origLabels.empty() );
CV_Assert( labels.rows == 1 || labels.cols == 1 );
CV_Assert( origLabels.rows == 1 || origLabels.cols == 1 );
CV_Assert( labels.total() == origLabels.total() );
CV_Assert( labels.type() == CV_32SC1 || labels.type() == CV_32FC1 );
CV_Assert( origLabels.type() == labels.type() );
vector<int> labelsMap;
bool isFlt = labels.type() == CV_32FC1;
if( !labelsEquivalent )
{
getLabelsMap( labels, sizes, labelsMap );
if( !getLabelsMap( labels, sizes, labelsMap ) )
return false;
for( int i = 0; i < labels.rows; i++ )
if( isFlt )
err += labels.at<float>(i, 0) != labelsMap[(int)origLabels.at<float>(i, 0)];
err += labels.at<float>(i) != labelsMap[(int)origLabels.at<float>(i)] ? 1.f : 0.f;
else
err += labels.at<int>(i, 0) != labelsMap[origLabels.at<int>(i, 0)];
err += labels.at<int>(i) != labelsMap[origLabels.at<int>(i)] ? 1.f : 0.f;
}
else
{
for( int i = 0; i < labels.rows; i++ )
if( isFlt )
err += labels.at<float>(i, 0) != origLabels.at<float>(i, 0);
err += labels.at<float>(i) != origLabels.at<float>(i) ? 1.f : 0.f;
else
err += labels.at<int>(i, 0) != origLabels.at<int>(i, 0);
err += labels.at<int>(i) != origLabels.at<int>(i) ? 1.f : 0.f;
}
return (float)err / (float)labels.rows;
err /= (float)labels.rows;
return true;
}
//--------------------------------------------------------------------------------------------
@@ -198,7 +223,8 @@ void CV_KMeansTest::run( int /*start_from*/ )
Mat data( pointsCount, 2, CV_32FC1 ), labels;
vector<int> sizes( sizesArr, sizesArr + sizeof(sizesArr) / sizeof(sizesArr[0]) );
vector<Mat> means, covs;
Mat means;
vector<Mat> covs;
defaultDistribs( means, covs );
generateData( data, labels, sizes, means, covs, CV_32SC1 );
@@ -207,8 +233,12 @@ void CV_KMeansTest::run( int /*start_from*/ )
Mat bestLabels;
// 1. flag==KMEANS_PP_CENTERS
kmeans( data, 3, bestLabels, TermCriteria( TermCriteria::COUNT, iters, 0.0), 0, KMEANS_PP_CENTERS, noArray() );
err = calcErr( bestLabels, labels, sizes, false );
if( err > 0.01f )
if( !calcErr( bestLabels, labels, sizes, err , false ) )
{
ts->printf( cvtest::TS::LOG, "Bad output labels if flag==KMEANS_PP_CENTERS.\n" );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
else if( err > 0.01f )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) if flag==KMEANS_PP_CENTERS.\n", err );
code = cvtest::TS::FAIL_BAD_ACCURACY;
@@ -216,10 +246,14 @@ void CV_KMeansTest::run( int /*start_from*/ )
// 2. flag==KMEANS_RANDOM_CENTERS
kmeans( data, 3, bestLabels, TermCriteria( TermCriteria::COUNT, iters, 0.0), 0, KMEANS_RANDOM_CENTERS, noArray() );
err = calcErr( bestLabels, labels, sizes, false );
if( err > 0.01f )
if( !calcErr( bestLabels, labels, sizes, err, false ) )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) if flag==KMEANS_PP_CENTERS.\n", err );
ts->printf( cvtest::TS::LOG, "Bad output labels if flag==KMEANS_RANDOM_CENTERS.\n" );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
else if( err > 0.01f )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) if flag==KMEANS_RANDOM_CENTERS.\n", err );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
@@ -229,10 +263,14 @@ void CV_KMeansTest::run( int /*start_from*/ )
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, noArray() );
err = calcErr( bestLabels, labels, sizes, false );
if( err > 0.01f )
if( !calcErr( bestLabels, labels, sizes, err, false ) )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) if flag==KMEANS_PP_CENTERS.\n", err );
ts->printf( cvtest::TS::LOG, "Bad output labels if flag==KMEANS_USE_INITIAL_LABELS.\n" );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
else if( err > 0.01f )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) if flag==KMEANS_USE_INITIAL_LABELS.\n", err );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
@@ -255,7 +293,8 @@ void CV_KNearestTest::run( int /*start_from*/ )
// train data
Mat trainData( pointsCount, 2, CV_32FC1 ), trainLabels;
vector<int> sizes( sizesArr, sizesArr + sizeof(sizesArr) / sizeof(sizesArr[0]) );
vector<Mat> means, covs;
Mat means;
vector<Mat> covs;
defaultDistribs( means, covs );
generateData( trainData, trainLabels, sizes, means, covs, CV_32FC1 );
@@ -267,8 +306,13 @@ void CV_KNearestTest::run( int /*start_from*/ )
KNearest knearest;
knearest.train( trainData, trainLabels );
knearest.find_nearest( testData, 4, &bestLabels );
float err = calcErr( bestLabels, testLabels, sizes, true );
if( err > 0.01f )
float err;
if( !calcErr( bestLabels, testLabels, sizes, err, true ) )
{
ts->printf( cvtest::TS::LOG, "Bad output labels.\n" );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
else if( err > 0.01f )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) on test data.\n", err );
code = cvtest::TS::FAIL_BAD_ACCURACY;
@@ -277,76 +321,167 @@ void CV_KNearestTest::run( int /*start_from*/ )
}
//--------------------------------------------------------------------------------------------
class CV_EMTest : public cvtest::BaseTest {
class CV_EMTest : public cvtest::BaseTest
{
public:
CV_EMTest() {}
protected:
virtual void run( int start_from );
int runCase( int caseIndex, const cv::EM::Params& params,
const cv::Mat& trainData, const cv::Mat& trainLabels,
const cv::Mat& testData, const cv::Mat& testLabels,
const vector<int>& sizes);
};
void CV_EMTest::run( int /*start_from*/ )
int CV_EMTest::runCase( int caseIndex, const cv::EM::Params& params,
const cv::Mat& trainData, const cv::Mat& trainLabels,
const cv::Mat& testData, const cv::Mat& testLabels,
const vector<int>& sizes )
{
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;
cv::Mat labels;
float err;
ExpectationMaximization em;
CvEMParams params;
params.nclusters = 3;
em.train( trainData, Mat(), params, &bestLabels );
cv::EM em;
em.train( trainData, Mat(), params, &labels );
// check train error
err = calcErr( bestLabels, trainLabels, sizes, false );
if( err > 0.002f )
if( !calcErr( labels, trainLabels, sizes, err , false ) )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) on train data.\n", err );
ts->printf( cvtest::TS::LOG, "Case index %i : Bad output labels.\n", caseIndex );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
else if( err > 0.006f )
{
ts->printf( cvtest::TS::LOG, "Case index %i : Bad accuracy (%f) on train data.\n", caseIndex, err );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
// check test error
bestLabels.create( testData.rows, 1, CV_32SC1 );
labels.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 );
Mat sample = testData.row(i);
labels.at<int>(i,0) = (int)em.predict( sample, 0 );
}
err = calcErr( bestLabels, testLabels, sizes, false );
if( err > 0.005f )
if( !calcErr( labels, testLabels, sizes, err, false ) )
{
ts->printf( cvtest::TS::LOG, "Bad accuracy (%f) on test data.\n", err );
ts->printf( cvtest::TS::LOG, "Case index %i : Bad output labels.\n", caseIndex );
code = cvtest::TS::FAIL_INVALID_OUTPUT;
}
else if( err > 0.006f )
{
ts->printf( cvtest::TS::LOG, "Case index %i : Bad accuracy (%f) on test data.\n", caseIndex, err );
code = cvtest::TS::FAIL_BAD_ACCURACY;
}
return code;
}
void CV_EMTest::run( int /*start_from*/ )
{
int sizesArr[] = { 500, 700, 800 };
int pointsCount = sizesArr[0]+ sizesArr[1] + sizesArr[2];
// Points distribution
Mat means;
vector<Mat> covs;
defaultDistribs( means, covs );
// train data
Mat trainData( pointsCount, 2, CV_32FC1 ), trainLabels;
vector<int> sizes( sizesArr, sizesArr + sizeof(sizesArr) / sizeof(sizesArr[0]) );
generateData( trainData, trainLabels, sizes, means, covs, CV_32SC1 );
// test data
Mat testData( pointsCount, 2, CV_32FC1 ), testLabels;
generateData( testData, testLabels, sizes, means, covs, CV_32SC1 );
cv::EM::Params params;
params.nclusters = 3;
Mat probs(trainData.rows, params.nclusters, CV_32FC1, cv::Scalar(1));
params.probs = &probs;
Mat weights(1, params.nclusters, CV_32FC1, cv::Scalar(1));
params.weights = &weights;
params.means = &means;
params.covs = &covs;
int code = cvtest::TS::OK;
int caseIndex = 0;
{
params.startStep = cv::EM::START_AUTO_STEP;
params.covMatType = cv::EM::COV_MAT_GENERIC;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_AUTO_STEP;
params.covMatType = cv::EM::COV_MAT_DIAGONAL;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_AUTO_STEP;
params.covMatType = cv::EM::COV_MAT_SPHERICAL;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_M_STEP;
params.covMatType = cv::EM::COV_MAT_GENERIC;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_M_STEP;
params.covMatType = cv::EM::COV_MAT_DIAGONAL;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_M_STEP;
params.covMatType = cv::EM::COV_MAT_SPHERICAL;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_E_STEP;
params.covMatType = cv::EM::COV_MAT_GENERIC;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_E_STEP;
params.covMatType = cv::EM::COV_MAT_DIAGONAL;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
{
params.startStep = cv::EM::START_E_STEP;
params.covMatType = cv::EM::COV_MAT_SPHERICAL;
int currCode = runCase(caseIndex++, params, trainData, trainLabels, testData, testLabels, sizes);
code = currCode == cvtest::TS::OK ? code : currCode;
}
ts->set_failed_test_info( code );
}
class CV_EMTest_Smoke : public cvtest::BaseTest {
class CV_EMTest_SaveLoad : public cvtest::BaseTest {
public:
CV_EMTest_Smoke() {}
CV_EMTest_SaveLoad() {}
protected:
virtual void run( int /*start_from*/ )
{
int code = cvtest::TS::OK;
CvEM em;
cv::EM em;
Mat samples = Mat(3,2,CV_32F);
Mat samples = Mat(3,1,CV_32F);
samples.at<float>(0,0) = 1;
samples.at<float>(1,0) = 2;
samples.at<float>(2,0) = 3;
CvEMParams params;
cv::EM::Params params;
params.nclusters = 2;
Mat labels;
@@ -361,10 +496,11 @@ protected:
string filename = tempfile() + ".xml";
{
FileStorage fs = FileStorage(filename, FileStorage::WRITE);
try
{
em.write(fs.fs, "EM");
fs << "em" << "{";
em.write(fs);
fs << "}";
}
catch(...)
{
@@ -378,11 +514,11 @@ protected:
// Read in
{
FileStorage fs = FileStorage(filename, FileStorage::READ);
FileNode fileNode = fs["EM"];
CV_Assert(fs.isOpened());
FileNode fn = fs["em"];
try
{
em.read(const_cast<CvFileStorage*>(fileNode.fs), const_cast<CvFileNode*>(fileNode.node));
em.read(fn);
}
catch(...)
{
@@ -410,4 +546,4 @@ protected:
TEST(ML_KMeans, accuracy) { CV_KMeansTest test; test.safe_run(); }
TEST(ML_KNearest, accuracy) { CV_KNearestTest test; test.safe_run(); }
TEST(ML_EM, accuracy) { CV_EMTest test; test.safe_run(); }
TEST(ML_EM, smoke) { CV_EMTest_Smoke test; test.safe_run(); }
TEST(ML_EM, save_load) { CV_EMTest_SaveLoad test; test.safe_run(); }
modules/ml/test/test_mltests2.cpp
-9
View File
@@ -451,7 +451,6 @@ CV_MLBaseTest::CV_MLBaseTest(const char* _modelName)
nbayes = 0;
knearest = 0;
svm = 0;
em = 0;
ann = 0;
dtree = 0;
boost = 0;
@@ -463,8 +462,6 @@ CV_MLBaseTest::CV_MLBaseTest(const char* _modelName)
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) )
@@ -487,8 +484,6 @@ CV_MLBaseTest::~CV_MLBaseTest()
delete knearest;
if( svm )
delete svm;
if( em )
delete em;
if( ann )
delete ann;
if( dtree )
@@ -756,8 +751,6 @@ void CV_MLBaseTest::save( const char* filename )
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) )
@@ -778,8 +771,6 @@ void CV_MLBaseTest::load( const char* filename )
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) )
modules/ml/test/test_precomp.hpp
-1
View File
@@ -44,7 +44,6 @@ protected:
CvNormalBayesClassifier* nbayes;
CvKNearest* knearest;
CvSVM* svm;
CvEM* em;
CvANN_MLP* ann;
CvDTree* dtree;
CvBoost* boost;