//--------------------------------------------------------------
void testApp::setup(){
ofSetFrameRate(30);
//Initialize the training and info variables
infoText = "";
trainingClassLabel = 1;
record = false;
//Open the connection with Synapse
synapseStreamer.openSynapseConnection();
//Set which joints we want to track : we track only the hand joints
synapseStreamer.trackAllJoints(false);
synapseStreamer.trackLeftHand(true);
synapseStreamer.trackRightHand(true);
synapseStreamer.computeHandDistFeature(true);
//The input to the training data will be the [x y z] of the two hands
//so we set the number of dimensions to 6
trainingData.setNumDimensions( 6 );
trainingClassLabel = 1; // on ne s'occupe pas du trainingClassLabel pour la reconnaissance
//Initialize the DTW classifier
DTW dtw;
//Turn on null rejection, this lets the classifier output the predicted class label of 0 when the likelihood of a gesture is low
dtw.enableNullRejection( true );
//Set the null rejection coefficient to 3, this controls the thresholds for the automatic null rejection
//You can increase this value if you find that your real-time gestures are not being recognized
//If you are getting too many false positives then you should decrease this value
dtw.setNullRejectionCoeff( PRECISION_RECO );
//Turn on the automatic data triming, this will remove any sections of none movement from the start and end of the training samples
dtw.enableTrimTrainingData(true, 0.1, 90);
//Offset the timeseries data by the first sample, this makes your gestures (more) invariant to the location the gesture is performed
dtw.setOffsetTimeseriesUsingFirstSample(true);
//Add the classifier to the pipeline (after we do this, we don't need the DTW classifier anymore)
pipeline.setClassifier( dtw );
//Load the data from TrainingData.txt, and train the pipeline
if( trainingData.loadDatasetFromFile("TrainingData.txt") )
{
infoText = "Training data saved to file";
if( pipeline.train( trainingData ) )
{
infoText = "Pipeline Trained";
}
else infoText = "WARNING: Failed to train pipeline";
}
else infoText = "WARNING: Failed to load training data from file";
}
bool GRT_Recognizer::initPipeline(string trainingdatafile, int dimension)
{
//Initialize the training and info variables
// infoText = "";
// trainingClassLabel = 1;
// noOfHands = 2;
//noOfTrackedHands = 0;
//The input to the training data will be the R[x y z]L[x y z] from the left end right hand
// so we set the number of dimensions to 6
LabelledTimeSeriesClassificationData trainingData;
//trainingData.setNumDimensions(6);
trainingData.loadDatasetFromFile(trainingdatafile);
//Initialize the DTW classifier
DTW dtw;
//Turn on null rejection, this lets the classifier output the predicted class label of 0 when the likelihood of a gesture is low
dtw.enableNullRejection( true);
//Set the null rejection coefficient to 3, this controls the thresholds for the automatic null rejection
//You can increase this value if you find that your real-time gestures are not being recognized
//If you are getting too many false positives then you should decrease this value
dtw.setNullRejectionCoeff(2);
//Turn on the automatic data triming, this will remove any sections of none movement from the start and end of the training samples
dtw.enableTrimTrainingData(true, 0.1, 90);
//Offset the timeseries data by the first sample, this makes your gestures (more) invariant to the location the gesture is performed
dtw.setOffsetTimeseriesUsingFirstSample(true);
//Add the classifier to the pipeline (after we do this, we don't need the DTW classifier anymore)
pipeline.setClassifier( dtw );
//pipeline.addPreProcessingModule(MovingAverageFilter(5,dimension));
//pipeline.addFeatureExtractionModule(FFT(16,1, dimension));
/*ClassLabelFilter myFilter = ClassLabelFilter();
myFilter.setBufferSize(6);
myFilter.setBufferSize(2);*/
pipeline.addPostProcessingModule(ClassLabelChangeFilter());
pipeline.train(trainingData);
return true;
}
int main (int argc, const char * argv[])
{
TimeSeriesClassificationData trainingData; //This will store our training data
GestureRecognitionPipeline pipeline; //This is a wrapper for our classifier and any pre/post processing modules
string dirPath = "/home/vlad/AndroidStudioProjects/DataCapture/dataSetGenerator/build";
if (!trainingData.loadDatasetFromFile(dirPath + "/acc-training-set-segmented.data")) {
printf("Cannot open training segmented set\n");
return 0;
}
printf("Successfully opened training data set ...\n");
DTW dtw;
// LowPassFilter lpf(0.1, 1, 1);
// pipeline.setPreProcessingModule(lpf);
// DoubleMovingAverageFilter filter( 1000, 3 );
// pipeline.setPreProcessingModule(filter);
//dtw.enableNullRejection( true );
//Set the null rejection coefficient to 3, this controls the thresholds for the automatic null rejection
//You can increase this value if you find that your real-time gestures are not being recognized
//If you are getting too many false positives then you should decrease this value
//dtw.setNullRejectionCoeff( 5 );
dtw.enableTrimTrainingData(true, 0.1, 90);
// dtw.setOffsetTimeseriesUsingFirstSample(true);
pipeline.setClassifier( dtw );
UINT KFolds = 5;
/* Separate input dataset using KFold */
KfoldTimeSeriesData* kFoldTS = new KfoldTimeSeriesData(trainingData);
if( !kFoldTS->spiltDataIntoKFolds(KFolds) ) {
printf("BaseTGTestModel: Failed to spiltDataIntoKFolds!");
return 0;
}
UINT maxTrainigSetSize = trainingData.getNumSamples() * (KFolds - 1) / (KFolds * trainingData.getNumClasses());
// KFolds
ofstream myfile;
myfile.open ("example.txt");
Float acc = 0;
for (GRT::UINT k = 1 ; k < KFolds; k++) {
printf("Running tests for: %d fold", k);
// maxTrainigSetSize
// for (UINT trainingSetSize = 1; trainingSetSize <= maxTrainigSetSize; trainingSetSize ++) {
/* Set up training datasets for current fold */
TimeSeriesClassificationData trainingDataset = kFoldTS->getTrainingFoldData(k, maxTrainigSetSize);
/* Set up validation datasets for current fold */
TimeSeriesClassificationDataStream testDataset = kFoldTS->getTestFoldData(k);
/* Log test dataset size */
//printf("Data set size: training %d; testing %d",
// trainingDataset.getNumSamples(), testDataset.getNumSamples());
/* Run test for current fold */
pipeline.train(trainingDataset);
pipeline.test(testDataset);
myfile << pipeline.getTestAccuracy() << "\n";
// }
}
myfile.close();
printf("Accuracy = %f ; %d\n", acc, maxTrainigSetSize);
}
//--------------------------------------------------------------
void testApp::setup() {
ofSetFrameRate(30);
//Initialize the training and info variables
infoText = "";
trainingClassLabel = 1;
record = false;
noOfHands = 1;
noOfTrackedHands = 0;
//The input to the training data will be the [x y] from the mouse, so we set the number of dimensions to 2
trainingData.setNumDimensions( noOfHands*3 );
//trainingData.setNumDimensions( 3 );
//Initialize the DTW classifier
DTW dtw;
//Turn on null rejection, this lets the classifier output the predicted class label of 0 when the likelihood of a gesture is low
dtw.enableNullRejection( true );
//Set the null rejection coefficient to 3, this controls the thresholds for the automatic null rejection
//You can increase this value if you find that your real-time gestures are not being recognized
//If you are getting too many false positives then you should decrease this value
dtw.setNullRejectionCoeff( 3 );
//Turn on the automatic data triming, this will remove any sections of none movement from the start and end of the training samples
dtw.enableTrimTrainingData(true, 0.1, 90);
//Offset the timeseries data by the first sample, this makes your gestures (more) invariant to the location the gesture is performed
dtw.setOffsetTimeseriesUsingFirstSample(true);
//Add the classifier to the pipeline (after we do this, we don't need the DTW classifier anymore)
pipeline.setClassifier( dtw );
//pipeline.inputVectorDimensions(3*noOfHands);
///setup nite
niteRc = nite::NiTE::initialize();
if (niteRc != nite::STATUS_OK)
{
printf("NiTE initialization failed\n");
return;
}
niteRc = handTracker.create();
if (niteRc != nite::STATUS_OK)
{
printf("Couldn't create user tracker\n");
return;
}
handTracker.startGestureDetection(nite::GESTURE_CLICK);
printf("\nPoint with your hand to start tracking it...\n");
//put cursor in the middle of the screen: SPI_GETWORKAREA
int screenX = GetSystemMetrics(SM_CXSCREEN);
int screenY = GetSystemMetrics(SM_CYSCREEN);
SetCursorPos(screenX / 2, screenY / 2);
xcursorpos = 500;
ycursorpos = 500;
}
int main (int argc, const char * argv[])
{
//Create a new DTW instance, using the default parameters
DTW dtw;
//Load some training data to train the classifier - the DTW uses TimeSeriesClassificationData
TimeSeriesClassificationData trainingData;
if( !trainingData.load("DTWTrainingData.grt") ){
cout << "Failed to load training data!\n";
return EXIT_FAILURE;
}
//Use 20% of the training dataset to create a test dataset
TimeSeriesClassificationData testData = trainingData.partition( 80 );
//Trim the training data for any sections of non-movement at the start or end of the recordings
dtw.enableTrimTrainingData(true,0.1,90);
//Train the classifier
if( !dtw.train( trainingData ) ){
cout << "Failed to train classifier!\n";
return EXIT_FAILURE;
}
//Save the DTW model to a file
if( !dtw.save("DTWModel.grt") ){
cout << "Failed to save the classifier model!\n";
return EXIT_FAILURE;
}
//Load the DTW model from a file
if( !dtw.load("DTWModel.grt") ){
cout << "Failed to load the classifier model!\n";
return EXIT_FAILURE;
}
//Use the test dataset to test the DTW model
double accuracy = 0;
for(UINT i=0; i<testData.getNumSamples(); i++){
//Get the i'th test sample - this is a timeseries
UINT classLabel = testData[i].getClassLabel();
MatrixDouble timeseries = testData[i].getData();
//Perform a prediction using the classifier
if( !dtw.predict( timeseries ) ){
cout << "Failed to perform prediction for test sampel: " << i <<"\n";
return EXIT_FAILURE;
}
//Get the predicted class label
UINT predictedClassLabel = dtw.getPredictedClassLabel();
double maximumLikelihood = dtw.getMaximumLikelihood();
VectorDouble classLikelihoods = dtw.getClassLikelihoods();
VectorDouble classDistances = dtw.getClassDistances();
//Update the accuracy
if( classLabel == predictedClassLabel ) accuracy++;
cout << "TestSample: " << i << "\tClassLabel: " << classLabel << "\tPredictedClassLabel: " << predictedClassLabel << "\tMaximumLikelihood: " << maximumLikelihood << endl;
}
cout << "Test Accuracy: " << accuracy/double(testData.getNumSamples())*100.0 << "%" << endl;
return EXIT_SUCCESS;
}
int main() {
vector<string> gestures(0,"");
GetFilesInDirectory(gestures, "rawdata");
CreateDirectory("processed", NULL);
sort(gestures.begin(), gestures.end());
data = vector<vector<vector<double > > >(gestures.size(), vector<vector<double > >(0,vector<double>(0,0)));
for(size_t i = 0; i < gestures.size(); i++) {
ifstream fin(gestures[i]);
int n; fin >> n;
// cerr << gestures[i] << endl;
// cerr << n << endl;
data[i] = vector<vector<double> >(n, vector<double>(NUMPARAM, 0));
for(int j = 0; j < n; j++) {
for(int k = 0; k < NUMPARAM; k++) {
fin >> data[i][j][k];
}
}
fin.close();
}
//Create a new instance of the TimeSeriesClassificationDataStream
TimeSeriesClassificationData trainingData;
// ax, ay, az
trainingData.setNumDimensions(3);
trainingData.setDatasetName("processed\\GestureTrainingData.txt");
ofstream labelfile("processed\\GestureTrainingDataLabels.txt");
UINT currLabel = 1;
Random random;
map<string, int> gesturenames;
for(size_t overall = 0; overall < gestures.size(); overall++) {
string nam = gestures[overall].substr(8,gestures[overall].find_first_of('_')-8);
if(gesturenames.count(nam)) currLabel = gesturenames[nam];
else {
currLabel = gesturenames.size()+1;
gesturenames[nam] = currLabel;
labelfile << currLabel << " " << nam << endl;
}
MatrixDouble trainingSample;
VectorDouble currVec( trainingData.getNumDimensions() );
for(size_t k = 1; k < data[overall].size(); k++) {
for(UINT j=0; j<currVec.size(); j++){
currVec[j] = data[overall][k][j];
}
trainingSample.push_back(currVec);
}
trainingData.addSample(currLabel, trainingSample);
}
for(size_t i = 0; i < gestures.size(); i++) {
MatrixDouble trainingSample;
VectorDouble currVec(trainingData.getNumDimensions());
for(UINT j = 0; j < currVec.size(); j++) {
currVec[j] = random.getRandomNumberUniform(-1.0, 1.0);
}
for(size_t k = 0; k < 100; k++) {
trainingSample.push_back(currVec);
}
trainingData.addSample(0, trainingSample);
}
//After recording your training data you can then save it to a file
if( !trainingData.save( "processed\\TrainingData.grt" ) ){
cout << "ERROR: Failed to save dataset to file!\n";
return EXIT_FAILURE;
}
//This can then be loaded later
if( !trainingData.load( "processed\\TrainingData.grt" ) ){
cout << "ERROR: Failed to load dataset from file!\n";
return EXIT_FAILURE;
}
//This is how you can get some stats from the training data
string datasetName = trainingData.getDatasetName();
string infoText = trainingData.getInfoText();
UINT numSamples = trainingData.getNumSamples();
UINT numDimensions = trainingData.getNumDimensions();
UINT numClasses = trainingData.getNumClasses();
cout << "Dataset Name: " << datasetName << endl;
cout << "InfoText: " << infoText << endl;
cout << "NumberOfSamples: " << numSamples << endl;
cout << "NumberOfDimensions: " << numDimensions << endl;
cout << "NumberOfClasses: " << numClasses << endl;
//You can also get the minimum and maximum ranges of the data
vector< MinMax > ranges = trainingData.getRanges();
cout << "The ranges of the dataset are: \n";
for(UINT j=0; j<ranges.size(); j++){
cout << "Dimension: " << j << " Min: " << ranges[j].minValue << " Max: " << ranges[j].maxValue << endl;
}
DTW dtw;
if( !dtw.train( trainingData ) ){
cerr << "Failed to train classifier!\n";
exit(EXIT_FAILURE);
}
dtw.enableNullRejection(true);
dtw.setNullRejectionCoeff(4);
dtw.enableTrimTrainingData(true, 0.1, 90);
//Save the DTW model to a file
if( !dtw.saveModelToFile("processed\\DTWModel.txt") ){
cerr << "Failed to save the classifier model!\n";
exit(EXIT_FAILURE);
}
trainingData.clear();
return EXIT_SUCCESS;
}
