int _tmain(int argc, _TCHAR* argv[]) { DTW dtw; cout << "Vector DTW Test" << endl; std::vector<LocalFeature> mainVec; std::vector<LocalFeature> testVec; LocalFeature p1(1, 2, 3); LocalFeature p2(2, 3, 4); LocalFeature p3(3, 2, 3); LocalFeature p4(2, 2, 3); mainVec.push_back(p1); mainVec.push_back(p2); mainVec.push_back(p4); testVec.push_back(p3); testVec.push_back(p4); GlobalFeature global(1,mainVec); dtw.addTrainingFeature(&global); GlobalFeature* result = dtw.getNextNeighbour(testVec); cout << "Distance: " << result->distance << endl; cout << "Label: " << result->classLabel << endl; system("PAUSE"); return 0; }
DTW::DTW(const DTW& copy) // Copy constructor { this->myCompared = copy.myCompared; this->myComparison = copy.myComparison; this->setFirst(copy.getFirst()); this->setSecond(copy.getSecond()); }
//-------------------------------------------------------------- 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; }
//-------------------------------------------------------------- void testApp::draw() { ofBackground(0, 0, 0); string text; int textX = 20; int textY = 20; //Draw the training info ofSetColor(255, 255, 255); text = "------------------- TrainingInfo -------------------"; ofDrawBitmapString(text, textX,textY); if( record ) ofSetColor(255, 0, 0); else ofSetColor(255, 255, 255); textY += 15; text = record ? "RECORDING" : "Not Recording"; ofDrawBitmapString(text, textX,textY); ofSetColor(255, 255, 255); textY += 15; text = "TrainingClassLabel: " + ofToString(trainingClassLabel); ofDrawBitmapString(text, textX,textY); textY += 15; text = "NumTrainingSamples: " + ofToString(trainingData.getNumSamples()); ofDrawBitmapString(text, textX,textY); //Draw the prediction info textY += 30; text = "------------------- Prediction Info -------------------"; ofDrawBitmapString(text, textX,textY); textY += 15; text = pipeline.getTrained() ? "Model Trained: YES" : "Model Trained: NO"; ofDrawBitmapString(text, textX,textY); textY += 15; text = "PredictedClassLabel: " + ofToString(pipeline.getPredictedClassLabel()); ofDrawBitmapString(text, textX,textY); textY += 15; text = "Likelihood: " + ofToString(pipeline.getMaximumLikelihood()); ofDrawBitmapString(text, textX,textY); textY += 15; text = "SampleRate: " + ofToString(ofGetFrameRate(),2); ofDrawBitmapString(text, textX,textY); //Draw the info text textY += 30; text = "InfoText: " + infoText; ofDrawBitmapString(text, textX,textY); //Draw number of hands currently dragged textY += 15; text = "Number of tracked hands: "+ ofToString(noOfTrackedHands); ofSetColor(255, 0, 0); ofDrawBitmapString(text, textX,textY); ofSetColor(255, 255, 255); //Draw the timeseries data if( record && noOfHands == noOfTrackedHands) { ofFill(); for(UINT i=0; i<timeseries.getNumRows(); i++) { double x = timeseries[i][0]; double y = timeseries[i][1]; //double r = ofMap(i,0,timeseries.getNumRows(),0,255); //double g = 0; //double b = 255-r; //ofSetColor(r,g,b); ofSetColor(250,0,0); ofEllipse(300+x,500-y,5,5); if(noOfHands >= 2) { ofSetColor(0,80,255); x = timeseries[i][3]; y = timeseries[i][4]; ofEllipse(300+x,500-y,5,5); } } } if( pipeline.getTrained() && noOfHands == noOfTrackedHands) { //Draw the data in the DTW input buffer DTW *dtw = pipeline.getClassifier< DTW >(); if( dtw != NULL ) { vector< VectorDouble > inputData = dtw->getInputDataBuffer(); for(UINT i=0; i<inputData.size(); i++) { double x = inputData[i][0]; double y = inputData[i][1]; // double r = ofMap(i,0,inputData.size(),0,255); // double g = 0; // double b = 255-r; ofSetColor(250,0,0); ofEllipse(300+x,500-y,5,5); if(noOfHands >= 2) { ofSetColor(0,80,250); x = inputData[i][3]; y = inputData[i][4]; ofEllipse(300+x,500-y,5,5); } } } } }
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; }
int* Querybh::MatchChroma(int* target, int targetsize) { int p0[] = {2,2,0,0,2,9,9,9,9,9,11,1,1,11,11,0,1,1,9,9,9,10,1,1,1,0,11,10,10,9,9,9,9,11,1,0,0,11,11,1,1,9,9,9}; int p1[] = {8,8,8,8,7,7,7,8,8,8,8,8,5,5,5,5,5,5,5,11,6,6,6,9,9,9,4,4,9,9,9,8,8,8,8,8,8,8,9,9,6,6,6,6,6,6,6,9,9,9}; int p2[] = {1,3,3,6,11,10,10,10,11,2,2,3,3,6,11,10,10,10,10,1,1,1,11,11,11,11,11,11,11,5,5,7,7,7,7,4,1,1,2,2,2}; int p3[] = {10,10,7,7,7,7,7,7,7,7,7,10,0,5,5,5,5,5,5,4,4,4,7,7,8,8,8,10,10,3,1,1,2,2,9,10,0,0,9,7,7,7,8,0,11,11,1,1,1,0,0,0,4,3,3,3,3,0,10,10,10,10,4,4,4,6,7,7,11,10,10,10,10,11,9,9,7,8,3,3,3}; int** p; p = new int*[4]; p[0] = new int[sizeof(p0)/sizeof(int)]; p[1] = new int[sizeof(p1)/sizeof(int)]; p[2] = new int[sizeof(p2)/sizeof(int)]; p[3] = new int[sizeof(p3)/sizeof(int)]; p[0] = p0; p[1] = p1; p[2] = p2; p[3] = p3; songlist.push_back("here comes the sun.wav"); songlist.push_back("someone like you.wav"); songlist.push_back("goodbye.wav"); songlist.push_back("hey jude.wav"); lengthlist.push_back(sizeof(p0)/sizeof(int)); lengthlist.push_back(sizeof(p1)/sizeof(int)); lengthlist.push_back(sizeof(p2)/sizeof(int)); lengthlist.push_back(sizeof(p3)/sizeof(int)); int* midp = new int[lengthlist.size()]; for(int i=0; i<lengthlist.size(); i++) midp[i] = mid(p[i], lengthlist[i]); int midpt = mid(target, targetsize); for (int i=0; i<lengthlist.size(); i++){ for(int j=0; j<lengthlist[i]; j++){ p[i][j] = (p[i][j]-midp[i]+midpt+12)%12; // cout<<p[i][j]<<","; } // cout<<endl<<endl; } for (int i=0; i<lengthlist.size(); i++) ps.push_back(p[i]); vector<double> dist; dist.clear(); // vector<double> dtemp; // for (int k=0; k<songlist.size(); k++){ // dtemp.clear(); // int pp=0; // if((lengthlist[k]-targetsize)>4){ // while (1) { // DTW *mDTW = NULL; // mDTW = new DTW(targetsize, targetsize+5); // dtemp.push_back(mDTW->run(target, targetsize, &ps[k][pp], targetsize+5)); // pp++; // if(pp+targetsize+5>lengthlist[k]) // break; // delete mDTW; // } // } // else if ((targetsize-lengthlist[k])>4){ // while (1) { // DTW *mDTW = NULL; // mDTW = new DTW(lengthlist[k]+5, lengthlist[k]); // dtemp.push_back(mDTW->run(&target[pp], lengthlist[k]+5, &ps[k][0], lengthlist[k])); // pp++; // if(pp+lengthlist[k]+5>targetsize) // break; // delete mDTW; // } // } // // else{ // DTW *mDTW = NULL; // mDTW = new DTW(targetsize, targetsize); // dtemp.push_back(mDTW->run(target, targetsize, &ps[k][0], targetsize)); // delete mDTW; // } // dist.push_back(MinVal(dtemp)); for (int k=0; k<lengthlist.size(); k++){ DTW *mDTW = NULL; mDTW = new DTW(targetsize, lengthlist[k]); dist.push_back(mDTW->run(target, targetsize, &ps[k][0], lengthlist[k])); delete mDTW; } return GetMinIndex(dist); }