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 set\n"); return 0; } printf("Successfully opened training data set ...\n"); HMM hmm; hmm.setHMMType( HMM_CONTINUOUS ); hmm.setDownsampleFactor( 5 ); hmm.setAutoEstimateSigma( true ); hmm.setSigma( 20.0 ); hmm.setModelType( HMM_LEFTRIGHT ); hmm.setDelta( 1 ); // LowPassFilter lpf(0.1, 1, 3); // pipeline.setPreProcessingModule(lpf); pipeline.setClassifier( hmm ); pipeline.train(trainingData, 20); //You can then get then get the accuracy of how well the pipeline performed during the k-fold cross validation testing double accuracy = pipeline.getCrossValidationAccuracy(); printf("Accuracy: %f\n", accuracy); }
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); }
int main(int argc, const char * argv[]){ //Load the training data TimeSeriesClassificationData trainingData; if( !trainingData.loadDatasetFromFile("HMMTrainingData.grt") ){ cout << "ERROR: Failed to load training data!\n"; return false; } //Remove 20% of the training data to use as test data TimeSeriesClassificationData testData = trainingData.partition( 80 ); //The input to the HMM must be a quantized discrete value //We therefore use a KMeansQuantizer to covert the N-dimensional continuous data into 1-dimensional discrete data const UINT NUM_SYMBOLS = 10; KMeansQuantizer quantizer( NUM_SYMBOLS ); //Train the quantizer using the training data if( !quantizer.train( trainingData ) ){ cout << "ERROR: Failed to train quantizer!\n"; return false; } //Quantize the training data TimeSeriesClassificationData quantizedTrainingData( 1 ); for(UINT i=0; i<trainingData.getNumSamples(); i++){ UINT classLabel = trainingData[i].getClassLabel(); MatrixDouble quantizedSample; for(UINT j=0; j<trainingData[i].getLength(); j++){ quantizer.quantize( trainingData[i].getData().getRowVector(j) ); quantizedSample.push_back( quantizer.getFeatureVector() ); } if( !quantizedTrainingData.addSample(classLabel, quantizedSample) ){ cout << "ERROR: Failed to quantize training data!\n"; return false; } } //Create a new HMM instance HMM hmm; //Set the number of states in each model hmm.setNumStates( 4 ); //Set the number of symbols in each model, this must match the number of symbols in the quantizer hmm.setNumSymbols( NUM_SYMBOLS ); //Set the HMM model type to LEFTRIGHT with a delta of 1 hmm.setModelType( HiddenMarkovModel::LEFTRIGHT ); hmm.setDelta( 1 ); //Set the training parameters hmm.setMinImprovement( 1.0e-5 ); hmm.setMaxNumIterations( 100 ); hmm.setNumRandomTrainingIterations( 20 ); //Train the HMM model if( !hmm.train( quantizedTrainingData ) ){ cout << "ERROR: Failed to train the HMM model!\n"; return false; } //Save the HMM model to a file if( !hmm.save( "HMMModel.grt" ) ){ cout << "ERROR: Failed to save the model to a file!\n"; return false; } //Load the HMM model from a file if( !hmm.load( "HMMModel.grt" ) ){ cout << "ERROR: Failed to load the model from a file!\n"; return false; } //Quantize the test data TimeSeriesClassificationData quantizedTestData( 1 ); for(UINT i=0; i<testData.getNumSamples(); i++){ UINT classLabel = testData[i].getClassLabel(); MatrixDouble quantizedSample; for(UINT j=0; j<testData[i].getLength(); j++){ quantizer.quantize( testData[i].getData().getRowVector(j) ); quantizedSample.push_back( quantizer.getFeatureVector() ); } if( !quantizedTestData.addSample(classLabel, quantizedSample) ){ cout << "ERROR: Failed to quantize training data!\n"; return false; } } //Compute the accuracy of the HMM models using the test data double numCorrect = 0; double numTests = 0; for(UINT i=0; i<quantizedTestData.getNumSamples(); i++){ UINT classLabel = quantizedTestData[i].getClassLabel(); hmm.predict( quantizedTestData[i].getData() ); if( classLabel == hmm.getPredictedClassLabel() ) numCorrect++; numTests++; VectorDouble classLikelihoods = hmm.getClassLikelihoods(); VectorDouble classDistances = hmm.getClassDistances(); cout << "ClassLabel: " << classLabel; cout << " PredictedClassLabel: " << hmm.getPredictedClassLabel(); cout << " MaxLikelihood: " << hmm.getMaximumLikelihood(); cout << " ClassLikelihoods: "; for(UINT k=0; k<classLikelihoods.size(); k++){ cout << classLikelihoods[k] << "\t"; } cout << "ClassDistances: "; for(UINT k=0; k<classDistances.size(); k++){ cout << classDistances[k] << "\t"; } cout << endl; } cout << "Test Accuracy: " << numCorrect/numTests*100.0 << endl; return true; }
int main (int argc, const char * argv[]) { //Create a new instance of the TimeSeriesClassificationData TimeSeriesClassificationData trainingData; //Set the dimensionality of the data (you need to do this before you can add any samples) trainingData.setNumDimensions( 3 ); //You can also give the dataset a name (the name should have no spaces) trainingData.setDatasetName("DummyData"); //You can also add some info text about the data trainingData.setInfoText("This data contains some dummy timeseries data"); //Here you would record a time series, when you have finished recording the time series then add the training sample to the training data UINT gestureLabel = 1; MatrixDouble trainingSample; //For now we will just add 10 x 20 random walk data timeseries Random random; for(UINT k=0; k<10; k++){//For the number of classes gestureLabel = k+1; //Get the init random walk position for this gesture VectorDouble startPos( trainingData.getNumDimensions() ); for(UINT j=0; j<startPos.size(); j++){ startPos[j] = random.getRandomNumberUniform(-1.0,1.0); } //Generate the 20 time series for(UINT x=0; x<20; x++){ //Clear any previous timeseries trainingSample.clear(); //Generate the random walk UINT randomWalkLength = random.getRandomNumberInt(90, 110); VectorDouble sample = startPos; for(UINT i=0; i<randomWalkLength; i++){ for(UINT j=0; j<startPos.size(); j++){ sample[j] += random.getRandomNumberUniform(-0.1,0.1); } //Add the sample to the training sample trainingSample.push_back( sample ); } //Add the training sample to the dataset trainingData.addSample( gestureLabel, trainingSample ); } } //After recording your training data you can then save it to a file if( !trainingData.saveDatasetToFile( "TrainingData.txt" ) ){ cout << "Failed to save dataset to file!\n"; return EXIT_FAILURE; } //This can then be loaded later if( !trainingData.loadDatasetFromFile( "TrainingData.txt" ) ){ cout << "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; } //If you want to partition the dataset into a training dataset and a test dataset then you can use the partition function //A value of 80 means that 80% of the original data will remain in the training dataset and 20% will be returned as the test dataset TimeSeriesClassificationData testData = trainingData.partition( 80 ); //If you have multiple datasets that you want to merge together then use the merge function if( !trainingData.merge( testData ) ){ cout << "Failed to merge datasets!\n"; return EXIT_FAILURE; } //If you want to run K-Fold cross validation using the dataset then you should first spilt the dataset into K-Folds //A value of 10 splits the dataset into 10 folds and the true parameter signals that stratified sampling should be used if( !trainingData.spiltDataIntoKFolds( 10, true ) ){ cout << "Failed to spiltDataIntoKFolds!\n"; return EXIT_FAILURE; } //After you have called the spilt function you can then get the training and test sets for each fold for(UINT foldIndex=0; foldIndex<10; foldIndex++){ TimeSeriesClassificationData foldTrainingData = trainingData.getTrainingFoldData( foldIndex ); TimeSeriesClassificationData foldTestingData = trainingData.getTestFoldData( foldIndex ); } //If need you can clear any training data that you have recorded trainingData.clear(); return EXIT_SUCCESS; }