void setup() {
stream.useNormalizer(normalize);
stream.setLabelsForAllDimensions({"red", "green", "blue"});
useStream(stream);
useOutputStream(oStream);
// useStream(stream);
pipeline.addPreProcessingModule(MovingAverageFilter(5, 3));
// use scaling, use null rejection, null rejection parameter
pipeline.setClassifier(ANBC(false, !always_pick_something, null_rej));
// null rejection parameter is multiplied by the standard deviation to determine
// the rejection threshold. the higher the number, the looser the filter; the
// lower the number, the tighter the filter.
usePipeline(pipeline);
registerTuneable(always_pick_something, "Always Pick Something",
"Whether to always pick (predict) one of the classes of training data, "
"even if it's not a very good match. If selected, 'Color Variability' "
"will not be used.", updateAlwaysPickSomething);
registerTuneable(null_rej, 1.0, 25.0, "Color Variability",
"How different from the training data a new color reading can be and "
"still be considered the same color. The higher the number, the more "
"different it can be.", updateVariability);
}
void setup() {
stream.setLabelsForAllDimensions({"x", "y", "z"});
useInputStream(stream);
DTW dtw(false, true, null_rej);
dtw.enableTrimTrainingData(true, 0.1, 75);
pipeline.setClassifier(dtw);
pipeline.addPostProcessingModule(ClassLabelTimeoutFilter(timeout));
usePipeline(pipeline);
registerTuneable(
null_rej, 0.1, 5.0, "Variability",
"How different from the training data a new gesture can be and "
"still be considered the same gesture. The higher the number, the "
"more different it can be.",
[](double new_null_rej) {
pipeline.getClassifier()->setNullRejectionCoeff(new_null_rej);
pipeline.getClassifier()->recomputeNullRejectionThresholds();
});
registerTuneable(
timeout, 1, 3000, "Timeout",
"How long (in milliseconds) to wait after recognizing a "
"gesture before recognizing another one.",
[](double new_timeout) {
ClassLabelTimeoutFilter* filter =
dynamic_cast<ClassLabelTimeoutFilter*>(
pipeline.getPostProcessingModule(0));
assert(filter != nullptr);
filter->setTimeoutDuration(new_timeout);
});
}
std::string GRT_Recognizer::findGesture(VectorDouble input)
{
if( pipeline.getTrained()){
pipeline.predict(input);
UINT label = pipeline.getPredictedClassLabel();
if(pipeline.getMaximumLikelihood() < 0.6)
return "";
}
return "";
}
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;
}
void setup()
{
stream.setLabelsForAllDimensions({"x", "y", "z"});
useStream(stream);
useOutputStream(oStream);
calibrator.setCalibrateFunction(processAccelerometerData);
calibrator.addCalibrateProcess("Resting",
"Rest accelerometer on flat surface.", restingDataCollected);
useCalibrator(calibrator);
pipeline.addFeatureExtractionModule(FeatureApply(3, 1, dotProduct));
pipeline.addFeatureExtractionModule(TimeseriesBuffer(80, 1));
pipeline.addFeatureExtractionModule(FeatureApply(80, 1, stddev));
pipeline.addFeatureExtractionModule(FeatureApply(1, 1, threshold));
usePipeline(pipeline);
registerTuneable(t, 0, 1.0, "Walking Threshold",
"How much the accelerometer data needs to be "
"changing to be considered walking.");
}
int main (int argc, const char * argv[])
{
//Create a new gesture recognition pipeline
GestureRecognitionPipeline pipeline;
//Add an ANBC module
pipeline.setClassifier( ANBC() );
//Add a ClassLabelFilter as a post processing module with a minCount of 5 and a buffer size of 10
pipeline.addPostProcessingModule( ClassLabelFilter(5,10) );
//Load some training data to train and test the classifier
ClassificationData trainingData;
ClassificationData testData;
if( !trainingData.loadDatasetFromFile("ClassLabelFilterTrainingData.txt") ){
cout << "Failed to load training data!\n";
return EXIT_FAILURE;
}
if( !testData.loadDatasetFromFile("ClassLabelFilterTestData.txt") ){
cout << "Failed to load training data!\n";
return EXIT_FAILURE;
}
//Train the classifier
if( !pipeline.train( trainingData ) ){
cout << "Failed to train classifier!\n";
return EXIT_FAILURE;
}
//Use the test dataset to demonstrate the output of the ClassLabelFilter
for(UINT i=0; i<testData.getNumSamples(); i++){
VectorDouble inputVector = testData[i].getSample();
if( !pipeline.predict( inputVector ) ){
cout << "Failed to perform prediction for test sampel: " << i <<"\n";
return EXIT_FAILURE;
}
//Get the predicted class label (this will be the processed class label)
UINT predictedClassLabel = pipeline.getPredictedClassLabel();
//Get the unprocessed class label (i.e. the direct output of the classifier)
UINT unprocessedClassLabel = pipeline.getUnProcessedPredictedClassLabel();
//Also print the results to the screen
cout << "Processed Class Label: \t" << predictedClassLabel << "\tUnprocessed Class Label: \t" << unprocessedClassLabel << endl;
}
return EXIT_SUCCESS;
}
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);
}
void setup() {
useInputStream(iStream);
useOutputStream(oStream);
calibrator.setCalibrateFunction(processAccelerometerData);
calibrator.addCalibrateProcess("Resting",
"Rest accelerometer on flat surface.", restingDataCollected);
useCalibrator(calibrator);
DTW dtw(false, true, null_rej);
pipeline.setClassifier(dtw);
usePipeline(pipeline);
registerTuneable(null_rej, 0.1, 5.0, "Variability",
"How different from the training data a new gesture can be and "
"still be considered the same gesture. The higher the number, the "
"more different it can be.", updateVariability);
useTrainingSampleChecker(checkTrainingSample);
}
int main (int argc, const char * argv[])
{
GestureRecognitionPipeline pipeline;
ANBC anbc;
ClassificationData trainingData;
trainingData.loadDatasetFromFile("training-data.txt")
pipeline.setClassifier(anbc);
pipeline.train(trainingData);
VectorDouble inputVector(SAMPLE_DIMENSION) = getDataFromSensor();
pipeline.predict(inputVector);
UINT predictedClassLabel = pipeline.getPredictedClassLabel();
double maxLikelihood = pipeline.getMaximumLikelihood();
printf("predictedClassLabel : %d , MaximumLikelihood : %f \n", predictedClassLabel, maxLikelihood);
return EXIT_SUCCESS;
}
bool train( CommandLineParser &parser ){
infoLog << "Training regression model..." << endl;
string trainDatasetFilename = "";
string modelFilename = "";
//Get the filename
if( !parser.get("filename",trainDatasetFilename) ){
errorLog << "Failed to parse filename from command line! You can set the filename using the -f." << endl;
printHelp();
return false;
}
//Get the model filename
parser.get("model-filename",modelFilename);
//Load the training data to train the model
ClassificationData trainingData;
infoLog << "- Loading Training Data..." << endl;
if( !trainingData.load( trainDatasetFilename ) ){
errorLog << "Failed to load training data!\n";
return false;
}
const unsigned int N = trainingData.getNumDimensions();
const unsigned int K = trainingData.getNumClasses();
infoLog << "- Num training samples: " << trainingData.getNumSamples() << endl;
infoLog << "- Num input dimensions: " << N << endl;
infoLog << "- Num classes: " << K << endl;
float learningRate = 0;
float minChange = 0;
unsigned int maxEpoch = 0;
unsigned int batchSize = 0;
parser.get( "learning-rate", learningRate );
parser.get( "min-change", minChange );
parser.get( "max-epoch", maxEpoch );
parser.get( "batch-size", batchSize );
infoLog << "Softmax settings: learning-rate: " << learningRate << " min-change: " << minChange << " max-epoch: " << maxEpoch << " batch-size: " << batchSize << endl;
//Create a new softmax instance
bool enableScaling = true;
Softmax classifier(enableScaling,learningRate,minChange,maxEpoch,batchSize);
//Create a new pipeline that will hold the classifier
GestureRecognitionPipeline pipeline;
//Add the classifier to the pipeline
pipeline << classifier;
infoLog << "- Training model...\n";
//Train the classifier
if( !pipeline.train( trainingData ) ){
errorLog << "Failed to train model!" << endl;
return false;
}
infoLog << "- Model trained!" << endl;
infoLog << "- Saving model to: " << modelFilename << endl;
//Save the pipeline
if( pipeline.save( modelFilename ) ){
infoLog << "- Model saved." << endl;
}else warningLog << "Failed to save model to file: " << modelFilename << endl;
infoLog << "- TrainingTime: " << pipeline.getTrainingTime() << endl;
string logFilename = "";
if( parser.get( "log-filename", logFilename ) && logFilename.length() > 0 ){
infoLog << "Writing training log to: " << logFilename << endl;
fstream logFile( logFilename.c_str(), fstream::out );
if( !logFile.is_open() ){
errorLog << "Failed to open training log file: " << logFilename << endl;
return false;
}
Vector< TrainingResult > trainingResults = pipeline.getTrainingResults();
for(UINT i=0; i<trainingResults.getSize(); i++){
logFile << trainingResults[i].getTrainingIteration() << "\t" << trainingResults[i].getAccuracy() << endl;
}
logFile.close();
}
return true;
}
void metrics_separate_data(){
// Training and test data
ClassificationData trainingData;
ClassificationData testData;
string file_path = "../../../data/";
if( !trainingData.loadDatasetFromFile(file_path + "train/grt/12345.txt") ){
std::cout <<"Failed to load training data!\n";
}
ANBC anbc;
anbc.enableScaling(true);
anbc.enableNullRejection(true);
SVM svm(SVM::RBF_KERNEL);
svm.enableScaling(true);
svm.enableNullRejection(true);
MinDist minDist;
minDist.setNumClusters(4);
minDist.enableScaling(true);
minDist.enableNullRejection(true);
ofstream outputFileStream("accuracy-mindist.csv");
outputFileStream << "classLabel,nullRejectionCoeff,accuracy, \n";
for(int class_name = 1; class_name<=5; class_name++){
if( !testData.loadDatasetFromFile(file_path + "test/grt/" + to_string(class_name) + ".txt") ){
std::cout <<"Failed to load training data!\n";
}
for(double nullRejectionCoeff = 0; nullRejectionCoeff <= 10; nullRejectionCoeff=nullRejectionCoeff+0.2){
// anbc.setNullRejectionCoeff(nullRejectionCoeff);
// svm.setNullRejectionCoeff(nullRejectionCoeff);
minDist.setNullRejectionCoeff(nullRejectionCoeff);
GestureRecognitionPipeline pipeline;
// pipeline.setClassifier(anbc);
// pipeline.setClassifier(svm);
pipeline.setClassifier(minDist);
// Train the pipeline
if( !pipeline.train( trainingData ) ){
std::cout << "Failed to train classifier!\n";
}
// Evaluation
double accuracy = 0;
for(UINT i=0; i<testData.getNumSamples(); i++){
UINT actualClassLabel = testData[i].getClassLabel();
vector< double > inputVector = testData[i].getSample();
if( !pipeline.predict( inputVector )){
std::cout << "Failed to perform prediction for test sampel: " << i <<"\n";
}
UINT predictedClassLabel = pipeline.getPredictedClassLabel();
if( actualClassLabel == predictedClassLabel) accuracy++;
}
outputFileStream << class_name << ',' << nullRejectionCoeff << ',' << accuracy/double(testData.getNumSamples())*100.0 << '\n';
cout<< "Done" << endl;
}
}
//---------------------- Null Gesture Test -----------------//
int class_name = 0;
if( !testData.loadDatasetFromFile(file_path + "test/grt/" + to_string(class_name) + ".txt") ){
std::cout <<"Failed to load training data!\n";
}
for(double nullRejectionCoeff = 0; nullRejectionCoeff <= 10; nullRejectionCoeff=nullRejectionCoeff+0.2){
// anbc.setNullRejectionCoeff(nullRejectionCoeff);
// svm.setNullRejectionCoeff(nullRejectionCoeff);
minDist.setNullRejectionCoeff(nullRejectionCoeff);
GestureRecognitionPipeline pipeline;
// pipeline.setClassifier(anbc);
// pipeline.setClassifier(svm);
pipeline.setClassifier(minDist);
// Train the pipeline
if( !pipeline.train( trainingData ) ){
std::cout << "Failed to train classifier!\n";
}
// Evaluation
double accuracy = 0;
for(UINT i=0; i<testData.getNumSamples(); i++){
vector< double > inputVector = testData[i].getSample();
if( !pipeline.predict( inputVector )){
std::cout << "Failed to perform prediction for test sampel: " << i <<"\n";
}
UINT predictedClassLabel = pipeline.getPredictedClassLabel();
if(predictedClassLabel == 0 ) accuracy++;
}
outputFileStream << class_name << ',' << nullRejectionCoeff << ',' << accuracy/double(testData.getNumSamples())*100.0 << '\n';
cout<< "Done" << endl;
}
}
int main (int argc, const char * argv[])
{
//Turn on the training log so we can print the training status of the LinearRegression to the screen
TrainingLog::enableLogging( true );
//Load the training data
RegressionData trainingData;
RegressionData testData;
if( !trainingData.loadDatasetFromFile("LinearRegressionTrainingData.txt") ){
cout << "ERROR: Failed to load training data!\n";
return EXIT_FAILURE;
}
if( !testData.loadDatasetFromFile("LinearRegressionTestData.txt") ){
cout << "ERROR: Failed to load test data!\n";
return EXIT_FAILURE;
}
//Make sure the dimensionality of the training and test data matches
if( trainingData.getNumInputDimensions() != testData.getNumInputDimensions() ){
cout << "ERROR: The number of input dimensions in the training data (" << trainingData.getNumInputDimensions() << ")";
cout << " does not match the number of input dimensions in the test data (" << testData.getNumInputDimensions() << ")\n";
return EXIT_FAILURE;
}
if( testData.getNumTargetDimensions() != testData.getNumTargetDimensions() ){
cout << "ERROR: The number of target dimensions in the training data (" << testData.getNumTargetDimensions() << ")";
cout << " does not match the number of target dimensions in the test data (" << testData.getNumTargetDimensions() << ")\n";
return EXIT_FAILURE;
}
cout << "Training and Test datasets loaded\n";
//Print the stats of the datasets
cout << "Training data stats:\n";
trainingData.printStats();
cout << "Test data stats:\n";
testData.printStats();
//Create a new gesture recognition pipeline
GestureRecognitionPipeline pipeline;
//Add a LinearRegression instance to the pipeline
pipeline.setRegressifier( LinearRegression() );
//Train the LinearRegression model
cout << "Training LogisticRegression model...\n";
if( !pipeline.train( trainingData ) ){
cout << "ERROR: Failed to train LinearRegression model!\n";
return EXIT_FAILURE;
}
cout << "Model trained.\n";
//Test the model
cout << "Testing LinearRegression model...\n";
if( !pipeline.test( testData ) ){
cout << "ERROR: Failed to test LinearRegression model!\n";
return EXIT_FAILURE;
}
cout << "Test complete. Test RMS error: " << pipeline.getTestRMSError() << endl;
//Run back over the test data again and output the results to a file
fstream file;
file.open("LinearRegressionResultsData.txt", fstream::out);
for(UINT i=0; i<testData.getNumSamples(); i++){
vector< double > inputVector = testData[i].getInputVector();
vector< double > targetVector = testData[i].getTargetVector();
//Map the input vector using the trained regression model
if( !pipeline.predict( inputVector ) ){
cout << "ERROR: Failed to map test sample " << i << endl;
return EXIT_FAILURE;
}
//Get the mapped regression data
vector< double > outputVector = pipeline.getRegressionData();
//Write the mapped value and also the target value to the file
for(UINT j=0; j<outputVector.size(); j++){
file << outputVector[j] << "\t";
}
for(UINT j=0; j<targetVector.size(); j++){
file << targetVector[j] << "\t";
}
file << endl;
}
//Close the file
file.close();
return EXIT_SUCCESS;
}
void prediction_axis_data(){
// Training and test data
ClassificationData trainingData;
ClassificationData testData;
string file_path = "../../../data/";
string class_name = "5";
if( !trainingData.loadDatasetFromFile(file_path + "train/grt/" + class_name + ".txt") ){
std::cout <<"Failed to load training data!\n";
}
if( !testData.loadDatasetFromFile(file_path + "test/grt/" + class_name + ".txt") ){
std::cout <<"Failed to load training data!\n";
}
// Pipeline setup
ANBC anbc;
anbc.setNullRejectionCoeff(1);
anbc.enableScaling(true);
anbc.enableNullRejection(true);
GestureRecognitionPipeline pipeline;
pipeline.setClassifier(anbc);
// Train the pipeline
if( !pipeline.train( trainingData ) ){
std::cout << "Failed to train classifier!\n";
}
// File stream
ofstream outputFileStream(class_name + ".csv");
// Evaluation
double accuracy = 0;
outputFileStream << "actualClass,predictedClass,maximumLikelihood,lZ,lY,lZ,rZ,rY,rZ \n";
for(UINT i=0; i<testData.getNumSamples(); i++){
UINT actualClassLabel = testData[i].getClassLabel();
vector< double > inputVector = testData[i].getSample();
if( !pipeline.predict( inputVector )){
std::cout << "Failed to perform prediction for test sampel: " << i <<"\n";
}
UINT predictedClassLabel = pipeline.getPredictedClassLabel();
double maximumLikelihood = pipeline.getMaximumLikelihood();
outputFileStream << actualClassLabel << "," << predictedClassLabel << "," << maximumLikelihood << ","
<< inputVector[0] << "," << inputVector[1] << "," << inputVector[2] << "," << inputVector[3] << "," << inputVector[4] << "," << inputVector[5] << "\n";
if( actualClassLabel == predictedClassLabel) accuracy++;
}
std::cout << "Test Accuracy testHandsUp : " << accuracy/double(testData.getNumSamples())*100.0 << " %\n";
}
void metrics_subset_data(){
ANBC anbc;
anbc.enableScaling(true);
anbc.enableNullRejection(true);
MinDist minDist;
minDist.setNumClusters(4);
minDist.enableScaling(true);
minDist.enableNullRejection(true);
// ofstream opRecall("anbc-recall-nr-0-10.csv");
// opRecall <<"nrCoeff,class0,class1,class2,class3,class4,class5\n";
//
// ofstream opInstanceRes("anbc-prediction-nr-2.csv");
// opInstanceRes <<"actualClass,predictedClass,maximumLikelihood,lZ,lY,lZ,rZ,rY,rZ\n";
//
// ofstream opMetrics("anbc-precision-recall-fmeasure-nr-2.csv");
// opMetrics <<"class1,class2,class3,class4,class5\n";
//
// ofstream opConfusion("anbc-confusion-nr-2.csv");
// opConfusion <<"class0,class1,class2,class3,class4,class5\n";
ofstream opRecall("mindist-recall-nr-0-10.csv");
opRecall <<"nrCoeff,class0,class1,class2,class3,class4,class5\n";
ofstream opInstanceRes("mindist-prediction-nr-2.csv");
opInstanceRes <<"actualClass,predictedClass,maximumLikelihood,lZ,lY,lZ,rZ,rY,rZ\n";
ofstream opMetrics("mindist-precision-recall-fmeasure-nr-2.csv");
opMetrics <<"class1,class2,class3,class4,class5\n";
ofstream opConfusion("mindist-confusion-nr-2.csv");
opConfusion <<"class0,class1,class2,class3,class4,class5\n";
// Training and test data
ClassificationData trainingData;
ClassificationData testData;
ClassificationData nullGestureData;
string file_path = "../../../data/";
if( !trainingData.loadDatasetFromFile(file_path + "train/grt/hri-training-dataset.txt") ){
std::cout <<"Failed to load training data!\n";
}
if( !nullGestureData.loadDatasetFromFile(file_path + "test/grt/0.txt") ){
std::cout <<"Failed to load null gesture data!\n";
}
testData = trainingData.partition(90);
testData.sortClassLabels();
// testData.saveDatasetToFile("anbc-validation-subset.txt");
testData.saveDatasetToFile("mindist-validation-subset.txt");
for(double nullRejectionCoeff = 0; nullRejectionCoeff <= 10; nullRejectionCoeff=nullRejectionCoeff+0.2){
// anbc.setNullRejectionCoeff(nullRejectionCoeff);
// GestureRecognitionPipeline pipeline;
// pipeline.setClassifier(anbc);
minDist.setNullRejectionCoeff(nullRejectionCoeff);
GestureRecognitionPipeline pipeline;
pipeline.setClassifier(minDist);
pipeline.train(trainingData);
pipeline.test(testData);
TestResult testRes = pipeline.getTestResults();
opRecall << nullRejectionCoeff << ",";
//null rejection prediction
double accuracy = 0;
for(UINT i=0; i<nullGestureData.getNumSamples(); i++){
vector< double > inputVector = nullGestureData[i].getSample();
if( !pipeline.predict( inputVector )){
std::cout << "Failed to perform prediction for test sampel: " << i <<"\n";
}
UINT predictedClassLabel = pipeline.getPredictedClassLabel();
if(predictedClassLabel == 0 ) accuracy++;
}
opRecall << accuracy/double(nullGestureData.getNumSamples()) << ",";
// other classes prediction
for(int cl = 0; cl < testRes.recall.size(); cl++ ){
opRecall << testRes.recall[cl];
if(cl < testRes.recall.size() - 1){
opRecall << ",";
}
}
opRecall<< endl;
// Calculate instance prediction, precision, recall, fmeasure and confusion matrix for nullRejection 2.0
if(AreDoubleSame(nullRejectionCoeff, 2.0))
{
//instance prediction
for(UINT i=0; i<testData.getNumSamples(); i++){
UINT actualClassLabel = testData[i].getClassLabel();
vector< double > inputVector = testData[i].getSample();
if( !pipeline.predict( inputVector )){
std::cout << "Failed to perform prediction for test sampel: " << i <<"\n";
}
UINT predictedClassLabel = pipeline.getPredictedClassLabel();
double maximumLikelihood = pipeline.getMaximumLikelihood();
opInstanceRes << actualClassLabel << "," << predictedClassLabel << "," << maximumLikelihood << ","
<< inputVector[0] << "," << inputVector[1] << "," << inputVector[2] << "," << inputVector[3] << "," << inputVector[4] << "," << inputVector[5] << "\n";
}
//precision, recall, fmeasure
for(int cl = 0; cl < testRes.precision.size(); cl++ ){
opMetrics << testRes.precision[cl];
if(cl < testRes.precision.size() - 1){
opMetrics << ",";
}
}
opMetrics<< endl;
for(int cl = 0; cl < testRes.recall.size(); cl++ ){
opMetrics << testRes.recall[cl];
if(cl < testRes.recall.size() - 1){
opMetrics << ",";
}
}
opMetrics<< endl;
for(int cl = 0; cl < testRes.fMeasure.size(); cl++ ){
opMetrics << testRes.fMeasure[cl];
if(cl < testRes.fMeasure.size() - 1){
opMetrics << ",";
}
}
opMetrics<< endl;
//confusion matrix
MatrixDouble matrix = testRes.confusionMatrix;
for(UINT i=0; i<matrix.getNumRows(); i++){
for(UINT j=0; j<matrix.getNumCols(); j++){
opConfusion << matrix[i][j];
if(j < matrix.getNumCols() - 1){
opConfusion << ",";
}
}
opConfusion << endl;
}
opConfusion << endl;
}
}
cout << "Done\n";
}
bool train( CommandLineParser &parser ){
infoLog << "Training regression model..." << endl;
string trainDatasetFilename = "";
string modelFilename = "";
float learningRate = 0;
float minChange = 0;
unsigned int maxEpoch = 0;
unsigned int batchSize = 0;
//Get the filename
if( !parser.get("filename",trainDatasetFilename) ){
errorLog << "Failed to parse filename from command line! You can set the filename using the -f." << endl;
printHelp();
return false;
}
//Get the parameters from the parser
parser.get("model-filename",modelFilename);
parser.get( "learning-rate", learningRate );
parser.get( "min-change", minChange );
parser.get( "max-epoch", maxEpoch );
parser.get( "batch-size", batchSize );
infoLog << "settings: learning-rate: " << learningRate << " min-change: " << minChange << " max-epoch: " << maxEpoch << " batch-size: " << batchSize << endl;
//Load the training data to train the model
RegressionData trainingData;
//Try and parse the input and target dimensions
unsigned int numInputDimensions = 0;
unsigned int numTargetDimensions = 0;
if( parser.get("num-inputs",numInputDimensions) && parser.get("num-targets",numTargetDimensions) ){
infoLog << "num input dimensions: " << numInputDimensions << " num target dimensions: " << numTargetDimensions << endl;
trainingData.setInputAndTargetDimensions( numInputDimensions, numTargetDimensions );
}
if( (numInputDimensions == 0 || numTargetDimensions == 0) && Util::stringEndsWith( trainDatasetFilename, ".csv" ) ){
errorLog << "Failed to parse num input dimensions and num target dimensions from input arguments. You must supply the input and target dimensions if the data format is CSV!" << endl;
printHelp();
return false;
}
infoLog << "- Loading Training Data..." << endl;
if( !trainingData.load( trainDatasetFilename ) ){
errorLog << "Failed to load training data!\n";
return false;
}
const unsigned int N = trainingData.getNumInputDimensions();
const unsigned int T = trainingData.getNumTargetDimensions();
infoLog << "- Num training samples: " << trainingData.getNumSamples() << endl;
infoLog << "- Num input dimensions: " << N << endl;
infoLog << "- Num target dimensions: " << T << endl;
//Create a new regression instance
LogisticRegression regression;
regression.setMaxNumEpochs( maxEpoch );
regression.setMinChange( minChange );
regression.setUseValidationSet( true );
regression.setValidationSetSize( 20 );
regression.setRandomiseTrainingOrder( true );
regression.enableScaling( true );
//Create a new pipeline that will hold the regression algorithm
GestureRecognitionPipeline pipeline;
//Add a multidimensional regression instance and set the regression algorithm to Linear Regression
pipeline.setRegressifier( MultidimensionalRegression( regression, true ) );
infoLog << "- Training model...\n";
//Train the classifier
if( !pipeline.train( trainingData ) ){
errorLog << "Failed to train model!" << endl;
return false;
}
infoLog << "- Model trained!" << endl;
infoLog << "- Saving model to: " << modelFilename << endl;
//Save the pipeline
if( pipeline.save( modelFilename ) ){
infoLog << "- Model saved." << endl;
}else warningLog << "Failed to save model to file: " << modelFilename << endl;
infoLog << "- TrainingTime: " << pipeline.getTrainingTime() << endl;
return true;
}
bool test( CommandLineParser &parser ){
infoLog << "Testing model..." << endl;
string datasetFilename = "";
string modelFilename = "";
string resultsFilename = "";
//Get the model filename
if( !parser.get("model-filename",modelFilename) ){
errorLog << "Failed to parse model filename from command line! You can set the model filename using the -m." << endl;
printUsage();
return false;
}
//Get the filename
if( !parser.get("dataset-filename",datasetFilename) ){
errorLog << "Failed to parse dataset filename from command line! You can set the dataset filename using the -f." << endl;
printUsage();
return false;
}
//Get the model filename
parser.get("results-filename",resultsFilename,string("results.txt"));
//Load the pipeline from a file
GestureRecognitionPipeline pipeline;
infoLog << "- Loading model..." << endl;
if( !pipeline.load( modelFilename ) ){
errorLog << "Failed to load model from file: " << modelFilename << endl;
printUsage();
return false;
}
infoLog << "- Model loaded!" << endl;
//Load the data to test the classifier
ClassificationData data;
infoLog << "- Loading Training Data..." << endl;
if( !data.load( datasetFilename ) ){
errorLog << "Failed to load data!\n";
return false;
}
const unsigned int N = data.getNumDimensions();
infoLog << "- Num training samples: " << data.getNumSamples() << endl;
infoLog << "- Num dimensions: " << N << endl;
infoLog << "- Num classes: " << data.getNumClasses() << endl;
//Test the classifier
if( !pipeline.test( data ) ){
errorLog << "Failed to test pipeline!" << endl;
return false;
}
infoLog << "- Test complete in " << pipeline.getTestTime()/1000.0 << " seconds with and accuracy of: " << pipeline.getTestAccuracy() << endl;
return saveResults( pipeline, resultsFilename );
}
int main (int argc, const char * argv[])
{
//Load some training data from a file
ClassificationData trainingData;
if( !trainingData.loadDatasetFromFile("HelloWorldTrainingData.grt") ){
cout << "ERROR: Failed to load training data from file\n";
return EXIT_FAILURE;
}
cout << "Data Loaded\n";
//Print out some stats about the training data
trainingData.printStats();
//Partition the training data into a training dataset and a test dataset. 80 means that 80%
//of the data will be used for the training data and 20% will be returned as the test dataset
ClassificationData testData = trainingData.partition(80);
//Create a new Gesture Recognition Pipeline using an Adaptive Naive Bayes Classifier
GestureRecognitionPipeline pipeline;
pipeline.setClassifier( ANBC() );
//Train the pipeline using the training data
if( !pipeline.train( trainingData ) ){
cout << "ERROR: Failed to train the pipeline!\n";
return EXIT_FAILURE;
}
//Save the pipeline to a file
if( !pipeline.savePipelineToFile( "HelloWorldPipeline.grt" ) ){
cout << "ERROR: Failed to save the pipeline!\n";
return EXIT_FAILURE;
}
//Load the pipeline from a file
if( !pipeline.loadPipelineFromFile( "HelloWorldPipeline.grt" ) ){
cout << "ERROR: Failed to load the pipeline!\n";
return EXIT_FAILURE;
}
//Test the pipeline using the test data
if( !pipeline.test( testData ) ){
cout << "ERROR: Failed to test the pipeline!\n";
return EXIT_FAILURE;
}
//Print some stats about the testing
cout << "Test Accuracy: " << pipeline.getTestAccuracy() << endl;
cout << "Precision: ";
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
cout << "\t" << pipeline.getTestPrecision(classLabel);
}cout << endl;
cout << "Recall: ";
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
cout << "\t" << pipeline.getTestRecall(classLabel);
}cout << endl;
cout << "FMeasure: ";
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
cout << "\t" << pipeline.getTestFMeasure(classLabel);
}cout << endl;
MatrixDouble confusionMatrix = pipeline.getTestConfusionMatrix();
cout << "ConfusionMatrix: \n";
for(UINT i=0; i<confusionMatrix.getNumRows(); i++){
for(UINT j=0; j<confusionMatrix.getNumCols(); j++){
cout << confusionMatrix[i][j] << "\t";
}cout << endl;
}
return EXIT_SUCCESS;
}
bool train( CommandLineParser &parser ){
string trainDatasetFilename = "";
string modelFilename = "";
unsigned int forestSize = 0;
unsigned int maxDepth = 0;
unsigned int minNodeSize = 0;
unsigned int numSplits = 0;
bool removeFeatures = false;
double bootstrapWeight = 0.0;
//Get the filename
if( !parser.get("filename",trainDatasetFilename) ){
errorLog << "Failed to parse filename from command line! You can set the filename using the -f." << endl;
printUsage();
return false;
}
//Get the model filename
parser.get("model-filename",modelFilename);
//Get the forest size
parser.get("forest-size",forestSize);
//Get the max depth
parser.get("max-depth",maxDepth);
//Get the min node size
parser.get("min-node-size",minNodeSize);
//Get the number of random splits
parser.get("num-splits",numSplits);
//Get the remove features
parser.get("remove-features",removeFeatures);
//Get the bootstrap weight
parser.get("bootstrap-weight",bootstrapWeight);
//Load some training data to train the classifier
ClassificationData trainingData;
infoLog << "- Loading Training Data..." << endl;
if( !trainingData.load( trainDatasetFilename ) ){
errorLog << "Failed to load training data!\n";
return false;
}
const unsigned int N = trainingData.getNumDimensions();
Vector< ClassTracker > tracker = trainingData.getClassTracker();
infoLog << "- Num training samples: " << trainingData.getNumSamples() << endl;
infoLog << "- Num dimensions: " << N << endl;
infoLog << "- Num classes: " << trainingData.getNumClasses() << endl;
infoLog << "- Class stats: " << endl;
for(unsigned int i=0; i<tracker.getSize(); i++){
infoLog << "- class " << tracker[i].classLabel << " number of samples: " << tracker[i].counter << endl;
}
//Create a new RandomForests instance
RandomForests forest;
//Set the decision tree node that will be used for each tree in the forest
string nodeType = "cluster-node"; //TODO: make this a command line option in the future
if( nodeType == "cluster-node" ){
forest.setDecisionTreeNode( DecisionTreeClusterNode() );
}
if( nodeType == "threshold-node" ){
forest.setTrainingMode( Tree::BEST_RANDOM_SPLIT );
forest.setDecisionTreeNode( DecisionTreeThresholdNode() );
}
//Set the number of trees in the forest
forest.setForestSize( forestSize );
//Set the maximum depth of the tree
forest.setMaxDepth( maxDepth );
//Set the minimum number of samples allowed per node
forest.setMinNumSamplesPerNode( minNodeSize );
//Set the number of random splits used per node
forest.setNumRandomSplits( numSplits );
//Set if selected features should be removed at each node
forest.setRemoveFeaturesAtEachSplit( removeFeatures );
//Set the bootstrap weight
forest.setBootstrappedDatasetWeight( bootstrapWeight );
//Add the classifier to a pipeline
GestureRecognitionPipeline pipeline;
pipeline.setClassifier( forest );
infoLog << "- Training model..." << endl;
//Train the classifier
if( !pipeline.train( trainingData ) ){
errorLog << "Failed to train classifier!" << endl;
return false;
}
infoLog << "- Model trained!" << endl;
infoLog << "- Training time: " << (pipeline.getTrainingTime() * 0.001) / 60.0 << " (minutes)" << endl;
infoLog << "- Saving model to: " << modelFilename << endl;
//Save the pipeline
if( !pipeline.save( modelFilename ) ){
warningLog << "Failed to save model to file: " << modelFilename << endl;
}
return true;
}
bool combineModels( CommandLineParser &parser ){
infoLog << "Combining models..." << endl;
string directoryPath = "";
string modelFilename = "";
if( !parser.get("data-dir",directoryPath) ){
errorLog << "Failed to parse data-directory from command line! You can set the data-directory using the --data-dir option." << endl;
printUsage();
return false;
}
//Get the filename
if( !parser.get("model-filename",modelFilename) ){
errorLog << "Failed to parse filename from command line! You can set the model filename using the --model." << endl;
printUsage();
return false;
}
Vector< string > files;
infoLog << "- Parsing data directory: " << directoryPath << endl;
//Parse the directory to get all the csv files
if( !Util::parseDirectory( directoryPath, ".grt", files ) ){
errorLog << "Failed to parse data directory!" << endl;
return false;
}
RandomForests forest; //Used to validate the random forest type
GestureRecognitionPipeline *mainPipeline = NULL; // Points to the first valid pipeline that all the models will be merged to
Vector< GestureRecognitionPipeline* > pipelineBuffer; //Stores the pipeline for each file that is loaded
unsigned int inputVectorSize = 0; //Set to zero to mark we haven't loaded any models yet
const unsigned int numFiles = files.getSize();
bool mainPipelineSet = false;
bool combineModelsSuccessful = false;
pipelineBuffer.reserve( numFiles );
//Loop over the files, load them, and add valid random forest pipelines to the pipelineBuffer so they can be combined with the mainPipeline
for(unsigned int i=0; i<numFiles; i++){
infoLog << "- Loading model " << files[i] << ". File " << i+1 << " of " << numFiles << endl;
GestureRecognitionPipeline *pipeline = new GestureRecognitionPipeline;
if( pipeline->load( files[i] ) ){
infoLog << "- Pipeline loaded. Number of input dimensions: " << pipeline->getInputVectorDimensionsSize() << endl;
if( pipelineBuffer.size() == 0 ){
inputVectorSize = pipeline->getInputVectorDimensionsSize();
}
if( pipeline->getInputVectorDimensionsSize() != inputVectorSize ){
warningLog << "- Pipeline " << i+1 << " input vector size does not match the size of the first pipeline!" << endl;
}else{
Classifier *classifier = pipeline->getClassifier();
if( classifier ){
if( classifier->getClassifierType() == forest.getClassifierType() ){ //Validate the classifier is a random forest
if( !mainPipelineSet ){
mainPipelineSet = true;
mainPipeline = pipeline;
}else pipelineBuffer.push_back( pipeline );
}else{
warningLog << "- Pipeline " << i+1 << " does not contain a random forest classifer! Classifier type: " << classifier->getClassifierType() << endl;
}
}
}
}else{
warningLog << "- WARNING: Failed to load model from file: " << files[i] << endl;
}
}
if( mainPipelineSet ){
//Combine the random forest models with the main pipeline model
const unsigned int numPipelines = pipelineBuffer.getSize();
RandomForests *mainForest = mainPipeline->getClassifier< RandomForests >();
for(unsigned int i=0; i<numPipelines; i++){
infoLog << "- Combing model " << i+1 << " of " << numPipelines << " with main model..." << endl;
RandomForests *f = pipelineBuffer[i]->getClassifier< RandomForests >();
if( !mainForest->combineModels( *f ) ){
warningLog << "- WARNING: Failed to combine model " << i+1 << " with the main model!" << endl;
}
}
if( mainPipeline->getTrained() ){
infoLog << "- Saving combined pipeline to file..." << endl;
combineModelsSuccessful = mainPipeline->save( modelFilename );
}
}else{
errorLog << "Failed to combined models, no models were loaded!" << endl;
}
//Cleanup the pipeline buffer
for(unsigned int i=0; i<pipelineBuffer.getSize(); i++){
delete pipelineBuffer[i];
pipelineBuffer[i] = NULL;
}
return combineModelsSuccessful;
}
int main (int argc, const char * argv[])
{
//We are going to use the Iris dataset, you can find more about the orginal dataset at: http://en.wikipedia.org/wiki/Iris_flower_data_set
//Create a new instance of LabelledClassificationData to hold the training data
LabelledClassificationData trainingData;
//Load the training dataset from a file, the file should be in the same directory as this program
if( !trainingData.loadDatasetFromFile("IrisData.txt") ){
cout << "Failed to load Iris data from file!\n";
return EXIT_FAILURE;
}
//Print some basic stats about the dataset we have loaded
trainingData.printStats();
//Partition the training dataset into a training dataset and test dataset
//We will use 60% of the data to train the algorithm and 40% of the data to test it
//The true parameter flags that we want to use stratified sampling, which means there
//should be an equal class distribution between the training and test datasets
LabelledClassificationData testData = trainingData.partition( 60, true );
//Setup the gesture recognition pipeline
GestureRecognitionPipeline pipeline;
//Add a KNN classification algorithm as the main classifier with a K value of 10
pipeline.setClassifier( KNN(10) );
//Train the KNN algorithm using the training dataset
if( !pipeline.train( trainingData ) ){
cout << "Failed to train the pipeline!\n";
return EXIT_FAILURE;
}
//Test the KNN model using the test dataset
if( !pipeline.test( testData ) ){
cout << "Failed to test the pipeline!\n";
return EXIT_FAILURE;
}
//Print some metrics about how successful the classification was
//Print the accuracy
cout << "The classification accuracy was: " << pipeline.getTestAccuracy() << "%\n" << endl;
//Print the precision for each class
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
double classPrecision = pipeline.getTestPrecision( classLabel );
cout << "The precision for class " << classLabel << " was " << classPrecision << endl;
}
cout << endl;
//Print the recall for each class
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
double classRecall = pipeline.getTestRecall( classLabel );
cout << "The recall for class " << classLabel << " was " << classRecall << endl;
}
cout << endl;
//Print the confusion matrix
Matrix< double > confusionMatrix = pipeline.getTestConfusionMatrix();
cout << "Confusion Matrix: \n";
for(UINT i=0; i<confusionMatrix.getNumRows(); i++){
for(UINT j=0; j<confusionMatrix.getNumCols(); j++){
cout << confusionMatrix[i][j] << "\t";
}
cout << endl;
}
cout << endl;
return EXIT_SUCCESS;
}
bool saveResults( const GestureRecognitionPipeline &pipeline, const string &filename ){
infoLog << "Saving results to file: " << filename << endl;
fstream file( filename.c_str(), fstream::out );
if( !file.is_open() ){
errorLog << "Failed to open results file: " << filename << endl;
return false;
}
file << pipeline.getTestAccuracy() << endl;
vector< UINT > classLabels = pipeline.getClassLabels();
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
file << pipeline.getTestPrecision( classLabels[k] );
if( k+1 < pipeline.getNumClassesInModel() ) file << "\t";
else file << endl;
}
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
file << pipeline.getTestRecall( classLabels[k] );
if( k+1 < pipeline.getNumClassesInModel() ) file << "\t";
else file << endl;
}
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
file << pipeline.getTestFMeasure( classLabels[k] );
if( k+1 < pipeline.getNumClassesInModel() ) file << "\t";
else file << endl;
}
MatrixDouble confusionMatrix = pipeline.getTestConfusionMatrix();
for(UINT i=0; i<confusionMatrix.getNumRows(); i++){
for(UINT j=0; j<confusionMatrix.getNumCols(); j++){
file << confusionMatrix[i][j];
if( j+1 < confusionMatrix.getNumCols() ) file << "\t";
}file << endl;
}
file.close();
infoLog << "Results saved." << endl;
return true;
}
void setup() {
stream.setLabelsForAllDimensions({"audio"});
pipeline.addFeatureExtractionModule(
FFT(kFftWindowSize, kFftHopSize,
DIM, FFT::HAMMING_WINDOW, true, false));
MFCC::Options options;
options.sample_rate = kSampleRate;
options.fft_size = kFftWindowSize / 2;
options.start_freq = 300;
options.end_freq = 3700;
options.num_tri_filter = 26;
options.num_cepstral_coeff = 12;
options.lifter_param = 22;
options.use_vad = true;
options.noise_level = noise_level;
pipeline.addFeatureExtractionModule(MFCC(options));
pipeline.setClassifier(SVM());
// GMM(16, true, false, 1, 100, 0.001));
// In post processing, we wait #n predicitons. If m out of n predictions are
// from the same class, we declare the class as the right one.
//
// n = (duration * sample_rate) / frame_size
// where duration = post_duration
// sample_rate = kSampleRate
// frame_size = kFftHopSize
// m = n * post_ratio
int num_predictions = post_duration / 1000 * kSampleRate / kFftHopSize;
pipeline.addPostProcessingModule(
ClassLabelFilter(num_predictions * post_ratio, num_predictions));
auto ratio_updater = [](double new_ratio) {
ClassLabelFilter* filter =
dynamic_cast<ClassLabelFilter*>(pipeline.getPostProcessingModule(0));
// Recalculate num_predictions as post_duration might have been changed
int num_predictions = post_duration / 1000 * kSampleRate / kFftHopSize;
filter->setMinimumCount(new_ratio * num_predictions);
};
auto duration_updater = [](int new_duration) {
ClassLabelFilter* filter =
dynamic_cast<ClassLabelFilter*>(pipeline.getPostProcessingModule(0));
// Recalculate num_predictions as post_duration might have been changed
int num_predictions = post_duration / 1000 * kSampleRate / kFftHopSize;
filter->setBufferSize(num_predictions);
};
auto noise_updater = [](int new_noise_level) {
MFCC *mfcc = dynamic_cast<MFCC*>(pipeline.getFeatureExtractionModule(1));
mfcc->setNoiseLevel(new_noise_level);
};
registerTuneable(noise_level, 0, 20,
"Noise Level",
"The threshold for the system to distinguish between "
"ambient noise and speech/sound",
noise_updater);
registerTuneable(post_duration, 0, 2000,
"Duration",
"Time (in ms) that is considered as a whole "
"for smoothing the prediction",
duration_updater);
registerTuneable(post_ratio, 0.0f, 1.0f,
"Ratio",
"The portion of time in duration that "
"should be from the same class",
ratio_updater);
useInputStream(stream);
useOutputStream(oStream);
usePipeline(pipeline);
useLeaveOneOutScoring(false);
setGUIBufferSize(kSampleRate);
}
void updateAlwaysPickSomething(bool new_val) {
pipeline.getClassifier()->enableNullRejection(!new_val);
}
bool train( CommandLineParser &parser ){
infoLog << "Training regression model..." << endl;
string trainDatasetFilename = "";
string modelFilename = "";
string defaultFilename = "linear-regression-model.grt";
bool removeFeatures = false;
bool defaultRemoveFeatures = false;
//Get the filename
if( !parser.get("filename",trainDatasetFilename) ){
errorLog << "Failed to parse filename from command line! You can set the filename using the -f." << endl;
printUsage();
return false;
}
//Get the model filename
parser.get("model-filename",modelFilename,defaultFilename);
//Load the training data to train the model
RegressionData trainingData;
infoLog << "- Loading Training Data..." << endl;
if( !trainingData.load( trainDatasetFilename ) ){
errorLog << "Failed to load training data!\n";
return false;
}
const unsigned int N = trainingData.getNumInputDimensions();
const unsigned int T = trainingData.getNumTargetDimensions();
infoLog << "- Num training samples: " << trainingData.getNumSamples() << endl;
infoLog << "- Num input dimensions: " << N << endl;
infoLog << "- Num target dimensions: " << T << endl;
//Create a new regression instance
LogisticRegression regression;
regression.setMaxNumEpochs( 500 );
regression.setMinChange( 1.0e-5 );
regression.setUseValidationSet( true );
regression.setValidationSetSize( 20 );
regression.setRandomiseTrainingOrder( true );
regression.enableScaling( true );
//Create a new pipeline that will hold the regression algorithm
GestureRecognitionPipeline pipeline;
//Add a multidimensional regression instance and set the regression algorithm to Linear Regression
pipeline.setRegressifier( MultidimensionalRegression( regression, true ) );
infoLog << "- Training model...\n";
//Train the classifier
if( !pipeline.train( trainingData ) ){
errorLog << "Failed to train model!" << endl;
return false;
}
infoLog << "- Model trained!" << endl;
infoLog << "- Saving model to: " << modelFilename << endl;
//Save the pipeline
if( pipeline.save( modelFilename ) ){
infoLog << "- Model saved." << endl;
}else warningLog << "Failed to save model to file: " << modelFilename << endl;
infoLog << "- TrainingTime: " << pipeline.getTrainingTime() << endl;
return true;
}
bool computeFeatureWeights( CommandLineParser &parser ){
infoLog << "Computing feature weights..." << endl;
string resultsFilename = "";
string modelFilename = "";
bool combineWeights = false;
//Get the model filename
if( !parser.get("model-filename",modelFilename) ){
errorLog << "Failed to parse filename from command line! You can set the model filename using the --model." << endl;
printUsage();
return false;
}
//Get the results filename
if( !parser.get("filename",resultsFilename) ){
errorLog << "Failed to parse results filename from command line! You can set the results filename using the -f." << endl;
printUsage();
return false;
}
//Get the results filename
parser.get("combine-weights",combineWeights);
//Load the model
GestureRecognitionPipeline pipeline;
if( !pipeline.load( modelFilename ) ){
errorLog << "Failed to load model from file: " << modelFilename << endl;
printUsage();
return false;
}
//Make sure the pipeline contains a random forest model and that it is trained
RandomForests *forest = pipeline.getClassifier< RandomForests >();
if( !forest ){
errorLog << "Model loaded, but the pipeline does not contain a RandomForests classifier!" << endl;
printUsage();
return false;
}
if( !forest->getTrained() ){
errorLog << "Model loaded, but the RandomForests classifier is not trained!" << endl;
printUsage();
return false;
}
//Compute the feature weights
if( combineWeights ){
VectorFloat weights = forest->getFeatureWeights();
if( weights.getSize() == 0 ){
errorLog << "Failed to compute feature weights!" << endl;
printUsage();
return false;
}
//Save the results to a file
fstream file;
file.open( resultsFilename.c_str(), fstream::out );
const unsigned int N = weights.getSize();
for(unsigned int i=0; i<N; i++){
file << weights[i] << endl;
}
file.close();
}else{
double norm = 0.0;
const unsigned int K = forest->getForestSize();
const unsigned int N = forest->getNumInputDimensions();
VectorFloat tmp( N, 0.0 );
MatrixDouble weights(K,N);
for(unsigned int i=0; i<K; i++){
DecisionTreeNode *tree = forest->getTree(i);
tree->computeFeatureWeights( tmp );
norm = 1.0 / Util::sum( tmp );
for(unsigned int j=0; j<N; j++){
tmp[j] *= norm;
weights[i][j] = tmp[j];
tmp[j] = 0;
}
}
//Save the results to a file
weights.save( resultsFilename );
}
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 updateVariability(double new_null_rej) {
pipeline.getClassifier()->setNullRejectionCoeff(new_null_rej);
pipeline.getClassifier()->recomputeNullRejectionThresholds();
}
