//--------------------------------------------------------------
void ofApp::setup(){
ofSetFrameRate(60);
//Initialize the training and info variables
infoText = "";
trainingClassLabel = 1;
record = false;
//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( 2 );
//Initialize the DTW classifier
ANBC naiveBayes;
//Turn on null rejection, this lets the classifier output the predicted class label of 0 when the likelihood of a gesture is low
naiveBayes.enableNullRejection( false );
//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
naiveBayes.setNullRejectionCoeff( 3 );
//Add the classifier to the pipeline (after we do this, we don't need the naiveBayes instance anymore)
pipeline.setClassifier( naiveBayes );
//Setup the colors for the 3 classes
classColors.resize( 3 );
classColors[0] = ofColor(255, 0, 0);
classColors[1] = ofColor(0, 255, 0);
classColors[2] = ofColor(0, 0, 255);
}
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";
}
int main (int argc, const char * argv[])
{
//Create a new ANBC instance
ANBC anbc;
anbc.setNullRejectionCoeff( 10 );
anbc.enableScaling( true );
anbc.enableNullRejection( true );
//Load some training data to train the classifier
ClassificationData trainingData;
if( !trainingData.loadDatasetFromFile("ANBCTrainingData.grt") ){
cout << "Failed to load training data!\n";
return EXIT_FAILURE;
}
//Use 20% of the training dataset to create a test dataset
ClassificationData testData = trainingData.partition( 80 );
//Train the classifier
bool trainSuccess = anbc.train( trainingData );
if( !trainSuccess ){
cout << "Failed to train classifier!\n";
return EXIT_FAILURE;
}
//Save the ANBC model to a file
bool saveSuccess = anbc.save("ANBCModel.grt");
if( !saveSuccess ){
cout << "Failed to save the classifier model!\n";
return EXIT_FAILURE;
}
//Load the ANBC model from a file
bool loadSuccess = anbc.load("ANBCModel.grt");
if( !loadSuccess ){
cout << "Failed to load the classifier model!\n";
return EXIT_FAILURE;
}
//Use the test dataset to test the ANBC model
double accuracy = 0;
for(UINT i=0; i<testData.getNumSamples(); i++){
//Get the i'th test sample
UINT classLabel = testData[i].getClassLabel();
vector< double > inputVector = testData[i].getSample();
//Perform a prediction using the classifier
bool predictSuccess = anbc.predict( inputVector );
if( !predictSuccess ){
cout << "Failed to perform prediction for test sampel: " << i <<"\n";
return EXIT_FAILURE;
}
//Get the predicted class label
UINT predictedClassLabel = anbc.getPredictedClassLabel();
vector< double > classLikelihoods = anbc.getClassLikelihoods();
vector< double > classDistances = anbc.getClassDistances();
//Update the accuracy
if( classLabel == predictedClassLabel ) accuracy++;
cout << "TestSample: " << i << " ClassLabel: " << classLabel << " PredictedClassLabel: " << predictedClassLabel << endl;
}
cout << "Test Accuracy: " << accuracy/double(testData.getNumSamples())*100.0 << "%" << endl;
return EXIT_SUCCESS;
}
