C++ OutputInfo::initialize方法代码示例

void MDDAGClassifier::saveLikelihoods(const string& dataFileName, const string& shypFileName,
                                      const string& outFileName, int numIterations)
{
    InputData* pData = loadInputData(dataFileName, shypFileName);

    if (_verbose > 0)
        cout << "Loading strong hypothesis..." << flush;

    // The class that loads the weak hypotheses
    UnSerialization us;

    // Where to put the weak hypotheses
    vector<BaseLearner*> weakHypotheses;

    // loads them
    us.loadHypotheses(shypFileName, weakHypotheses, pData);

    // where the results go
    vector< ExampleResults* > results;

    if (_verbose > 0)
        cout << "Classifying..." << flush;

    const int numClasses = pData->getNumClasses();
    const int numExamples = pData->getNumExamples();


    ofstream outFile(outFileName.c_str());
    string exampleName;

    if (_verbose > 0)
        cout << "Output likelihoods..." << flush;

    // get the results
    /////////////////////////////////////////////////////////////////////
    // computeResults( pData, weakHypotheses, results, numIterations );
    assert( !weakHypotheses.empty() );

    // Initialize the output info
    OutputInfo* pOutInfo = NULL;

    if ( !_outputInfoFile.empty() )
        pOutInfo = new OutputInfo(_outputInfoFile, "err");

    // Creating the results structures. See file Structures.h for the
    // PointResults structure
    results.clear();
    results.reserve(numExamples);
    for (int i = 0; i < numExamples; ++i)
        results.push_back( new ExampleResults(i, numClasses) );

    // sum votes for classes
    vector< AlphaReal > votesForExamples( numClasses );
    vector< AlphaReal > expVotesForExamples( numClasses );

    // iterator over all the weak hypotheses
    vector<BaseLearner*>::const_iterator whyIt;
    int t;

    pOutInfo->initialize( pData );

    // for every feature: 1..T
    for (whyIt = weakHypotheses.begin(), t = 0;
            whyIt != weakHypotheses.end() && t < numIterations; ++whyIt, ++t)
    {
        BaseLearner* currWeakHyp = *whyIt;
        AlphaReal alpha = currWeakHyp->getAlpha();

        // for every point
        for (int i = 0; i < numExamples; ++i)
        {
            // a reference for clarity and speed
            vector<AlphaReal>& currVotesVector = results[i]->getVotesVector();

            // for every class
            for (int l = 0; l < numClasses; ++l)
                currVotesVector[l] += alpha * currWeakHyp->classify(pData, i, l);
        }

        // if needed output the step-by-step information
        if ( pOutInfo )
        {
            pOutInfo->outputIteration(t);
            pOutInfo->outputCustom(pData, currWeakHyp);

            // Margins and edge requires an update of the weight,
            // therefore I keep them out for the moment
            //outInfo.outputMargins(pData, currWeakHyp);
            //outInfo.outputEdge(pData, currWeakHyp);

            pOutInfo->endLine();

        } // for (int i = 0; i < numExamples; ++i)
        // calculate likelihoods from votes

        fill( votesForExamples.begin(), votesForExamples.end(), 0.0 );
        AlphaReal lLambda = 0.0;
        for (int i = 0; i < numExamples; ++i)
        {
            // a reference for clarity and speed
//.........这里部分代码省略.........

// Returns the results into ptRes
void MDDAGClassifier::computeResults(InputData* pData, vector<BaseLearner*>& weakHypotheses,
                                     vector< ExampleResults* >& results, int numIterations)
{
    assert( !weakHypotheses.empty() );

    const int numClasses = pData->getNumClasses();
    const int numExamples = pData->getNumExamples();

    // Initialize the output info
    OutputInfo* pOutInfo = NULL;

    if ( !_outputInfoFile.empty() )
    {
        if ( _args.getNumValues("outputinfo") > 1 )
        {
            pOutInfo = new OutputInfo(_args);;
        }
        else
        {
            pOutInfo = new OutputInfo(_outputInfoFile, "e01hamauc", false);
        }

    }


    // Creating the results structures. See file Structures.h for the
    // PointResults structure
    results.clear();
    results.reserve(numExamples);
    for (int i = 0; i < numExamples; ++i)
        results.push_back( new ExampleResults(i, numClasses) );

    // iterator over all the weak hypotheses
    vector<BaseLearner*>::const_iterator whyIt;
    int t;

    if ( pOutInfo )
    {
        pOutInfo->initialize( pData );
        pOutInfo->outputHeader(pData->getClassMap(),
                               true, // output iterations
                               false, // output time
                               true // endline
                              );
    }

    // for every feature: 1..T
    for (whyIt = weakHypotheses.begin(), t = 0;
            whyIt != weakHypotheses.end() && t < numIterations; ++whyIt, ++t)
    {
        BaseLearner* currWeakHyp = *whyIt;
        AlphaReal alpha = currWeakHyp->getAlpha();

        // for every point
        for (int i = 0; i < numExamples; ++i)
        {
            // a reference for clarity and speed
            vector<AlphaReal>& currVotesVector = results[i]->getVotesVector();

            // for every class
            for (int l = 0; l < numClasses; ++l)
                currVotesVector[l] += alpha * currWeakHyp->classify(pData, i, l);
        }

        // if needed output the step-by-step information
        if ( pOutInfo )
        {
            pOutInfo->outputIteration(t);
            //				pOutInfo->outputError(pData, currWeakHyp);
            //				pOutInfo->outTPRFPR(pData);
            //pOutInfo->outputBalancedError(pData, currWeakHyp);
            //				if ( ( t % 1 ) == 0 ) {
            //					pOutInfo->outputROC(pData);
            //				}

            pOutInfo->outputCustom(pData, currWeakHyp);
            // Margins and edge requires an update of the weight,
            // therefore I keep them out for the moment
            //outInfo.outputMargins(pData, currWeakHyp);
            //outInfo.outputEdge(pData, currWeakHyp);
            pOutInfo->endLine();
        }
    }

    if (pOutInfo)
        delete pOutInfo;

}

    void FilterBoostLearner::run(const nor_utils::Args& args)
    {
        // load the arguments
        this->getArgs(args);

        time_t startTime, currentTime;
        time(&startTime);

        // get the registered weak learner (type from name)
        BaseLearner* pWeakHypothesisSource = 
            BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
        // initialize learning options; normally it's done in the strong loop
        // also, here we do it for Product learners, so input data can be created
        pWeakHypothesisSource->initLearningOptions(args);

        BaseLearner* pConstantWeakHypothesisSource = 
            BaseLearner::RegisteredLearners().getLearner("ConstantLearner");

        // get the training input data, and load it

        InputData* pTrainingData = pWeakHypothesisSource->createInputData();
        pTrainingData->initOptions(args);
        pTrainingData->load(_trainFileName, IT_TRAIN, _verbose);

        const int numClasses = pTrainingData->getNumClasses();
        const int numExamples = pTrainingData->getNumExamples();
                
        //initialize the margins variable
        _margins.resize( numExamples );
        for( int i=0; i<numExamples; i++ )
        {
            _margins[i].resize( numClasses );
            fill( _margins[i].begin(), _margins[i].end(), 0.0 );
        }


        // get the testing input data, and load it
        InputData* pTestData = NULL;
        if ( !_testFileName.empty() )
        {
            pTestData = pWeakHypothesisSource->createInputData();
            pTestData->initOptions(args);
            pTestData->load(_testFileName, IT_TEST, _verbose);
        }

        // The output information object
        OutputInfo* pOutInfo = NULL;


        if ( !_outputInfoFile.empty() ) 
        {
            // Baseline: constant classifier - goes into 0th iteration

            BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
            pConstantWeakHypothesis->initLearningOptions(args);
            pConstantWeakHypothesis->setTrainingData(pTrainingData);
            AlphaReal constantEnergy = pConstantWeakHypothesis->run();

            pOutInfo = new OutputInfo(args);
            pOutInfo->initialize(pTrainingData);

            updateMargins( pTrainingData, pConstantWeakHypothesis );

            if (pTestData)
                pOutInfo->initialize(pTestData);
            pOutInfo->outputHeader(pTrainingData->getClassMap() );

            pOutInfo->outputIteration(-1);
            pOutInfo->outputCustom(pTrainingData, pConstantWeakHypothesis);

            if (pTestData)
            {
                pOutInfo->separator();
                pOutInfo->outputCustom(pTestData, pConstantWeakHypothesis);
            }
                        
            pOutInfo->outputCurrentTime();

            pOutInfo->endLine();
            pOutInfo->initialize(pTrainingData);
                        
            if (pTestData)
                pOutInfo->initialize(pTestData);
        }
        // reload the previously found weak learners if -resume is set. 
        // otherwise just return 0
        int startingIteration = resumeWeakLearners(pTrainingData);


        Serialization ss(_shypFileName, _isShypCompressed );
        ss.writeHeader(_baseLearnerName); // this must go after resumeProcess has been called

        // perform the resuming if necessary. If not it will just return
        resumeProcess(ss, pTrainingData, pTestData, pOutInfo);

        if (_verbose == 1)
            cout << "Learning in progress..." << endl;
                                
        ///////////////////////////////////////////////////////////////////////
        // Starting the AdaBoost main loop
//.........这里部分代码省略.........

//.........这里部分代码省略.........
		InputData* pAutoassociativeData = new InputData();
		pAutoassociativeData->initOptions(args);
		pAutoassociativeData->load(autoassociativeFileName,IT_TRAIN,verbose);
		
		// for the original labels
		InputData* pLabelsData = new InputData();
		pLabelsData->initOptions(args);
		pLabelsData->load(labelsFileName,IT_TRAIN,verbose);
		
		// set up all the InputData members identically to pAutoassociativeData
		EncodeData* pOnePoint = new EncodeData();
		pOnePoint->initOptions(args);
		pOnePoint->load(autoassociativeFileName,IT_TRAIN,verbose);
		
		const int numExamples = pAutoassociativeData->getNumExamples();
		BaseLearner* pWeakHypothesisSource = 
		BaseLearner::RegisteredLearners().getLearner("ParasiteLearner");
		pWeakHypothesisSource->declareArguments(args);
		
		ParasiteLearner* pWeakHypothesis;
		
		ofstream outFile(outputFileName.c_str());
		if (!outFile.is_open())
		{
			cerr << "ERROR: Cannot open strong hypothesis file <" << outputFileName << ">!" << endl;
			exit(1);
		}
		
		for (int i = 0; i < numExamples ; ++i)
		{
			vector<float> alphas;
			alphas.resize(numBaseLearners);
			fill(alphas.begin(), alphas.end(), 0);
			
			if (verbose >= 1)
				cout << "--> Encoding example no " << (i+1) << endl;
			pOnePoint->resetData();
			pOnePoint->addExample( pAutoassociativeData->getExample(i) );
			AlphaReal energy = 1;
			
			OutputInfo* pOutInfo = NULL;
			if ( args.hasArgument("outputinfo") ) 
			{
				args.getValue("outputinfo", 0, outputInfoFile);
				pOutInfo = new OutputInfo(args);
				pOutInfo->initialize(pOnePoint);
			}
			
			
			for (int t = 0; t < numIterations; ++t)
			{
				pWeakHypothesis = (ParasiteLearner*)pWeakHypothesisSource->create();
				pWeakHypothesis->initLearningOptions(args);
				pWeakHypothesis->setTrainingData(pOnePoint);
				energy *= pWeakHypothesis->run();
				// 	    if (verbose >= 2)
				//  	       cout << "energy = " << energy << endl << flush;
				AdaBoostMHLearner adaBoostMHLearner;
				
				if (i == 0 && t == 0)
				{
					if ( pWeakHypothesis->getBaseLearners().size() < numBaseLearners )
						numBaseLearners = pWeakHypothesis->getBaseLearners().size();
					outFile << "%Hidden representation using autoassociative boosting" << endl << endl;
					outFile << "@RELATION " << outputFileName << endl << endl;
					outFile << "% numBaseLearners" << endl;
					for (int j = 0; j < numBaseLearners; ++j) 
						outFile << "@ATTRIBUTE " << j << "_" <<
						pWeakHypothesis->getBaseLearners()[j]->getId() << " NUMERIC" << endl;
					outFile << "@ATTRIBUTE class {" << pLabelsData->getClassMap().getNameFromIdx(0);
					for (int l = 1; l < pLabelsData->getClassMap().getNumNames(); ++l)
						outFile << ", " << pLabelsData->getClassMap().getNameFromIdx(l);
					outFile << "}" << endl<< endl<< "@DATA" << endl;
				}
				alphas[pWeakHypothesis->getSelectedIndex()] += 
				pWeakHypothesis->getAlpha() * pWeakHypothesis->getSignOfAlpha();
				if ( pOutInfo )
					adaBoostMHLearner.printOutputInfo(pOutInfo, t, pOnePoint, NULL, pWeakHypothesis);
				adaBoostMHLearner.updateWeights(pOnePoint,pWeakHypothesis);
			}
			float sumAlphas = 0;
			for (int j = 0; j < numBaseLearners; ++j)
				sumAlphas += alphas[j];
			
			for (int j = 0; j < numBaseLearners; ++j)
				outFile << alphas[j]/sumAlphas << ",";
			const vector<Label>& labels = pLabelsData->getLabels(i);
			for (int l = 0; l < labels.size(); ++l)
				if (labels[l].y > 0)
					outFile << pLabelsData->getClassMap().getNameFromIdx(labels[l].idx) << endl;
			delete pOutInfo;
		}
		outFile.close();
	}
	
	if (pModel)
		delete pModel;
	
	return 0;
}

	void FilterBoostLearner::run(const nor_utils::Args& args)
	{
		// load the arguments
		this->getArgs(args);

		time_t startTime, currentTime;
		time(&startTime);

		// get the registered weak learner (type from name)
		BaseLearner* pWeakHypothesisSource = 
			BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
		// initialize learning options; normally it's done in the strong loop
		// also, here we do it for Product learners, so input data can be created
		pWeakHypothesisSource->initLearningOptions(args);

		BaseLearner* pConstantWeakHypothesisSource = 
			BaseLearner::RegisteredLearners().getLearner("ConstantLearner");

		// get the training input data, and load it

		InputData* pTrainingData = pWeakHypothesisSource->createInputData();
		pTrainingData->initOptions(args);
		pTrainingData->load(_trainFileName, IT_TRAIN, _verbose);

		const int numClasses = pTrainingData->getNumClasses();
		const int numExamples = pTrainingData->getNumExamples();
		
		//initialize the margins variable
		_margins.resize( numExamples );
		for( int i=0; i<numExamples; i++ )
		{
			_margins[i].resize( numClasses );
			fill( _margins[i].begin(), _margins[i].end(), 0.0 );
		}


		// get the testing input data, and load it
		InputData* pTestData = NULL;
		if ( !_testFileName.empty() )
		{
			pTestData = pWeakHypothesisSource->createInputData();
			pTestData->initOptions(args);
			pTestData->load(_testFileName, IT_TEST, _verbose);
		}

		// The output information object
		OutputInfo* pOutInfo = NULL;


		if ( !_outputInfoFile.empty() ) 
		{
			// Baseline: constant classifier - goes into 0th iteration

			BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
			pConstantWeakHypothesis->initLearningOptions(args);
			pConstantWeakHypothesis->setTrainingData(pTrainingData);
			float constantEnergy = pConstantWeakHypothesis->run();

			pOutInfo = new OutputInfo(_outputInfoFile);
			pOutInfo->initialize(pTrainingData);

			updateMargins( pTrainingData, pConstantWeakHypothesis );

			if (pTestData)
				pOutInfo->initialize(pTestData);
			pOutInfo->outputHeader();

			pOutInfo->outputIteration(-1);
			pOutInfo->outputError(pTrainingData, pConstantWeakHypothesis);

			if (pTestData)
				pOutInfo->outputError(pTestData, pConstantWeakHypothesis);
			/*
			pOutInfo->outputMargins(pTrainingData, pConstantWeakHypothesis);
			
			pOutInfo->outputEdge(pTrainingData, pConstantWeakHypothesis);

			if (pTestData)
				pOutInfo->outputMargins(pTestData, pConstantWeakHypothesis);

			pOutInfo->outputMAE(pTrainingData);

			if (pTestData)
				pOutInfo->outputMAE(pTestData);
			*/
			pOutInfo->outputCurrentTime();

			pOutInfo->endLine();
			pOutInfo->initialize(pTrainingData);
			
			if (pTestData)
				pOutInfo->initialize(pTestData);
		}
		// reload the previously found weak learners if -resume is set. 
		// otherwise just return 0
		int startingIteration = resumeWeakLearners(pTrainingData);


		Serialization ss(_shypFileName, _isShypCompressed );
		ss.writeHeader(_baseLearnerName); // this must go after resumeProcess has been called
//.........这里部分代码省略.........

	void AdaBoostMHLearner::run(const nor_utils::Args& args)
	{
		// load the arguments
		this->getArgs(args);

		// get the registered weak learner (type from name)
		BaseLearner* pWeakHypothesisSource = 
			BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
		// initialize learning options; normally it's done in the strong loop
		// also, here we do it for Product learners, so input data can be created
		pWeakHypothesisSource->initLearningOptions(args);

		BaseLearner* pConstantWeakHypothesisSource = 
			BaseLearner::RegisteredLearners().getLearner("ConstantLearner");

		// get the training input data, and load it

		InputData* pTrainingData = pWeakHypothesisSource->createInputData();
		pTrainingData->initOptions(args);
		pTrainingData->load(_trainFileName, IT_TRAIN, _verbose);
		
		// get the testing input data, and load it
		InputData* pTestData = NULL;
		if ( !_testFileName.empty() )
		{
			pTestData = pWeakHypothesisSource->createInputData();
			pTestData->initOptions(args);
			pTestData->load(_testFileName, IT_TEST, _verbose);
		}

		// The output information object
		OutputInfo* pOutInfo = NULL;


		if ( !_outputInfoFile.empty() ) 
		{
			// Baseline: constant classifier - goes into 0th iteration

			BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
			pConstantWeakHypothesis->initLearningOptions(args);
			pConstantWeakHypothesis->setTrainingData(pTrainingData);
			AlphaReal constantEnergy = pConstantWeakHypothesis->run();

			//pOutInfo = new OutputInfo(_outputInfoFile);
            pOutInfo = new OutputInfo(args);
			pOutInfo->initialize(pTrainingData);

			if (pTestData)
				pOutInfo->initialize(pTestData);
			pOutInfo->outputHeader(pTrainingData->getClassMap());

			pOutInfo->outputIteration(-1);
            pOutInfo->outputCustom(pTrainingData, pConstantWeakHypothesis);
            
			if (pTestData != NULL)
            {
                pOutInfo->separator();
                pOutInfo->outputCustom(pTestData, pConstantWeakHypothesis);   
            }

			pOutInfo->outputCurrentTime();

			pOutInfo->endLine(); 
			pOutInfo->initialize(pTrainingData);

			if (pTestData)
				pOutInfo->initialize(pTestData);
		}
		//cout << "Before serialization" << endl;
		// reload the previously found weak learners if -resume is set. 
		// otherwise just return 0
		int startingIteration = resumeWeakLearners(pTrainingData);


		Serialization ss(_shypFileName, _isShypCompressed );
		ss.writeHeader(_baseLearnerName); // this must go after resumeProcess has been called

		// perform the resuming if necessary. If not it will just return
		resumeProcess(ss, pTrainingData, pTestData, pOutInfo);

		if (_verbose == 1)
			cout << "Learning in progress..." << endl;

		//I put here the starting time, but it may take very long time to load the saved model
		time_t startTime, currentTime;
		time(&startTime);

		///////////////////////////////////////////////////////////////////////
		// Starting the AdaBoost main loop
		///////////////////////////////////////////////////////////////////////
		for (int t = startingIteration; t < _numIterations; ++t)
		{
			if (_verbose > 1)
				cout << "------- WORKING ON ITERATION " << (t+1) << " -------" << endl;

			BaseLearner* pWeakHypothesis = pWeakHypothesisSource->create();
			pWeakHypothesis->initLearningOptions(args);
			//pTrainingData->clearIndexSet();

			pWeakHypothesis->setTrainingData(pTrainingData);
//.........这里部分代码省略.........

    void SoftCascadeLearner::run(const nor_utils::Args& args)
    {
        // load the arguments
        this->getArgs(args);
        
        //print cascade properties
        if (_verbose > 0) {
            cout    << "[+] Softcascade parameters :" << endl
                    << "\t --> target detection rate = " << _targetDetectionRate << endl
                    << "\t --> alpha (exp param) = " << _alphaExponentialParameter << endl
                    << "\t --> bootstrap rate = " << _bootstrapRate << endl
                    << endl;
        }
        

        // get the registered weak learner (type from name)
        BaseLearner* pWeakHypothesisSource = 
            BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
        // initialize learning options; normally it's done in the strong loop
        // also, here we do it for Product learners, so input data can be created
        pWeakHypothesisSource->initLearningOptions(args);

        // get the training input data, and load it

        InputData* pTrainingData = pWeakHypothesisSource->createInputData();
        pTrainingData->initOptions(args);
        pTrainingData->load(_trainFileName, IT_TRAIN, 5);

        InputData* pBootstrapData = NULL;
        if (!_bootstrapFileName.empty()) {
            pBootstrapData = pWeakHypothesisSource->createInputData();
            pBootstrapData->initOptions(args);
            pBootstrapData->load(_bootstrapFileName, IT_TRAIN, 5);
        }
        
        // get the testing input data, and load it
        InputData* pTestData = NULL;
        if ( !_testFileName.empty() )
        {
            pTestData = pWeakHypothesisSource->createInputData();
            pTestData->initOptions(args);
            pTestData->load(_testFileName, IT_TEST, 5);
        }

        Serialization ss(_shypFileName, false );
        ss.writeHeader(_baseLearnerName);
        
        
//        outputHeader();
        // The output information object
        OutputInfo* pOutInfo = NULL;

        if ( !_outputInfoFile.empty() ) 
        {
            pOutInfo = new OutputInfo(args, true);
            pOutInfo->setOutputList("sca", &args);
            
            pOutInfo->initialize(pTrainingData);
            
            if (pTestData)
                pOutInfo->initialize(pTestData);
            pOutInfo->outputHeader(pTrainingData->getClassMap(), true, true, false);
            pOutInfo->outputUserHeader("thresh");
            pOutInfo->headerEndLine();
        }
        
        
//        ofstream trainPosteriorsFile;
//        ofstream testPosteriorsFile;
        
        
        const NameMap& namemap = pTrainingData->getClassMap();
        _positiveLabelIndex = namemap.getIdxFromName(_positiveLabelName);

        // FIXME: output posteriors

//        OutputInfo* pTrainPosteriorsOut = NULL;
//        OutputInfo* pTestPosteriorsOut = NULL;
        
//        if (! _trainPosteriorsFileName.empty()) {
//            pTrainPosteriorsOut = new OutputInfo(_trainPosteriorsFileName, "pos", true);
//            pTrainPosteriorsOut->initialize(pTrainingData);
//            dynamic_cast<PosteriorsOutput*>( pTrainPosteriorsOut->getOutputInfoObject("pos") )->addClassIndex(_positiveLabelIndex );
//        }
        
//        if (! _testPosteriorsFileName.empty() && !_testFileName.empty() ) {
//            pTestPosteriorsOut = new OutputInfo(_testPosteriorsFileName, "pos", true);
//            pTestPosteriorsOut->initialize(pTestData);
//            dynamic_cast<PosteriorsOutput*>( pTestPosteriorsOut->getOutputInfoObject("pos") )->addClassIndex(_positiveLabelIndex );            
//        }
        
        const int numExamples = pTrainingData->getNumExamples();

        vector<BaseLearner*> inWeakHypotheses;
        
        if (_fullRun) {            
            // TODO : the full training is implementet, testing is needed
            AdaBoostMHLearner* sHypothesis = new AdaBoostMHLearner();
            sHypothesis->run(args, pTrainingData, _baseLearnerName, _numIterations, inWeakHypotheses );
            delete sHypothesis;
//.........这里部分代码省略.........