C++ BaseLearner::run方法代码示例

    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.........

	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.........

	float BanditProductLearner::run()
	{
		if ( ! this->_banditAlgo->isInitialized() ) {
			init();
		}
		// the bandit algorithm selects the subset the tree learner is allowed to use
		// the armindexes will be stored in _armsForPulling
		getArms();

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

		// Backup original labels
		for (int i = 0; i < numExamples; ++i) {
			const vector<Label>& labels = _pTrainingData->getLabels(i);
			vector<char> exampleLabels;
			for (int l = 0; l < numClasses; ++l)
				exampleLabels.push_back(labels[l].y);
			_savedLabels.push_back(exampleLabels);
		}

		for(int ib = 0; ib < _numBaseLearners; ++ib)
			_baseLearners[ib]->setTrainingData(_pTrainingData);

		float energy = numeric_limits<float>::max();
		float previousEnergy, hx, previousAlpha;
		BaseLearner* pPreviousBaseLearner = 0;

		bool firstLoop = true;
		int ib = -1;
		while (1) {
			ib += 1;
			if (ib >= _numBaseLearners) {
				ib = 0;
				firstLoop = false;
			}
			previousEnergy = energy;
			previousAlpha = _alpha;
			if (pPreviousBaseLearner)
				delete pPreviousBaseLearner;
			if ( !firstLoop ) {
				// take the old learner off the labels
				for (int i = 0; i < numExamples; ++i) {
					vector<Label>& labels = _pTrainingData->getLabels(i);
					for (int l = 0; l < numClasses; ++l) {
						// Here we could have the option of using confidence rated setting so the
						// real valued output of classify instead of its sign
						hx = _baseLearners[ib]->classify(_pTrainingData,i,l);
						if ( hx < 0 )
							labels[l].y *= -1;
						else if ( hx == 0 ) { // have to redo the multiplications, haven't been tested
							for(int ib1 = 0; ib1 < _numBaseLearners && labels[l].y != 0; ++ib1) {
								if (ib != ib1) {
									hx = _baseLearners[ib1]->classify(_pTrainingData,i,l);
									if (hx < 0)
										labels[l].y *= -1;
									else if (hx == 0)
										labels[l].y = 0;
								}
							}
						}
					}
				}
			}
			pPreviousBaseLearner = _baseLearners[ib]->copyState();
			energy = dynamic_cast< FeaturewiseLearner* >(_baseLearners[ib])->run(_armsForPulling );
			// check if it is signailing_nan
			if ( energy != energy )
			{
				if (_verbose > 2) {
					cout << "Cannot find weak hypothesis, constant learner is used!!" << endl;
				}
				BaseLearner* pConstantWeakHypothesisSource = 
					BaseLearner::RegisteredLearners().getLearner("ConstantLearner");
				BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
				pConstantWeakHypothesis->setTrainingData( _pTrainingData );
				energy = pConstantWeakHypothesis->run();
				
				delete _baseLearners[ib];
				_baseLearners[ib] = pConstantWeakHypothesis;
				
			}
			_alpha = _baseLearners[ib]->getAlpha();
			if (_verbose > 2) {
				cout << "E[" << (ib+1) <<  "] = " << energy << endl << flush;
				cout << "alpha[" << (ib+1) <<  "] = " << _alpha << endl << flush;
			}
			for (int i = 0; i < numExamples; ++i) {
				vector<Label>& labels = _pTrainingData->getLabels(i);
				for (int l = 0; l < numClasses; ++l) {
					// Here we could have the option of using confidence rated setting so the
					// real valued output of classify instead of its sign
					if (labels[l].y != 0) { // perhaps replace it by nor_utils::is_zero(labels[l].y)
						hx = _baseLearners[ib]->classify(_pTrainingData,i,l);
						if ( hx < 0 )
							labels[l].y *= -1;
						else if ( hx == 0 )
							labels[l].y = 0;
					}
				}
//.........这里部分代码省略.........