|| || || || || || || ||

---

mainCrossValidate.cpp

Go to the documentation of this file.

#include "Link/Mpi/MpiFuncs.h"
#include "Core/ApplicationFactory.h"

// since we are not using libraries:
#include "Link/Svm/LinkSvm.cpp"

namespace Impala
{
namespace Application
{

using namespace Core;
using namespace Core::Training;

void WriteResults(Util::PropertySet *properties, DataFactory *dataFactory,
                  String concept, ParameterSearcher *searcher)
{
    if (Link::Mpi::MyId() == 0)
    {
        Util::IOBuffer* buf = dataFactory->MakeBestFileWrite(concept);
        buf->Puts("value:" + MakeString(searcher->GetBestScore()));
        properties->Print(buf);
        delete buf;

        //write allparameters file
        buf = dataFactory->MakeAllParametersFile(concept);
        searcher->PrintAllScores(buf);
        delete buf;
    }
}

void CrossValidate(Util::PropertySet* properties,
                   Training::Factory* trainFactory,
                   DataFactory* dataFactory)
{
    ILOG_VAR(main);
    ILOG_DEBUG_ONCE("start application");
    std::vector<String> conceptList = dataFactory->MakeConceptList();

    for (int i=0 ; i<conceptList.size(); ++i)
    {
        String concept = conceptList[i];
        properties->Add("concept", concept);
        ILOG_INFO_ONCE("starting on concept " << i << ": " << concept);
        // if best file already exists: skip!
        if(!dataFactory->CanMakeBestFile(concept))
        {
            ILOG_INFO_ONCE("bestfile already exists: skipping...");
            continue;
        }

        ILOG_DEBUG_ONCE("loading annotation...");
        Table::AnnotationTable* annotation = dataFactory->MakeAnnotation(concept);
        if(annotation == 0)
        {
            ILOG_INFO("no annotation found for " << concept << ", skipping...");
            continue;
        }
        ILOG_DEBUG("anno size: "<< annotation->Size());
        ILOG_DEBUG_ONCE("creating searcher...");
        ParameterSearcher* searcher =
            trainFactory->MakeSearcher(annotation, dataFactory);
        ILOG_DEBUG_ONCE("starting search...");
        Util::PropertySet results = searcher->Search();

        ILOG_INFO_ONCE("saving results for " << concept);
        WriteResults(&results, dataFactory, concept, searcher);
        delete searcher;
        ILOG_DEBUG_ONCE("deleted searcher");
        delete annotation;
        ILOG_DEBUG_ONCE("deleted annotation");
    }

    return;
}

int mainCrossValidate(int argc, char** argv)
{
    ILOG_VAR(main);
    Link::Mpi::Init(&argc, &argv);
    int retval = 0;
    CmdOptions& options = CmdOptions::GetInstance();
    options.Initialise(false, false, true);
    options.AddOption(0, "start", "index of concept to start with", "0");
    options.AddOption(0, "number", "number of concepts", "-1");
    options.AddOption(0, "concept", "name", "");
    options.AddOption(0, "w1", "number or range", "[log-3:3/10]");
    options.AddOption(0, "w2", "number or range", "[log-3:3/10]");
    options.AddOption(0, "autoweight", "bool", "0");
    options.AddOption(0, "C", "number or range", "1");
    options.AddOption(0, "gamma", "number or range (-1 for 1/feat length)", "-1");
    options.AddOption('r', "repetitions", "number", "2");
    options.AddOption(0, "episode-constrained", "bool", "1");
    options.AddOption(0, "assume-shotid", "bool", "0");
    options.AddOption
        (0, "evaluator",
         "choose from {AP, BAP, AUC, P@N, R@N} where N is number (precision @ n)",
         "AP");
    options.AddOption('f', "folds", "number", "3");
    options.AddOption('m', "cache", "megabytes", "500");
    options.AddOption('p', "probability", "bool", "0");
    options.AddOption
        (0, "kernel",
         "string: [linear,poly,rbf,sigmoid,precomputed,hist,dist-precomputed]",
         "rbf");
    options.AddOption(0, "precompute-kernel", "string: [chi2]", "chi2");
    options.AddOption(0, "maxVideoId", "index", "-1");
    options.AddOption(0, "maxPosPerVideo", "number", "-1");
    options.AddOption(0, "maxNegPerVideo", "number", "-1");
    options.AddOption(0, "dumpFolds", "", "0");
    // prevent dataserver from keeping all ImageArchives open
    options.AddOption(0, "imCacheSize", "size", "1");
    if (options.ParseArgs(argc, argv, "dataSet concepts model featureDef", 4))
    {
        ApplicationFactory factory(&options);
        Util::PropertySet* properties = factory.MakeClassifierProperties();
        Training::Factory* trainFactory = factory.MakeTrainFactory(properties);
        DataFactory* dataFactory = factory.MakeDataFactory();
        /* when we use a distributed kernel matix we assume that node 0 does
           computation while other nodes load the distributed kernel matrix */
        if(options.GetString("kernel") == "dist-precomputed"
           && Link::Mpi::MyId() != 0)
        {
            dataFactory->ServeDistributedAccess();
        }
        else
        {
            // make sure we subscribe, even if we are skipping all concepts;
            // otherwise the program will hang
            if(options.GetString("kernel") == "dist-precomputed") 
                dataFactory->GetDistributedAccess();
            std::cout <<"id: "<< Link::Mpi::MyId() << " ,kernel = "<<
                options.GetString("kernel") << std::endl; 
            CrossValidate(properties, trainFactory, dataFactory);
        }
        ILOG_DEBUG_ONCE("deleting dataFactory");
        delete dataFactory;
        ILOG_DEBUG_ONCE("deleting trainFactory");
        delete trainFactory;
        ILOG_DEBUG_ONCE("deleting properties");
        delete properties;
    }

    Link::Mpi::Finalize();
    return retval;
}

} // namespace Application
} // namespace Impala

int
main(int argc, char* argv[])
{
    return Impala::Application::mainCrossValidate(argc, argv);
}

---