summaryrefslogtreecommitdiff
path: root/training/mpi_compute_cllh.cc
diff options
context:
space:
mode:
authorChris Dyer <cdyer@allegro.clab.cs.cmu.edu>2012-11-18 13:35:42 -0500
committerChris Dyer <cdyer@allegro.clab.cs.cmu.edu>2012-11-18 13:35:42 -0500
commit1b8181bf0d6e9137e6b9ccdbe414aec37377a1a9 (patch)
tree33e5f3aa5abff1f41314cf8f6afbd2c2c40e4bfd /training/mpi_compute_cllh.cc
parent7c4665949fb93fb3de402e4ce1d19bef67850d05 (diff)
major restructure of the training code
Diffstat (limited to 'training/mpi_compute_cllh.cc')
-rw-r--r--training/mpi_compute_cllh.cc134
1 files changed, 0 insertions, 134 deletions
diff --git a/training/mpi_compute_cllh.cc b/training/mpi_compute_cllh.cc
deleted file mode 100644
index 066389d0..00000000
--- a/training/mpi_compute_cllh.cc
+++ /dev/null
@@ -1,134 +0,0 @@
-#include <iostream>
-#include <vector>
-#include <cassert>
-#include <cmath>
-
-#include "config.h"
-#ifdef HAVE_MPI
-#include <boost/mpi.hpp>
-#endif
-#include <boost/program_options.hpp>
-#include <boost/program_options/variables_map.hpp>
-
-#include "cllh_observer.h"
-#include "sentence_metadata.h"
-#include "verbose.h"
-#include "hg.h"
-#include "prob.h"
-#include "inside_outside.h"
-#include "ff_register.h"
-#include "decoder.h"
-#include "filelib.h"
-#include "weights.h"
-
-using namespace std;
-namespace po = boost::program_options;
-
-bool InitCommandLine(int argc, char** argv, po::variables_map* conf) {
- po::options_description opts("Configuration options");
- opts.add_options()
- ("weights,w",po::value<string>(),"Input feature weights file")
- ("training_data,t",po::value<string>(),"Training data corpus")
- ("decoder_config,c",po::value<string>(),"Decoder configuration file");
- po::options_description clo("Command line options");
- clo.add_options()
- ("config", po::value<string>(), "Configuration file")
- ("help,h", "Print this help message and exit");
- po::options_description dconfig_options, dcmdline_options;
- dconfig_options.add(opts);
- dcmdline_options.add(opts).add(clo);
-
- po::store(parse_command_line(argc, argv, dcmdline_options), *conf);
- if (conf->count("config")) {
- ifstream config((*conf)["config"].as<string>().c_str());
- po::store(po::parse_config_file(config, dconfig_options), *conf);
- }
- po::notify(*conf);
-
- if (conf->count("help") || !conf->count("training_data") || !conf->count("decoder_config")) {
- cerr << dcmdline_options << endl;
- return false;
- }
- return true;
-}
-
-void ReadInstances(const string& fname, int rank, int size, vector<string>* c) {
- assert(fname != "-");
- ReadFile rf(fname);
- istream& in = *rf.stream();
- string line;
- int lc = 0;
- while(in) {
- getline(in, line);
- if (!in) break;
- if (lc % size == rank) c->push_back(line);
- ++lc;
- }
-}
-
-static const double kMINUS_EPSILON = -1e-6;
-
-#ifdef HAVE_MPI
-namespace mpi = boost::mpi;
-#endif
-
-int main(int argc, char** argv) {
-#ifdef HAVE_MPI
- mpi::environment env(argc, argv);
- mpi::communicator world;
- const int size = world.size();
- const int rank = world.rank();
-#else
- const int size = 1;
- const int rank = 0;
-#endif
- if (size > 1) SetSilent(true); // turn off verbose decoder output
- register_feature_functions();
-
- po::variables_map conf;
- if (!InitCommandLine(argc, argv, &conf))
- return false;
-
- // load cdec.ini and set up decoder
- ReadFile ini_rf(conf["decoder_config"].as<string>());
- Decoder decoder(ini_rf.stream());
- if (decoder.GetConf()["input"].as<string>() != "-") {
- cerr << "cdec.ini must not set an input file\n";
- abort();
- }
-
- // load weights
- vector<weight_t>& weights = decoder.CurrentWeightVector();
- if (conf.count("weights"))
- Weights::InitFromFile(conf["weights"].as<string>(), &weights);
-
- vector<string> corpus;
- ReadInstances(conf["training_data"].as<string>(), rank, size, &corpus);
- assert(corpus.size() > 0);
-
- if (rank == 0)
- cerr << "Each processor is decoding ~" << corpus.size() << " training examples...\n";
-
- ConditionalLikelihoodObserver observer;
- for (int i = 0; i < corpus.size(); ++i)
- decoder.Decode(corpus[i], &observer);
-
- double objective = 0;
- unsigned total_words = 0;
-#ifdef HAVE_MPI
- reduce(world, observer.acc_obj, objective, std::plus<double>(), 0);
- reduce(world, observer.trg_words, total_words, std::plus<unsigned>(), 0);
-#else
- objective = observer.acc_obj;
-#endif
-
- if (rank == 0) {
- cout << "CONDITIONAL LOG_e LIKELIHOOD: " << objective << endl;
- cout << "CONDITIONAL LOG_2 LIKELIHOOD: " << (objective/log(2)) << endl;
- cout << " CONDITIONAL ENTROPY: " << (objective/log(2) / total_words) << endl;
- cout << " PERPLEXITY: " << pow(2, (objective/log(2) / total_words)) << endl;
- }
-
- return 0;
-}
-