logprob-to-post.cc File Reference

#include "base/kaldi-common.h"
#include "util/common-utils.h"
#include "gmm/am-diag-gmm.h"
#include "hmm/transition-model.h"
#include "hmm/hmm-utils.h"
#include "hmm/posterior.h"

Include dependency graph for logprob-to-post.cc:

Go to the source code of this file.

Functions
int	main (int argc, char *argv[])

Function Documentation

main()

int main	(	int	argc,
		char *	argv[]
	)

Definition at line 39 of file logprob-to-post.cc.

References VectorBase< Real >::Dim(), SequentialTableReader< Holder >::Done(), kaldi::Exp(), ParseOptions::GetArg(), rnnlm::i, rnnlm::j, KALDI_LOG, SequentialTableReader< Holder >::Key(), SequentialTableReader< Holder >::Next(), ParseOptions::NumArgs(), MatrixBase< Real >::NumRows(), ParseOptions::PrintUsage(), kaldi::RandUniform(), ParseOptions::Read(), ParseOptions::Register(), SequentialTableReader< Holder >::Value(), and TableWriter< Holder >::Write().

                                 {
  using namespace kaldi;
  typedef kaldi::int32 int32;
  try {
    const char *usage =
        "Convert a matrix of log-probabilities (e.g. from nnet-logprob) to posteriors\n"
        "Usage:  logprob-to-post [options] <logprob-matrix-rspecifier> <posteriors-wspecifier>\n"
        "e.g.:\n"
        " nnet-logprob [args] | logprob-to-post ark:- ark:1.post\n"
        "Caution: in this particular example, the output would be posteriors of pdf-ids,\n"
        "rather than transition-ids (c.f. post-to-pdf-post)\n";
    
    ParseOptions po(usage);

    BaseFloat min_post = 0.01;
    bool random_prune = true; // preserve expectations.

    po.Register("min-post", &min_post, "Minimum posterior we will output (smaller "
                "ones are pruned).  Also see --random-prune");
    po.Register("random-prune", &random_prune, "If true, prune posteriors with a "
                "randomized method that preserves expectations.");
    
    po.Read(argc, argv);

    if (po.NumArgs() != 2) {
      po.PrintUsage();
      exit(1);
    }

    std::string logprob_rspecifier = po.GetArg(1);
    std::string posteriors_wspecifier = po.GetArg(2);

    int32 num_done = 0;
    SequentialBaseFloatMatrixReader logprob_reader(logprob_rspecifier);
    PosteriorWriter posterior_writer(posteriors_wspecifier);

    for (; !logprob_reader.Done(); logprob_reader.Next()) {
      num_done++;
      const Matrix<BaseFloat> &logprobs = logprob_reader.Value();
      // Posterior is vector<vector<pair<int32, BaseFloat> > >
      Posterior post(logprobs.NumRows());
      for (int32 i = 0; i < logprobs.NumRows(); i++) {
        SubVector<BaseFloat> row(logprobs, i);
        for (int32 j = 0; j < row.Dim(); j++) {
          BaseFloat p = Exp(row(j));
          if (p >= min_post) {
            post[i].push_back(std::make_pair(j, p));
          } else if (random_prune && (p / min_post) >= RandUniform()) {
            post[i].push_back(std::make_pair(j, min_post));
          }
        }
      }
      posterior_writer.Write(logprob_reader.Key(), post);
    }
    KALDI_LOG << "Converted " << num_done << " log-prob matrices to posteriors.";
    return (num_done != 0 ? 0 : 1);
  } catch(const std::exception &e) {
    std::cerr << e.what();
    return -1;
  }
}