nnet-train-simple.cc File Reference

#include "base/kaldi-common.h"
#include "util/common-utils.h"
#include "hmm/transition-model.h"
#include "nnet2/train-nnet.h"
#include "nnet2/am-nnet.h"

Include dependency graph for nnet-train-simple.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 27 of file nnet-train-simple.cc.

References ParseOptions::GetArg(), AmNnet::GetNnet(), KALDI_LOG, ParseOptions::NumArgs(), ParseOptions::PrintUsage(), AmNnet::Read(), ParseOptions::Read(), TransitionModel::Read(), NnetSimpleTrainerConfig::Register(), ParseOptions::Register(), Output::Stream(), Input::Stream(), kaldi::nnet2::TrainNnetSimple(), AmNnet::Write(), TransitionModel::Write(), and Nnet::ZeroStats().

                                 {
  try {
    using namespace kaldi;
    using namespace kaldi::nnet2;
    typedef kaldi::int32 int32;
    typedef kaldi::int64 int64;

    const char *usage =
        "Train the neural network parameters with backprop and stochastic\n"
        "gradient descent using minibatches.  Training examples would be\n"
        "produced by nnet-get-egs.\n"
        "\n"
        "Usage:  nnet-train-simple [options] <model-in> <training-examples-in> <model-out>\n"
        "\n"
        "e.g.:\n"
        "nnet-train-simple 1.nnet ark:1.egs 2.nnet\n";
    
    bool binary_write = true;
    bool zero_stats = true;
    int32 srand_seed = 0;
    std::string use_gpu = "yes";
    NnetSimpleTrainerConfig train_config;
    
    ParseOptions po(usage);
    po.Register("binary", &binary_write, "Write output in binary mode");
    po.Register("zero-stats", &zero_stats, "If true, zero occupation "
                "counts stored with the neural net (only affects mixing up).");
    po.Register("srand", &srand_seed, "Seed for random number generator "
                "(relevant if you have layers of type AffineComponentPreconditioned "
                "with l2-penalty != 0.0");
    po.Register("use-gpu", &use_gpu,
                "yes|no|optional|wait, only has effect if compiled with CUDA");
    
    train_config.Register(&po);
    
    po.Read(argc, argv);
    
    if (po.NumArgs() != 3) {
      po.PrintUsage();
      exit(1);
    }
    srand(srand_seed);
    
#if HAVE_CUDA==1
    CuDevice::Instantiate().SelectGpuId(use_gpu);
#endif

    std::string nnet_rxfilename = po.GetArg(1),
        examples_rspecifier = po.GetArg(2),
        nnet_wxfilename = po.GetArg(3);

    int64 num_examples;
    
    {
      TransitionModel trans_model;
      AmNnet am_nnet;
      {
        bool binary_read;
        Input ki(nnet_rxfilename, &binary_read);
        trans_model.Read(ki.Stream(), binary_read);
        am_nnet.Read(ki.Stream(), binary_read);
      }

      if (zero_stats) am_nnet.GetNnet().ZeroStats();

      SequentialNnetExampleReader example_reader(examples_rspecifier);
      
      num_examples = TrainNnetSimple(train_config, &(am_nnet.GetNnet()),
                                     &example_reader);
    
      {
        Output ko(nnet_wxfilename, binary_write);
        trans_model.Write(ko.Stream(), binary_write);
        am_nnet.Write(ko.Stream(), binary_write);
      }
    }
#if HAVE_CUDA==1
    CuDevice::Instantiate().PrintProfile();
#endif
    
    KALDI_LOG << "Finished training, processed " << num_examples
              << " training examples.  Wrote model to "
              << nnet_wxfilename;
    return (num_examples == 0 ? 1 : 0);
  } catch(const std::exception &e) {
    std::cerr << e.what() << '\n';
    return -1;
  }
}