Blame view
src/nnet2bin/nnet-train-simple.cc
3.64 KB
8dcb6dfcb
first commit
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
// nnet2bin/nnet-train-simple.cc
// Copyright 2012 Johns Hopkins University (author: Daniel Povey)
// See ../../COPYING for clarification regarding multiple authors
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// THIS CODE IS PROVIDED *AS IS* BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION ANY IMPLIED
// WARRANTIES OR CONDITIONS OF TITLE, FITNESS FOR A PARTICULAR PURPOSE,
// MERCHANTABLITY OR NON-INFRINGEMENT.
// See the Apache 2 License for the specific language governing permissions and
// limitations under the License.
#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"
int main(int argc, char *argv[]) {
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
"
"gradient descent using minibatches. Training examples would be
"
"produced by nnet-get-egs.
"
"
"
"Usage: nnet-train-simple [options] <model-in> <training-examples-in> <model-out>
"
"
"
"e.g.:
"
"nnet-train-simple 1.nnet ark:1.egs 2.nnet
";
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() << '
';
return -1;
}
}
|