view release on metacpan or  search on metacpan

examples/char_lstm.pl  view on Meta::CPAN

#!/usr/bin/perl
use strict;
use warnings;
use PDL;
use Math::Random::Discrete;
use AI::MXNet qw(mx);
use AI::MXNet::Function::Parameters;
use Getopt::Long qw(HelpMessage);

GetOptions(
    'num-layers=i'   => \(my $num_layers   = 2       ),
    'num-hidden=i'   => \(my $num_hidden   = 256     ),
    'num-embed=i'    => \(my $num_embed    = 10      ),
    'num-seq=i'      => \(my $seq_size     = 60      ),
    'gpus=s'         => \(my $gpus                   ),
    'kv-store=s'     => \(my $kv_store     = 'device'),
    'num-epoch=i'    => \(my $num_epoch    = 25      ),
    'lr=f'           => \(my $lr           = 0.001    ),
    'optimizer=s'    => \(my $optimizer    = 'adam'   ),
    'mom=f'          => \(my $mom          = 0       ),
    'wd=f'           => \(my $wd           = 0.00001 ),
    'batch-size=i'   => \(my $batch_size   = 32      ),
    'disp-batches=i' => \(my $disp_batches = 50      ),
    'chkp-prefix=s'  => \(my $chkp_prefix  = 'lstm_' ),
    'cell-mode=s'    => \(my $cell_mode    = 'LSTM'  ),
    'sample-size=i'  => \(my $sample_size  = 10000   ),
    'chkp-epoch=i'   => \(my $chkp_epoch   = 1       ),
    'bidirectional=i'=> \(my $bidirectional= 0       ),
    'help'           => sub { HelpMessage(0) },
) or HelpMessage(1);

=head1 NAME

    char_lstm.pl - Example of training char LSTM RNN on tiny shakespeare using high level RNN interface
                   with optional inferred sampling (RNN generates Shakespeare like text)

=head1 SYNOPSIS

    --num-layers     number of stacked RNN layers, default=2
    --num-hidden     hidden layer size, default=256
    --num-embed      embed size, default=10
    --num-seq        sequence size, default=60
    --gpus           list of gpus to run, e.g. 0 or 0,2,5. empty means using cpu.
                     Increase batch size when using multiple gpus for best performance.
    --kv-store       key-value store type, default='device'
    --num-epochs     max num of epochs, default=25
    --lr             initial learning rate, default=0.01
    --optimizer      the optimizer type, default='adam'
    --mom            momentum for sgd, default=0.0
    --wd             weight decay for sgd, default=0.00001
    --batch-size     the batch size type, default=32
    --bidirectional  use bidirectional cell, default false (0)
    --disp-batches   show progress for every n batches, default=50
    --chkp-prefix    prefix for checkpoint files, default='lstm_'
    --cell-mode      RNN cell mode (LSTM, GRU, RNN, default=LSTM)
    --sample-size    a size of inferred sample text (default=10000) after each epoch
    --chkp-epoch     save checkpoint after this many epoch, default=1 (saving every checkpoint)

=cut

package AI::MXNet::RNN::IO::ASCIIIterator;
use Mouse;
extends AI::MXNet::DataIter;
has 'data'          => (is => 'ro',  isa => 'PDL',   required => 1);
has 'seq_size'      => (is => 'ro',  isa => 'Int',   required => 1);
has '+batch_size'   => (is => 'ro',  isa => 'Int',   required => 1);
has 'data_name'     => (is => 'ro',  isa => 'Str',   default => 'data');
has 'label_name'    => (is => 'ro',  isa => 'Str',   default => 'softmax_label');
has 'dtype'         => (is => 'ro',  isa => 'Dtype', default => 'float32');
has [qw/nd counter seq_counter vocab_size
    data_size provide_data provide_label idx/] => (is => 'rw', init_arg => undef);

sub BUILD
{
    my $self = shift;
    $self->data_size($self->data->nelem);
    my $segments = int(($self->data_size-$self->seq_size)/($self->batch_size*$self->seq_size));
    $self->idx([0..$segments-1]);
    $self->vocab_size($self->data->uniq->shape->at(0));
    $self->counter(0);
    $self->seq_counter(0);
    $self->nd(mx->nd->array($self->data, dtype => $self->dtype));
    my $shape = [$self->batch_size, $self->seq_size];
    $self->provide_data([
        AI::MXNet::DataDesc->new(
            name  => $self->data_name,
            shape => $shape,
            dtype => $self->dtype
        )
    ]);
    $self->provide_label([
        AI::MXNet::DataDesc->new(
            name  => $self->label_name,
            shape => $shape,
            dtype => $self->dtype
        )
    ]);
    $self->reset;
}

method reset()
{
    $self->counter(0);
    @{ $self->idx } = List::Util::shuffle(@{ $self->idx });