view release on metacpan or  search on metacpan

lib/AI/MXNet/Module/Bucketing.pm  view on Meta::CPAN

    my $invalid_label = 0;

    my ($train_sentences, $vocabulary) = tokenize_text(
        './data/ptb.train.txt', start_label => $start_label,
        invalid_label => $invalid_label
    );
    my ($validation_sentences) = tokenize_text(
        './data/ptb.test.txt', vocab => $vocabulary,
        start_label => $start_label, invalid_label => $invalid_label
    );
    my $data_train  = mx->rnn->BucketSentenceIter(
        $train_sentences, $batch_size, buckets => $buckets,
        invalid_label => $invalid_label
    );
    my $data_val    = mx->rnn->BucketSentenceIter(
        $validation_sentences, $batch_size, buckets => $buckets,
        invalid_label => $invalid_label
    );

    my $stack = mx->rnn->SequentialRNNCell();
    for my $i (0..$num_layers-1)
    {
        $stack->add(mx->rnn->LSTMCell(num_hidden => $num_hidden, prefix => "lstm_l${i}_"));
    }

    my $sym_gen = sub {
        my $seq_len = shift;
        my $data  = mx->sym->Variable('data');
        my $label = mx->sym->Variable('softmax_label');
        my $embed = mx->sym->Embedding(
            data => $data, input_dim => scalar(keys %$vocabulary),
            output_dim => $num_embed, name => 'embed'
        );
        $stack->reset;
        my ($outputs, $states) = $stack->unroll($seq_len, inputs => $embed, merge_outputs => 1);
        my $pred = mx->sym->Reshape($outputs, shape => [-1, $num_hidden]);
        $pred    = mx->sym->FullyConnected(data => $pred, num_hidden => scalar(keys %$vocabulary), name => 'pred');
        $label   = mx->sym->Reshape($label, shape => [-1]);
        $pred    = mx->sym->SoftmaxOutput(data => $pred, label => $label, name => 'softmax');
        return ($pred, ['data'], ['softmax_label']);
    };

    my $contexts;
    if(defined $gpus)
    {
        $contexts = [map { mx->gpu($_) } split(/,/, $gpus)];
    }
    else
    {
        $contexts = mx->cpu(0);
    }

    my $model = mx->mod->BucketingModule(
        sym_gen             => $sym_gen,
        default_bucket_key  => $data_train->default_bucket_key,
        context             => $contexts
    );

    $model->fit(
        $data_train,
        eval_data           => $data_val,
        eval_metric         => mx->metric->Perplexity($invalid_label),
        kvstore             => $kv_store,
        optimizer           => $optimizer,
        optimizer_params    => {
                                    learning_rate => $lr,
                                    momentum      => $mom,
                                    wd            => $wd,
                            },
        initializer         => mx->init->Xavier(factor_type => "in", magnitude => 2.34),
        num_epoch           => $num_epoch,
        batch_end_callback  => mx->callback->Speedometer($batch_size, $disp_batches),
        ($chkp_epoch ? (epoch_end_callback  => mx->rnn->do_rnn_checkpoint($stack, $chkp_prefix, $chkp_epoch)) : ())
    );

=head1 DESCRIPTION

    Implements the AI::MXNet::Module::Base API, and allows multiple
    symbols to be used depending on the `bucket_key` provided by each different
    mini-batch of data
=cut


=head2 new

    Parameters
    ----------
    $sym_gen : subref or any perl object that overloads &{} op
        A sub when called with a bucket key, returns a list with triple
        of ($symbol, $data_names, $label_names).
    $default_bucket_key : str or anything else
        The key for the default bucket.
    $logger : Logger
    $context : AI::MXNet::Context or array ref of AI::MXNet::Context objects
        Default is cpu(0)
    $work_load_list : array ref of Num
        Default is undef, indicating uniform workload.
    $fixed_param_names: arrayref of str
        Default is undef, indicating no network parameters are fixed.
    $state_names : arrayref of str
        states are similar to data and label, but not provided by data iterator.
        Instead they are initialized to 0 and can be set by set_states()
=cut

extends 'AI::MXNet::Module::Base';
has '_sym_gen'            => (is => 'ro', init_arg => 'sym_gen', required => 1);
has '_default_bucket_key' => (is => 'rw', init_arg => 'default_bucket_key', required => 1);
has '_context'            => (
    is => 'ro', isa => 'AI::MXNet::Context|ArrayRef[AI::MXNet::Context]',
    lazy => 1, default => sub { AI::MXNet::Context->cpu },
    init_arg => 'context'
);
has '_work_load_list'     => (is => 'rw', init_arg => 'work_load_list', isa => 'ArrayRef[Num]');
has '_curr_module'        => (is => 'rw', init_arg => undef);
has '_curr_bucket_key'    => (is => 'rw', init_arg => undef);
has '_buckets'            => (is => 'rw', init_arg => undef, default => sub { +{} });
has '_fixed_param_names'  => (is => 'rw', isa => 'ArrayRef[Str]', init_arg => 'fixed_param_names');
has '_state_names'        => (is => 'rw', isa => 'ArrayRef[Str]', init_arg => 'state_names');
has '_params_dirty'       => (is => 'rw', init_arg => undef);

sub BUILD
{

lib/AI/MXNet/Module/Bucketing.pm  view on Meta::CPAN

            $mod->borrow_optimizer($self->_curr_module);
        }
    }
    $self->optimizer_initialized(1);
}

method prepare(AI::MXNet::DataBatch $data_batch)
{
    assert($self->binded and $self->params_initialized);
    ## perform bind if have not done so yet
    my $original_bucket_key = $self->_curr_bucket_key;
    $self->switch_bucket(
        bucket_key   => $data_batch->bucket_key,
        data_shapes  => $data_batch->provide_data,
        label_shapes => $data_batch->provide_label
    );
    # switch back
    $self->switch_bucket(bucket_key => $original_bucket_key);
}

method forward(
    AI::MXNet::DataBatch  $data_batch,
    Bool                 :$is_train=
)
{
    assert($self->binded and $self->params_initialized);
    $self->switch_bucket(
        bucket_key   => $data_batch->bucket_key,
        data_shapes  => $data_batch->provide_data,
        label_shapes => $data_batch->provide_label
    );
    $self->_curr_module->forward($data_batch, is_train => $is_train);
}

method backward(Maybe[ArrayRef[AI::MXNet::NDArray]|AI::MXNet::NDArray] $out_grads=)
{
    assert($self->binded and $self->params_initialized);
    $self->_curr_module->backward($out_grads);
}

method update()
{
    assert($self->binded and $self->params_initialized and $self->optimizer_initialized);
    $self->_params_dirty(1);
    $self->_curr_module->update;
}

method get_outputs(Bool $merge_multi_context=1)
{
    assert($self->binded and $self->params_initialized);
    return $self->_curr_module->get_outputs($merge_multi_context);
}

method get_input_grads(Bool $merge_multi_context=1)
{
    assert($self->binded and $self->params_initialized and $self->inputs_need_grad);
    return $self->_curr_module->get_input_grads($merge_multi_context);
}

method update_metric(
    AI::MXNet::EvalMetric $eval_metric,
    ArrayRef[AI::MXNet::NDArray] $labels
)
{
    assert($self->binded and $self->params_initialized);
    $self->_curr_module->update_metric($eval_metric, $labels);
}

method symbol()
{
    assert($self->binded);
    return $self->_curr_module->symbol;
}

method get_symbol()
{
    assert($self->binded);
    return $self->_buckets->{ $self->_default_bucket_key }->symbol;
}

method install_monitor(AI::MXNet::Monitor $mon)
{
    assert($self->binded);
    for my $mod (values %{ $self->_buckets })
    {
        $mod->install_monitor($mon);
    }
}

1;