view release on metacpan or  search on metacpan

examples/cudnn_lstm_bucketing.pl  view on Meta::CPAN

            $cell, $model_prefix, $load_epoch);
    }
    $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,
                            },
        begin_epoch         => $load_epoch,
        initializer         => mx->init->Xavier(factor_type => "in", magnitude => 2.34),
        num_epoch           => $num_epoch,
        batch_end_callback  => mx->callback->Speedometer($batch_size, $disp_batches),
        ($model_prefix ? (epoch_end_callback  => mx->rnn->do_rnn_checkpoint($cell, $model_prefix, 1)) : ())
    );
};

my $test = sub {
    assert($model_prefix, "Must specifiy path to load from");
    my (undef, $data_val, $vocab) = get_data('NT');
    my $stack;
    if($stack_rnn)
    {
        $stack = mx->rnn->SequentialRNNCell();
        for my $i (0..$num_layers-1)
        {
            my $cell = mx->rnn->LSTMCell(num_hidden => $num_hidden, prefix => "lstm_${i}l0_");
            if($bidirectional)
            {
                $cell = mx->rnn->BidirectionalCell(
                    $cell,
                    mx->rnn->LSTMCell(
                        num_hidden => $num_hidden,
                        prefix => "lstm_${i}r0_"
                    ),
                    output_prefix => "bi_lstm_$i"
                );
            }
            $stack->add($cell);
        }
    }
    else
    {
        $stack = mx->rnn->FusedRNNCell(
            $num_hidden,  num_layers    => $num_layers,
            mode=>'lstm', bidirectional => $bidirectional
        )->unfuse()
    }
    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 => $data, input_dim => scalar(keys %$vocab),
            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, $num_hidden*(1+$bidirectional)]);
        $pred    = mx->sym->FullyConnected(data => $pred, num_hidden => scalar(keys %$vocab), 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 $contexts;
    if($gpus)
    {
        $contexts = [map { mx->gpu($_) } split(/,/, $gpus)];
    }
    else
    {
        $contexts = mx->cpu(0);
    }

    my ($arg_params, $aux_params);
    if($load_epoch)
    {
        (undef, $arg_params, $aux_params) = mx->rnn->load_rnn_checkpoint(
            $stack, $model_prefix, $load_epoch);
    }
    my $model = mx->mod->BucketingModule(
        sym_gen             => $sym_gen,
        default_bucket_key  => $data_val->default_bucket_key,
        context             => $contexts
    );
    $model->bind(
        data_shapes  => $data_val->provide_data,
        label_shapes => $data_val->provide_label,
        for_training => 0,
        force_rebind => 0
    );
    $model->set_params($arg_params, $aux_params);
    my $score = $model->score($data_val,
        mx->metric->Perplexity($invalid_label),
        batch_end_callback=>mx->callback->Speedometer($batch_size, 5)
    );
};

if($num_layers >= 4 and split(/,/,$gpus) >= 4 and not $stack_rnn)
{
    print("WARNING: stack-rnn is recommended to train complex model on multiple GPUs\n");
}

if($do_test)
{
    # Demonstrates how to load a model trained with CuDNN RNN and predict
    # with non-fused MXNet symbol
    $test->();
}
else
{
    $train->();
}