view release on metacpan or  search on metacpan

lib/AI/MXNet/Gluon/Contrib/NN/BasicLayers.pm  view on Meta::CPAN

        $net = nn->Concurrent();
        # use net's name_scope to give children blocks appropriate names.
        $net->name_scope(sub {
            $net->add(nn->Dense(10, activation=>'relu'));
            $net->add(nn->Dense(20));
            $net->add(nn->Identity());
        });

    Parameters
    ----------
    axis : int, default -1
        The axis on which to concatenate the outputs.
=cut
has 'axis' => (is => 'rw', isa => 'Int', default => -1);
method python_constructor_arguments() { ['axis'] }

method forward(GluonInput $x)
{
    return AI::MXNet::NDArray->concat((map { $_->($x) } $self->_children->values), dim=>$self->axis);
}

__PACKAGE__->register('AI::MXNet::Gluon::NN');

package AI::MXNet::Gluon::NN::HybridConcurrent;

lib/AI/MXNet/Gluon/Contrib/NN/BasicLayers.pm  view on Meta::CPAN

        $net = nn->HybridConcurrent();
        # use net's name_scope to give children blocks appropriate names.
        $net->name_scope(sub {
            $net->add(nn->Dense(10, activation=>'relu'));
            $net->add(nn->Dense(20));
            $net->add(nn->Identity());
        });

    Parameters
    ----------
    axis : int, default -1
        The axis on which to concatenate the outputs.
=cut
has 'axis' => (is => 'rw', isa => 'Int', default => -1);
method python_constructor_arguments() { ['axis'] }

method hybrid_forward(GluonClass $F, GluonInput $x)
{
    return $F->concat((map { $_->($x) } $self->_children->values), dim=>$self->axis);
}

__PACKAGE__->register('AI::MXNet::Gluon::NN');

package AI::MXNet::Gluon::NN::Identity;

lib/AI/MXNet/Gluon/Contrib/NN/BasicLayers.pm  view on Meta::CPAN

    This SparseBlock is designed for distributed training with extremely large
    input dimension. Both weight and gradient w.r.t. weight are AI::MXNet::NDArray::RowSparse.

    Parameters
    ----------
    input_dim : int
        Size of the vocabulary, i.e. maximum integer index + 1.
    output_dim : int
        Dimension of the dense embedding.
    dtype : Dtype, default 'float32'
        Data type of output embeddings.
    weight_initializer : Initializer
        Initializer for the embeddings matrix.
=cut

has 'input_dim'          => (is => 'ro', isa => 'Int', required => 1);
has 'output_dim'         => (is => 'ro', isa => 'Int', required => 1);
has 'dtype'              => (is => 'ro', isa => 'Dtype', default => 'float32');
has 'weight_initializer' => (is => 'ro', isa => 'Maybe[Initializer]');
method python_constructor_arguments() { [qw/input_dim output_dim dtype weight_initializer/] }

sub BUILD
{
    my $self = shift;
    $self->_kwargs({
        input_dim => $self->input_dim, 
        output_dim => $self->output_dim,
        dtype => $self->dtype,