AI-MXNet-Gluon-ModelZoo
view release on metacpan or search on metacpan
examples/image_classification.pl view on Meta::CPAN
use warnings;
use AI::MXNet::Gluon::ModelZoo 'get_model';
use AI::MXNet::Gluon::Utils 'download';
use Getopt::Long qw(HelpMessage);
GetOptions(
## my Pembroke Welsh Corgi Kyuubi, enjoing Solar eclipse of August 21, 2017
'image=s' => \(my $image = 'http://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/'.
'gluon/dataset/kyuubi.jpg'),
'model=s' => \(my $model = 'resnet152_v2'),
'help' => sub { HelpMessage(0) },
) or HelpMessage(1);
## get a pretrained model (download parameters file if necessary)
my $net = get_model($model, pretrained => 1);
## ImageNet classes
my $fname = download('http://data.mxnet.io/models/imagenet/synset.txt');
my @text_labels = map { chomp; s/^\S+\s+//; $_ } IO::File->new($fname)->getlines;
## get the image from the disk or net
lib/AI/MXNet/Gluon/ModelZoo.pm view on Meta::CPAN
The context in which to load the pretrained weights.
:$root : Str, default '~/.mxnet/models'
Location for keeping the model parameters.
Returns
-------
HybridBlock
The model.
=cut
sub get_model
{
if(exists $models{lc $_[1]})
{
shift;
}
my ($name, %kwargs) = @_;
$name = lc $name;
Carp::confess(
"Model $name is not present in the zoo\nValid models are:\n".
join(', ', sort keys %models)."\n"
) unless exists $models{$name};
my $sub = $models{$name};
AI::MXNet::Gluon::ModelZoo::Vision->$sub(%kwargs);
}
sub vision { 'AI::MXNet::Gluon::ModelZoo::Vision' }
1;
=head1 AUTHOR
Sergey Kolychev, <sergeykolychev.github@gmail.com>
=head1 COPYRIGHT & LICENSE
This library is licensed under Apache 2.0 license L<https://www.apache.org/licenses/LICENSE-2.0>
lib/AI/MXNet/Gluon/ModelZoo/Vision.pm view on Meta::CPAN
use warnings;
use AI::MXNet::Gluon::ModelZoo::ModelStore;
use AI::MXNet::Gluon::ModelZoo::Vision::AlexNet;
use AI::MXNet::Gluon::ModelZoo::Vision::DenseNet;
use AI::MXNet::Gluon::ModelZoo::Vision::Inception;
use AI::MXNet::Gluon::ModelZoo::Vision::MobileNet;
use AI::MXNet::Gluon::ModelZoo::Vision::ResNet;
use AI::MXNet::Gluon::ModelZoo::Vision::SqueezeNet;
use AI::MXNet::Gluon::ModelZoo::Vision::VGG;
sub import
{
my ($class, $short_name) = @_;
if($short_name)
{
$short_name =~ s/[^\w:]//g;
if(length $short_name)
{
my $short_name_package =<<"EOP";
package $short_name;
\@${short_name}::ISA = ('AI::MXNet::Gluon::ModelZoo::Vision');
lib/AI/MXNet/Gluon/ModelZoo/Vision/AlexNet.pm view on Meta::CPAN
AlexNet model from the "One weird trick..." <https://arxiv.org/abs/1404.5997> paper.
Parameters
----------
classes : Int, default 1000
Number of classes for the output layer.
=cut
has 'classes' => (is => 'ro', isa => 'Int', default => 1000);
method python_constructor_arguments() { ['classes'] }
sub BUILD
{
my $self = shift;
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>''));
$self->features->name_scope(sub {
$self->features->add(nn->Conv2D(64, kernel_size=>11, strides=>4,
padding=>2, activation=>'relu'));
$self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2));
$self->features->add(nn->Conv2D(192, kernel_size=>5, padding=>2,
activation=>'relu'));
$self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2));
$self->features->add(nn->Conv2D(384, kernel_size=>3, padding=>1,
activation=>'relu'));
$self->features->add(nn->Conv2D(256, kernel_size=>3, padding=>1,
activation=>'relu'));
lib/AI/MXNet/Gluon/ModelZoo/Vision/DenseNet.pm view on Meta::CPAN
use strict;
use warnings;
use AI::MXNet::Base;
use AI::MXNet::Function::Parameters;
use AI::MXNet::Gluon::Mouse;
extends 'AI::MXNet::Gluon::HybridBlock';
func _make_dense_block($num_layers, $bn_size, $growth_rate, $dropout, $stage_index)
{
my $out = nn->HybridSequential(prefix=>"stage${stage_index}_");
$out->name_scope(sub {
for(1..$num_layers)
{
$out->add(_make_dense_layer($growth_rate, $bn_size, $dropout));
}
});
return $out;
}
func _make_dense_layer($growth_rate, $bn_size, $dropout)
{
lib/AI/MXNet/Gluon/ModelZoo/Vision/DenseNet.pm view on Meta::CPAN
Number of classification classes.
=cut
has [qw/num_init_features
growth_rate/] => (is => 'ro', isa => 'Int', required => 1);
has 'block_config' => (is => 'ro', isa => 'ArrayRef[Int]', required => 1);
has 'bn_size' => (is => 'ro', isa => 'Int', default => 4);
has 'dropout' => (is => 'ro', isa => 'Num', default => 0);
has 'classes' => (is => 'ro', isa => 'Int', default => 1000);
method python_constructor_arguments(){ [qw/num_init_features growth_rate block_config bn_size dropout classes/] }
sub BUILD
{
my $self = shift;
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>''));
$self->features->add(
nn->Conv2D(
$self->num_init_features, kernel_size=>7,
strides=>2, padding=>3, use_bias=>0
)
);
$self->features->add(nn->BatchNorm());
$self->features->add(nn->Activation('relu'));
$self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2, padding=>1));
lib/AI/MXNet/Gluon/ModelZoo/Vision/Inception.pm view on Meta::CPAN
}
}
$out->add(_make_basic_conv(%kwargs));
}
return $out;
}
func _make_A($pool_features, $prefix)
{
my $out = nn->HybridConcurrent(axis=>1, prefix=>$prefix);
$out->name_scope(sub {
$out->add(_make_branch('', [64, 1, undef, undef]));
$out->add(_make_branch(
'',
[48, 1, undef, undef],
[64, 5, undef, 2]
));
$out->add(_make_branch(
'',
[64, 1, undef, undef],
[96, 3, undef, 1],
[96, 3, undef, 1]
));
$out->add(_make_branch('avg', [$pool_features, 1, undef, undef]));
});
return $out;
}
func _make_B($prefix)
{
my $out = nn->HybridConcurrent(axis=>1, prefix=>$prefix);
$out->name_scope(sub {
$out->add(_make_branch('', [384, 3, 2, undef]));
$out->add(_make_branch(
'',
[64, 1, undef, undef],
[96, 3, undef, 1],
[96, 3, 2, undef]
));
$out->add(_make_branch('max'));
});
return $out;
}
func _make_C($channels_7x7, $prefix)
{
my $out = nn->HybridConcurrent(axis=>1, prefix=>$prefix);
$out->name_scope(sub {
$out->add(_make_branch('', [192, 1, undef, undef]));
$out->add(_make_branch(
'',
[$channels_7x7, 1, undef, undef],
[$channels_7x7, [1, 7], undef, [0, 3]],
[192, [7, 1], undef, [3, 0]]
));
$out->add(_make_branch(
'',
[$channels_7x7, 1, undef, undef],
lib/AI/MXNet/Gluon/ModelZoo/Vision/Inception.pm view on Meta::CPAN
'avg',
[192, 1, undef, undef]
));
});
return $out;
}
func _make_D($prefix)
{
my $out = nn->HybridConcurrent(axis=>1, prefix=>$prefix);
$out->name_scope(sub {
$out->add(_make_branch(
'',
[192, 1, undef, undef],
[320, 3, 2, undef]
));
$out->add(_make_branch(
'',
[192, 1, undef, undef],
[192, [1, 7], undef, [0, 3]],
[192, [7, 1], undef, [3, 0]],
[192, 3, 2, undef]
));
$out->add(_make_branch('max'));
});
return $out;
}
func _make_E($prefix)
{
my $out = nn->HybridConcurrent(axis=>1, prefix=>$prefix);
$out->name_scope(sub {
$out->add(_make_branch('', [320, 1, undef, undef]));
my $branch_3x3 = nn->HybridSequential(prefix=>'');
$out->add($branch_3x3);
$branch_3x3->add(_make_branch(
'',
[384, 1, undef, undef]
));
my $branch_3x3_split = nn->HybridConcurrent(axis=>1, prefix=>'');
$branch_3x3_split->add(_make_branch('', [384, [1, 3], undef, [0, 1]]));
lib/AI/MXNet/Gluon/ModelZoo/Vision/Inception.pm view on Meta::CPAN
Parameters
----------
classes : Int, default 1000
Number of classification classes.
=cut
has 'classes' => (is => 'ro', isa => 'Int', default => 1000);
method python_constructor_arguments(){ ['classes'] }
sub BUILD
{
my $self = shift;
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>''));
$self->features->add(_make_basic_conv(channels=>32, kernel_size=>3, strides=>2));
$self->features->add(_make_basic_conv(channels=>32, kernel_size=>3));
$self->features->add(_make_basic_conv(channels=>64, kernel_size=>3, padding=>1));
$self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2));
$self->features->add(_make_basic_conv(channels=>80, kernel_size=>1));
$self->features->add(_make_basic_conv(channels=>192, kernel_size=>3));
$self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2));
$self->features->add(_make_A(32, 'A1_'));
$self->features->add(_make_A(64, 'A2_'));
lib/AI/MXNet/Gluon/ModelZoo/Vision/MobileNet.pm view on Meta::CPAN
)
{
$out->add(nn->Conv2D($channels, $kernel, $stride, $pad, groups=>$num_group, use_bias=>0));
$out->add(nn->BatchNorm(scale=>1));
if($active)
{
$out->add($relu6 ? AI::MXNet::Gluon::ModelZoo::Vision::MobileNet::RELU6->new : nn->Activation('relu'));
}
}
sub BUILD
{
my $self = shift;
$self->use_shortcut($self->stride == 1 and $self->in_channels == $self->channels);
$self->name_scope(sub {
$self->out(nn->HybridSequential());
_add_conv($self->out, $self->in_channels * $self->t, relu6=>1);
_add_conv(
$self->out, $self->in_channels * $self->t, kernel=>3, stride=>$self->stride,
pad=>1, num_group=>$self->in_channels * $self->t, relu6=>1
);
_add_conv($self->out, $self->channels, active=>0, relu6=>1);
});
}
lib/AI/MXNet/Gluon/ModelZoo/Vision/MobileNet.pm view on Meta::CPAN
}
func _add_conv_dw($out, :$dw_channels=, :$channels=, :$stride=, :$relu6=0)
{
_add_conv($out, channels=>$dw_channels, kernel=>3, stride=>$stride,
pad=>1, num_group=>$dw_channels, relu6=>$relu6);
_add_conv($out, channels=>$channels, relu6=>$relu6);
}
sub BUILD
{
my $self = shift;
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>''));
$self->features->name_scope(sub {
_add_conv($self->features, channels=>int(32 * $self->multiplier), kernel=>3, pad=>1, stride=>2);
my $dw_channels = [map { int($_ * $self->multiplier) } (32, 64, (128)x2, (256)x2, (512)x6, 1024)];
my $channels = [map { int($_ * $self->multiplier) } (64, (128)x2, (256)x2, (512)x6, (1024)x2)];
my $strides = [(1, 2)x3, (1)x5, 2, 1];
for(zip($dw_channels, $channels, $strides))
{
my ($dwc, $c, $s) = @$_;
_add_conv_dw($self->features, dw_channels=>$dwc, channels=>$c, stride=>$s);
}
$self->features->add(nn->GlobalAvgPool2D());
lib/AI/MXNet/Gluon/ModelZoo/Vision/MobileNet.pm view on Meta::CPAN
)
{
$out->add(nn->Conv2D($channels, $kernel, $stride, $pad, groups=>$num_group, use_bias=>0));
$out->add(nn->BatchNorm(scale=>1));
if($active)
{
$out->add($relu6 ? AI::MXNet::Gluon::ModelZoo::Vision::MobileNet::RELU6->new : nn->Activation('relu'));
}
}
sub BUILD
{
my $self = shift;
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>'features_'));
$self->features->name_scope(sub {
_add_conv(
$self->features, int(32 * $self->multiplier), kernel=>3,
stride=>2, pad=>1, relu6=>1
);
my $in_channels_group = [map { int($_ * $self->multiplier) } (32, 16, (24)x2, (32)x3, (64)x4, (96)x3, (160)x3)];
my $channels_group = [map { int($_ * $self->multiplier) } (16, (24)x2, (32)x3, (64)x4, (96)x3, (160)x3, 320)];
my $ts = [1, (6)x16];
my $strides = [(1, 2)x2, 1, 1, 2, (1)x6, 2, (1)x3];
lib/AI/MXNet/Gluon/ModelZoo/Vision/MobileNet.pm view on Meta::CPAN
)
);
}
my $last_channels = $self->multiplier > 1 ? int(1280 * $self->multiplier) : 1280;
_add_conv($self->features, $last_channels, relu6=>1);
$self->features->add(nn->GlobalAvgPool2D());
});
$self->output(nn->HybridSequential(prefix=>'output_'));
$self->output->name_scope(sub {
$self->output->add(
nn->Conv2D($self->classes, 1, use_bias=>0, prefix=>'pred_'),
nn->Flatten()
);
});
});
}
method hybrid_forward(GluonClass $F, GluonInput $x)
{
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
has 'in_channels' => (is => 'ro', isa => 'Int', default => 0);
method python_constructor_arguments() { [qw/channels stride downsample/] }
func _conv3x3($channels, $stride, $in_channels)
{
return nn->Conv2D(
$channels, kernel_size=>3, strides=>$stride, padding=>1,
use_bias=>0, in_channels=>$in_channels
);
}
sub BUILD
{
my $self = shift;
$self->body(nn->HybridSequential(prefix=>''));
$self->body->add(_conv3x3($self->channels, $self->stride, $self->in_channels));
$self->body->add(nn->BatchNorm());
$self->body->add(nn->Activation('relu'));
$self->body->add(_conv3x3($self->channels, 1, $self->channels));
$self->body->add(nn->BatchNorm());
if($self->downsample)
{
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
has 'in_channels' => (is => 'ro', isa => 'Int', default => 0);
method python_constructor_arguments() { [qw/channels stride downsample/] }
func _conv3x3($channels, $stride, $in_channels)
{
return nn->Conv2D(
$channels, kernel_size=>3, strides=>$stride, padding=>1,
use_bias=>0, in_channels=>$in_channels
);
}
sub BUILD
{
my $self = shift;
$self->body(nn->HybridSequential(prefix=>''));
$self->body->add(nn->Conv2D(int($self->channels/4), kernel_size=>1, strides=>$self->stride));
$self->body->add(nn->BatchNorm());
$self->body->add(nn->Activation('relu'));
$self->body->add(_conv3x3(int($self->channels/4), 1, int($self->channels/4)));
$self->body->add(nn->BatchNorm());
$self->body->add(nn->Activation('relu'));
$self->body->add(nn->Conv2D($self->channels, kernel_size=>1, strides=>1));
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
has 'in_channels' => (is => 'ro', isa => 'Int', default => 0);
method python_constructor_arguments() { [qw/channels stride downsample/] }
func _conv3x3($channels, $stride, $in_channels)
{
return nn->Conv2D(
$channels, kernel_size=>3, strides=>$stride, padding=>1,
use_bias=>0, in_channels=>$in_channels
);
}
sub BUILD
{
my $self = shift;
$self->bn1(nn->BatchNorm());
$self->conv1(_conv3x3($self->channels, $self->stride, $self->in_channels));
$self->bn2(nn->BatchNorm());
$self->conv2(_conv3x3($self->channels, 1, $self->channels));
if($self->downsample)
{
$self->downsample(
nn->Conv2D($self->channels, kernel_size=>1, strides=>$self->stride,
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
has 'in_channels' => (is => 'ro', isa => 'Int', default => 0);
method python_constructor_arguments() { [qw/channels stride downsample/] }
func _conv3x3($channels, $stride, $in_channels)
{
return nn->Conv2D(
$channels, kernel_size=>3, strides=>$stride, padding=>1,
use_bias=>0, in_channels=>$in_channels
);
}
sub BUILD
{
my $self = shift;
$self->bn1(nn->BatchNorm());
$self->conv1(nn->Conv2D(int($self->channels/4), kernel_size=>1, strides=>1, use_bias=>0));
$self->bn2(nn->BatchNorm());
$self->conv2(_conv3x3(int($self->channels/4), $self->stride, int($self->channels/4)));
$self->bn3(nn->BatchNorm());
$self->conv3(nn->Conv2D($self->channels, kernel_size=>1, strides=>1, use_bias=>0));
if($self->downsample)
{
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
has 'thumbnail' => (is => 'ro', isa => 'Bool', default => 0);
method python_constructor_arguments() { [qw/block layers channels classes thumbnail/] }
func _conv3x3($channels, $stride, $in_channels)
{
return nn->Conv2D(
$channels, kernel_size=>3, strides=>$stride, padding=>1,
use_bias=>0, in_channels=>$in_channels
);
}
sub BUILD
{
my $self = shift;
assert(@{ $self->layers } == (@{ $self->channels } - 1));
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>''));
if($self->thumbnail)
{
$self->features->add(_conv3x3($self->channels->[0], 1, 0));
}
else
{
$self->features->add(nn->Conv2D($self->channels->[0], 7, 2, 3, use_bias=>0));
$self->features->add(nn->BatchNorm());
$self->features->add(nn->Activation('relu'));
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
);
}
$self->features->add(nn->GlobalAvgPool2D());
$self->output(nn->Dense($self->classes, in_units=>$self->channels->[-1]));
});
}
method _make_layer($block, $layers, $channels, $stride, $stage_index, :$in_channels=0)
{
my $layer = nn->HybridSequential(prefix=>"stage${stage_index}_");
$layer->name_scope(sub {
$layer->add(
$block->new(
$channels, $stride, $channels != $in_channels, in_channels=>$in_channels,
prefix=>''
)
);
for(1..$layers-1)
{
$layer->add($block->new($channels, 1, 0, in_channels=>$channels, prefix=>''));
}
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
has 'thumbnail' => (is => 'ro', isa => 'Bool', default => 0);
method python_constructor_arguments() { [qw/block layers channels classes thumbnail/] }
func _conv3x3($channels, $stride, $in_channels)
{
return nn->Conv2D(
$channels, kernel_size=>3, strides=>$stride, padding=>1,
use_bias=>0, in_channels=>$in_channels
);
}
sub BUILD
{
my $self = shift;
assert(@{ $self->layers } == (@{ $self->channels } - 1));
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>''));
$self->features->add(nn->BatchNorm(scale=>0, center=>0));
if($self->thumbnail)
{
$self->features->add(_conv3x3($self->channels->[0], 1, 0));
}
else
{
$self->features->add(nn->Conv2D($self->channels->[0], 7, 2, 3, use_bias=>0));
$self->features->add(nn->BatchNorm());
lib/AI/MXNet/Gluon/ModelZoo/Vision/ResNet.pm view on Meta::CPAN
$self->features->add(nn->Activation('relu'));
$self->features->add(nn->GlobalAvgPool2D());
$self->features->add(nn->Flatten());
$self->output(nn->Dense($self->classes, in_units=>$in_channels));
});
}
method _make_layer($block, $layers, $channels, $stride, $stage_index, :$in_channels=0)
{
my $layer = nn->HybridSequential(prefix=>"stage${stage_index}_");
$layer->name_scope(sub {
$layer->add(
$block->new(
$channels, $stride, $channels != $in_channels, in_channels=>$in_channels,
prefix=>''
)
);
for(1..$layers-1)
{
$layer->add($block->new($channels, 1, 0, in_channels=>$channels, prefix=>''));
}
lib/AI/MXNet/Gluon/ModelZoo/Vision/SqueezeNet.pm view on Meta::CPAN
version : Str
Version of squeezenet. Options are '1.0', '1.1'.
classes : Int, default 1000
Number of classification classes.
=cut
has 'version' => (is => 'ro', isa => enum([qw[1.0 1.1]]), required => 1);
has 'classes' => (is => 'ro', isa => 'Int', default => 1000);
method python_constructor_arguments() { [qw/version classes/] }
sub BUILD
{
my $self = shift;
$self->name_scope(sub {
$self->features(nn->HybridSequential(prefix=>''));
if($self->version eq '1.0')
{
$self->features->add(nn->Conv2D(96, kernel_size=>7, strides=>2));
$self->features->add(nn->Activation('relu'));
$self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2, ceil_mode=>1));
$self->features->add(_make_fire(16, 64, 64));
$self->features->add(_make_fire(16, 64, 64));
$self->features->add(_make_fire(32, 128, 128));
$self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2, ceil_mode=>1));
lib/AI/MXNet/Gluon/ModelZoo/Vision/VGG.pm view on Meta::CPAN
Number of classification classes.
batch_norm : Bool, default 0
Use batch normalization.
=cut
method python_constructor_arguments() { [qw/layers filters classes batch_norm/] }
has ['layers',
'filters'] => (is => 'ro', isa => 'ArrayRef[Int]', required => 1);
has 'classes' => (is => 'ro', isa => 'Int', default => 1000);
has 'batch_norm' => (is => 'ro', isa => 'Bool', default => 0);
sub BUILD
{
my $self = shift;
assert(@{ $self->layers } == @{ $self->filters });
$self->name_scope(sub {
$self->features($self->_make_features());
$self->features->add(nn->Dense(4096, activation=>'relu',
weight_initializer=>'normal',
bias_initializer=>'zeros'));
$self->features->add(nn->Dropout(rate=>0.5));
$self->features->add(nn->Dense(4096, activation=>'relu',
weight_initializer=>'normal',
bias_initializer=>'zeros'));
$self->features->add(nn->Dropout(rate=>0.5));
$self->output(nn->Dense($self->classes,
t/test_gluon_model_zoo.t view on Meta::CPAN
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
use strict;
use warnings;
use AI::MXNet::Gluon::ModelZoo qw(get_model);
use Test::More tests => 34;
sub test_models
{
my @all_models = ('resnet34_v1', 'resnet18_v1', 'resnet50_v1', 'resnet101_v1', 'resnet152_v1',
'resnet18_v2', 'resnet34_v2', 'resnet50_v2', 'resnet101_v2', 'resnet152_v2',
'vgg11', 'vgg13', 'vgg16', 'vgg19',
'vgg11_bn', 'vgg13_bn', 'vgg16_bn', 'vgg19_bn',
'alexnet', 'inceptionv3',
'densenet121', 'densenet161', 'densenet169', 'densenet201',
'squeezenet1.0', 'squeezenet1.1',
'mobilenet1.0', 'mobilenet0.75', 'mobilenet0.5', 'mobilenet0.25',
'mobilenetv2_1.0', 'mobilenetv2_0.75', 'mobilenetv2_0.5', 'mobilenetv2_0.25');
( run in 0.867 second using v1.01-cache-2.11-cpan-a5abf4f5562 )