view release on metacpan or  search on metacpan

lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod  view on Meta::CPAN

    $pdl;
}

# image_size => [width, height] (but usually square images)
my %model_name_to_params = (
    centernet_hourglass_512x512 => {
        handle => 'https://tfhub.dev/tensorflow/centernet/hourglass_512x512/1',
        image_size => [ 512, 512 ],
    },
);

my $model_name = 'centernet_hourglass_512x512';

say "Selected model: $model_name : $model_name_to_params{$model_name}{handle}";

my $model_uri = URI->new( $model_name_to_params{$model_name}{handle} );
$model_uri->query_form( 'tf-hub-format' => 'compressed' );
my $model_base = substr( $model_uri->path, 1 ) =~ s,/,_,gr;
my $model_archive_path = "${model_base}.tar.gz";

my $http = HTTP::Tiny->new;

for my $download ( [ $model_uri  => $model_archive_path ],) {
    my ($uri, $path) = @$download;
    say "Downloading $uri to $path";
    next if -e $path;
    $http->mirror( $uri, $path );
}

use Archive::Extract;
my $ae = Archive::Extract->new( archive => $model_archive_path );
die "Could not extract archive" unless $ae->extract( to => $model_base );

my $saved_model = path($model_base)->child('saved_model.pb');
say "Saved model is in $saved_model" if -f $saved_model;

# Get the labels
my $response = $http->get('https://raw.githubusercontent.com/tensorflow/models/a4944a57ad2811e1f6a7a87589a9fc8a776e8d3c/object_detection/data/mscoco_label_map.pbtxt');

my %labels_map = $response->{content} =~ m<
(?:item \s+ \{  \s+
  \Qname:\E \s+ "[^"]+" \s+
  \Qid:\E   \s+ (\d+) \s+
  \Qdisplay_name:\E \s+ "([^"]+)" \s+
})+
>sgx;

my $label_count = List::Util::max keys %labels_map;

say "We have a label count of $label_count. These labels include: ",
    join ", ", List::Util::head( 5, @labels_map{ sort keys %labels_map } );

my @tags = ( 'serve' );

if( File::Which::which('saved_model_cli')) {
    local $ENV{TF_CPP_MIN_LOG_LEVEL} = 3; # quiet the TensorFlow logger for the following command
    system(qw(saved_model_cli show),
        qw(--dir)           => $model_base,
        qw(--tag_set)       => join(',', @tags),
        qw(--signature_def) => 'serving_default'
    ) == 0 or die "Could not run saved_model_cli";
} else {
    say "Install the tensorflow Python package to get the `saved_model_cli` command.";
}

my $opt = AI::TensorFlow::Libtensorflow::SessionOptions->New;

my $graph = AI::TensorFlow::Libtensorflow::Graph->New;
my $session = AI::TensorFlow::Libtensorflow::Session->LoadFromSavedModel(
    $opt, undef, $model_base, \@tags, $graph, undef, $s
);
AssertOK($s);

my %ops = (
    in  => {
        op   =>  $graph->OperationByName('serving_default_input_tensor'),
        dict => {
            input_tensor => 0,
        }
    },
    out => {
        op => $graph->OperationByName('StatefulPartitionedCall'),
        dict => {
            detection_boxes   => 0,
            detection_classes => 1,
            detection_scores  => 2,
            num_detections    => 3,
        }
    },
);

my %outputs;

%outputs = map {
    my $put_type = $_;
    my $op = $ops{$put_type}{op};
    my $port_dict = $ops{$put_type}{dict};

   $put_type => +{
        map {
            my $dict_key = $_;
            my $index = $port_dict->{$_};
            $dict_key => AI::TensorFlow::Libtensorflow::Output->New( {
                oper => $op,
                index => $index,
            });
        } keys %$port_dict
     }
} keys %ops;

p %outputs;

use HTML::Tiny;

my %images_for_test_to_uri = (
    "beach_scene" => 'https://github.com/tensorflow/models/blob/master/research/object_detection/test_images/image2.jpg?raw=true',
);

my @image_names = sort keys %images_for_test_to_uri;
my $h = HTML::Tiny->new;

my $image_name = 'beach_scene';
if( IN_IPERL ) {
    IPerl->html(
        $h->a( { href => $images_for_test_to_uri{$image_name} },
            $h->img({
                src => $images_for_test_to_uri{$image_name},
                alt => $image_name,
                width => '100%',
            })
        ),
    );
}

sub load_image_to_pdl {
    my ($uri, $image_size) = @_;

lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubCenterNetObjDetect.pod  view on Meta::CPAN

  );
  
  my $model_name = 'centernet_hourglass_512x512';
  
  say "Selected model: $model_name : $model_name_to_params{$model_name}{handle}";

We download the model to the current directory and then extract the model to a folder with the name given in C<$model_base>.

  my $model_uri = URI->new( $model_name_to_params{$model_name}{handle} );
  $model_uri->query_form( 'tf-hub-format' => 'compressed' );
  my $model_base = substr( $model_uri->path, 1 ) =~ s,/,_,gr;
  my $model_archive_path = "${model_base}.tar.gz";
  
  my $http = HTTP::Tiny->new;
  
  for my $download ( [ $model_uri  => $model_archive_path ],) {
      my ($uri, $path) = @$download;
      say "Downloading $uri to $path";
      next if -e $path;
      $http->mirror( $uri, $path );
  }
  
  use Archive::Extract;
  my $ae = Archive::Extract->new( archive => $model_archive_path );
  die "Could not extract archive" unless $ae->extract( to => $model_base );
  
  my $saved_model = path($model_base)->child('saved_model.pb');
  say "Saved model is in $saved_model" if -f $saved_model;

We need to download the COCO 2017 classification labels and parse out the mapping from the numeric index to the textual descriptions.

  # Get the labels
  my $response = $http->get('https://raw.githubusercontent.com/tensorflow/models/a4944a57ad2811e1f6a7a87589a9fc8a776e8d3c/object_detection/data/mscoco_label_map.pbtxt');
  
  my %labels_map = $response->{content} =~ m<
  (?:item \s+ \{  \s+
    \Qname:\E \s+ "[^"]+" \s+
    \Qid:\E   \s+ (\d+) \s+
    \Qdisplay_name:\E \s+ "([^"]+)" \s+
  })+
  >sgx;
  
  my $label_count = List::Util::max keys %labels_map;
  
  say "We have a label count of $label_count. These labels include: ",
      join ", ", List::Util::head( 5, @labels_map{ sort keys %labels_map } );

=head2 Load the model and session

We define the tag set C<[ 'serve' ]> which we will use to load the model.

  my @tags = ( 'serve' );

We can examine what computations are contained in the graph in terms of the names of the inputs and outputs of an operation found in the graph by running C<saved_model_cli>.

  if( File::Which::which('saved_model_cli')) {
      local $ENV{TF_CPP_MIN_LOG_LEVEL} = 3; # quiet the TensorFlow logger for the following command
      system(qw(saved_model_cli show),
          qw(--dir)           => $model_base,
          qw(--tag_set)       => join(',', @tags),
          qw(--signature_def) => 'serving_default'
      ) == 0 or die "Could not run saved_model_cli";
  } else {
      say "Install the tensorflow Python package to get the `saved_model_cli` command.";
  }

The above C<saved_model_cli> output shows that the model input is at C<serving_default_input_tensor:0> which means the operation named C<serving_default_input_tensor> at index C<0> and there are multiple outputs with different shapes.

Per the L<model description|https://tfhub.dev/tensorflow/centernet/hourglass_512x512/1> on TensorFlow Hub:

=over 2

B<Inputs>

A three-channel image of variable size - the model does NOT support batching. The input tensor is a C<tf.uint8> tensor with shape [1, height, width, 3] with values in [0, 255].

B<Outputs>

The output dictionary contains:

=over

=item -

C<num_detections>: a C<tf.int> tensor with only one value, the number of detections [N].

=item -

C<detection_boxes>: a C<tf.float32> tensor of shape [N, 4] containing bounding box coordinates in the following order: [ymin, xmin, ymax, xmax].

=item -

C<detection_classes>: a C<tf.int> tensor of shape [N] containing detection class index from the label file.

=item -

C<detection_scores>: a C<tf.float32> tensor of shape [N] containing detection scores.

=back

=back

Note that the above documentation has two errors: both C<num_detections> and C<detection_classes> are not of type C<tf.int>, but are actually C<tf.float32>.

Now we can load the model from that folder with the tag set C<[ 'serve' ]> by using the C<LoadFromSavedModel> constructor to create a C<::Graph> and a C<::Session> for that graph.

  my $opt = AI::TensorFlow::Libtensorflow::SessionOptions->New;
  
  my $graph = AI::TensorFlow::Libtensorflow::Graph->New;
  my $session = AI::TensorFlow::Libtensorflow::Session->LoadFromSavedModel(
      $opt, undef, $model_base, \@tags, $graph, undef, $s
  );
  AssertOK($s);

So let's use the names from the C<saved_model_cli> output to create our C<::Output> C<ArrayRef>s.

  my %ops = (
      in  => {
          op   =>  $graph->OperationByName('serving_default_input_tensor'),
          dict => {
              input_tensor => 0,
          }
      },
      out => {
          op => $graph->OperationByName('StatefulPartitionedCall'),
          dict => {
              detection_boxes   => 0,
              detection_classes => 1,
              detection_scores  => 2,
              num_detections    => 3,
          }
      },
  );
  
  my %outputs;
  
  %outputs = map {
      my $put_type = $_;
      my $op = $ops{$put_type}{op};
      my $port_dict = $ops{$put_type}{dict};
  
     $put_type => +{
          map {
              my $dict_key = $_;
              my $index = $port_dict->{$_};
              $dict_key => AI::TensorFlow::Libtensorflow::Output->New( {
                  oper => $op,
                  index => $index,
              });
          } keys %$port_dict
       }
  } keys %ops;
  
  p %outputs;

Now we can get the following testing image from GitHub.

  use HTML::Tiny;
  
  my %images_for_test_to_uri = (
      "beach_scene" => 'https://github.com/tensorflow/models/blob/master/research/object_detection/test_images/image2.jpg?raw=true',
  );
  
  my @image_names = sort keys %images_for_test_to_uri;
  my $h = HTML::Tiny->new;
  
  my $image_name = 'beach_scene';
  if( IN_IPERL ) {
      IPerl->html(
          $h->a( { href => $images_for_test_to_uri{$image_name} },
              $h->img({
                  src => $images_for_test_to_uri{$image_name},
                  alt => $image_name,
                  width => '100%',
              })
          ),
      );
  }