view release on metacpan or  search on metacpan

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

          }
      },
      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%',
              })
          ),
      );
  }

=head2 Download the test image and transform it into suitable input data

We now fetch the image and prepare it to be in the needed format by using C<Imager>. Note that this model does not need the input image to be of a certain size so no resizing or padding is required.

Then we turn the C<Imager> data into a C<PDL> ndarray. Since we just need the 3 channels of the image as they are, they can be stored directly in a C<PDL> ndarray of type C<byte>.

The reason why we need to concatenate the C<PDL> ndarrays here despite the model only taking a single image at a time is to get an ndarray with four (4) dimensions with the last C<PDL> dimension of size one (1).

  sub load_image_to_pdl {
      my ($uri, $image_size) = @_;
  
      my $http = HTTP::Tiny->new;
      my $response = $http->get( $uri );
      die "Could not fetch image from $uri" unless $response->{success};
      say "Downloaded $uri";
  
      my $img = Imager->new;
      $img->read( data => $response->{content} );
  
      # Create PDL ndarray from Imager data in-memory.
      my $data;
      $img->write( data => \$data, type => 'raw' )
          or die "could not write ". $img->errstr;
  
      die "Image does not have 3 channels, it has @{[ $img->getchannels ]} channels"
          if $img->getchannels != 3;
  
      # $data is packed as PDL->dims == [w,h] with RGB pixels
      my $pdl_raw = zeros(byte, $img->getchannels, $img->getwidth, $img->getheight);
      ${ $pdl_raw->get_dataref } = $data;
      $pdl_raw->upd_data;
  
      $pdl_raw;
  }
  
  my @pdl_images = map {
      load_image_to_pdl(
          $images_for_test_to_uri{$_},
          $model_name_to_params{$model_name}{image_size}
      );
  } ($image_names[0]);
  
  my $pdl_image_batched = cat(@pdl_images);
  my $t = Uint8PDLTOTFTensor($pdl_image_batched);
  
  die "There should be 4 dimensions" unless $pdl_image_batched->ndims == 4;
  
  die "With the final dimension of length 1" unless $pdl_image_batched->dim(3) == 1;
  
  p $pdl_image_batched;
  p $t;

=head2 Run the model for inference

We can use the C<Run> method to run the session and get the multiple output C<TFTensor>s. The following uses the names in C<$outputs> mapping to help process the multiple outputs more easily.

  my $RunSession = sub {
      my ($session, $t) = @_;
      my @outputs_t;
  
      my @keys = keys %{ $outputs{out} };
      my @values = $outputs{out}->@{ @keys };
      $session->Run(