view release on metacpan or  search on metacpan

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

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) = @_;

    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;

my $RunSession = sub {
    my ($session, $t) = @_;
    my @outputs_t;

    my @keys = keys %{ $outputs{out} };
    my @values = $outputs{out}->@{ @keys };
    $session->Run(
        undef,
        [ values %{$outputs{in} } ], [$t],
        \@values, \@outputs_t,
        undef,
        undef,
        $s
    );
    AssertOK($s);

    return { mesh \@keys, \@outputs_t };
};

undef;

my $tftensor_output_by_name = $RunSession->($session, $t);

my %pdl_output_by_name = map {
    $_ => FloatTFTensorToPDL( $tftensor_output_by_name->{$_} )
} keys $tftensor_output_by_name->%*;

undef;

my $min_score_thresh = 0.30;

my $which_detect = which( $pdl_output_by_name{detection_scores} > $min_score_thresh );

my %subset;

$subset{detection_boxes}   = $pdl_output_by_name{detection_boxes}->dice('X', $which_detect);
$subset{detection_classes} = $pdl_output_by_name{detection_classes}->dice($which_detect);
$subset{detection_scores}  = $pdl_output_by_name{detection_scores}->dice($which_detect);

$subset{detection_class_labels}->@* = map { $labels_map{$_} } $subset{detection_classes}->list;

p %subset;

use PDL::Graphics::Gnuplot;

my $plot_output_path = 'objects-detected.png';
my $gp = gpwin('pngcairo', font => ",12", output => $plot_output_path, aa => 2, size => [10] );

my @qual_cmap = ('#a6cee3','#1f78b4','#b2df8a','#33a02c','#fb9a99','#e31a1c','#fdbf6f','#ff7f00','#cab2d6');

$gp->options(
    map {
        my $idx = $_;
        my $lc_rgb = $qual_cmap[ $subset{detection_classes}->slice("($idx)")->squeeze % @qual_cmap ];

        my $box_corners_yx_norm = $subset{detection_boxes}->slice([],$idx,[0,0,0]);
        $box_corners_yx_norm->reshape(2,2);

        my $box_corners_yx_img = $box_corners_yx_norm * $pdl_images[0]->shape->slice('-1:-2');

        my $from_xy = join ",", $box_corners_yx_img->slice('-1:0,(0)')->list;
        my $to_xy   = join ",", $box_corners_yx_img->slice('-1:0,(1)')->list;
        my $label_xy = join ",", $box_corners_yx_img->at(1,1), $box_corners_yx_img->at(0,1);

        (
            [ object => [ "rect" =>
                from => $from_xy, to => $to_xy,
                qq{front fs empty border lc rgb "$lc_rgb" lw 5} ], ],
            [ label => [
                sprintf("%s: %.1f",
                    $subset{detection_class_labels}[$idx],
                    100*$subset{detection_scores}->at($idx,0) ) =>
                at => $label_xy, 'left',
                offset => 'character 0,-0.25',
                qq{font ",12" boxed front tc rgb "#ffffff"} ], ],
        )
    } 0..$subset{detection_boxes}->dim(1)-1
);

$gp->plot(
    topcmds => q{set style textbox opaque fc "#505050f0" noborder},
    square => 1,
    yrange => [$pdl_images[0]->dim(2),0],
    with => 'image', $pdl_images[0],
);

$gp->close;

IPerl->png( bytestream => path($plot_output_path)->slurp_raw ) if IN_IPERL;

use Filesys::DiskUsage qw/du/;

my $total = du( { 'human-readable' => 1, dereference => 1 },
    $model_archive_path, $model_base );

say "Disk space usage: $total"; undef;

__END__

=pod

=encoding UTF-8

=head1 NAME

AI::TensorFlow::Libtensorflow::Manual::Notebook::InferenceUsingTFHubCenterNetObjDetect - Using TensorFlow to do object detection using a pre-trained model

=head1 SYNOPSIS

The following tutorial is based on the L<TensorFlow Hub Object Detection Colab notebook|https://www.tensorflow.org/hub/tutorials/tf2_object_detection>. It uses a pre-trained model based on the I<CenterNet> architecture trained on the I<COCO 2017> dat...

Some of this code is identical to that of C<InferenceUsingTFHubMobileNetV2Model> notebook. Please look there for an explanation for that code. As stated there, this will later be wrapped up into a high-level library to hide the details behind an API.

=head1 COLOPHON

The following document is either a POD file which can additionally be run as a Perl script or a Jupyter Notebook which can be run in L<IPerl|https://p3rl.org/Devel::IPerl> (viewable online at L<nbviewer|https://nbviewer.org/github/EntropyOrg/perl-AI-...

=over

=item *

C<PDL::Graphics::Gnuplot> requires C<gnuplot>.

=back

If you are running the code, you may optionally install the L<C<tensorflow> Python package|https://www.tensorflow.org/install/pip> in order to access the C<saved_model_cli> command, but this is only used for informational purposes.

=head1 TUTORIAL

=head2 Load the library

First, we need to load the C<AI::TensorFlow::Libtensorflow> library and more helpers. We then create an C<AI::TensorFlow::Libtensorflow::Status> object and helper function to make sure that the calls to the C<libtensorflow> C library are working prop...

  use strict;
  use warnings;
  use utf8;
  use constant IN_IPERL => !! $ENV{PERL_IPERL_RUNNING};
  no if IN_IPERL, warnings => 'redefine'; # fewer messages when re-running cells
  
  use feature qw(say state postderef);
  use Syntax::Construct qw(each-array);
  
  use lib::projectroot qw(lib);
  
  BEGIN {
      if( IN_IPERL ) {
          $ENV{TF_CPP_MIN_LOG_LEVEL} = 3;
      }
      require AI::TensorFlow::Libtensorflow;
  }
  
  use URI ();
  use HTTP::Tiny ();
  use Path::Tiny qw(path);
  
  use File::Which ();
  
  use List::Util 1.56 qw(mesh);
  
  use Data::Printer ( output => 'stderr', return_value => 'void', filters => ['PDL'] );
  use Data::Printer::Filter::PDL ();
  use Text::Table::Tiny qw(generate_table);
  
  use Imager;
  
  my $s = AI::TensorFlow::Libtensorflow::Status->New;
  sub AssertOK {
      die "Status $_[0]: " . $_[0]->Message
          unless $_[0]->GetCode == AI::TensorFlow::Libtensorflow::Status::OK;
      return;

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

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%',
              })
          ),
      );
  }

=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 };
      $session->Run(
          undef,
          [ values %{$outputs{in} } ], [$t],
          \@values, \@outputs_t,
          undef,
          undef,
          $s
      );
      AssertOK($s);
  
      return { mesh \@keys, \@outputs_t };
  };
  
  undef;



  my $tftensor_output_by_name = $RunSession->($session, $t);
  
  my %pdl_output_by_name = map {
      $_ => FloatTFTensorToPDL( $tftensor_output_by_name->{$_} )
  } keys $tftensor_output_by_name->%*;
  
  undef;

=head2 Results summary

Then we use a score threshold to select the objects of interest.

  my $min_score_thresh = 0.30;
  
  my $which_detect = which( $pdl_output_by_name{detection_scores} > $min_score_thresh );
  
  my %subset;
  
  $subset{detection_boxes}   = $pdl_output_by_name{detection_boxes}->dice('X', $which_detect);
  $subset{detection_classes} = $pdl_output_by_name{detection_classes}->dice($which_detect);
  $subset{detection_scores}  = $pdl_output_by_name{detection_scores}->dice($which_detect);
  
  $subset{detection_class_labels}->@* = map { $labels_map{$_} } $subset{detection_classes}->list;
  
  p %subset;

The following uses the bounding boxes and class label information to draw boxes and labels on top of the image using Gnuplot.

  use PDL::Graphics::Gnuplot;
  
  my $plot_output_path = 'objects-detected.png';
  my $gp = gpwin('pngcairo', font => ",12", output => $plot_output_path, aa => 2, size => [10] );
  
  my @qual_cmap = ('#a6cee3','#1f78b4','#b2df8a','#33a02c','#fb9a99','#e31a1c','#fdbf6f','#ff7f00','#cab2d6');
  
  $gp->options(
      map {
          my $idx = $_;
          my $lc_rgb = $qual_cmap[ $subset{detection_classes}->slice("($idx)")->squeeze % @qual_cmap ];
  
          my $box_corners_yx_norm = $subset{detection_boxes}->slice([],$idx,[0,0,0]);
          $box_corners_yx_norm->reshape(2,2);
  
          my $box_corners_yx_img = $box_corners_yx_norm * $pdl_images[0]->shape->slice('-1:-2');
  
          my $from_xy = join ",", $box_corners_yx_img->slice('-1:0,(0)')->list;
          my $to_xy   = join ",", $box_corners_yx_img->slice('-1:0,(1)')->list;
          my $label_xy = join ",", $box_corners_yx_img->at(1,1), $box_corners_yx_img->at(0,1);
  
          (
              [ object => [ "rect" =>
                  from => $from_xy, to => $to_xy,
                  qq{front fs empty border lc rgb "$lc_rgb" lw 5} ], ],
              [ label => [
                  sprintf("%s: %.1f",
                      $subset{detection_class_labels}[$idx],
                      100*$subset{detection_scores}->at($idx,0) ) =>
                  at => $label_xy, 'left',
                  offset => 'character 0,-0.25',
                  qq{font ",12" boxed front tc rgb "#ffffff"} ], ],
          )
      } 0..$subset{detection_boxes}->dim(1)-1
  );
  
  $gp->plot(
      topcmds => q{set style textbox opaque fc "#505050f0" noborder},
      square => 1,
      yrange => [$pdl_images[0]->dim(2),0],
      with => 'image', $pdl_images[0],
  );
  
  $gp->close;
  
  IPerl->png( bytestream => path($plot_output_path)->slurp_raw ) if IN_IPERL;

=head1 RESOURCE USAGE

  use Filesys::DiskUsage qw/du/;
  
  my $total = du( { 'human-readable' => 1, dereference => 1 },
      $model_archive_path, $model_base );
  
  say "Disk space usage: $total"; undef;

=head1 CPANFILE

  requires 'AI::TensorFlow::Libtensorflow';
  requires 'AI::TensorFlow::Libtensorflow::DataType';
  requires 'Archive::Extract';
  requires 'Data::Printer';
  requires 'Data::Printer::Filter::PDL';
  requires 'FFI::Platypus::Buffer';
  requires 'FFI::Platypus::Memory';
  requires 'File::Which';
  requires 'Filesys::DiskUsage';
  requires 'HTML::Tiny';
  requires 'HTTP::Tiny';
  requires 'Imager';
  requires 'List::Util', '1.56';
  requires 'PDL';
  requires 'PDL::Graphics::Gnuplot';
  requires 'Path::Tiny';
  requires 'Syntax::Construct';
  requires 'Text::Table::Tiny';
  requires 'URI';
  requires 'constant';
  requires 'feature';
  requires 'lib::projectroot';
  requires 'strict';
  requires 'utf8';
  requires 'warnings';

=head1 AUTHOR

Zakariyya Mughal <zmughal@cpan.org>

=head1 COPYRIGHT AND LICENSE

This software is Copyright (c) 2022-2023 by Auto-Parallel Technologies, Inc.

This is free software, licensed under:

  The Apache License, Version 2.0, January 2004

=cut