AI-TensorFlow-Libtensorflow

 view release on metacpan or  search on metacpan

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

# PODNAME: AI::TensorFlow::Libtensorflow::Manual::Notebook::InferenceUsingTFHubCenterNetObjDetect


## DO NOT EDIT. Generated from notebook/InferenceUsingTFHubCenterNetObjDetect.ipynb using ./maint/process-notebook.pl.

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 $_[0]->GetCode == AI::TensorFlow::Libtensorflow::Status::OK;
    return;
}
AssertOK($s);

use PDL;
use AI::TensorFlow::Libtensorflow::DataType qw(FLOAT UINT8);

use FFI::Platypus::Memory qw(memcpy);
use FFI::Platypus::Buffer qw(scalar_to_pointer);

sub FloatPDLTOTFTensor {
    my ($p) = @_;
    return AI::TensorFlow::Libtensorflow::Tensor->New(
        FLOAT, [ reverse $p->dims ], $p->get_dataref, sub { undef $p }
    );
}

sub FloatTFTensorToPDL {
    my ($t) = @_;

    my $pdl = zeros(float,reverse( map $t->Dim($_), 0..$t->NumDims-1 ) );

    memcpy scalar_to_pointer( ${$pdl->get_dataref} ),
        scalar_to_pointer( ${$t->Data} ),
        $t->ByteSize;
    $pdl->upd_data;

    $pdl;
}

sub Uint8PDLTOTFTensor {
    my ($p) = @_;
    return AI::TensorFlow::Libtensorflow::Tensor->New(
        UINT8, [ reverse $p->dims ], $p->get_dataref, sub { undef $p }
    );
}

sub Uint8TFTensorToPDL {
    my ($t) = @_;

    my $pdl = zeros(byte,reverse( map $t->Dim($_), 0..$t->NumDims-1 ) );

    memcpy scalar_to_pointer( ${$pdl->get_dataref} ),
        scalar_to_pointer( ${$t->Data} ),
        $t->ByteSize;
    $pdl->upd_data;

    $pdl;
}

# image_size => [width, height] (but usually square images)

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

    },
);

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;

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

=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 $_[0]->GetCode == AI::TensorFlow::Libtensorflow::Status::OK;
      return;
  }
  AssertOK($s);

And create helpers for converting between C<PDL> ndarrays and C<TFTensor> ndarrays.

  use PDL;
  use AI::TensorFlow::Libtensorflow::DataType qw(FLOAT UINT8);
  
  use FFI::Platypus::Memory qw(memcpy);
  use FFI::Platypus::Buffer qw(scalar_to_pointer);
  
  sub FloatPDLTOTFTensor {
      my ($p) = @_;
      return AI::TensorFlow::Libtensorflow::Tensor->New(
          FLOAT, [ reverse $p->dims ], $p->get_dataref, sub { undef $p }
      );
  }
  
  sub FloatTFTensorToPDL {
      my ($t) = @_;
  
      my $pdl = zeros(float,reverse( map $t->Dim($_), 0..$t->NumDims-1 ) );
  
      memcpy scalar_to_pointer( ${$pdl->get_dataref} ),
          scalar_to_pointer( ${$t->Data} ),
          $t->ByteSize;
      $pdl->upd_data;
  
      $pdl;
  }
  
  sub Uint8PDLTOTFTensor {
      my ($p) = @_;
      return AI::TensorFlow::Libtensorflow::Tensor->New(
          UINT8, [ reverse $p->dims ], $p->get_dataref, sub { undef $p }
      );
  }
  
  sub Uint8TFTensorToPDL {
      my ($t) = @_;
  
      my $pdl = zeros(byte,reverse( map $t->Dim($_), 0..$t->NumDims-1 ) );
  
      memcpy scalar_to_pointer( ${$pdl->get_dataref} ),
          scalar_to_pointer( ${$t->Data} ),
          $t->ByteSize;
      $pdl->upd_data;
  
      $pdl;
  }

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

  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%',
              })
          ),
      );
  }

=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( $tftensor_output_by_name->{$_} )



( run in 2.173 seconds using v1.01-cache-2.11-cpan-39bf76dae61 )