AI-TensorFlow-Libtensorflow

 view release on metacpan or  search on metacpan

lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubMobileNetV2Model.pod  view on Meta::CPAN

  die "Labels should have @{[ IMAGENET_LABEL_COUNT_WITH_BG ]} items"
      unless @labels == IMAGENET_LABEL_COUNT_WITH_BG;
  say "Got labels: ", join( ", ", List::Util::head(5, @labels) ), ", etc.";

B<STREAM (STDOUT)>:

  Downloading https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/classification/5?tf-hub-format=compressed to google_imagenet_mobilenet_v2_100_224_classification_5.tar.gz
  Downloading https://storage.googleapis.com/download.tensorflow.org/data/ImageNetLabels.txt to ImageNetLabels.txt
  Saved model is in google_imagenet_mobilenet_v2_100_224_classification_5/saved_model.pb
  Got labels: background, tench, goldfish, great white shark, tiger shark, etc.

B<RESULT>:

  1

=head2 Load the model and session

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

  my @tags = ( 'serve' );

B<RESULT>:

  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.";
  }

B<STREAM (STDOUT)>:

  The given SavedModel SignatureDef contains the following input(s):
    inputs['inputs'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 224, 224, 3)
        name: serving_default_inputs:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['logits'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 1001)
        name: StatefulPartitionedCall:0
  Method name is: tensorflow/serving/predict

B<RESULT>:

  1

The above C<saved_model_cli> output shows that the model input is at C<serving_default_inputs:0> which means the operation named C<serving_default_inputs> at index C<0> and the output is at C<StatefulPartitionedCall:0> which means the operation named...

It also shows the type and shape of the C<TFTensor>s for those inputs and outputs. Together this is known as a signature.

For the C<input>, we have C<(-1, 224, 224, 3)> which is a L<common input image specification for TensorFlow Hub|https://www.tensorflow.org/hub/common_signatures/images#input>. This is known as C<channels_last> (or C<NHWC>) layout where the TensorFlow...

For the C<output>, we have C<(-1, 1001)> which is C<[batch_size, num_classes]> where the elements are scores that the image received for that ImageNet class.

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  => $graph->OperationByName('serving_default_inputs'),
      out => $graph->OperationByName('StatefulPartitionedCall'),
  );
  
  die "Could not get all operations" unless List::Util::all(sub { defined }, values %ops);
  
  my %outputs = map { $_ => [ AI::TensorFlow::Libtensorflow::Output->New( { oper => $ops{$_}, index => 0 } ) ] }
      keys %ops;
  
  p %outputs;
  
  say "Input: " , $outputs{in}[0];
  say "Output: ", $outputs{out}[0];

B<STREAM (STDOUT)>:

  Input: serving_default_inputs:0
  Output: StatefulPartitionedCall:0

B<STREAM (STDERR)>:

=for html <span style="display:inline-block;margin-left:1em;"><pre style="display: block"><code><span style="color: #33ccff;">{</span><span style="">
    </span><span style="color: #6666cc;">in</span><span style=""> </span><span style="color: #33ccff;">   </span><span style="color: #33ccff;">[</span><span style="">
        </span><span style="color: #9999cc;">[0] </span><span style="color: #cc66cc;">AI::TensorFlow::Libtensorflow::Output</span><span style=""> </span><span style="color: #33ccff;">{</span><span style="">
                </span><span style="color: #6666cc;">index</span><span style="color: #33ccff;">   </span><span style="color: #ff6633;">0</span><span style="color: #33ccff;">,</span><span style="">
                </span><span style="color: #6666cc;">oper</span><span style=""> </span><span style="color: #33ccff;">   </span><span style="color: #cc66cc;">AI::TensorFlow::Libtensorflow::Operation</span><span style=""> </span><span style="color: #33...
                    </span><span style="color: #6666cc;">Name</span><span style="">      </span><span style="color: #33ccff;">   </span><span style="color: #33ccff;">&quot;</span><span style="color: #669933;">serving_default_inputs</span><span style=...
                    </span><span style="color: #6666cc;">NumInputs</span><span style=""> </span><span style="color: #33ccff;">   </span><span style="color: #ff6633;">0</span><span style="color: #33ccff;">,</span><span style="">
                    </span><span style="color: #6666cc;">NumOutputs</span><span style="color: #33ccff;">   </span><span style="color: #ff6633;">1</span><span style="color: #33ccff;">,</span><span style="">
                    </span><span style="color: #6666cc;">OpType</span><span style="">    </span><span style="color: #33ccff;">   </span><span style="color: #33ccff;">&quot;</span><span style="color: #669933;">Placeholder</span><span style="color: #33...
                </span><span style="color: #33ccff;">}</span><span style="">
            </span><span style="color: #33ccff;">}</span><span style="">
    </span><span style="color: #33ccff;">]</span><span style="color: #33ccff;">,</span><span style="">
    </span><span style="color: #6666cc;">out</span><span style="color: #33ccff;">   </span><span style="color: #33ccff;">[</span><span style="">
        </span><span style="color: #9999cc;">[0] </span><span style="color: #cc66cc;">AI::TensorFlow::Libtensorflow::Output</span><span style=""> </span><span style="color: #33ccff;">{</span><span style="">
                </span><span style="color: #6666cc;">index</span><span style="color: #33ccff;">   </span><span style="color: #ff6633;">0</span><span style="color: #33ccff;">,</span><span style="">
                </span><span style="color: #6666cc;">oper</span><span style=""> </span><span style="color: #33ccff;">   </span><span style="color: #cc66cc;">AI::TensorFlow::Libtensorflow::Operation</span><span style=""> </span><span style="color: #33...
                    </span><span style="color: #6666cc;">Name</span><span style="">      </span><span style="color: #33ccff;">   </span><span style="color: #33ccff;">&quot;</span><span style="color: #669933;">StatefulPartitionedCall</span><span style...
                    </span><span style="color: #6666cc;">NumInputs</span><span style=""> </span><span style="color: #33ccff;">   </span><span style="color: #ff6633;">263</span><span style="color: #33ccff;">,</span><span style="">
                    </span><span style="color: #6666cc;">NumOutputs</span><span style="color: #33ccff;">   </span><span style="color: #ff6633;">1</span><span style="color: #33ccff;">,</span><span style="">
                    </span><span style="color: #6666cc;">OpType</span><span style="">    </span><span style="color: #33ccff;">   </span><span style="color: #33ccff;">&quot;</span><span style="color: #669933;">StatefulPartitionedCall</span><span style...
                </span><span style="color: #33ccff;">}</span><span style="">
            </span><span style="color: #33ccff;">}</span><span style="">
    </span><span style="color: #33ccff;">]</span><span style="">



( run in 0.723 second using v1.01-cache-2.11-cpan-39bf76dae61 )