Getting started

Processing Block API is a scalable interface that replaces Legacy API for easier integration of Face SDK capabilities into your application.

Key features

• Multiple components combined into a single integration
• Simplicity and ease of learning
• Rapid implementation
• Long-term support and updates

Requirements

• Windows x86 64-bit or Linux x86 64-bit.
• Face SDK windows_x86_64 or linux_x86_64 is installed (see Getting Started).

Context-container

Processing Block API is based on the use of Context. Context is a heterogeneous container that consists of a set of hierarchically organized data presented in the form of key–value pairs. The closest analogue of Context is a JSON object. Each Context object can contain a scalar object (integer, real, boolean, string), a memory area or pointer, a sequential array of Context objects, or an associative container of string-Context pairs, with unlimited nesting.

How to create and use a Context object

1. Create a FacerecService.

2. Create a Context-container:

   C++

   auto array_elem0 = service->createContext();

   Python

   array_elem0 = service.createContext({})

   Flutter

   Context array_elem0 = service.createContext({});

   C#

   Context array_elem0 = service.CreateContext(new());

   Java

   Context array_elem0 = service.createContext();

3. Common set of operations with a Context-container:

• creating an associative container by calling ["key"] on empty Context:

  C++

  array_elem0["name"] = "Julius Zeleny";      // pass string
  array_elem0["phone"] = 11111111111l;        // pass integer (long)
  array_elem0["social_score"] = 0.999;        // pass double
  array_elem0["verified"] = true;             // pass bool

  Python

  array_elem0["name"] = "Julius Zeleny"       # pass string
  array_elem0["phone"] = 11111111111          # pass integer
  array_elem0["social_score"] = 0.999         # pass double
  array_elem0["verified"] = True              # pass bool

  Flutter

  array_elem0["name"] = "Julius Zeleny";       // pass string
  array_elem0["phone"] = 11111111111;          // pass integer
  array_elem0["social_score"] = 0.999;         // pass double
  array_elem0["verified"] = true;              // pass bool

  C#

  array_elem0["name"] = "Julius Zeleny";       // pass string
  array_elem0["phone"] = 11111111111L;         // pass integer
  array_elem0["social_score"] = 0.999;         // pass double
  array_elem0["verified"] = true;              // pass bool

  Java

  array_elem0.get("name").setString("Julius Zeleny");       // pass string
  array_elem0.get("phone").setLong(11111111111l);           // pass integer
  array_elem0.get("social_score").setDouble(0.99);          // pass double
  array_elem0.get("verified").setBool(true);                // pass bool

• getters:

  C++

  ASSERT_EQ( array_elem0["name"].getString(), "Julius Zeleny" );
  ASSERT_EQ( array_elem0["phone"].getLong(), 11111111111l );
  ASSERT_EQ( array_elem0["social_score"].getDouble(),  0.999 );
  ASSERT_EQ( array_elem0["verified"].getBool(), true );

  Python

  assert array_elem0["name"].get_value(), "Julius Zeleny"
  assert array_elem0["phone"].get_value() == 11111111111
  assert array_elem0["social_score"].get_value() ==  0.999
  assert array_elem0["verified"].get_value() == True

  Flutter

  assert (array_elem0["name"].get_value() == "Julius Zeleny");
  assert (array_elem0["phone"].get_value() == 11111111111);
  assert (array_elem0["social_score"].get_value() ==  0.999);
  assert (array_elem0["verified"].get_value() == true);

  C#

  Debug.Assert(array_elem0["name"].GetString() == "Julius Zeleny");
  Debug.Assert(array_elem0["phone"].GetLong() == 11111111111L);
  Debug.Assert(array_elem0["social_score"].GetDouble() ==  0.999);
  Debug.Assert(array_elem0["verified"].GetBool() == true);

  Java

  assertTrue(array_elem0.get("name").getString().equals("Julius Zeleny"));
  assertTrue(array_elem0.get("phone").getLong() == 11111111111l);
  assertTrue(array_elem0.get("social_score").getDouble() == 0.99);
  assertTrue(array_elem0.get("verified").getBool() == true);

• creating a sequence array by calling push_back on empty Context:

  C++

  auto array == service->createContext();
  array.push_back(array_elem0);

  Python

  array = service.create_context([])
  array.push_back(array_elem0)

  Flutter

  Context array = service.createContext([]);
  array.pushBack(array_elem0);

  C#

  Context array == service->CreateContext(new());
  array.PushBack(array_elem0);

  Java

  Context array = service.createContext();
  array.pushBack(array_elem0);

• iterating over array:

  C++

  
  // get by index
  ASSERT_EQ( array[0]["phone"].getLong(), 11111111111l );
  
  // iterate with index
  size_t array_sz = array.size();
  for(size_t i = 0; i < array_sz; ++i)
    array[i]["phone"];
  
  // or with iterators
  for(auto iter = array.begin(); iter != array.end(); ++iter)
    (*iter)["phone"]; // deference returns nested Context
  
  // or с foreach
  for(auto val : array)
    val["phone"];

  Python

  # get by index
  assert array[0]["phone"].get_value() == 11111111111
  
  # iterate with index
  for i in range(len(array)):
      array[i]["phone"]
  
  # or with iterators
  for elem in array:
      elem["phone"]
  

  Flutter

  // get by index
  assert (array[0]["phone"].get_value() == 11111111111);
  
  // iterate with index
  for (int i = 0; i < array.len(); i++)
    array[i]["phone"];

  C#

  // get by index
  Debug.Assert(array[0]["phone"].GetLong() == 11111111111L);
  
  // iterate with index
  for (long i = 0; i < array.Length(); i++)
    array[i]["phone"];

  Java

  // get by index
  assertTrue(array.get(0).get("phone").getLong() == 11111111111l);
  
  // iterate with index
  for (int i = 0; i < array.size(); i++)
    array.get(i).get("phone");

• operations with a nested associative container:

  C++

  auto full = service->createContext();
  full["friends"] = std::move(array); // move assignment without copying
  
  // access to the nested object
  ASSERT_EQ( full["friends"][0]["social_score"].getDouble(), 0.999 );
  
  // iterate over associative containers values
  for(auto iter = full.begin(); iter != full.end(); ++iter) {
    iter.key(); // get the key value from iterator
    (*iter)[0]["social_score"].getDouble(); // get the value
  }
  
  // с foreach
  for(auto val : full)
    val[0]["social_score"].getDouble();

  Python

  full = service.create_context()
  full["friends"] = array.to_dict()
  
  # access to the nested object
  assert full["friends"][0]["social_score"].get_value() == 0.999
  
  # iterate over associative containers values
  for key in full.keys():
      full[key][0]["social_score"].get_value()
  

  Flutter

  Context full = service.createContext({});
  full["friends"] = array.toMap();
  
  // access to the nested object
  assert (full["friends"][0]["social_score"].get_value() == 0.999);
  
  // iterate over associative containers values
  for (var key in full.getKeys())
    full[key][0]["social_score"].get_value();

  C#

  Context full = service.createContext(new());
  full["friends"] = array;
  
  // access to the nested object
  Debug.Assert(full["friends"][0]["social_score"].GetDouble() == 0.999);
  
  // iterate over associative containers values
  foreach (String key in full.GetKeys())
    full[key][0]["social_score"].GetDouble();

  Java

  Context full = service.createContext();
  full.get("friends").setContext(array);
  
  // access to the nested object
  assertTrue(full.get("friends").get(0).get("social_score").getDouble() == 0.999);
  
  // iterate over associative containers values
  for (String key : full.getKeys())
  {
    full.get(key).get(0).get("social_score").getDouble();
  }
  

• other Context's convenient methods:

  C++

  void clear()
  bool contains(const std::string& key);       // for an assosiative container
  Context operator[](size_t index);           // for a sequence array,  access specified element with bounds checking
  Context operator[](const std::string& key);  // for an assosiative container, access or insert
  Context at(const std::string& key);          // for an assosiative container, with bounds checking
  size_t size();                               // returned elements count for a container
  bool isNone();                               // is empty
  bool isArray();                              // is a sequence array
  bool isObject();                             // is an assosiative container
  bool isLong(), isDouble(), isString(), isBool(); // check if contains a certain scalar type

  Python

  def to_dict(self) -> dict                          # converts context to dictionary
  def is_none(self) -> bool                          # is empty
  def is_array(self) -> bool                         # check for sequential array
  def is_object(self) -> bool                        # check for associative container
  def is_long, is_double, is_string, is_bool -> bool # check for a scalar data type

  Flutter

  Context operator[](int index)                // for a sequence array,  access specified element with bounds checking
  Context operator[](String key)               // for an assosiative container, access or insert
  int len()                                    // returned elements count for a container
  bool is_none()                               // is empty
  bool is_array()                              // is a sequence array
  bool is_object()                             // is an assosiative container
  bool is_long(), is_double(), is_string(), is_bool() // check if contains a certain scalar type

  C#

  bool Contains(string key);                   // for an assosiative container
  Context this[int index];                     // for a sequence array,  access specified element with bounds checking
  Context this[string key];                    // for an assosiative container, access or insert
  Context GetByKey(string key);                // for an assosiative container, with bounds checking
  Context GetByIndex(int index);               // for an assosiative container, with bounds checking
  ulong Length();                              // returned elements count for a container
  bool IsNone();                               // is empty
  bool IsArray();                              // is a sequence array
  bool IsObject();                             //  is an assosiative container
  bool IsLong(), IsDouble(), IsString(), IsBool(); // check if contains a certain scalar type

  Java

  void clear();
  boolean contains(String key);                   // for an assosiative container
  Context get(long index);                        // for a sequence array,  access specified element with bounds checking
  Context get(String key);                        // for an assosiative container, access or insert
  long size();                                    // returned elements count for a container
  boolean isNone();                               // is empty
  boolean isArray();                              // is a sequence array
  boolean isObject();                             // is an assosiative container
  boolean isLong(), isDouble(), isString(), isBool(); // check if contains a certain scalar type

• FacerecService methods connected with Context:

  C++

  // get Context from image file
  pbio::Context createContextFromEncodedImage(const uint8_t* data, uint64_t dataSize);
  pbio::Context createContextFromEncodedImage(const std::vector<uint8_t>& data);
  pbio::Context createContextFromEncodedImage(const std::string& data);
  pbio::Context createContextFromEncodedImage(const std::vector<char>& data);
  
  // get Context from image bytes
  pbio::Context createContextFromFrame(uint8_t* data, int32_t width, int32_t height, pbio::Context::Format format, int32_t baseAngle);

  Python

  # get Context from image file
  def create_context_from_encoded_image(self, data: bytes) -> Context
  
  # get Context from image bytes
  def create_context_from_frame(self, data: bytes, width: int, height: int, format: ContextFormat, base_angle: int) -> Context:

  Flutter

  // get Context from image file
  Context createContextFromEncodedImage(Uint8List data);
  
  // get Context from image bytes
  Context createContextFromFrame(Uint8List data, int width, int height, {ContextFormat format, int baseAngle});

  C#

  // get Context from image file
  Context CreateContextFromImage(byte[] data);
  
  // get Context from image bytes
  Context CreateContextFromFrame(byte[] data, int width, int height, Context.Format format, int baseAngle);

  Java

  // get Context from image file
  Context createContextFromEncodedImage(byte[] data);
  
  // get Context from image bytes
  Context createContextFromFrame(byte[] data, int width, int height, Context.Format format, int baseAngle);

Binary image format

Most of the processing blocks operate on Context with an image in binary format:

{
 "image" : { "format": "NDARRAY",
             "blob": "data pointer",
             "dtype": "uint8_t",
             "shape": [height, width, channels] }
}

The "blob" key contains a smart pointer to data. The pointer is set by the function void Context::setDataPtr(void* ptr, int copy_sz), where copy_sz is the size of memory in Bytes, that will be copied, and then automatically released when Context objects lifetime ends.

Copying will not perform if 0 is passed as argument copy_sz. In this case the Context object does not control the lifetime of the object it points to. You can also allocate a raw memory, f.e. to copy data later, passing nullptr and size as arguments of setDataPtr.

The "dtype" can contain one of these values: "uint8_t", "int8_t", "uint16_t", "int16_t", "int32_t", "float", "double". This is according to OpenCV types: CV_8U, CV_8S, CV_16U, CV_16S, CV_32S, CV_32F, CV_64F.

Create a Context-container with RGB-image

1. Create a FacerecService.

C++

2. Read an image from the file:

std::string inputImagePath = "{path_to_image}";
std::ifstream imageFile(inputImagePath, std::ios::binary);
std::istreambuf_iterator<char> start(file);
std::vector<char> imageData(start, std::istreambuf_iterator<char>());

3 Create a Context container with an image using the createContextFromEncodedImage() method

pbio::Context ioData = service->createContextFromEncodedImage(imageData);

Python

2. Read an image from the file:

input_image_path = "{path_to_image}"
image_data = bytes()
with open(input_image_path, "rb") as image_file:
    image_data = image_file.read()

3. Create a Context container with an image using the create_context_from_encoded_image() method:

ioData = service.create_context_from_encoded_image(image_data)

Flutter

2. Read an image from the file:

File file = File("{imagePath}");
final Uint8List bytes = await file.readAsBytes();

3. Create a Context container with an image using the createContextFromEncodedImage() method:

Context ioData = service.createContextFromEncodedImage(bytes);

C#

2. Read an image from the file:

string inputImagePath = "<path_to_image>"
byte[] imageData = File.ReadAllBytes(inputImagePath);

3. Create a Context container with an image using the CreateContextFromImage() method:

Context ioData = service.CreateContextFromImage(imageData);

Java

2. Read an image from the file:

final String inputImagePath = "<path_to_image>";
byte[] imageData = Files.readAllBytes(Paths.get(inputImagePath));

3. Create a Context container with an image using the createContextFromEncodedImage() method:

Context ioData = service.createContextFromEncodedImage(imageData);

Processing Blocks

Processing Blocks types

• FACE_DETECTOR
• HUMAN_BODY_DETECTOR
• HUMAN_POSE_ESTIMATOR
• OBJECT_DETECTOR
• FACE_FITTER
• EMOTION_ESTIMATOR
• AGE_ESTIMATOR
• GENDER_ESTIMATOR
• MASK_ESTIMATOR
• LIVENESS_ESTIMATOR
• QUALITY_ASSESSMENT_ESTIMATOR
• FACE_TEMPLATE_EXTRACTOR
• TEMPLATE_INDEX
• MATCHER_MODULE
• VERIFICATION_MODULE

note

Examples of using Processing Block API are demonstrated in:

• Samples processing_block_demo in C++
• Python examples examples/python/processing_blocks/
• Samples processing_block_demo in Flutter

Processing Block parameters

• unit_type: string — main parameter of the processing block, defines the type of the created module.
• modification: string — optional parameter, defines modification of the processing block. If not specified, the default value will be used.
• version: int64 — optional parameter, defines the version of modification of the processing block. If not specified, the default value will be used.
• model_path: string — optional parameter, defines the path to the processing block model. If not specified, the default value will be used.
• use_cuda: bool — optional parameter, responsible for starting the processing block on GPU. The default value is false.
• use_legacy: bool — optional parameter, needed to use older onnxruntime library. The default value is false.
• ONNXRuntime — key for onnxruntime configuration parameters.
  • library_path: string — path to the onnxruntime libraries, by default the path to the libfacerec.so directory.
  • intra_op_num_threads: int64 — number of threads for paralleling the module, the default value is 1.

Processing Block usage

1. Create a Context-container, specify the parameters you need and pass it to the FacerecService.createProcessingBlock() method.

   C++

   // mandatory, specify the name of processing block
   auto configCtx =  service->createContext();
   configCtx["unit_type"] = "<name_of_processing_block>";
   
   // if omitted, the default value will be used
   configCtx["modification"] = "<modification>";
   
   // if not specified, the first version of the modification will be used
   configCtx["version"] = <version>;
   
   // the default models are located in the Face SDK distribution directory: share/processing_block/<modification>/(<version>/ or <version>.enc)
   // you can set your own path to the model
   configCtx["model_path"] = "<path_to_model_file>";
   
   // default location of the onnxruntime library in <FaceSDKShortProductName /> distribution: the "lib" folder for Linux platfrom or the "bin" folder for Windows platfrom
   // you can specify your own path to onnxruntime library
   // if value is not specified, the os-specific default search order will be used
   configCtx["ONNXRuntime"]["library_path"] = "../lib"; // for Linux
   configCtx["ONNXRuntime"]["library_path"] = "../bin"; // for Windows
   
   // optional, "true" if you want to use GPU acceleration (CUDA) for processing block that support it
   configCtx["use_cuda"] = false;
   pbio::ProcessingBlock processing_block = service->createProcessingBlock(configCtx);

   Python

   configDict = {};
   # mandatory, specify the name of processing block
   configDict["unit_type"] = "<name_of_processing_block>"
   
   # if omitted, the default value will be used
   configDict["modification"] = "<modification>"
   
   # if not specified, the first version of the modification will be used
   configDict["version"] = <version>
   
   # the default models are located in the Face SDK distribution directory: share/processing_block/<modification>/(<version>/ or <version>.enc)
   # you can set your own path to the model
   configDict["model_path"] = "<path_to_model_file>"
   
   # default location of the onnxruntime library in Face SDK folder for Linux platfrom or the "bin" folder for Windows platfrom
   # you can specify your own path to onnxruntime library
   # if value is not specified, the os-specific default search order will be used
   configDict["ONNXRuntime"]["library_path"] = "../lib" # for Linux
   configDict["ONNXRuntime"]["library_path"] = "../bin" # for Windows
   
   # optional, "true" if you want to use GPU acceleration (CUDA) for processing block that support it
   configDict["use_cuda"] = False
   
   processing_block = service.create_processing_block(configDict);

   Flutter

   Map<String, dynamic> configMap = {};
   // mandatory, specify the name of processing block
   configMap["unit_type"] = "<name_of_processing_block>";
   
   // if omitted, the default value will be used
   configMap["modification"] = "<modification>";
   
   // if not specified, the first version of the modification will be used
   configMap["version"] = <version>;
   
   // the default models are located in the Face SDK distribution directory: share/processing_block/<modification>/(<version>/ or <version>.enc)
   // you can set your own path to the model
   configMap["model_path"] = "<path_to_model_file>";
   
   processing_block = service.createProcessingBlock(configMap);

   C#

   Dictionary<object, object> configDict = new Dictionary<object, object>();
   // mandatory, specify the name of processing block
   configDict["unit_type"] = "<name_of_processing_block>"
   
   // if omitted, the default value will be used
   configDict["modification"] = "<modification>"
   
   // if not specified, the first version of the modification will be used
   configDict["version"] = <version>
   
   // the default models are located in the Face SDK distribution directory: share/processing_block/<modification>/(<version>/ or <version>.enc)
   // you can set your own path to the model
   configDict["model_path"] = "<path_to_model_file>"
   
   / default location of the onnxruntime library in <FaceSDKShortProductName /> distribution: the "lib" folder for Linux platfrom or the "bin" folder for Windows platfrom
   // you can specify your own path to onnxruntime library
   // if value is not specified, the os-specific default search order will be used
   configDict["ONNXRuntime"]["library_path"] = "../lib" # для Linux
   configDict["ONNXRuntime"]["library_path"] = "../bin" # для Windows
   
   // optional, "true" if you want to use GPU acceleration (CUDA) for processing block that support it
   configDict["use_cuda"] = False
   ProcessingBlock processingBlock = service.CreateProcessingBlock(configDict);

   Java

   // mandatory, specify the name of processing block
   Context configCtx = service.createContext();
   configCtx.get("unit_type").setString("{name_of_processing_block}");
   
   // if omitted, the default value will be used
   configCtx.get("modification").setString("{modification}");
   
   // if not specified, the first version of the modification will be used
   configCtx.get("version").setLong({version});
   
   // the default models are located in the Face SDK distribution directory: share/processing_block/<modification>/(<version>/ or <version>.enc)
   // you can set your own path to the model
   configCtx.get("model_path").setString("{path_to_model_file}");
   
   // default location of the onnxruntime library in <FaceSDKShortProductName /> distribution: the "lib" folder for Linux platfrom or the "bin" folder for Windows platfrom
   // you can specify your own path to onnxruntime library
   // if value is not specified, the os-specific default search order will be used
   configCtx.get("ONNXRuntime").get("library_path").setString("../lib"); // для Linux
   configCtx.get("ONNXRuntime").get("library_path").setString("../bin"); // для Windows
   
   // optional, "true" if you want to use GPU acceleration (CUDA) for processing block that support it
   configCtx.get("use_cuda").setBool(false);
   
   ProcessingBlock processing_block = service.createProcessingBlock(configCtx);

2. Prepare input Context and pass it to processing block

   C++

   std::string input_image_path = "{path_to_image}";
   cv::Mat image = cv::imread(input_image_path, cv::IMREAD_COLOR);
   cv::Mat input_image;
   cv::cvtColor(image, input_image, cv::COLOR_BGR2RGB);
   
   // creating a Context container with a binary image
   auto imgCtx = service->createContext();
   pbio::context_utils::putImage(imgCtx, input_image.data, input_image.rows, input_image.cols, pbio::IRawImage::FORMAT_RGB, true);
   
   // creating the input Context
   auto ioData = service->createContext();
   ioData["image"] = imgCtx;
   
   // Processing Block call
   processing_block(ioData);

   Python

   input_image_path = "{path_to_image}"
   image = cv2.imread(input_image_path, cv2.IMREAD_COLOR)
   input_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
   
   # creating a Context container with a binary image
   imgDict = {
       "blob": input_image.tobytes(),
       "dtype": "uint8_t",
       "format": "NDARRAY",
       "shape": [dim for dim in input_image.shape]
   }
   imgCtx = service.create_context(imgDict)
   
   # creating the input Context
   ioData = service.create_context({})
   ioData["image"] = imgCtx;
   
   # Processing Block call
   processing_block(ioData);

   Flutter

   File file = File(imagePath);
   final Uint8List bytes = await file.readAsBytes();
   final ImageDescriptor descriptor = await ImageDescriptor.encoded(await ImmutableBuffer.fromUint8List(bytes));
   Map<String, dynamic> imageContext = {
       "blob": bytes,
       "dtype": "uint8_t",
       "format": "NDARRAY",
       "shape": [descriptor.height, descriptor.width, 3]
   };
   
   // creating the input Context
   ioData = service.createContext({
       "objects": [],
       "image": {
           "blob": {byte array with RGB image},
           "dtype": "uint8_t",
           "format": "NDARRAY",
           "shape": [{image height in px}, {image width in px}, 3]
       }
   });
   
   // Processing Block call
   processing_block.process(ioData);

   C#

   string inputImagePath = "<path_to_image>"
   Mat image = Cv2.ImRead(inputImagePath);
   Mat inputImage = new();
   Cv2.CvtColor(image, inputImage, ColorConversionCodes.BGR2RGB);
   
   // creating a Context container with a binary image
   Dictionary<int, string> CvTypeToStr = new()
   {
       { MatType.CV_8U, "uint8_t" }, { MatType.CV_8S, "int8_t" },
       { MatType.CV_16U, "uint16_t" }, { MatType.CV_16S, "int16_t" },
       { MatType.CV_32S, "int32_t" }, { MatType.CV_32F, "float" }, { MatType.CV_64F, "double" }
   };
   Dictionary<object, object> imgDict = new();
   
   var inputImage = img.IsContinuous() ? img : img.Clone();
   long size = inputImage.Total() * inputImage.ElemSize();
   List<object> sizes = [];
   byte[] buffer = new byte[size];
   
   using (Mat temp = new(inputImage.Rows, inputImage.Cols, inputImage.Type(), buffer))
   {
       inputImage.CopyTo(temp);
   }
   
   for (int i = 0; i < inputImage.Dims; ++i)
   {
       sizes.Add(inputImage.Size(i));
   }
   
   sizes.Add(inputImage.Channels());
   
   imgDict["blob"] = buffer;
   imgDict["format"] = "NDARRAY";
   imgDict["shape"] = sizes;
   imgDict["dtype"] = CvTypeToStr[inputImage.Depth()];
   
   // creating the input Context
   Context ioData = service.CreateContext
   (
       new Dictionary<object, object>
       {
           { "image", imageContext }
       }
   );
   
   // Processing Block call
   processingBlock.Invoke(ioData);

   Java

   final String inputImagePath = "<path_to_image>";
   final File file = new File(inputImagePath);
   final BufferedImage img = ImageIO.read(file);
   
   // creating the input Context
   Context ioData = service.createContext();
   
   // creating a Context container with a binary image
   Context imgCtx = ioData.get("image");
   final byte[] pixels = ((DataBufferByte) img.getRaster().getDataBuffer()).getData();
   
   imgCtx.get("format").setString("NDARRAY");
   imgCtx.get("dtype").setString("uint8_t");
   imgCtx.get("blob").setDataBytes(pixels);
   Context shapeImgCtx = imgCtx.get("shape");
   shapeImgCtx.pushBack(img.getHeight());
   shapeImgCtx.pushBack(img.getWidth());
   shapeImgCtx.pushBack(3l);
   
   // Processing Block call
   processing_block.process(ioData);

GPU acceleration

Processing Blocks can be used with GPU acceleration (CUDA). To activate acceleration you need to define the ["use_cuda"] key with the true value for Processing Block configuration container. To start processing blocks on cuda-10.1, it is necessary to define the key "use_legacy" with the value true for the Context container of the Processing Block. The system requirements are available here.