C++ Processing Block sample

At this page, you'll learn how to run the Processing Block Demo Sample on Windows and Linux.

The processing_block_demo sample demonstrates the usage of Processing Block API and compatible components.

note

To run the processing_block_demo sample, you need to install Face SDK 3.15 or higher with Windows or Linux platform files (according to your OS).

• If Face SDK is not installed, follow the installation instructions Getting Started. Select platform in the "Selection Components" section.

• If Face SDK is installed without Windows or Linux platform files, use the utility maintenancetool and install platform by selecting it in the "Selection Components" section.

How to launch

Startup arguments:

• --input_image - mandatory, path to the input image file.
• --unit_type - optional, type of used processing block, default value is "objects", see the list of available types below.
• --sdk_path - optional, path to the Face SDK directory, default value is ".." to launch from the default location {Face SDK}/bin.
• --use_cuda - optional, acceleration of compatible blocks on GPU (CUDA), see Requirements.

The basic format of console command to launch processing_block_demo from the bin directory:

• Linux:

  ./processing_block_demo [--input_image <path_to_image>] [--unit_type <type_of_processing_block>] [--sdk_path <path_to_sdk_directory>] [--use_cuda]
• Windows:

  .\processing_block_demo.exe [--input_image <path_to_image>] [--unit_type <type_of_processing_block>] [--sdk_path <path_to_sdk_directory>] [--use_cuda]

List of available processing blocks (unit types)

• face - Face Detector
• body - Human Body Detector
• objects - Object Detector
• pose - Human Pose Estimator
• emotions - Emotion Estimator
• age - Age Estimator
• gender - Gender Estimator
• liveness - 2D RGB Liveness Estimator
• quality - Quality Assessment Estimator

Launch example

Console commands to launch the sample from the bin directory with the "body" processing block (unit type):

• Linux:

  ./processing_block_demo --input_image group/01.jpg --unit_type body

• Windows:

  .\processing_block_demo.exe --input_image group\01.jpg --unit_type body

  The processing results will be displayed in the window.

  

  Result of body detection

Error messages, if any, are also printed in the console.

Troubleshooting

• Error Assertion failed (ERROR: not found libonnxruntime.so), error code: 0x032ad038:

  • Check existence of the file lib/libonnxruntime.so in the Face SDK's root directory.
  • Add the path to the directory that contains the file libonnxruntime.so to environment variable LD_LIBRARY_PATH.

• Error Assertion failed (ERROR: not found onnxruntime.dll), error code: 0x032ad038:

  • Check existence of the file bin\onnxruntime.dll in the Face SDK's root directory.

note

Source code of the processing_block_demo sample available at the link. Also, the source code and instructions of building (file README.txt) are available in the examples/cpp/ directory of the Face SDK distributive.