Inference Engine Samples

The Inference Engine sample applications are simple console applications that demonstrate how you can use the Inference Engine in your applications.

The OpenVINO™ toolkit sample and demo applications are available in the <INSTALL_DIR>/deployment_tools/inference_engine/samples directory. The difference between samples, tools and demos is the following:

• Samples and tools are mostly simple applications that demonstrate the Inference Engine API.
• Demos are more complicated applications that demonstrate the usage of Inference Engine API to solve specific use-cases.

The OpenVINO™ toolkit includes the following samples and tools:

• Automatic Speech Recognition C++ Sample - Acoustic model inference based on Kaldi neural networks and speech feature vectors.
• Hello Autoresize Classification C++ Sample - Input of any size and layout can be set to an infer request which will be pre-processed automatically during inference (the sample supports only images as inputs).
• Hello Infer Request Classification C++ Sample - Inference of image classification networks via Infer Request API (the sample supports only images as inputs).
• Hello Shape Infer SSD C++ Sample - Inference of SSD networks resized by ShapeInfer API according to an input size.
• Image Classification C++ Sample Async- Maximize performance via pipelined execution, the sample supports only images as inputs.
• Image Classification C++ Sample - Inference of image classification networks like AlexNet and GoogLeNet (the sample supports only images as inputs).
• LeNet Network Graph Builder C++ Sample - Demonstrates constructing of the LeNet network using Graph Builder API.
• Neural Style Transfer C++ Sample - Style Transfer sample (the sample supports only images as inputs).
• Object Detection for SSD C++ Sample - Inference of object detection networks based on the SSD, this sample is simplified version that supports only images as inputs.
• Perfcheck Sample - Performance estimation using asynchronous mode.
• Benchmark Application - Estimates deep learning inference performance on supported devices for synchronous and asynchronous modes.
• Validation Application - Infers pack of images resulting in total accuracy (only images as inputs).

The OpenVINO™ toolkit includes the following demos:

• Action Recognition Python* Demo - Demo application for Action Recognition algorithm, which classifies actions that are being performed on input video.
• Crossroad Camera C++ Demo - Person Detection followed by the Person Attributes Recognition and Person Reidentification Retail, supports images/video and camera inputs.
• End-to-end video analytics end2end_video_analytics_ie C++ Demo - End-to-end demo application for image classification with inference engine.
• End-to-end video analytics end2end_video_analytics_opencv C++ Demo - End-to-end demo application for image classification with OpenCVDNN.
• Human Pose Estimation C++ Demo - Human pose estimation demo.
• Image Segmentation C++ Demo - Inference of image segmentation networks like FCN8 (the sample supports only images as inputs).
• Instance Segmentation Python* Demo - Inference of instance segmentation networks trained in Detectron or maskrcnn-benchmark.
• Interactive Face Detection C++ Demo - Face Detection coupled with Age/Gender, Head-Pose, Emotion, and Facial Landmarks detectors. Supports video and camera inputs.
• Mask R-CNN C++ Demo for TensorFlow* Object Detection API - Inference of instance segmentation networks created with TensorFlow* Object Detection API.
• Multi-Channel C++ Demos - Simultaneous Multi-Camera demos.
• Object Detection C++ Demo - Inference of object detection networks like Faster R-CNN (the sample supports only images as inputs).
• Object Detection for SSD C++ Demo - Demo application for SSD-based Object Detection networks, new Async API performance showcase, and simple OpenCV interoperability (supports video and camera inputs).
• Object Detection for YOLO V3 C++ Demo - Demo application for YOLOV3-based Object Detection networks, new Async API performance showcase, and simple OpenCV interoperability (supports video and camera inputs).
• Pedestrian Tracker C++ Demo - Demo application for pedestrian tracking scenario.
• Security Barrier Camera C++ Demo - Vehicle Detection followed by the Vehicle Attributes and License-Plate Recognition, supports images/video and camera inputs.
• Smart Classroom C++ Demo - Face recognition and action detection demo for classroom environment.
• Super Resolution C++ Demo - Super Resolution demo (the demo supports only images as inputs). It enhances the resolution of the input image.
• Text Detection C++ Demo - Text Detection demo. It detects and recognizes multi-oriented scene text on an input image and puts a bounding box around detected area.
• Several C++ samples referenced above have simplified implementation in Python (<INSTALL_DIR>/deployment_tools/inference_engine/samples/python_samples)*.

Media Files Available for Samples

To run the sample applications, you can use images and videos from the media files collection available at https://github.com/intel-iot-devkit/sample-videos.

Samples that Support Pre-Trained Models

You can download the pre-trained models using the OpenVINO Model Downloader or from https://download.01.org/opencv/. The table below shows the correlation between models, samples, and supported plugins. The plugin names are exactly as they are passed to the samples with -d option. The correlation between the plugins and supported devices see in the Supported Devices section. The samples are available in <INSTALL_DIR>/deployment_tools/inference_engine/samples.

Model	Samples supported on the model	CPU	GPU	MYRIAD/HDDL	HETERO:FPGA,CPU
action-recognition-0001-decoder	Action Recognition Demo	Supported	Supported
action-recognition-0001-encoder	Action Recognition Demo	Supported	Supported
driver-action-recognition-adas-0002-decoder	Action Recognition Demo	Supported	Supported
driver-action-recognition-adas-0002-encoder	Action Recognition Demo	Supported	Supported		Supported
resnet50-binary-0001	Classification Sample, Classification Sample Async	Supported	Supported
person-attributes-recognition-crossroad-0230	Crossroad Camera Demo	Supported	Supported		Supported
person-reidentification-retail-0031	Crossroad Camera Demo	Supported	Supported	Supported	Supported
person-reidentification-retail-0076	Crossroad Camera Demo	Supported	Supported	Supported	Supported
person-reidentification-retail-0079	Crossroad Camera Demo	Supported	Supported	Supported	Supported
person-vehicle-bike-detection-crossroad-0078	Crossroad Camera Demo	Supported	Supported	Supported	Supported
human-pose-estimation-adas-0001	Human Pose Estimation Demo	Supported	Supported		Supported
semantic-segmentation-adas-0001	Image Segmentation Demo	Supported	Supported		Supported
instance-segmentation-security-0033	Instance Segmentation Demo	Supported	Supported		Supported
instance-segmentation-security-0049	Instance Segmentation Demo	Supported	Supported		Supported
age-gender-recognition-retail-0013	Interactive Face Detection Demo	Supported	Supported	Supported	Supported
emotions-recognition-retail-0003	Interactive Face Detection Demo	Supported	Supported	Supported	Supported
face-detection-adas-0001	Interactive Face Detection Demo	Supported	Supported	Supported	Supported
face-detection-adas-binary-0001	Interactive Face Detection Demo	Supported	Supported
face-detection-retail-0004	Interactive Face Detection Demo	Supported	Supported	Supported	Supported
facial-landmarks-35-adas-0002	Interactive Face Detection Demo	Supported	Supported		Supported
head-pose-estimation-adas-0001	Interactive Face Detection Demo	Supported	Supported	Supported	Supported
license-plate-recognition-barrier-0001	Security Barrier Camera Demo	Supported	Supported	Supported	Supported
vehicle-attributes-recognition-barrier-0039	Security Barrier Camera Demo	Supported	Supported	Supported	Supported
vehicle-license-plate-detection-barrier-0106	Security Barrier Camera Demo	Supported	Supported	Supported	Supported
face-reidentification-retail-0095	Smart Classroom Demo	Supported	Supported	Supported	Supported
landmarks-regression-retail-0009	Smart Classroom Demo	Supported	Supported	Supported	Supported
person-detection-action-recognition-0005	Smart Classroom Demo	Supported	Supported		Supported
person-detection-action-recognition-teacher-0002	Smart Classroom Demo	Supported	Supported		Supported
single-image-super-resolution-1032	Super Resolution Demo	Supported	Supported		Supported
single-image-super-resolution-1033	Super Resolution Demo	Supported	Supported		Supported
text-detection-0002	Text Detection Demo	Supported	Supported		Supported
text-recognition-0012	Text Detection Demo	Supported	Supported
face-person-detection-retail-0002	any demo that supports SSD*-based models, above	Supported	Supported	Supported	Supported
pedestrian-and-vehicle-detector-adas-0001	any demo that supports SSD*-based models, above	Supported	Supported	Supported	Supported
pedestrian-detection-adas-0002	any demo that supports SSD*-based models, above	Supported	Supported	Supported	Supported
pedestrian-detection-adas-binary-0001	any demo that supports SSD*-based models, above	Supported	Supported
person-detection-retail-0002	any demo that supports SSD*-based models, above	Supported	Supported	Supported	Supported
person-detection-retail-0013	any demo that supports SSD*-based models, above	Supported	Supported	Supported	Supported
road-segmentation-adas-0001	any demo that supports SSD*-based models, above	Supported	Supported	Supported	Supported
vehicle-detection-adas-binary-0001	any demo that supports SSD*-based models, above	Supported	Supported
vehicle-detection-adas-0002	any demo that supports SSD*-based models, above	Supported	Supported	Supported	Supported

*Several C++ samples referenced above have simplified equivalents in Python (<INSTALL_DIR>/deployment_tools/inference_engine/samples/python_samples)*.

Notice that the FPGA support comes through a heterogeneous execution, for example, when the post-processing is happening on the CPU.

Build the Sample Applications

Build the Sample Applications on Linux*

The officially supported Linux* build environment is the following:

• Ubuntu* 16.04 LTS 64-bit or CentOS* 7.4 64-bit
• GCC* 5.4.0 (for Ubuntu* 16.04) or GCC* 4.8.5 (for CentOS* 7.4)
• CMake* version 2.8 or higher

To build the sample applications for Linux, go to the directory with the build_samples.sh script and run it:

build_samples.sh

You can also build the sample applications manually:

NOTE: If you have installed the product as a root user, switch to root mode before you continue: sudo -i

1. Navigate to a directory that you have write access to and create a samples build directory. This example uses a directory named build:

   mkdir build

   NOTE: If you ran the Image Classification demo, the samples build directory was already created in your home directory: /home/<user>/inference_engine_samples_build/

2. Go to the created directory:

   cd build

3. Run CMake to generate the Make files for release or debug configuration:
   • For release configuration:

     cmake -DCMAKE_BUILD_TYPE=Release <INSTALL_DIR>/deployment_tools/inference_engine/samples

   • For debug configuration:

     cmake -DCMAKE_BUILD_TYPE=Debug <INSTALL_DIR>/deployment_tools/inference_engine/samples

4. Run make to build the samples:

   make

For the release configuration, the sample application binaries are in <path_to_build_directory>/intel64/Release/; for the debug configuration — in <path_to_build_directory>/intel64/Debug/.

Build the Sample Applications on Microsoft Windows* OS

The recommended Windows* build environment is the following:

• Microsoft Windows* 10
• Microsoft Visual Studio* 2015, 2017, or 2019
• CMake* version 2.8 or higher

NOTE: If you want to use Microsoft Visual Studio 2019, you are required to install CMake 3.14.

To build the sample applications for Windows, run the build_samples_msvc.bat batch file:

<INSTALL_DIR>\inference_engine\samples\build_samples_msvc.bat

By default, the script automatically detects the highest Microsoft Visual Studio version installed on the machine and uses it to create and build a solution for a sample code. Optionally, you can also specify the preferred Microsoft Visual Studio version to be used by the script. Supported versions are VS2015, VS2017, and VS2019. For example, to build the samples using the Microsoft Visual Studio 2017, use the following command:

<INSTALL_DIR>\inference_engine\samples\build_samples_msvc.bat VS2017

The sample applications binaries are in the C:\Users\<username>\Documents\Intel\OpenVINO\inference_engine_samples_build\intel64\Release directory.

You can also build a generated solution manually, for example, if you want to build binaries in Debug configuration. Run the appropriate version of the Microsoft Visual Studio and open the generated solution file from the C:\Users\<username>\Documents\Intel\OpenVINO\inference_engine_samples_build\Samples.sln directory.

Get Ready for Running the Sample Applications

Get Ready for Running the Sample Applications on Linux*

Before running compiled binary files, make sure your application can find the Inference Engine and OpenCV libraries. Run the setupvars script to set all necessary environment variables:

source <INSTALL_DIR>/bin/setupvars.sh

**(Optional)**: The OpenVINO environment variables are removed when you close the shell. As an option, you can permanently set the environment variables as follows:

1. Open the .bashrc file in <user_home_directory>:

   vi <user_home_directory>/.bashrc

2. Add this line to the end of the file:

   source /opt/intel/openvino/bin/setupvars.sh

3. Save and close the file: press the Esc key, type :wq and press the Enter key.
4. To test your change, open a new terminal. You will see [setupvars.sh] OpenVINO environment initialized.

You are ready to run sample applications. To learn about how to run a particular sample, read the sample documentation by clicking the sample name in the samples list above.

Get Ready for Running the Sample Applications on Windows*

Before running compiled binary files, make sure your application can find the Inference Engine and OpenCV libraries. Use the setupvars script, which sets all necessary environment variables:

<INSTALL_DIR>\bin\setupvars.bat

To debug or run the samples on Windows in Microsoft Visual Studio, make sure you have properly configured Debugging environment settings for the Debug and Release configurations. Set correct paths to the OpenCV libraries, and debug and release versions of the Inference Engine libraries. For example, for the Debug configuration, go to the project's Configuration Properties to the Debugging category and set the PATH variable in the Environment field to the following:

PATH=<INSTALL_DIR>\deployment_tools\inference_engine\bin\intel64\Debug;<INSTALL_DIR>\opencv\bin;%PATH%

where <INSTALL_DIR> is the directory in which the OpenVINO toolkit is installed.

You are ready to run sample applications. To learn about how to run a particular sample, read the sample documentation by clicking the sample name in the samples list above.

See Also

• Introduction to Intel's Deep Learning Inference Engine