Get Started with C++ Samples

The guide presents a basic workflow for building and running C++ code samples in OpenVINO. Note that these steps will not work with the Python samples.

To get started, you must first install OpenVINO Runtime, install OpenVINO Development tools, and build the sample applications. See the Prerequisites section for instructions.

Once the prerequisites have been installed, perform the following steps:

  1. Use Model Downloader to download a suitable model.

  2. Convert the model with Model Optimizer.

  3. Download media files to run inference.

  4. Run inference with the Image Classification sample application and see the results.


Install OpenVINO Runtime

To use sample applications, install OpenVINO Runtime via one of the following distribution channels (other distributions do not include sample files):

Make sure that you also install OpenCV, as it’s required for running sample applications.

Install OpenVINO Development Tools

To install OpenVINO Development Tools, follow the instructions for C++ developers on the Install OpenVINO Development Tools page. This guide uses the googlenet-v1 model from the Caffe framework, therefore, when you get to Step 4 of the installation, run the following command to install OpenVINO with the Caffe requirements:

pip install openvino-dev[caffe]

Build Samples

To build OpenVINO samples, follow the build instructions for your operating system on the OpenVINO Samples page. The build will take about 5-10 minutes, depending on your system.

Step 1: Download the Models

You must have a model that is specific for your inference task. Example model types are:

  • Classification (AlexNet, GoogleNet, SqueezeNet, others): Detects one type of element in an image

  • Object Detection (SSD, YOLO): Draws bounding boxes around multiple types of objects in an image

  • Custom: Often based on SSD

You can use one of the following options to find a model suitable for OpenVINO:

  • Download public or Intel pre-trained models from Open Model Zoo using Model Downloader tool

  • Download from GitHub, Caffe Zoo, TensorFlow Zoo, etc.

  • Train your own model with machine learning tools

This guide uses OpenVINO Model Downloader to get pre-trained models. You can use one of the following commands to find a model with this method:

  • List the models available in the downloader.

    omz_info_dumper --print_all
  • Use grep to list models that have a specific name pattern (e.g. ssd-mobilenet, yolo). Replace <model_name> with the name of the model.

    omz_info_dumper --print_all | grep <model_name>
  • Use Model Downloader to download models. Replace <models_dir> with the directory to download the model to and <model_name> with the name of the model.

    omz_downloader --name <model_name> --output_dir <models_dir>

This guide used the following model to run the Image Classification Sample:

Model Name

Code Sample or Demo App


Image Classification Sample

Step 2: Convert the Model with Model Optimizer

In this step, your trained models are ready to run through the Model Optimizer to convert them to the IR (Intermediate Representation) format. For most model types, this is required before using OpenVINO Runtime with the model.

Models in the IR format always include an .xml and .bin file and may also include other files such as .json or .mapping. Make sure you have these files together in a single directory so OpenVINO Runtime can find them.

REQUIRED: model_name.xml REQUIRED: model_name.bin OPTIONAL: model_name.json, model_name.mapping, etc.

This tutorial uses the public GoogleNet v1 Caffe model to run the Image Classification Sample. See the example in the Download Models section of this page to learn how to download this model.

The googlenet-v1 model is downloaded in the Caffe format. You must use Model Optimizer to convert the model to IR.

Create an <ir_dir> directory to contain the model’s Intermediate Representation (IR).

mkdir ~/ir
mkdir %USERPROFILE%\Documents\ir
mkdir ~/ir

To save disk space for your IR file, you can apply weights compression to FP16. To generate an IR with FP16 weights, run Model Optimizer with the --compress_to_fp16 option.

Generic Model Optimizer script:

mo --input_model <model_dir>/<model_file>

The IR files produced by the script are written to the <ir_dir> directory.

The command with most placeholders filled in and FP16 precision:

mo --input_model ~/models/public/googlenet-v1/googlenet-v1.caffemodel --compress_to_fp16 --output_dir ~/ir
mo --input_model %USERPROFILE%\Documents\models\public\googlenet-v1\googlenet-v1.caffemodel --compress_to_fp16 --output_dir %USERPROFILE%\Documents\ir
mo --input_model ~/models/public/googlenet-v1/googlenet-v1.caffemodel --compress_to_fp16 --output_dir ~/ir

Step 3: Download a Video or a Photo as Media

Most of the samples require you to provide an image or a video as the input to run the model on. You can get them from sites like Pexels or Google Images.

As an alternative, OpenVINO also provides several sample images and videos for you to run code samples and demo applications:

Step 4: Run Inference on a Sample

To run the Image Classification code sample with an input image using the IR model:

  1. Set up the OpenVINO environment variables:

    source  <INSTALL_DIR>/
    source <INSTALL_DIR>/
  2. Go to the code samples release directory created when you built the samples earlier:

    cd ~/openvino_cpp_samples_build/intel64/Release
    cd  %USERPROFILE%\Documents\Intel\OpenVINO\openvino_samples_build\intel64\Release
    cd ~/openvino_cpp_samples_build/intel64/Release
  3. Run the code sample executable, specifying the input media file, the IR for your model, and a target device for performing inference:

    classification_sample_async -i <path_to_media> -m <path_to_model> -d <target_device>
    classification_sample_async.exe -i <path_to_media> -m <path_to_model> -d <target_device>
    classification_sample_async -i <path_to_media> -m <path_to_model> -d <target_device>


Running Inference on CPU

The following command shows how to run the Image Classification Code Sample using the dog.bmp file as an input image, the model in IR format from the ir directory, and the CPU as the target hardware:

./classification_sample_async -i ~/Downloads/dog.bmp -m ~/ir/googlenet-v1.xml -d CPU
.\classification_sample_async.exe -i %USERPROFILE%\Downloads\dog.bmp -m %USERPROFILE%\Documents\ir\googlenet-v1.xml -d CPU
./classification_sample_async -i ~/Downloads/dog.bmp -m ~/ir/googlenet-v1.xml -d CPU

When the sample application is complete, you are given the label and confidence for the top 10 categories. The input image and sample output of the inference results is shown below:
Top 10 results:

Image dog.bmp

   classid probability label
   ------- ----------- -----
   156     0.6875963   Blenheim spaniel
   215     0.0868125   Brittany spaniel
   218     0.0784114   Welsh springer spaniel
   212     0.0597296   English setter
   217     0.0212105   English springer, English springer spaniel
   219     0.0194193   cocker spaniel, English cocker spaniel, cocker
   247     0.0086272   Saint Bernard, St Bernard
   157     0.0058511   papillon
   216     0.0057589   clumber, clumber spaniel
   154     0.0052615   Pekinese, Pekingese, Peke

The following two examples show how to run the same sample using GPU or MYRIAD as the target device.

Running Inference on GPU


Running inference on Intel® Processor Graphics (GPU) requires additional hardware configuration steps, as described earlier on this page. Running on GPU is not compatible with macOS.

./classification_sample_async -i ~/Downloads/dog.bmp -m ~/ir/googlenet-v1.xml -d GPU
.\classification_sample_async.exe -i %USERPROFILE%\Downloads\dog.bmp -m %USERPROFILE%\Documents\ir\googlenet-v1.xml -d GPU

Running Inference on MYRIAD


Running inference on VPU devices (Intel® Movidius™ Neural Compute Stick or Intel® Neural Compute Stick 2) with the MYRIAD plugin requires additional hardware configuration steps, as described earlier on this page.

./classification_sample_async -i ~/Downloads/dog.bmp -m ~/ir/googlenet-v1.xml -d MYRIAD
.\classification_sample_async.exe -i %USERPROFILE%\Downloads\dog.bmp -m %USERPROFILE%\Documents\ir\googlenet-v1.xml -d MYRIAD
./classification_sample_async -i ~/Downloads/dog.bmp -m ~/ir/googlenet-v1.xml -d MYRIAD

Other Demos and Samples

See the Samples page for more sample applications. Each sample page explains how the application works and shows how to run it. Use the samples as a starting point that can be adapted for your own application.

OpenVINO also provides demo applications for using off-the-shelf models from Open Model Zoo. Visit Open Model Zoo Demos if you’d like to see even more examples of how to run model inference with the OpenVINO API.