Configuring the Model Optimizer

You must configure the Model Optimizer for the framework that was used to train the model. This section tells you how to configure the Model Optimizer either through scripts or by using a manual process.

Using Configuration Scripts

You can either configure all three frameworks at the same time or install an individual framework. The scripts delivered with the tool install all required dependencies and provide the fastest and easiest way to configure the Model Optimizer.

To configure all three frameworks, go to the <INSTALL_DIR>/deployment_tools/model_optimizer/install_prerequisites directory and run:

To configure a specific framework, go to the <INSTALL_DIR>/deployment_tools/model_optimizer/install_prerequisites directory and run:

IMPORTANT: ONLY FOR CAFFE* By default, you do not need to install Caffe to create an Intermediate Representation for a Caffe model, unless you use Caffe for custom layer shape inference and do not write Model Optimizer extensions. To learn more about implementing Model Optimizer custom operations and the limitations of using Caffe for shape inference, see Custom Layers in Model Optimizer.

Using Manual Configuration Process

If you prefer, you can manually configure the Model Optimizer for one framework at a time.

  1. Go to the Model Optimizer directory:
    cd <INSTALL_DIR>/deployment_tools/model_optimizer/
  2. Strongly recommended for all global Model Optimizer dependency installations: Create and activate a virtual environment. While not required, this step is strongly recommended since the virtual environment creates a Python* sandbox, and dependencies for the Model Optimizer do not influence the global Python configuration, installed libraries, or other components. In addition, a flag ensures that system-wide Python libraries are available in this sandbox. Skip this step only if you do want to install all the Model Optimizer dependencies globally:
    • Create a virtual environment:
      virtualenv -p /usr/bin/python3.6 .env3 --system-site-packages
    • Activate the virtual environment:
      virtualenv -p /usr/bin/python3.6 .env3/bin/activate
  3. Install all dependencies or only the dependencies for a specific framework:
    • To install dependencies for all frameworks:
      pip3 install -r requirements.txt
    • To install dependencies only for Caffe:
      pip3 install -r requirements_caffe.txt
    • To install dependencies only for TensorFlow:
      pip3 install -r requirements_tf.txt
    • To install dependencies only for MXNet:
      pip3 install -r requirements_mxnet.txt
    • To install dependencies only for Kaldi:
      pip3 install -r requirements_kaldi.txt
    • To install dependencies only for ONNX:
      pip3 install -r requirements_onnx.txt

Using the protobuf Library in the Model Optimizer for Caffe*

These procedures require:

Model Optimizer uses the protobuf library to load trained Caffe models. By default, the library executes pure Python* language implementation, which is slow. These steps show how to use the faster C++ implementation of the protobuf library on Windows OS or Linux OS.

Using the protobuf Library on Linux* OS

To use the C++ implementation of the protobuf library on Linux, it is enough to set up the environment variable:


Using the protobuf Library on Windows* OS

On Windows, pre-built protobuf packages for Python versions 3.4, 3.5, 3.6, and 3.7 are provided with the installation package and can be found in the <INSTALL_DIR>\deployment_tools\model_optimizer\install_prerequisites folder. Please note that they are not installed with the install_prerequisites.bat installation script due to possible issues with pip, and you can install them at your own discretion. Make sure that you install the protobuf version that matches the Python version you use:

To install the protobuf package:

  1. Open the command prompt as administrator.
  2. Go to the install_prerequisites folder of the OpenVINO toolkit installation directory:
    cd <INSTALL_DIR>\deployment_tools\model_optimizer\install_prerequisites
  3. Run the following command to install the protobuf for Python 3.6. If you want to install the protobuf for Python 3.4, 3.5, or 3.7, replace protobuf-3.6.1-py3.6-win-amd64.egg with the corresponding file name from the list above.
    python -m easy_install protobuf-3.6.1-py3.6-win-amd64.egg
    If the Python version you use is lower than 3.4, you need to update it or build the library manually.

Building the protobuf Library on Windows* OS

NOTE: These steps are optional. If you use Python version 3.4, 3.5, 3.6, or 3.7, you can install the protobuf library using the pre-built packages.

To compile the protobuf library from sources on Windows OS, do the following:

  1. Clone protobuf source files from GitHub:
    git clone
    cd protobuf
  2. Create a Visual Studio solution file. Run these commands:
    cd C:\Path\to\protobuf\cmake\build
    mkdir solution
    cd solution C:\Path\to\protobuf\cmake\build\solution
    cmake -G "Visual Studio 12 2013 Win64" ../..
  3. Change the runtime library option for libprotobuf and libprotobuf-lite:
    • Open the project's Property Pages dialog box
    • Expand the C/C++** tab
    • Select the **Code Generation property page
    • Change the Runtime Library property to Multi-thread DLL (/MD)
  4. Build the libprotoc, protoc, libprotobuf, and libprotobuf-lite projects in the Release configuration.
  5. Add a path to the build directory to the PATH environment variable:
    set PATH=%PATH%;C:\Path\to\protobuf\cmake\build\solution\Release
  6. Go to the python directory:
    cd C:\Path\to\protobuf\python
  7. Use a text editor to open and change these options:
    • Change from ​libraries = ['protobuf'] to libraries = ['libprotobuf', 'libprotobuf-lite']
    • Change from extra_objects = ['../src/.libs/libprotobuf.a', '../src/.libs/libprotobuf-lite.a'] to extra_objects = ['../cmake/build/solution/Release/libprotobuf.lib', '../cmake/build/solution/Release/libprotobuf-lite.lib']
  8. Build the Python package with the C++ implementation:
    python build –cpp_implementation
  9. Install the Python package with the C++ implementation:
    python3 -m easy_install dist/protobuf-3.6.1-py3.6-win-amd64.egg
  10. Set an environment variable to boost the protobuf performance:

See Also