# Install OpenVINO™ Development Tools¶

If you want to download, convert, optimize and tune pre-trained deep learning models, install OpenVINO™ Development Tools, which provides the following tools:

• Model Optimizer

• Benchmark Tool

• Accuracy Checker and Annotation Converter

• Post-Training Optimization Tool

Note

From the 2022.1 release, the OpenVINO™ Development Tools can only be installed via PyPI.

## For Python Developers¶

If you are a Python developer, you can find the main steps below to install OpenVINO Development Tools. For more details, see https://pypi.org/project/openvino-dev.

While installing OpenVINO Development Tools, OpenVINO Runtime will also be installed as a dependency, so you don’t need to install OpenVINO Runtime separately.

### Step 1. Set Up Python Virtual Environment¶

Use a virtual environment to avoid dependency conflicts.

To create a virtual environment, use the following command:

python3 -m venv openvino_env

python -m venv openvino_env


### Step 2. Activate Virtual Environment¶

source openvino_env/bin/activate

openvino_env\Scripts\activate


### Step 3. Set Up and Update PIP to the Highest Version¶

Use the following command:

python -m pip install --upgrade pip

### Step 4. Install the Package¶

To install and configure the components of the development package for working with specific frameworks, use the following command:

pip install openvino-dev[extras]

where the extras parameter specifies one or more deep learning frameworks via these values: caffe, kaldi, mxnet, onnx, pytorch, tensorflow, tensorflow2. Make sure that you install the corresponding frameworks for your models.

For example, to install and configure the components for working with TensorFlow 2.x and ONNX, use the following command:

pip install openvino-dev[tensorflow2,onnx]

Note

Model Optimizer support for TensorFlow 1.x environment has been deprecated. Use TensorFlow 2.x environment to convert both TensorFlow 1.x and 2.x models. Use the tensorflow2 value as much as possible. The tensorflow value is provided only for compatibility reasons.

### Step 5. Verify the Installation¶

To verify if the package is properly installed, run the command below (this may take a few seconds):

mo -h

You will see the help message for Model Optimizer if installation finished successfully.

## For C++ Developers¶

Note the following things:

Use either of the following ways to install OpenVINO Development Tools:

### Alternative: Install from the openvino-dev Package¶

You can also use the following command to install the latest package version available in the index:

pip install openvino-dev[EXTRAS]

where the EXTRAS parameter specifies one or more deep learning frameworks via these values: caffe, kaldi, mxnet, onnx, pytorch, tensorflow, tensorflow2. Make sure that you install the corresponding frameworks for your models.

If you have installed OpenVINO Runtime via the installer, to avoid version conflicts, specify your version in the command. For example:

pip install openvino-dev[tensorflow2,onnx]==2022.1

Note

Model Optimizer support for TensorFlow 1.x environment has been deprecated. Use TensorFlow 2.x environment to convert both TensorFlow 1.x and 2.x models. The tensorflow value is provided only for compatibility reasons, use the tensorflow2 value instead.

For more details, see https://pypi.org/project/openvino-dev/.

## What’s Next?¶

Now you may continue with the following tasks: