A collection of Python notebooks for learning and experimenting with OpenVINO

📚 OpenVINO Notebooks

🚧 Notebooks are currently in beta. We plan to publish a stable release this summer. Please submit issues on GitHub, start a discussion or join our Unofficial Developer Discord Server* to stay in touch.

A collection of ready-to-run Python* notebooks for learning and experimenting with OpenVINO developer tools. The notebooks are meant to provide an introduction to OpenVINO basics and teach developers how to leverage our APIs for optimized deep learning inference in their applications.

💻 Getting Started

The notebooks are designed to run almost anywhere — your laptop, a cloud VM, or even a Docker container. Here’s what you need to get started:

• CPU (64-bit)
• Windows*, Linux* or macOS*
• Python* 3.6-3.8

Before you proceed to the Installation Guide, please review the detailed System Requirements below.

⚙️ System Requirements

The table below lists the supported operating systems and Python versions required to run the OpenVINO notebooks.

📝 Installation Guide

NOTE: If OpenVINO is installed globally, please do not run any of these commands in a terminal where setupvars.bat or setupvars.sh are sourced. For Windows, we recommend using Command Prompt (cmd.exe), not PowerShell.

Step 1: Clone the Repository

git clone https://github.com/openvinotoolkit/openvino_notebooks.git

Step 2: Create a Virtual Environment

# Linux and macOS may require typing python3 instead of python
cd openvino_notebooks
python -m venv openvino_env

Step 3: Activate the Environment

For Linux and macOS:

source openvino_env/bin/activate

For Windows:

openvino_env\Scripts\activate

Step 4: Install the Packages

Installs OpenVINO tools and dependencies like Jupyter Lab:

# Upgrade pip to the 20.2.* version to avoid dependency issues
python -m pip install --upgrade pip==20.2.4
pip install -r requirements.txt

Step 5: Install the virtualenv Kernel in Jupyter

python -m ipykernel install --user --name openvino_env

Step 6: Launch the Notebooks!

# To launch a single notebook
jupyter notebook <notebook_filename>

# To launch all notebooks in Jupyter Lab
jupyter lab notebooks

In Jupyter Lab, select a notebook from the file browser using the left sidebar. Each notebook is located in a subdirectory within the notebooks directory.

🧹 Cleaning Up

Shut Down Jupyter Kernel

To end your Jupyter session, press Ctrl-c. This will prompt you to Shutdown this Jupyter server (y/[n])? enter y and hit Enter.

Deativate Virtual Environment

To deactivate your virtualenv, simply run deactivate from the terminal window where you activated openvino_env. This will deactivate your environment.

To reactivate your environment, simply repeat Step 3 from the Install Guide.

Delete Virtual Environment (Optional)

To remove your virtual environment, simply delete the openvino_env directory:

On Linux and macOS:

rm -rf openvino_env

On Windows:

rmdir /s openvino_env

Remove openvino_env Kernel from Jupyter

jupyter kernelspec remove openvino_env

⚠️ Troubleshooting

• On Ubuntu, if you see the error “libpython3.7m.so.1.0: cannot open shared object file: No such object or directory” please install the required package using apt install libpython3.7-dev

• If you get an ImportError, doublecheck that you installed the kernel in Step 5. If necessary, choose the openvinoenv kernel from the _Kernel->Change Kernel menu)

• On Linux and macOS you may need to type python3 instead of python when creating your virtual environment

• On Linux and macOS you may need to install pip and/or python-venv (depending on your Linux distribution)

• On Windows, if you have installed multiple versions of Python, use py -3.7 when creating your virtual environment to specify a supported version (in this case 3.7)

• On Fedora*, Red Hat and Amazon* Linux you may need to install the OpenGL (Open Graphics Library) to use OpenCV. Please run yum install mesa-libGL before launching the notebooks.

• For macOS systems with Apple* M1, please see community discussion about using Rosetta* 2.

* Other names and brands may be claimed as the property of others.