A powerhouse for artificial intelligence enthusiasts, the OpenVINO™ Notebooks offer a treasure trove of resources designed to help users learn and experiment with the OpenVINO Toolkit. Whether you’re a beginner or an experienced developer, the notebooks facilitate seamless learning of deep learning inference techniques. In this article, we’ll guide you through everything you need to get started with OpenVINO™ Notebooks, from installation to troubleshooting.

Table of Contents

• Installation Guide
• Getting Started
• System Requirements
• Run the Notebooks
• Cleaning Up
• Troubleshooting
• Additional Resources
• FAQ

Installation Guide

Before diving into the notebooks, ensure you have Python and Git installed on your machine. Follow the appropriate guide based on your operating system:

• Windows
• Ubuntu
• macOS
• Red Hat
• CentOS
• Azure ML
• Docker
• Amazon SageMaker

Getting Started

Explore Jupyter notebooks using this page. Pick a notebook that fits your needs or experiment with multiple notebooks. Good Luck!

NOTE: The main branch of this repository was updated for OpenVINO 2024.4. If you’re upgrading, run the following command in your openvino_env virtual environment:

pip install --upgrade -r requirements.txt

For users wanting to revert to older versions of OpenVINO, refer to the 2024.3 branch or the 2023.3 branch.

System Requirements

The notebooks can operate on various platforms, including:

• Ubuntu 20.04 LTS, 64-bit (Python 3.8 – 3.11)
• Ubuntu 22.04 LTS, 64-bit (Python 3.8 – 3.11)
• Red Hat Enterprise Linux 8, 64-bit (Python 3.8 – 3.11)
• CentOS 7, 64-bit (Python 3.8 – 3.11)
• macOS 10.15.x and higher (Python 3.8 – 3.11)
• Windows 10 Pro, Enterprise, or Education (Python 3.8 – 3.11)
• Windows Server 2016 or higher (Python 3.8 – 3.11)

Run the Notebooks

To Launch a Single Notebook

If you want to execute a single notebook, such as the Monodepth notebook, use the command:

jupyter lab notebooks/vision-monodepth/vision-monodepth.ipynb

To Launch all Notebooks

Start Jupyter Lab with the index README.md to easily navigate through your notebooks:

jupyter lab notebooks/README.md

Alternatively, you can select a notebook directly from the Jupyter Lab file browser.

Cleaning Up

Shut Down Jupyter Kernel

To safely end your Jupyter session, press Ctrl-C and respond with ‘y’ to shut down.

Deactivate Virtual Environment

To exit your virtual environment, run the command:

deactivate

Delete Virtual Environment (Optional)

If you want to completely remove your virtual environment, execute:

• On Linux and macOS: rm -rf openvino_env
• On Windows: rmdir /s openvino_env

Troubleshooting

Encountering issues? Here are some solutions to common problems:

• For installation issues, run python check_install.py located in the openvino_notebooks directory after activating openvino_env.
• If faced with an ImportError, ensure the Jupyter kernel is installed and select the openvino_env kernel via the Kernel menu in Jupyter Lab.
• When OpenVINO is globally installed, avoid running installation commands in terminals where setupvars.bat or setupvars.sh are sourced.
• For Windows installations, prefer using Command Prompt (cmd.exe) over PowerShell.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Additional Resources

• OpenVINO Blog – Technical articles on best practices and tutorials.
• Awesome OpenVINO – Curated list of OpenVINO-based AI projects.
• OpenVINO GenAI Samples – Collection of GenAI API samples.
• Edge AI Reference Kit – Accelerates AI application development.
• Open Model Zoo demos – Templates for implementing deep learning inference scenarios.
• oneAPI-samples repository showcasing tools and performance across architectures.

FAQ

• Which devices does OpenVINO support?
• What is the first CPU generation supported by OpenVINO?
• Are there success stories deploying solutions with OpenVINO?

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.