Getting Started
This document will guide you through the process of installing OpenVINO™ Toolkit and OpenVINO™ Notebooks.
These contents target OpenVINO™ Toolkit 2022.3 LTS, which is the latest version at the time of writing (March 7, 2023).
This time, Ubuntu 20.04.5 LTS was used as the OS, and Intel® NUC, a product handled by our company, was used as the hardware.
This procedure is based on the github ULR of Intel® Distribution of OpenVINO™ Toolkit and OpenVINO™ Notebooks below.
Reference:
- Intel® Distribution of OpenVINO™ Toolkit
- OpenVINO™ Notebooks github
- Intel® NUC A compact and extremely powerful computer in your hands
＜The products we used in this project
- Intel® NUC with 11th generation Intel® Core™ processor
Preparation
STEP 1-1: Install Ubuntu 20.04.
Install Ubuntu 20.04 and run apt-get update and apt-get upgrade.
sudo apt-get update
sudo apt-get upgrade
STEP 1-2 : Install Python on Ubuntu 20.04.
Install Python 3.8 and vennv virtual environment on Ubuntu.
sudo apt install python3.8-venv
2. Install OpenVINO™ Toolkit 2022.3 LTS
Refer to the Intel® Distribution of OpenVINO™ Toolkit link to download and install OpenVINO™.
This time, we will use the PyPI method, which is the easiest way to install OpenVINO™ Toolkit, so select the following
Environment :. Development Tools
Operating System : Linux Linux
Version : Linux 2022.3 (Recommended)
Distribution : PIP PIP
The necessary commands are displayed according to the selected Environment, Operating System, Version, and Distribution as shown below.
STEP 2-1 : Create a virtual environment.
python3 -m venv openvino_env
STEP 2-2 : Activate the virtual environment.
source openvino_env/bin/activate
STEP 2-3 : Upgrade pip to the latest version.
python -m pip install --upgrade pip
STEP 2-4 : Download and install the Development Tools, specifying the version.
pip install openvino-dev==2022.3.0
As shown below, a message will appear after executing the command. If no error occurs, the environment building is complete.
If the terminal window is closed, execute STEP 2-2 again to activate the OpenVINO™ virtual environment.
source openvino_env/bin/activate
3. Install and run OpenVINO™ Notebooks
Refer to the OpenVINO™ Notebooks Ubuntu link on the OpenVINO™ Notebooks github to install OpenVINO™ Notebooks.
STEP 3-1 : Deactivate the OpenVINO™ virtual environment and install additional libraries.
deactivate
sudo apt-get install build-essential python3-dev git-all
STEP 3-2: Activate the OpenVINO™ virtual environment.
source openvino_env/bin/activate
STEP 3-3 : Clone the repository.
git clone --depth=1 https://github.com/openvinotoolkit/openvino_notebooks.git
STEP 3-4 : Move to the openvino_notebooks directory by cd command.
cd openvino_notebooks
STEP 3-5 : Install packages such as dependencies.
pip install wheel setuptools
pip install -r requirements.txt
STEP 3-6 : Start all notebooks at once.
jupyter lab notebooks
You have successfully started the notebooks. Select "notebooks" from the sidebar on the left side of the screen.
Each notebook is located in a subdirectory of the notebooks directory.
STEP 3-7 : Monodepth notebook (depth estimation) example, but you can also specify a single notebooks to start.
jupyter notebook notebooks/201-vision-monodepth/201-vision-monodepth.ipynb
The notebooks have been successfully launched.
STEP 3-8 : Running Notebooks
Basically, you can execute each step by simply clicking the Run button at the top.
This is the result of executing the seventh code from the top.
The result of depth estimation for the source image on the left is displayed on the right.
This is the result of running the 11th code from the top.
For the left source video, the resulting depth-estimated video is displayed on the right.
Summary
There are many notebooks available, but please refer to Getting Started in the following link to try it out.
Reference: