click on the blue word
Follow us to make development more interesting
Author: Wu Zeng, Deng Shumeng Guangdong Rongxu Intelligent Technology Co., Ltd.
Introduction to this article
Many readers are very interested in how to build an Anomalib + OpenVINO? development environment from scratch on the Intel Developer Kit after reading “Rongxu Intelligent Building an Intelligent Optical Character Defect Detection System Based on Anomalib”.
This article will introduce how to build Anomalib + OpenVINO? development environment step by step on Ubuntu22.04 based on Intel Developer Kit.
After getting the Intel Developer Kit, please refer to the official Ubuntu installation documentation to install Ubuntu22.04.
Official website link (copy and open in browser):
https://ubuntu.com/tutorials/install-ubuntu-desktop#1-overview
Development environment construction
After installing Ubuntu22.04, this article will introduce in turn how to install and build the software tools that Anomalib + OpenVINO? development environment depends on, including Anaconda, Git, OpenVINO? Notebooks and VSCode .
With the support of these tools, developers will find that the experience of learning and developing OpenVINO? programs on Linux and Windows is almost exactly the same. Developers who are not familiar with Linux can quickly migrate their development experience on Windows to Linux.
First step
Download and install Anaconda
Anaconda is a very popular Python virtual environment and package management tool, which can easily solve the dependency problems when multiple Python versions coexist and install Python packages, and the user experience is good.
Go to Anaconda official website: https://www.anaconda.com
Download Anaconda3-xxx-Linux-86_64.sh, and then use the command: bash Anaconda3-xxx-Linux-86_64.sh to complete the installation, as shown in Figure 1-1 .
Figure 1-1 Download and install Anaconda
Second step
Create and activate a virtual environment
After completing the Anaconda installation and restarting the terminal, it will automatically enter the Anaconda default “base” virtual environment. Use the command: conda create -n ov python=3.10 to create a new virtual environment named “ov” , as shown in Figure 1-2.
Figure 1-2 Create a new virtual environment
Then use the command: conda activate ov to activate the newly created virtual environment.
Step 3
Install and start OpenVINO? Notebooks
OpenVINO? Notebooks is a set of executable Jupyter notebooks, which is convenient for developers to learn and use the OpenVINO? tool suite.
Github code warehouse (copy to browser to open):
https://github.com/openvinotoolkit/openvino_notebooks
First, install the dependencies of OpenVINO? Notebooks using the command:
sudo apt update sudo apt upgrade sudo apt install git sudo apt install intel-opencl-icd
Swipe right to view the full code
Then, use the command to clone the OpenVINO? Notebooks code warehouse to the local, and install dependencies:
git clone --depth=1 https://github.com/openvinotoolkit/openvino_notebooks.git cd openvino_notebooks pip install -r requirements.txt
Swipe right to view the full code
Finally, use the command to start OpenVINO? Notebooks, and then run 002-openvino-api.ipynb, as shown in Figure 1-3. If the hardware information is successfully obtained, it means OpenVINO? Toolkit and OpenVINO? Notebooks installed successfully.
jupyter lab notebooks
Figure 1-3 Start OpenVINO? Notebooks
Step 4
Install and configure VS Code
VS Code is an open source code editor developed by Microsoft. It includes built-in debugging support, Git version control, syntax highlighting, code auto-completion and other functions. Through the configuration of various plug-ins, VS Code can be configured as a graphical Python integrated development platform (IDE) under Ubuntu. Use The experience is almost the same as developing Python code with VS Code in Windows.
From the official website of VS Code: https://code.visualstudio.com/
Download the code_xxx.deb installation package, and then complete the installation through the right-click menu → “Open with Software Install”, as shown in Figure 1-4.
Figure 1-4 Download and install VS Code
Start VS Code, open 002-openvino-api.ipynb, and run the code. If you get the results shown in Figure 1-5, it means that VS Code is installed successfully, and you can write and debug OpenVINO? Python code.
Figure 1-5 Running OpenVINO? Python code in VS Code
Step five
Install and learn Anomalib
Anomalib provides a set of notebooks for beginners to get started quickly. Based on this set of notebooks, you can quickly master the usage of Anomalib. Therefore, please clone the Anomalib code warehouse to the local:
git clone https://github.com/openvinotoolkit/anomalib.git
Swipe right to view the full code
Then, use the command to complete the installation of anomalib:
pip install anomalib
Finally, in VS Code, open 001_getting_started.ipynb in Anomalib notebooks to start learning how to use Anomalib.
Summary
This article introduces in detail the whole process of building an Anomalib + OpenVINO? development environment from scratch on the Intel Developer Kit. With the help of the sample programs of OpenVINO? Notebooks and Anomalib Notebooks, you can Quickly learn the use of OpenVINO? and Anomalib. If you have further needs, please feel free to contact me.
Guangdong Rongxu Intelligent Technology Co., Ltd. official website:
https://www.gdrosmart.com/
–END–
You may want to know (click the blue word to view) OpenVINO? DevCon 2023 is back! Intel stimulates the infinite potential of developers with innovative products 5th Anniversary Update | OpenVINO? 2023.0, making AI deployment and acceleration easier The highlight of OpenVINO? 5th Anniversary! The 2023.0 version continues to upgrade AI deployment and acceleration performance OpenVINO? 2023.0 actual combat | Deploy YOLOv8 object detection model in LabVIEW Developer actual combat series resource packs are here! Draw with AI, wish her a happy holiday; three simple steps, OpenVINO? Help you easily experience AIGC Don't know how to draw with OpenVINO Click for tutorial. A few lines of code easily realize real-time reasoning for PaddleOCR, come get it! Use OpenVINO to quickly realize high-performance artificial intelligence reasoning in "device-edge-cloud" Extracting text from pictures is amazing? Try to achieve OCR in three steps! 【Notebook Series Issue 6】Based on the Pytorch pre-training model to achieve semantic segmentation tasks Use OpenVINO? preprocessing API to further improve YOLOv5 reasoning performance
Scan the QR code below to experience it immediately OpenVINO? Toolkit 2023.0
Click to read the original text and experience OpenVINO 2023.0 now
The article is so wonderful, are you “reading” it?