openvino/ubuntu18_dev Docker 镜像 - 轩辕镜像

Latest tag

• 2022.2.0, latest

Intel® Distribution of OpenVINO™ toolkit Docker image for Ubuntu* 18.04 LTS

The Intel® Distribution of OpenVINO™ toolkit quickly deploys applications and solutions that emulate human vision. Based on Convolutional Neural Networks (CNN), the toolkit extends computer vision (CV) workloads across Intel® hardware, maximizing performance.

• Homepage: [***]
• Release Notes: [***]
• Documentation: [***]
• Support forum: [***]

You can use DockerHub CI framework for Intel® Distribution of OpenVINO™ toolkit to generate a Dockerfile, build, test, and deploy an image with the Intel® Distribution of OpenVINO™ toolkit. You can reuse available Dockerfiles, add your layer, and customize the image of OpenVINO™ for your needs.

TIP: Install the Deep Learning Workbench to get familiar with most OpenVINO™ components in a web-based graphical environment. With the DL Workbench, you can optimize, fine-tune, analyze, visualize, and compare the performance of deep learning models on various Intel® architecture configurations. Proceed to an easy installation from Docker Hub to get started.

Content: This openvino/ubuntu18_dev image includes: OpenVINO Runtime (IE core, nGraph), plugins, samples, Python dev tools: Model Optimizer, Post-Training Optimization tool, Accuracy Checker, Open Model Zoo tools (Downloader, Converter). OpenCV and Open Model Zoo demos are not included since 2022.1.0 release. TensorFlow* 2 is the default in the image since the 2021.4 release. The old images contain Python TensorFlow* 2. virtual environment in /opt/intel/venv_tf2 folder for Model Optimizer and Model Downloader/Converter, because TensorFlow* 1. (default in the oldest images) and TensorFlow* 2. are not compatible. Please follow this guide to activate and use it.

• Images with the _src postfix in a tag include sources of 3d party LGPL/GPL packages in the /thirdparty folder. Alternatively sources are stored here
• Images with the _tgl postfix in a tag to natively support inference on 11th Generation Intel® Core™ Processor Family for Internet of Things (IoT) Applications (formerly codenamed Tiger Lake) from OpenVINO Docker container. Since release 2021.4.1 all images natively support the Tiger Lake platform.

The following configurations were verified for this docker image:

• If your host system is Windows* 10 and above with WSL2, you can run inference inside the Docker image on CPU and iGPU targets.
• To run an image on CPU, use the following command:

sh
docker run -it --rm openvino/ubuntu18_dev:latest 

• To run inference on GPU, the host system is required to be Windows 10 21H2 or Windows 11, and have Intel iGPU drivers with version 30.0.100.9684 or above installed. Use the following command (available since 2022.1.0 release):

sh
docker run -it --rm --device /dev/dxg --volume /usr/lib/wsl:/usr/lib/wsl openvino/ubuntu18_dev:latest 

• If your host system is Ubuntu* 18.04 then inference run inside the docker image is available for CPU, GPU, Myriad* (NCS2), HDDL targets.
• Default run:

sh
docker run -it --device /dev/dri:/dev/dri --device-cgroup-rule='c 189:* rmw' -v /dev/bus/usb:/dev/bus/usb --rm openvino/ubuntu18_dev:latest

• If you need GPU accelerator only, run the image with the following command:

sh
docker run -it --device /dev/dri:/dev/dri --rm openvino/ubuntu18_dev:latest

If your host system is Ubuntu 20, follow the Configuration Guide for the Intel® Graphics Compute Runtime for OpenCL™ on Ubuntu* 20.04.

• If you need Myriad* (NCS2) accelerator only, run the image with the following command:

sh
docker run -it --device-cgroup-rule='c 189:* rmw' -v /dev/bus/usb:/dev/bus/usb --rm openvino/ubuntu18_dev:latest 

• If you need inference on the HDDL, setup HDDL driver on host machine, follow the configuration guide for HDDL device:

bash
docker run -it --rm --device=/dev/ion:/dev/ion -v /var/tmp:/var/tmp openvino/ubuntu18_dev:latest

• If your host system is macOS*, you can run inference inside the Docker image using the following command (CPU only):
• To run the image, use the following command:

sh
docker run -it --rm openvino/ubuntu18_dev:latest 

Licenses

Copyright © 2018-2022 Intel Corporation

LEGAL NOTICE: Your use of this software and any required dependent software (the "Software Package") is subject to the terms and conditions of the software license agreements for the Software Package, which may also include notices, disclaimers, or license terms for third party or open source software included in or with the Software Package, and your use indicates your acceptance of all such terms. Please refer to the "third-party-programs.txt" or other similarly-named text file included with the Software Package for additional details.

Intel is committed to the respect of human rights and avoiding complicity in human rights abuses, a policy reflected in the Intel Global Human Rights Principles. Accordingly, by accessing the Intel material on this platform you agree that you will not use the material in a product or application that causes or contributes to a violation of an internationally recognized human right.

By downloading and using this container and the included software, you agree to the terms and conditions of the software license agreements located here. Please, review content inside <openvino_install_root>/licensing folder for more details.

As for any pre-built image usage, it is the image user's responsibility to ensure that any use of this image complies with any relevant licenses and potential fees for all software contained within. We will have no indemnity or warranty coverage from suppliers.

Components:

• Ubuntu
• Intel® Distribution of OpenVINO™ toolkit

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