Skip to content

Latest commit

 

History

History
 
 

dockerfiles

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
dl-workbench
dl-workbench
 
 
rhel8
rhel8
 
 
ubuntu18
ubuntu18
 
 
ubuntu20
ubuntu20
 
 
windows20h2
windows20h2
 
 
winserver2019
winserver2019
 
 
README.md
README.md
 
 

README.md

Dockerfiles with Intel® Distribution of OpenVINO™ toolkit

This repository folder contains Dockerfiles to build an docker image with the Intel® Distribution of OpenVINO™ toolkit. You can use Docker CI framework to build an image, please follow Get Started with DockerHub CI for Intel® Distribution of OpenVINO™ toolkit.

  1. Supported Operating Systems for Docker image
  2. Supported devices and distributions
  3. Where to get OpenVINO package
  4. How to build
  5. Prebuilt images
  6. How to run a container

Supported Operating Systems for Docker image

  • ubuntu18 folder (Ubuntu* 18.04 LTS)
  • ubuntu20 folder (Ubuntu* 20.04 LTS)
  • rhel8 folder (RHEL* 8)
  • winserver2019 folder (Windows* Server Core base OS LTSC 2019)
  • windows20h2 folder (Windows* OS 20H2)

Note: dl-workbench folder contains Dockerfiles for OpenVINO™ Deep Learning Workbench.

Supported devices and distributions

OpenVINO Dockerfile Name

Devices:

OpenVINO documentation for supported devices.

Distributions:

  • runtime: IE core, nGraph, OpenCV, plugins
  • data_runtime: runtime image content + DL Streamer runtimes
  • dev: IE core, nGraph, OpenCV, plugins, samples, demos, Python dev tools: Model Optimizer, Post training Optimization tool, Accuracy checker, Open Model Zoo tools (downloader, converter)
  • data_dev: data_runtime image + dev image + Media SDK, Speech Libraries and End-to-End Speech Demos
  • base (only for CPU): IE core, nGraph
  • proprietary: data_dev + installer

You can generate Dockerfile with your settings, please follow the DockerHub CI documentation.

  • runtime, data_runtime, dev, data_dev distributions based on archive package of OpenVINO product. You can just remove unnecessary parts.
  • base distribution is created by OpenVINO™ Deployment Manager.
  • proprietary distribution based on installer package of OpenVINO product. You can configure installation COMPONENTS, follow Command-Line Silent Instructions

Where to get OpenVINO package

You can get OpenVINO distribution packages (runtime, dev, data_dev) directly from public storage and proprietary package with registration here. For example:

  • take data_dev l_openvino_toolkit_data_dev_ubuntu18_p_2021.2.185.tgz package and specify -dist data_dev option for Docker CI docker_openvino.py or take a Dockerfile with data_dev suffix.
  • take runtime l_openvino_toolkit_runtime_ubuntu18_p_2021.2.185.tgz package and specify -dist runtime or -dist data_runtime option for Docker CI docker_openvino.py or take a Dockerfile with runtime/data_runtime suffix.
  • take proprietary l_openvino_toolkit_p_2021.3.249.tgz package and specify -dist proprietary option for Docker CI docker_openvino.py or take a Dockerfile with proprietary suffix.

How to build

Note: Please use Docker CI framework release version corresponding to the version of OpenVINO™ Toolkit that you need to build.

  • Base image with CPU only:

You can use Docker CI framework to build an image, please follow Get Started with DockerHub CI for Intel® Distribution of OpenVINO™ toolkit.

python3 docker_openvino.py build --file "dockerfiles/ubuntu18/openvino_c_base_2020.3.dockerfile" -os ubuntu18 -dist base -p 2020.3.341

Or via Docker Engine directly, but you need specify BUILD_ID argument:

docker build --build-arg BUILD_ID=2020.3.341 -t ubuntu18_base_cpu:2020.3.341 - < dockerfiles/ubuntu18/openvino_c_base_2020.3.dockerfile
  • Dev/data_dev/runtime/data_runtime/proprietary image:

You can use Docker CI framework to build an image, please follow Get Started with DockerHub CI for Intel® Distribution of OpenVINO™ toolkit.

python3 docker_openvino.py build --file "dockerfiles/ubuntu18/openvino_cgvh_dev_2021.dockerfile" -os ubuntu18 -dist dev -p 2021.1

For data_dev/runtime/data_runtime/proprietary distributions, please set appropriate -dist and --file options.

Or via Docker Engine directly, but you need specify package_url argument (see Where to get OpenVINO package section) and OpenCL* version with INTEL_OPENCL argument to support GPU. Use the 20.35.17767 version of OpenCL* runtime 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:

docker build --build-arg package_url=https://storage.openvinotoolkit.org/repositories/openvino/packages/2021.4/l_openvino_toolkit_dev_ubuntu18_p_2021.4.582.tgz \
             --build-arg INTEL_OPENCL=20.35.17767 \
             -t ubuntu18_dev:2021.4 -f dockerfiles/ubuntu18/openvino_cgvh_dev_2021.4.dockerfile .

Prebuilt images

Prebuilt images are available on:

How to run a container

Please follow Run a container section in DockerHub CI getting started guide.

Documentation

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