OpenVINO™ Execution Provider for ONNX Runtime Docker image for Ubuntu* 18.04 LTS
4.1K
This is archived and no longer supported. Please refer to openvino/onnxruntime_ep_ubuntu20 for latest builds. The OpenVINO Execution Provider (EP) for ONNX Runtime accelerates inference applications using APIs from ONNX Runtime machine learning framework on Intel CPUs, Intel integrated GPUs, and Intel Discrete GPUs using Intel's OpenVINO™ runtime.
This docker image provides a development environment for ONNX Runtime applications written using the Python API. Refer to the OpenVINO EP Python API options.
This docker image can be used to accelerate Deep Learning inference applications written using ONNX Runtime API on the following Intel hardware:-
To select a particular hardware option as target for Inference, use the device_type ONNX Runtime configuration option from the list of OpenVINO EP configurations options.
The default hardware target for this docker image is the Intel® CPU. To choose other targets, use the configuration option above.
Alternatively, to build a docker image with a different hardware target as the default, use this Dockerfile and provide argument --build-arg DEVICE=<device_choice> along with the docker build instruction. The device type is one of the allowed values for the device_type configuration option for OpenVINO EP.
This docker image may be run as a container with the following arguments to ensure access to various hardware. The list of settings for all hardware targets may be found in the OpenVINO EP docker instructions page.
docker run -it --rm --device-cgroup-rule='c 189:* rmw' -v /dev/bus/usb:/dev/bus/usb openvino/onnxruntime_ep_ubuntu18:latest
docker run -it --rm --device-cgroup-rule='c 189:* rmw' -v /dev/bus/usb:/dev/bus/usb --device /dev/dri:/dev/dri openvino/onnxruntime_ep_ubuntu18:latest
Copyright © 2018-2023 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 for ONNX Runtime located here and for OpenVINO 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.
The GPL/LGPL license obligation of having source code of the associated components made available to the user is fulfilled by packaging those sources inside the docker image.
Components:
OpenVINO™ is a registered trademark of Intel Corporation. ONNX is a registered trademark of The Linux Foundation. ONNX Runtime is a registered trademark of Microsoft Corporation. All other product names, logos, and brands are property of their respective owners.
Content type
Image
Digest
Size
595.4 MB
Last updated
over 4 years ago
docker pull openvino/onnxruntime_ep_ubuntu18:2022.1.0