/ai-visual-inference-samples

Intel® AI Visual Inference Samples are easy to use script implementations of workloads with processing pipelines consisting of media and AI inference elements. Samples are built on top of open source media and AI inference frameworks to demonstrate functionality and performance of Intel® Data Center GPU Flex Series for AI visual inference use cases

Primary LanguageC++MIT LicenseMIT

DISCONTINUATION OF PROJECT

This project will no longer be maintained by Intel.
This project has been identified as having known security escapes.
Intel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.
Intel no longer accepts patches to this project.

Intel® AI Visual Inference Samples

Intel® AI Visual Inference Samples are easy to use python* scripts implementations of workloads with media and AI inference pipelines. The samples are based on media and AI inference frameworks to demonstrate performance of Intel® Data Center GPU Flex Series.

Contents

Releases

Each release of the Intel® AI Visual Inference Samples provides samples for use with a single, specific AI Inference framework. These samples are optimized for best performance with the configurations they are released with, and for best results it is recommended that you use the latest release intended for your preferred AI inference framework. Target AI Inference framework can be easily identified by the string following the version number in the release tag, for example a release targeting pytorch may look like v0.5.0-pytorch.
If a specific update is required, you may use the tip of main, all samples from main will function as expected, but be aware optimal performance is not guaranteed.

Requirements

Operating System Requirements

  • Ubuntu 22.04

Hardware Requirements

  • Intel® Data Center GPU Flex Series on Intel® Xeon® platform hosts

Running Sample Applications using Docker

Please refer to instructions here on how to run sample applications.

Please refer to instructions here on how to measure performace using sample applications.

Known Issues

There are currently no known issues

Get support

Report questions, issues and suggestions, using:

License

This project is licensed under the MIT License. See the LICENSE file for details.

How to Contribute

See CONTRIBUTING.md for more information.

Security Policy

See SECURITY.md for more information.

Code of Conduct

For information on the contributor code of coduct see CODE_OF_CONDUCT.md for more information.



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