OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Go to file
Mikhail Nosov 173f328c53
Checking compatibility between 'pyopenvino' and 'libopenvino' (#10668)
* Checking compatibility between 'pyopenvino' and 'libopenvino' on 'import phase'

This fix is to prevent undefined behavior when user loads OpenVINO from python, but pyopenvino loads different version of 'libopenvino'
This may happen if user has several releases installed and played around PATH/PYTHONPATH environment variables.

In such case, user may have undefined behavior - application may crash in the middle of the usage or use incorrect release.

Fix checks build versions for pyopenvino and ov::get_openvino_version. If mismatch occurs, exception is thrown.

This logic is disabled if user has built OpenVINO locally, experienced developers probably know what they're doing, so if version has 'custom_'  prefix - this logic is disabled

* Removed custom logic for CI_BUILD_NUMBER, it is reused from already included version.cmake

* Use addVersionDefines macro
2022-02-28 17:04:59 +03:00
.ci Azure CI: Disable tests on Mac due to long building 2022-02-16 13:12:06 +03:00
.github Fix NCC (#10105) 2022-02-03 16:51:26 +03:00
cmake Moved ngraphConfig.cmake to root (#10618) 2022-02-25 15:47:21 +03:00
docs Add pytorch Resnext101 from fb into documentation (#10665) 2022-02-28 15:30:33 +03:00
licensing Update third party files (#9992) 2022-02-01 21:06:06 +03:00
samples creating remote ocl buffer/tensor per request, to avoid simulteneous locking of the same ocl buffer when auto-batching is used (#10607) 2022-02-28 15:04:03 +03:00
scripts [Scripts] Remove MacOS install dependencies (#10397) 2022-02-16 12:52:57 +03:00
src Checking compatibility between 'pyopenvino' and 'libopenvino' (#10668) 2022-02-28 17:04:59 +03:00
tests [CPU] Fix for subnormal numbers nullifying routine (#10622) 2022-02-25 10:55:59 +03:00
thirdparty renamed streams property (#10620) 2022-02-24 10:49:38 +03:00
tools [POT] Update samples and samplers with the new DataLoader format (#10595) 2022-02-28 16:26:07 +03:00
.gitattributes [POT] Update tests with new data (#8209) 2021-10-27 12:40:19 +03:00
.gitignore [Python API] Move old python bindings (#9134) 2022-01-24 13:16:07 +03:00
.gitmodules [GPU] Moved onednn_gpu to plugin folder (#9458) 2021-12-29 11:06:14 +03:00
CMakeLists.txt Moved ngraphConfig.cmake to root (#10618) 2022-02-25 15:47:21 +03:00
CODEOWNERS [VPU] Rename INTEL_VPU to INTEL_MYRIAD, move thirdparty and vpu_dependencies (#9827) 2022-01-31 16:58:33 +03:00
CONTRIBUTING.md Add original contribution guide to root (#10644) 2022-02-24 16:13:21 +00:00
install_build_dependencies.sh Update year to 2022 in copyright notice (#9755) 2022-01-19 01:07:49 +03:00
Jenkinsfile Beautify Jenkinsfile a little bit 2021-05-31 15:24:56 +03:00
LICENSE Publishing R3 2018-10-16 13:45:03 +03:00
README.md Removed obsolete documentation (#10504) 2022-02-18 13:02:55 +03:00
SECURITY.md Added SECURITY.md back (#3177) 2020-11-17 16:44:44 +03:00

OpenVINO™ Toolkit

Stable release Apache License Version 2.0 GitHub branch checks state Azure DevOps builds (branch) PyPI Downloads

This toolkit allows developers to deploy pre-trained deep learning models through a high-level OpenVINO™ Runtime C++ and Python APIs integrated with application logic.

This open source version includes several components: namely Model Optimizer, OpenVINO™ Runtime, Post-Training Optimization Tool, as well as CPU, GPU, MYRIAD, multi device and heterogeneous plugins to accelerate deep learning inferencing on Intel® CPUs and Intel® Processor Graphics. It supports pre-trained models from the Open Model Zoo, along with 100+ open source and public models in popular formats such as TensorFlow, ONNX, PaddlePaddle, MXNet, Caffe, Kaldi.

Repository components

License

Deep Learning Deployment Toolkit is licensed under Apache License Version 2.0. By contributing to the project, you agree to the license and copyright terms therein and release your contribution under these terms.

Resources

Support

Please report questions, issues and suggestions using:


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