From 370c4c5672bcdbecaf9316552063ed6aec15a45d Mon Sep 17 00:00:00 2001 From: sfatimar Date: Wed, 27 Apr 2022 22:19:44 +0530 Subject: [PATCH] Ov ep docx update 22.2 (#11296) * Update eps.md * Update OpenVINOExecutionProvider.md * Update OpenVINOExecutionProvider.md --- docs/build/eps.md | 4 +-- .../OpenVINO-ExecutionProvider.md | 27 +++++++++++++++++-- 2 files changed, 27 insertions(+), 4 deletions(-) diff --git a/docs/build/eps.md b/docs/build/eps.md index d6f8a3be3f..f9817bbccf 100644 --- a/docs/build/eps.md +++ b/docs/build/eps.md @@ -229,7 +229,7 @@ See more information on the OpenVINO Execution Provider [here](../execution-prov ### Prerequisites {: .no_toc } -1. Install the Intel® Distribution of OpenVINOTM Toolkit **Release 2022.1** for the appropriate OS and target hardware: +1. Install the openvino offline/online installer from Intel® Distribution of OpenVINOTM Toolkit **Release 2022.1** for the appropriate OS and target hardware: * [Linux - CPU, GPU, VPU, VAD-M](https://software.intel.com/en-us/openvino-toolkit/choose-download/free-download-linux) * [Windows - CPU, GPU, VPU, VAD-M](https://software.intel.com/en-us/openvino-toolkit/choose-download/free-download-windows). @@ -243,7 +243,7 @@ See more information on the OpenVINO Execution Provider [here](../execution-prov * To configure Intel® MovidiusTM USB, please follow this getting started guide: [Linux](https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_linux.html#additional-NCS-steps) * To configure Intel® Vision Accelerator Design based on 8 MovidiusTM MyriadX VPUs, please follow this configuration guide: [Windows](https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_windows.html#hddl-myriad), [Linux](https://docs.openvino.ai/2021.4/openvino_docs_install_guides_installing_openvino_linux.html#install-VPU). Follow steps 3 and 4 to complete the configuration. -3. Initialize the OpenVINO environment by running the setupvars script as shown below: +3. Initialize the OpenVINO environment by running the setupvars script as shown below. This is a required step: * For Linux run till OpenVINO 2021.4 version: ``` $ source /bin/setupvars.sh diff --git a/docs/execution-providers/OpenVINO-ExecutionProvider.md b/docs/execution-providers/OpenVINO-ExecutionProvider.md index 2f7e1e0c4a..11e87da822 100644 --- a/docs/execution-providers/OpenVINO-ExecutionProvider.md +++ b/docs/execution-providers/OpenVINO-ExecutionProvider.md @@ -20,8 +20,8 @@ Accelerate ONNX models on Intel CPUs, GPUs and VPUs with ONNX Runtime and the In ## Install Pre-built packages and Docker images are published for ONNX Runtime with OpenVINO by Intel for each release. -* OpenVINO-EP Release page: [Latest v4.0 Release](https://github.com/intel/onnxruntime/releases) -* Python wheels: [intel/onnxruntime](https://github.com/intel/onnxruntime/releases) +* OpenVINO-EP Release page: [Latest v4.0 Release](https://github.com/intel/onnxruntime/releases) +* Python wheels Ubuntu/Windows: [intel/onnxruntime](https://github.com/intel/onnxruntime/releases) * Docker image: [openvino/onnxruntime_ep_ubuntu18](https://hub.docker.com/r/openvino/onnxruntime_ep_ubuntu18) ## Requirements @@ -47,6 +47,29 @@ OpenVINO 2022.1. ## Usage +**OpenVINO Environment** + +Before running any ort samples(Python/C++/C#) with the OpenVINOExecutionProvider it is must to set up the OpenVINO Environment Variables using the full installer package of OpenVINO. +Initialize the OpenVINO environment by running the setupvars script as shown below. This is a required step: + * For Linux run till OpenVINO 2021.4 version: + ``` + $ source /bin/setupvars.sh + ``` + * For Linux run from OpenVINO 2022.1 version: + ``` + $ source /setupvars.sh + ``` + * For Windows run till OpenVINO 2021.4 version: + ``` + C:\ \bin\setupvars.bat + ``` + * For Windows run from OpenVINO 2022.1 version: + ``` + C:\ \setupvars.bat + ``` + **Note:** If you are using a dockerfile to use OpenVINO-EP, sourcing OpenVINO won't be possible within the dockerfile. You would have to explicitly set the LD_LIBRARY_PATH to point to OpenVINO libraries location. Refer our [dockerfile].(https://github.com/microsoft/onnxruntime/blob/master/dockerfiles/Dockerfile.openvino) + + **C#** To use csharp api for openvino execution provider create a custom nuget package. Follow the instructions [here](../build/inferencing.md#build-nuget-packages) to install prerequisites for nuget creation. Once prerequisites are installed follow the instructions to [build openvino](../build/eps.md#openvino) and add an extra flag `--build_nuget` to create nuget packages. Two nuget packages will be created Microsoft.ML.OnnxRuntime.Managed and Microsoft.ML.OnnxRuntime.Openvino.