IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[DOCS] installation guide restructuring 23.1 master (#19241)

Browse Source
This commit is contained in:
Karol Blaszczak 2023-09-06 17:46:55 +02:00 committed by GitHub
parent 5644ca40f6
commit c123843d0d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
29 changed files with 449 additions and 772 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
docs/MO_DG/prepare_model/Getting_performance_numbers.md
View File

@ -10,30 +10,21 @@ information on using ITT and Intel® VTune™ Profiler to get performance insigh
Test performance with the benchmark_app
###########################################################
Prerequisites
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
To run benchmarks, you need both OpenVINO developer tools and Runtime installed. Follow the
:doc:`Installation guide <openvino_docs_install_guides_install_dev_tools>` and make sure to install the latest
general release package with support for frameworks of the models you want to test.
To test performance of your model, make sure you :doc:`prepare the model for use with OpenVINO <openvino_docs_model_processing_introduction>`.
For example, if you use :doc:`OpenVINO's automation tools <omz_tools_downloader>`, these two lines of code will download the
resnet-50-tf and convert it to OpenVINO IR.
You can run OpenVINO benchmarks in both C++ and Python APIs, yet the experience differs in each case.
The Python one is part of OpenVINO Runtime installation, while C++ is available as a code sample.
For a detailed description, see:
* :doc:`benchmark_app for C++ <openvino_inference_engine_samples_benchmark_app_README>`
* :doc:`benchmark_app for Python <openvino_inference_engine_tools_benchmark_tool_README>`.
.. code-block:: sh
omz_downloader --name resnet-50-tf
omz_converter --name resnet-50-tf
Make sure to install the latest release package with support for frameworks of the models you want to test.
For the most reliable performance benchmarks, :doc:`prepare the model for use with OpenVINO <openvino_docs_model_processing_introduction>`.
Running the benchmark application
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
For a detailed description, see the dedicated articles:
:doc:`benchmark_app for C++ <openvino_inference_engine_samples_benchmark_app_README>` and
:doc:`benchmark_app for Python <openvino_inference_engine_tools_benchmark_tool_README>`.
The benchmark_app includes a lot of device-specific options, but the primary usage is as simple as:
.. code-block:: sh

6
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_ONNX.md
View File

@ -17,9 +17,9 @@ Introduction to ONNX
Converting an ONNX Model
########################
This page provides instructions on model conversion from the ONNX format to the OpenVINO IR format. To use model conversion API, install OpenVINO Development Tools by following the :doc:`installation instructions <openvino_docs_install_guides_install_dev_tools>`.
This page provides instructions on model conversion from the ONNX format to the OpenVINO IR format.
Model conversion process assumes you have an ONNX model that was directly downloaded from a public repository or converted from any framework that supports exporting to the ONNX format.
The model conversion process assumes you have an ONNX model that was directly downloaded from a public repository or converted from any framework that supports exporting to the ONNX format.
.. tab-set::
@ -48,7 +48,7 @@ Model conversion process assumes you have an ONNX model that was directly downlo
mo --input_model <INPUT_MODEL>.onnx
There are no ONNX specific parameters, so only framework-agnostic parameters are available to convert your model. For details, see the *General Conversion Parameters* section in the :doc:`Converting a Model to Intermediate Representation (IR) <openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model>` guide.
There are no ONNX-specific parameters, so only framework-agnostic parameters are available to convert your model. For details, see the *General Conversion Parameters* section in the :doc:`Converting a Model to Intermediate Representation (IR) <openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model>` guide.
Supported ONNX Layers
#####################

2
docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md
View File

@ -11,8 +11,6 @@ This page provides general instructions on how to run model conversion from a Te
.. note:: TensorFlow models are supported via :doc:`FrontEnd API <openvino_docs_MO_DG_TensorFlow_Frontend>`. You may skip conversion to IR and read models directly by OpenVINO runtime API. Refer to the :doc:`inference example <openvino_docs_OV_UG_Integrate_OV_with_your_application>` for more details. Using ``convert_model`` is still necessary in more complex cases, such as new custom inputs/outputs in model pruning, adding pre-processing, or using Python conversion extensions.
To use model conversion API, install OpenVINO Development Tools by following the :doc:`installation instructions <openvino_docs_install_guides_install_dev_tools>`.
Converting TensorFlow 1 Models
###############################

12
docs/OV_Runtime_UG/Samples_Overview.md
View File

@ -51,7 +51,7 @@ If you installed OpenVINO via PyPI, download `the OpenVINO repository <https://g
The applications include:
- **Speech Sample** - Acoustic model inference based on Kaldi neural networks and speech feature vectors.
- **Speech Sample** - ``[DEPRECATED]`` Acoustic model inference based on Kaldi neural networks and speech feature vectors.
- :doc:`Automatic Speech Recognition C++ Sample <openvino_inference_engine_samples_speech_sample_README>`
- :doc:`Automatic Speech Recognition Python Sample <openvino_inference_engine_ie_bridges_python_sample_speech_sample_README>`
@ -98,13 +98,15 @@ The applications include:
- **Benchmark Application** – Estimates deep learning inference performance on supported devices for synchronous and asynchronous modes.
- :doc:`Benchmark C++ Tool <openvino_inference_engine_samples_benchmark_app_README>`
Note that the Python version of the benchmark tool is currently available only through the :doc:`OpenVINO Development Tools installation <openvino_docs_install_guides_install_dev_tools>`. It is not created in the samples directory but can be launched with the following command: ``benchmark_app -m <model> -i <input> -d <device>``. For more information, check the :doc:`Benchmark Python Tool <openvino_inference_engine_tools_benchmark_tool_README>` documentation.
Note that the Python version of the benchmark tool is a core component of the OpenVINO installation package and
may be executed with the following command: ``benchmark_app -m <model> -i <input> -d <device>``.
For more information, check the :doc:`Benchmark Python Tool <openvino_inference_engine_tools_benchmark_tool_README>`.
.. note::
All C++ samples support input paths containing only ASCII characters, except for the Hello Classification Sample, that supports Unicode.
All C++ samples support input paths containing only ASCII characters, except for the Hello Classification Sample, which supports Unicode.
Media Files Available for Samples
#################################
@ -119,7 +121,7 @@ To run the sample, you can use :doc:`public <omz_models_group_public>` or :doc:`
Build the Sample Applications
#############################
.. _build-samples-linux:
Build the Sample Applications on Linux
++++++++++++++++++++++++++++++++++++++

21
docs/OV_Runtime_UG/migration_ov_2_0/deployment_migration.md
View File

@ -16,7 +16,19 @@ One of the main concepts for OpenVINO™ API 2.0 is being "easy to use", which i
* Development and deployment of OpenVINO-based applications.
To accomplish that, the 2022.1 release OpenVINO introduced significant changes to the installation and deployment processes. This guide will walk you through these changes.
To accomplish that, the 2022.1 release OpenVINO introduced significant changes to the installation
and deployment processes. Further changes were implemented in 2023.1, aiming at making the installation
process even simpler.
.. tip::
These instructions are largely deprecated and should be used for versions prior to 2023.1.
OpenVINO Development Tools is being deprecated and will be discontinued entirely in 2025.
With this change, the OpenVINO Runtime package has become the default choice for installing the
software. It now includes all components necessary to utilize OpenVINO's functionality.
The Installer Package Contains OpenVINO™ Runtime Only
#####################################################
@ -47,8 +59,8 @@ In previous versions, OpenVINO Development Tools was a part of the main package.
$ mo.py -h
For 2022.1 and After
++++++++++++++++++++
For 2022.1 and After (prior to 2023.1)
++++++++++++++++++++++++++++++++++++++++++
In OpenVINO 2022.1 and later, you can install the development tools only from a `PyPI <https://pypi.org/project/openvino-dev/>`__ repository, using the following command (taking TensorFlow as an example):
@ -67,7 +79,8 @@ Then, the tools can be used by commands like:
$ pot -h
Installation of any other dependencies is not required. For more details on the installation steps, see the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>`.
Installation of any other dependencies is not required. For more details on the installation steps, see the
`Install OpenVINO Development Tools <https://docs.openvino.ai/2023.0/openvino_docs_install_guides_install_dev_tools.html>`__ prior to OpenVINO 2023.1.
Interface Changes for Building C/C++ Applications
#################################################

6
docs/get_started/get_started_demos.md
View File

@ -35,6 +35,8 @@ To use sample applications, install OpenVINO Runtime via one of the following di
Make sure that you also `install OpenCV <https://github.com/opencv/opencv/wiki/BuildOpenCV4OpenVINO>`__ , as it's required for running sample applications.
Install OpenVINO Development Tools
++++++++++++++++++++++++++++++++++
@ -49,6 +51,10 @@ To install OpenVINO Development Tools, follow the :doc:`instructions for C++ dev
pip install openvino-dev[caffe]
Build Samples
+++++++++++++

0
docs/install_guides/installing-model-dev-tools.md → docs/install_guides/--installing-model-dev-tools.md
View File

16
docs/install_guides/--installing-openvino-macos.md
View File

@ -1,16 +0,0 @@
# Install OpenVINO™ Runtime for macOS from Installer
@sphinxdirective
Currently only the following ways are provided to install OpenVINO™ on macOS:
* :doc:`Install OpenVINO Runtime using an Archive File <openvino_docs_install_guides_installing_openvino_from_archive_macos>`
* :doc:`Install OpenVINO Runtime using Homebrew <openvino_docs_install_guides_installing_openvino_brew>`
* :doc:`Install OpenVINO using PyPI <openvino_docs_install_guides_installing_openvino_pip>`
* :doc:`Install OpenVINO using Conda Forge <openvino_docs_install_guides_installing_openvino_conda>`
* `Build From Source <https://github.com/openvinotoolkit/openvino/blob/master/docs/dev/build.md>`__
The other installation methods are temporarily unavailable.
@endsphinxdirective

201
docs/install_guides/--installing-openvino-raspbian-removedfromtoc.md
View File

@ -1,201 +0,0 @@
# Install OpenVINO™ Runtime for Raspbian OS
@sphinxdirective
.. note::
* These steps apply to Raspbian OS (the official OS for Raspberry Pi boards).
* These steps have been validated with Raspberry Pi 3.
* There is also an open-source version of OpenVINO™ that can be compiled for aarch64 (see `build instructions <https://github.com/openvinotoolkit/openvino/blob/master/docs/dev/build_raspbian.md>`_).
Development and Target Systems
###############################
.. tab-set::
.. tab-item:: System Requirements
:sync: system-requirements
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`_
.. tab-item:: Software Requirements
:sync: software-requirements
* CMake 3.10 or higher
* Python 3.7 - 3.11
.. _install-openvino:
Step 1: Download and Install OpenVINO Runtime
#############################################
1. Open the Terminal or your preferred console application.
2. Create an installation folder for OpenVINO. If the folder already exists, skip this step.
.. code-block:: sh
sudo mkdir -p /opt/intel
.. note::
The ``/opt/intel`` path is the recommended folder path for administrators or root users. If you prefer to install OpenVINO in regular userspace, the recommended path is ``/home/<USER>/intel``. You may use a different path if desired.
3. Go to your ``~/Downloads`` directory and download OpenVINO Runtime archive file for Debian from `OpenVINO package repository <https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.0/linux/>`_.
.. tab-set::
.. tab-item:: ARM 64-bit
:sync: arm-64
.. code-block:: sh
cd ~/Downloads/
sudo wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.0/linux/l_openvino_toolkit_debian9_2023.0.0.10926.b4452d56304_arm64.tgz -O openvino_2023.0.0.tgz
.. tab-item:: ARM 32-bit
:sync: arm-32
.. code-block:: sh
cd ~/Downloads/
sudo wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.0/linux/l_openvino_toolkit_debian9_2023.0.0.10926.b4452d56304_armhf.tgz -O openvino_2023.0.0.tgz
4. Extract the archive file and move it to the installation folder:
.. tab-set::
.. tab-item:: ARM 64-bit
:sync: arm-64
.. code-block:: sh
sudo tar -xf openvino_2023.0.0.tgz
sudo mv l_openvino_toolkit_debian9_2023.0.0.10926.b4452d56304_arm64 /opt/intel/openvino_2023.0.0
.. tab-item:: ARM 32-bit
:sync: arm-32
.. code-block:: sh
sudo tar -xf openvino_2023.0.0.tgz
sudo mv l_openvino_toolkit_debian9_2023.0.0.10926.b4452d56304_armhf /opt/intel/openvino_2023.0.0
5. Install required system dependencies on Linux. To do this, OpenVINO provides a script in the extracted installation directory. Run the following command:
.. code-block:: sh
sudo -E ./install_dependencies/install_openvino_dependencies.sh
6. For simplicity, it is useful to create a symbolic link as below:
.. code-block:: sh
sudo ln -s openvino_2023.0.0 openvino_2023
.. note::
If you have already installed a previous release of OpenVINO 2023, a symbolic link to the ``openvino_2023`` folder may already exist. Unlink the previous link with ``sudo unlink openvino_2023``, and then re-run the command above.
Congratulations, you finished the installation! The ``/opt/intel/openvino_2023`` folder now contains the core components for OpenVINO. If you used a different path in Step 2, for example, ``/home/<USER>/intel/``, OpenVINO is then installed in ``/home/<USER>/intel/openvino_2023``. The path to the ``openvino_2023`` directory is also referred as ``<INSTALL_DIR>`` throughout the OpenVINO documentation.
.. _install-external-dependencies:
Step 2: Install External Software Dependencies
##############################################
CMake version 3.10 or higher is required for building the OpenVINO™ toolkit sample application. To install, open a Terminal window and run the following command:
.. code-block:: sh
sudo apt install cmake
CMake is installed. Continue to the next section to set the environment variables.
.. _set-the-environment-variables-raspbian:
Step 3: Set the Environment Variables
#####################################
You must update several environment variables before you can compile and run OpenVINO applications. Open a terminal window and run the ``setupvars.sh`` script as shown below to temporarily set your environment variables. If your <INSTALL_DIR> is not ``/opt/intel/openvino_2023``, use the correct one instead.
.. code-block:: sh
source /opt/intel/openvino_2023/setupvars.sh
If you have more than one OpenVINO version on your machine, you can easily switch its version by sourcing the ``setupvars.sh`` of your choice.
.. note::
The above command must be re-run every time you start a new terminal session. To set up Linux to automatically run the command every time a new terminal is opened, open ``~/.bashrc`` in your favorite editor and add ``source /opt/intel/openvino_2023/setupvars.sh`` after the last line. Next time when you open a terminal, you will see ``[setupvars.sh] OpenVINO™ environment initialized``. Changing ``.bashrc`` is not recommended when you have multiple OpenVINO versions on your machine and want to switch among them.
The environment variables are set. Continue to the next section if you want to download any additional components.
.. _model-optimizer:
Step 4 (Optional): Install Additional Components
################################################
If you want to use your model for inference, the model must be converted to the ``.bin`` and ``.xml`` Intermediate Representation (IR) files that are used as input by OpenVINO Runtime. To get the optimized models, you can use one of the following options:
* Download public and Intel's pre-trained models from the `Open Model Zoo <https://github.com/openvinotoolkit/open_model_zoo>`_ using :doc:`Model Downloader tool <omz_tools_downloader>`. For more information on pre-trained models, see :doc:`Pre-Trained Models Documentation <omz_models_group_intel>`.
* OpenCV is necessary to run demos from Open Model Zoo (OMZ). Some OpenVINO samples can also extend their capabilities when compiled with OpenCV as a dependency. To install OpenCV for OpenVINO, see the `instructions on Github <https://github.com/opencv/opencv/wiki/BuildOpenCV4OpenVINO)>`_.
* Convert the models using the model conversion API, which is included in OpenVINO Development Tools.
* OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models. It provides tools like model conversion API, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader. See the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>` page for step-by-step installation instructions.
What's Next?
####################
Now that you've installed OpenVINO Runtime, you're ready to run your own machine learning applications! Learn more about how to integrate a model in OpenVINO applications by trying out the following tutorials.
.. tab-set::
.. tab-item:: Get started with Python
:sync: get-started-python
Try the `Python Quick Start Example <notebooks/201-vision-monodepth-with-output.html>`__ to estimate depth in a scene using an OpenVINO monodepth model in a Jupyter Notebook inside your web browser.
.. image:: https://user-images.githubusercontent.com/15709723/127752390-f6aa371f-31b5-4846-84b9-18dd4f662406.gif
:width: 400
Visit the :ref:`Tutorials <notebook tutorials>` page for more Jupyter Notebooks to get you started with OpenVINO, such as:
* `OpenVINO Python API Tutorial <notebooks/002-openvino-api-with-output.html>`__
* `Basic image classification program with Hello Image Classification <notebooks/001-hello-world-with-output.html>`__
* `Convert a PyTorch model and use it for image background removal <notebooks/205-vision-background-removal-with-output.html>`__
.. tab-item:: Get started with C++
:sync: get-started-python
Try the `C++ Quick Start Example <openvino_docs_get_started_get_started_demos.html>`_ for step-by-step instructions on building and running a basic image classification C++ application.
.. image:: https://user-images.githubusercontent.com/36741649/127170593-86976dc3-e5e4-40be-b0a6-206379cd7df5.jpg
:width: 400
Visit the :ref:`Samples <code samples>` page for other C++ example applications to get you started with OpenVINO, such as:
* `Basic object detection with the Hello Reshape SSD C++ sample <openvino_inference_engine_samples_hello_reshape_ssd_README.html>`_
* `Automatic speech recognition C++ sample <openvino_inference_engine_samples_speech_sample_README.html>`_
Additional Resources
####################
* :ref:`Troubleshooting Guide for OpenVINO Installation & Configuration <troubleshooting guide for install>`
* Converting models for use with OpenVINO™: :ref:`Model Optimizer User Guide <deep learning model optimizer>`
* Writing your own OpenVINO™ applications: :ref:`OpenVINO™ Runtime User Guide <deep learning openvino runtime>`
* Sample applications: :ref:`OpenVINO™ Toolkit Samples Overview <code samples>`
* Pre-trained deep learning models: :ref:`Overview of OpenVINO™ Toolkit Pre-Trained Models <model zoo>`
* IoT libraries and code samples in the GitHUB repository: `Intel® IoT Developer Kit <https://github.com/intel-iot-devkit>`__
@endsphinxdirective

28
docs/install_guides/--installing-openvino-runtime.md
View File

@ -1,28 +0,0 @@
# Install OpenVINO™ Runtime
@sphinxdirective
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Windows, macOS, and
Linux operating systems, using various installation methods.
.. toctree::
:maxdepth: 2
:hidden:
Linux <openvino_docs_install_guides_installing_openvino_linux_header>
Windows <openvino_docs_install_guides_installing_openvino_windows_header>
macOS <openvino_docs_install_guides_installing_openvino_macos_header>
You can choose how to install OpenVINO™ Runtime according to your operating system:
* :doc:`Install OpenVINO Runtime on Linux <openvino_docs_install_guides_installing_openvino_linux_header>`
* :doc:`Install OpenVINO Runtime on Windows <openvino_docs_install_guides_installing_openvino_windows_header>`
* :doc:`Install OpenVINO Runtime on macOS <openvino_docs_install_guides_installing_openvino_macos_header>`
Enjoy your journey with OpenVINO.
@endsphinxdirective

12
docs/install_guides/--installing-openvino-windows.md
View File

@ -1,12 +0,0 @@
# Install OpenVINO™ Runtime on Windows from Installer
Currently only the following ways are provided to install OpenVINO™:
* [Install OpenVINO Runtime from an Archive File](installing-openvino-from-archive-windows.md)
* [Install OpenVINO from PyPI](installing-openvino-pip.md)
* [Install OpenVINO with Docker](installing-openvino-docker-windows.md)
* [Build From Source](https://github.com/openvinotoolkit/openvino/blob/master/docs/dev/build.md)
The other installation methods are temporarily unavailable.

53
docs/install_guides/--uninstalling-openvino.md
View File

@ -1,53 +0,0 @@
# Uninstalling the Intel® Distribution of OpenVINO™ Toolkit
@sphinxdirective
.. meta::
:description: Learn how to uninstall Intel® Distribution of OpenVINO™ Toolkit from your
operating system.
.. note::
Uninstallation procedures remove all Intel® Distribution of OpenVINO™ Toolkit component files but don't affect user files in the installation directory.
Uninstall Using the Original Installation Package
#################################################
If you have installed OpenVINO Runtime from archive files, you can uninstall it by deleting the archive files and the extracted folders.
.. tab-set::
.. tab-item:: Windows
:sync: windows
If you have created the symbolic link, remove the link first.
Use either of the following methods to delete the files:
* Use Windows Explorer to remove the files.
* Open a Command Prompt and run:
.. code-block:: sh
rmdir /s <extracted_folder>
del <path_to_archive>
.. tab-item:: Linux & macOS
:sync: linux-and-macos
If you have created the symbolic link, remove the link first:
.. code-block:: sh
sudo rm /opt/intel/openvino_2023
To delete the files:
.. code-block:: sh
rm -r <extracted_folder> && rm <path_to_archive>
@endsphinxdirective

22
docs/install_guides/configurations-header.md
View File

@ -17,10 +17,26 @@
For GNA <openvino_docs_install_guides_configurations_for_intel_gna>
After you have installed OpenVINO™ Runtime, you may also need do some additional configurations for your device to work with OpenVINO™. See the following pages:
For certain use cases, you may need to install additional software, to get the full
potential of OpenVINO™. Check the following list for components pertaining to your
workflow:
| **Open Computer Vision Library**
| OpenCV is used to extend the capabilities of some models, for example enhance some of
OpenVINO samples, when used as a dependency in compilation. To install OpenCV for OpenVINO, see the
`instructions on GtHub <https://github.com/opencv/opencv/wiki/BuildOpenCV4OpenVINO>`__.
| **GPU drivers**
| If you want to run inference on a GPU, make sure your GPU's drivers are properly installed.
See the :doc:`guide on GPU configuration <openvino_docs_install_guides_configurations_for_intel_gpu>`
for details.
| **GNA drivers**
| If you want to run inference on a GNA (note that it is currently being deprecated and will no longer
be supported beyond 2023.2), make sure your GPU's drivers are properly installed. See the
:doc:`guide on GNA configuration <openvino_docs_install_guides_configurations_for_intel_gna>`
for details.
* :doc:`Configurations for GPU <openvino_docs_install_guides_configurations_for_intel_gpu>`
* :doc:`Configurations for GNA <openvino_docs_install_guides_configurations_for_intel_gna>`
@endsphinxdirective

77
docs/install_guides/installing-openvino-apt.md
View File

@ -1,36 +1,20 @@
# Install Intel® Distribution of OpenVINO™ Toolkit for Linux Using APT Repository {#openvino_docs_install_guides_installing_openvino_apt}
@sphinxdirective
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Linux operating
system, using the APT repository, which is a recommended
installation method for C++ developers.
:description: Learn how to install OpenVINO™ Runtime on the Linux operating
system, using the APT repository.
.. note::
Note that the APT distribution:
With the OpenVINO™ 2023.0 release, you can install OpenVINO Runtime on Linux using the APT repository.
OpenVINO™ Development Tools can be installed via PyPI only.
See `Installing Additional Components <step-3-optional-install-additional-components>`__ for more information.
* offers both C++ and Python APIs
* does not offer support for GNA and NPU inference
* additionally includes code samples
* is dedicated to Linux users.
See the `Release Notes <https://www.intel.com/content/www/us/en/developer/articles/release-notes/openvino/2023-0.html>`__
for more information on updates in the latest release.
Installing OpenVINO Runtime from APT is recommended for C++ developers. If you are working with Python,
the PyPI package has everything needed for Python development and deployment on CPU and GPUs. Visit the
:doc:`Install OpenVINO from PyPI <openvino_docs_install_guides_installing_openvino_pip>` page for instructions
on how to install OpenVINO Runtime for Python using PyPI.
.. warning::
By downloading and using this container and the included software, you agree to the terms and
conditions of the
`software license agreements <https://software.intel.com/content/dam/develop/external/us/en/documents/intel-openvino-license-agreements.pdf>`__.
Prerequisites
#######################################
.. tab-set::
@ -43,8 +27,8 @@ Prerequisites
.. tab-item:: Processor Notes
:sync: processor-notes
Processor graphics are not included in all processors.
See `Product Specifications <https://ark.intel.com/>`__ for information about your processor.
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
.. tab-item:: Software Requirements
:sync: software-requirements
@ -60,8 +44,6 @@ Installing OpenVINO Runtime
Step 1: Set Up the OpenVINO Toolkit APT Repository
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1. Install the GPG key for the repository
a. Download the `GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB <https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB>`__
@ -130,8 +112,8 @@ Step 1: Set Up the OpenVINO Toolkit APT Repository
Step 2: Install OpenVINO Runtime Using the APT Package Manager
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Install OpenVINO Runtime
------------------------
1. Install OpenVINO Runtime
.. tab-set::
@ -172,8 +154,7 @@ Install OpenVINO Runtime
Keep in mind that the build tools must be installed **separately** if you want to compile the samples.
Check for Installed Packages and Versions
-----------------------------------------
2. Check for Installed Packages and Versions
Run the following command:
@ -182,27 +163,14 @@ Run the following command:
apt list --installed | grep openvino
Step 3 (Optional): Install Additional Components
++++++++++++++++++++++++++++++++++++++++++++++++
Congratulations! You've just Installed OpenVINO! For some use cases you may still
need to install additional components. Check the
:doc:`list of additional configurations <openvino_docs_install_guides_configurations_header>`
to see if your case needs any of them.
OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models.
It provides tools like Model Optimizer, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader.
If you installed OpenVINO Runtime using APT, OpenVINO Development Tools must be installed separately.
See the **For C++ Developers** section on the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>` page for instructions.
Step 4 (Optional): Configure Inference on Non-CPU Devices
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
To enable the toolkit components to use processor graphics (GPU) on your system, follow the steps
in :doc:`GPU Setup Guide <openvino_docs_install_guides_configurations_for_intel_gpu>`.
Step 5: Build Samples
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
To build the C++ or C sample applications for Linux, run the ``build_samples.sh`` script:
With the APT distribution, you can build OpenVINO sample files, as explained in the
:doc:`guide for OpenVINO sample applications <openvino_docs_OV_UG_Samples_Overview>`.
For C++ and C, just run the ``build_samples.sh`` script:
.. tab-set::
@ -220,9 +188,6 @@ To build the C++ or C sample applications for Linux, run the ``build_samples.sh`
/usr/share/openvino/samples/c/build_samples.sh
For more information, refer to :ref:`Build the Sample Applications on Linux <build-samples-linux>`.
Uninstalling OpenVINO Runtime
#######################################

42
docs/install_guides/installing-openvino-brew.md
View File

@ -4,24 +4,15 @@
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Linux and macOS
operating systems, using Homebrew, which is a recommended
installation method for C++ developers.
operating systems, using Homebrew.
.. note::
Note that the `Homebrew <https://brew.sh/>`__ distribution:
Installing OpenVINO Runtime from Homebrew is recommended for C++ developers.
If you work with Python, consider :doc:`installing OpenVINO from PyPI <openvino_docs_install_guides_installing_openvino_pip>`
You can use `Homebrew <https://brew.sh/>`__ to install OpenVINO Runtime on macOS and Linux.
OpenVINO™ Development Tools can be installed via PyPI only.
See `Installing Additional Components <#optional-installing-additional-components>`__ for more information.
.. warning::
By downloading and using this container and the included software, you agree to the terms and conditions of the
`software license agreements <https://software.intel.com/content/dam/develop/external/us/en/documents/intel-openvino-license-agreements.pdf>`_.
* offers both C++ and Python APIs
* does not offer support for GNA and NPU inference
* is dedicated to macOS users.
.. tab-set::
@ -32,6 +23,12 @@ See `Installing Additional Components <#optional-installing-additional-component
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
.. tab-item:: Processor Notes
:sync: processor-notes
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
.. tab-item:: Software Requirements
:sync: software-requirements
@ -55,13 +52,12 @@ See `Installing Additional Components <#optional-installing-additional-component
* (Optional) Apple Xcode IDE (not required for OpenVINO™, but useful for development)
Installing OpenVINO Runtime
###########################
1. Make sure that you have installed Homebrew on your system. If not, follow the instructions on `the Homebrew website <https://brew.sh/>`__ to install and configure it.
2. Open a command prompt terminal window, and run the following command to install OpenVINO Runtime:
2. Run the following command in the terminal:
.. code-block:: sh
@ -74,16 +70,12 @@ Installing OpenVINO Runtime
brew list
Congratulations, you've finished the installation!
Congratulations! You've just Installed OpenVINO! For some use cases you may still
need to install additional components. Check the
:doc:`list of additional configurations <openvino_docs_install_guides_configurations_header>`
to see if your case needs any of them.
(Optional) Installing Additional Components
###########################################
OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models. It provides tools like Model Optimizer, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader. If you installed OpenVINO Runtime using Homebrew, OpenVINO Development Tools must be installed separately.
See the **For C++ Developers** section on the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>` page for instructions.
OpenCV is necessary to run demos from Open Model Zoo (OMZ). Some OpenVINO samples can also extend their capabilities when compiled with OpenCV as a dependency. To install OpenCV for OpenVINO, see the `instructions on GitHub <https://github.com/opencv/opencv/wiki/BuildOpenCV4OpenVINO>`__.
Uninstalling OpenVINO
#####################

42
docs/install_guides/installing-openvino-conda.md
View File

@ -4,14 +4,17 @@
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Windows, Linux, and
macOS operating systems, using Conda Forge - a recommended
installation method for C++ developers.
macOS operating systems, using Conda Forge.
.. note::
Note that the Conda Forge distribution:
* offers both C++ and Python APIs
* does not offer support for GNA and NPU inference
* is dedicated to users of all major OSs: Windows, Linux, macOS.
Installing OpenVINO Runtime from Conda Forge is recommended for C++ developers, as it provides only the C++ Runtime API.
If you work with Python, consider :doc:`installing OpenVINO from PyPI <openvino_docs_install_guides_installing_openvino_pip>`
.. tab-set::
@ -21,16 +24,14 @@
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
.. comment to publish in the future, when gpu support comes back:
.. tab-set::
.. tab-item:: Processor Notes
:sync: processor-notes
| Not all Intel CPUs include integrated graphics processors.
| See `Product Specifications <https://ark.intel.com/>`__ for information about your hardware.
.. tab-item:: Processor Notes
:sync: processor-notes
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
.. tab-item:: Software
:sync: software
@ -63,10 +64,13 @@ Installing OpenVINO Runtime with Anaconda Package Manager
conda install -c conda-forge openvino=2023.0.1
Congratulations! You have finished installing OpenVINO Runtime.
Congratulations! You've just Installed OpenVINO! For some use cases you may still
need to install additional components. Check the description below, as well as the
:doc:`list of additional configurations <openvino_docs_install_guides_configurations_header>`
to see if your case needs any of them.
Compiling with OpenVINO Runtime from Conda-Forge on Linux
###########################################################
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
When linking OpenVINO libraries from Conda on Linux, ensure that you have the necessary Conda compilers installed.
To do so, run the following command in your Conda environment:
@ -84,7 +88,9 @@ To reactivate your Conda environment, execute the following command:
conda activate py310
Once you have reactivated your Conda environment, make sure that all the necessary environment variables are properly set and proceed with linking the OpenVINO libraries.
Once you have reactivated your Conda environment, make sure that all the necessary environment
variables are properly set and proceed with linking the OpenVINO libraries.
Uninstalling OpenVINO™ Runtime
###########################################################
@ -115,12 +121,6 @@ Visit the :doc:`Samples <openvino_docs_OV_UG_Samples_Overview>` page for other C
* `Automatic speech recognition C++ sample <openvino_inference_engine_samples_speech_sample_README.html>`__
Additional Resources
###########################################################
* `OpenVINO Runtime Conda Forge <https://anaconda.org/conda-forge/openvino>`__
* :doc:`OpenVINO™ Toolkit Samples Overview <openvino_docs_OV_UG_Samples_Overview>`
@endsphinxdirective

89
docs/install_guides/installing-openvino-from-archive-linux.md
View File

@ -1,38 +1,54 @@
# Install OpenVINO™ Runtime on Linux from an Archive File {#openvino_docs_install_guides_installing_openvino_from_archive_linux}
@sphinxdirective
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Linux operating
system, using an archive file, which is a recommended
installation method for C++ developers.
:description: Learn how to install OpenVINO™ Runtime on the Linux operating
system, using an archive file.
Installing OpenVINO Runtime from archive files is recommended for C++ developers. It will contain code samples,
as well as pre-built binaries and library files needed for OpenVINO Runtime. If you work with Python,
the PyPI package may be a better choice. See the :doc:`Install OpenVINO from PyPI <openvino_docs_install_guides_installing_openvino_pip>`
page for instructions on how to install OpenVINO Runtime for Python using PyPI.
.. note::
Note that the Archive distribution:
* offers both C++ and Python APIs
* additionally includes code samples
* is dedicated to users of all major OSs: Windows, Linux, macOS
* may offer different hardware support under different operating systems
(see the drop-down below for more details).
.. dropdown:: Inference Options
=================== ===== ===== ===== ===== ======== ============= ======== ========
Operating System CPU GPU GNA NPU AUTO Auto-batch HETERO MULTI
=================== ===== ===== ===== ===== ======== ============= ======== ========
Debian9 armhf V n/a n/a n/a V V V n/a
Debian9 arm64 V n/a n/a n/a V V V n/a
CentOS7 x86_64 V V V n/a V V V V
Ubuntu18 x86_64 V V V n/a V V V V
Ubuntu20 x86_64 V V V V V V V V
Ubuntu22 x86_64 V V V V V V V V
RHEL8 x86_64 V V V n/a V V V V
Windows x86_64 V V V V V V V V
MacOS x86_64 V n/a n/a n/a V V V n/a
MacOS arm64 V n/a n/a n/a V V V n/a
=================== ===== ===== ===== ===== ======== ============= ======== ========
The following development tools can be installed via `pypi.org <https://pypi.org/project/openvino-dev/>`__ only:
model conversion API, Post-Training Optimization Tool, Model Downloader and other Open Model Zoo tools,
Accuracy Checker, and Annotation Converter.
See the `Release Notes <https://www.intel.com/content/www/us/en/developer/articles/release-notes/openvino/2023-0.html>`__ for more information on updates in the latest release.
.. tab-set::
.. tab-item:: System Requirements
:sync: system-requirements
Full requirement listing is available in `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
.. tab-item:: Processor Notes
:sync: processor-notes
Processor graphics are not included in all processors. See `Product Specifications <https://ark.intel.com/>`__ for information about your processor.
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
.. tab-item:: Software
:sync: software
@ -80,6 +96,9 @@ See the `Release Notes <https://www.intel.com/content/www/us/en/developer/articl
Installing OpenVINO Runtime
############################################################
@ -215,6 +234,9 @@ OpenVINO is now in ``/home/<USER>/intel/openvino_2023``. The path to the ``openv
also referred as ``<INSTALL_DIR>`` throughout the OpenVINO documentation.
Step 2: Configure the Environment
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
@ -237,41 +259,8 @@ If you have more than one OpenVINO version installed on your system, you can eas
Next time when you open a terminal, you will see ``[setupvars.sh] OpenVINO™ environment initialized``.
Changing ``.bashrc`` is not recommended when you have multiple OpenVINO versions on your machine and want to switch among them.
The environment variables are set. Continue to the next section if you want to download any additional components.
The environment variables are set.
Step 3 (Optional): Install Additional Components
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models.
It provides tools like model conversion API, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader.
If you install OpenVINO Runtime using archive files, OpenVINO Development Tools must be installed separately.
See the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>`
page for step-by-step installation instructions.
OpenCV is necessary to run demos from Open Model Zoo (OMZ). Some OpenVINO samples can also extend their
capabilities when compiled with OpenCV as a dependency. To install OpenCV for OpenVINO, see the
`instructions on GitHub <https://github.com/opencv/opencv/wiki/BuildOpenCV4OpenVINO>`__.
Step 4 (Optional): Configure Inference on Non-CPU Devices
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
OpenVINO Runtime has a plugin architecture that enables you to run inference on multiple devices
without rewriting your code. Supported devices include integrated GPUs, discrete GPUs and GNAs.
See the instructions below to set up OpenVINO on these devices.
.. tab-set::
.. tab-item:: GPU
:sync: gpu
To enable the toolkit components to use processor graphics (GPU) on your system, follow the steps in :ref:`GPU Setup Guide <gpu guide>`.
.. tab-item:: GNA
:sync: gna
To enable the toolkit components to use Intel® Gaussian & Neural Accelerator (GNA) on your system, follow the steps in :ref:`GNA Setup Guide <gna guide>`.
What's Next?

65
docs/install_guides/installing-openvino-from-archive-macos.md
View File

@ -4,18 +4,36 @@
.. meta::
:description: Learn how to install OpenVINO™ Runtime on macOS operating
system, using an archive file, which is a recommended
installation method for C++ developers.
system, using an archive file.
With the OpenVINO™ 2023.0 release, you can download and use archive files to install OpenVINO Runtime. The archive files contain pre-built binaries and library files needed for OpenVINO Runtime, as well as code samples.
Installing OpenVINO Runtime from archive files is recommended for C++ developers. If you are working with Python, the PyPI package has everything needed for Python development and deployment on CPU and GPUs. Visit the :doc:`Install OpenVINO from PyPI <openvino_docs_install_guides_installing_openvino_pip>` page for instructions on how to install OpenVINO Runtime for Python using PyPI.
See the `Release Notes <https://www.intel.com/content/www/us/en/developer/articles/release-notes/openvino/2023-0.html>`__ for more information on updates in the latest release.
.. note::
Note that the Archive distribution:
* offers both C++ and Python APIs
* additionally includes code samples
* is dedicated to users of all major OSs: Windows, Linux, macOS
* may offer different hardware support under different operating systems
(see the drop-down below for more details)
.. dropdown:: Inference Options
=================== ===== ===== ===== ===== ======== ============= ======== ========
Operating System CPU GPU GNA NPU AUTO Auto-batch HETERO MULTI
=================== ===== ===== ===== ===== ======== ============= ======== ========
Debian9 armhf V n/a n/a n/a V V V n/a
Debian9 arm64 V n/a n/a n/a V V V n/a
CentOS7 x86_64 V V V n/a V V V V
Ubuntu18 x86_64 V V V n/a V V V V
Ubuntu20 x86_64 V V V V V V V V
Ubuntu22 x86_64 V V V V V V V V
RHEL8 x86_64 V V V n/a V V V V
Windows x86_64 V V V V V V V V
MacOS x86_64 V n/a n/a n/a V V V n/a
MacOS arm64 V n/a n/a n/a V V V n/a
=================== ===== ===== ===== ===== ======== ============= ======== ========
Since the OpenVINO™ 2022.1 release, the following development tools: Model Optimizer, Post-Training Optimization Tool, Model Downloader and other Open Model Zoo tools, Accuracy Checker, and Annotation Converter can be installed via `pypi.org <https://pypi.org/project/openvino-dev/>`__ only.
.. tab-set::
@ -24,7 +42,7 @@ See the `Release Notes <https://www.intel.com/content/www/us/en/developer/articl
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
.. tab-item:: Software Requirements
:sync: software-requirements
@ -108,12 +126,18 @@ Step 1: Install OpenVINO Core Components
If you have already installed a previous release of OpenVINO 2023, a symbolic link to the ``openvino_2023`` folder may already exist. Unlink the previous link with ``sudo unlink openvino_2023``, and then re-run the command above.
Congratulations, you finished the installation! The ``/opt/intel/openvino_2023`` folder now contains the core components for OpenVINO. If you used a different path in Step 2, you will find the ``openvino_2023`` folder there. The path to the ``openvino_2023`` directory is also referred as ``<INSTALL_DIR>`` throughout the OpenVINO documentation.
Congratulations, you have finished the installation! The ``/opt/intel/openvino_2023`` folder now contains
the core components for OpenVINO. If you used a different path in Step 2, for example, ``/home/<USER>/intel/``,
OpenVINO is now in ``/home/<USER>/intel/openvino_2023``. The path to the ``openvino_2023`` directory is
also referred as ``<INSTALL_DIR>`` throughout the OpenVINO documentation.
Step 2: Configure the Environment
+++++++++++++++++++++++++++++++++
You must update several environment variables before you can compile and run OpenVINO applications. Open a terminal window and run the ``setupvars.sh`` script as shown below to temporarily set your environment variables. If your ``<INSTALL_DIR>`` is not ``/opt/intel/openvino_2023``, use the correct one instead.
You must update several environment variables before you can compile and run OpenVINO applications. Open a terminal window and run the ``setupvars.sh``
script as shown below to temporarily set your environment variables. If your ``<INSTALL_DIR>`` (the folder you used to install OpenVINO) is not
the default ``/opt/intel/openvino_2023``, use the correct one instead.
.. code-block:: sh
@ -127,16 +151,7 @@ If you have more than one OpenVINO™ version on your machine, you can easily sw
The above command must be re-run every time you start a new terminal session. To set up macOS to automatically run the command every time a new terminal is opened, open ``~/.zshrc`` in your favorite editor and add ``source /opt/intel/openvino_2023/setupvars.sh`` after the last line. Next time when you open a terminal, you will see ``[setupvars.sh] OpenVINO™ environment initialized``. Changing ``~/.zshrc`` is not recommended when you have multiple OpenVINO versions on your machine and want to switch among them.
The environment variables are set. Continue to the next section if you want to download any additional components.
Step 3 (Optional): Install Additional Components
++++++++++++++++++++++++++++++++++++++++++++++++
OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models. It provides tools like Model Optimizer, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader. If you install OpenVINO Runtime using archive files, OpenVINO Development Tools must be installed separately.
See the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>` page for step-by-step installation instructions.
OpenCV is necessary to run demos from Open Model Zoo (OMZ). Some OpenVINO samples can also extend their capabilities when compiled with OpenCV as a dependency. To install OpenCV for OpenVINO, see the `instructions on GitHub <https://github.com/opencv/opencv/wiki/BuildOpenCV4OpenVINO>`__.
What's Next?
####################
@ -201,14 +216,6 @@ Additional Resources
* Pre-trained deep learning models: :ref:`Overview of OpenVINO™ Toolkit Pre-Trained Models <model zoo>`
* IoT libraries and code samples in the GitHUB repository: `Intel® IoT Developer Kit <https://github.com/intel-iot-devkit>`__
<!---
To learn more about converting models from specific frameworks, go to:
* :ref:`Convert Your Caffe Model <convert model caffe>`
* :ref:`Convert Your TensorFlow Model <convert model tf>`
* :ref:`Convert Your TensorFlow Lite Model <convert model tfl>`
* :ref:`Convert Your Apache MXNet Model <convert model mxnet>`
* :ref:`Convert Your Kaldi Model <convert model kaldi>`
* :ref:`Convert Your ONNX Model <convert model onnx>`
--->
@endsphinxdirective

92
docs/install_guides/installing-openvino-from-archive-windows.md
View File

@ -4,21 +4,37 @@
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Windows operating
system, using an archive file, which is a recommended
installation method for C++ developers.
system, using an archive file.
With the OpenVINO™ 2023.0 release, you can download and use archive files to install OpenVINO Runtime. The archive files contain pre-built binaries and library files needed for OpenVINO Runtime, as well as code samples.
Installing OpenVINO Runtime from archive files is recommended for C++ developers. If you are working with Python, the PyPI package has everything needed for Python development and deployment on CPU and GPUs. See the :doc:`Install OpenVINO from PyPI <openvino_docs_install_guides_installing_openvino_pip>` page for instructions on how to install OpenVINO Runtime for Python using PyPI.
.. note::
Note that the Archive distribution:
* offers both C++ and Python APIs
* additionally includes code samples
* is dedicated to users of all major OSs: Windows, Linux, macOS
* may offer different hardware support under different operating systems
(see the drop-down below for more details)
.. dropdown:: Inference Options
Since the OpenVINO™ 2022.1 release, the following development tools: Model Optimizer, Post-Training Optimization Tool, Model Downloader and other Open Model Zoo tools, Accuracy Checker, and Annotation Converter can be installed via `pypi.org <https://pypi.org/project/openvino-dev/>`__ only.
=================== ===== ===== ===== ===== ======== ============= ======== ========
Operating System CPU GPU GNA NPU AUTO Auto-batch HETERO MULTI
=================== ===== ===== ===== ===== ======== ============= ======== ========
Debian9 armhf V n/a n/a n/a V V V n/a
Debian9 arm64 V n/a n/a n/a V V V n/a
CentOS7 x86_64 V V V n/a V V V V
Ubuntu18 x86_64 V V V n/a V V V V
Ubuntu20 x86_64 V V V V V V V V
Ubuntu22 x86_64 V V V V V V V V
RHEL8 x86_64 V V V n/a V V V V
Windows x86_64 V V V V V V V V
MacOS x86_64 V n/a n/a n/a V V V n/a
MacOS arm64 V n/a n/a n/a V V V n/a
=================== ===== ===== ===== ===== ======== ============= ======== ========
See the `Release Notes <https://www.intel.com/content/www/us/en/developer/articles/release-notes/openvino/2023-0.html>`__ for more information on updates in the latest release.
System Requirements
####################
@ -26,28 +42,26 @@ System Requirements
.. tab-item:: System Requirements
:sync: system-requirements
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`_
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
.. tab-item:: Processor Notes
:sync: processor-notes
Processor graphics are not included in all processors.
See `Product Specifications`_ for information about your processor.
.. _Product Specifications: https://ark.intel.com/
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
.. tab-item:: Software
:sync: software
* `Microsoft Visual Studio 2019 with MSBuild <https://visualstudio.microsoft.com/vs/older-downloads/>`_ or `Microsoft Visual Studio 2022 <http://visualstudio.microsoft.com/ downloads/>`_
* `CMake 3.14 or higher, 64-bit <https://cmake.org/download/>`_ (optional, only required for building sample applications)
* `Python 3.7 - 3.11, 64-bit <https://www.python.org/downloads/windows/>`_
* `Microsoft Visual Studio 2019 with MSBuild <https://visualstudio.microsoft.com/vs/older-downloads/>`__ or `Microsoft Visual Studio 2022 <http://visualstudio.microsoft.com/ downloads/>`__
* `CMake 3.14 or higher, 64-bit <https://cmake.org/download/>`__ (optional, only required for building sample applications)
* `Python 3.7 - 3.11, 64-bit <https://www.python.org/downloads/windows/>`__
.. note::
To install Microsoft Visual Studio 2019, follow the `Microsoft Visual Studio installation guide <https://docs.microsoft.com/en-us/visualstudio/install/install-visual-studio?view=vs-2019>`_. You can choose to download the Community version. During installation in the **Workloads** tab, choose **Desktop development with C++**.
To install Microsoft Visual Studio 2019, follow the `Microsoft Visual Studio installation guide <https://docs.microsoft.com/en-us/visualstudio/install/install-visual-studio?view=vs-2019>`__. You can choose to download the Community version. During installation in the **Workloads** tab, choose **Desktop development with C++**.
.. note::
@ -55,7 +69,7 @@ System Requirements
.. important::
When installing Python, make sure you click the option **Add Python 3.x to PATH** to `add Python <https://docs.python.org/3/using/windows.html#installation-steps>`_ to your `PATH` environment variable.
When installing Python, make sure you click the option **Add Python 3.x to PATH** to `add Python <https://docs.python.org/3/using/windows.html#installation-steps>`__ to your `PATH` environment variable.
@ -155,43 +169,11 @@ You must update several environment variables before you can compile and run Ope
.. note::
If you see an error indicating Python is not installed, Python may not be added to the PATH environment variable (as described `here <https://docs.python.org/3/using/windows.html#finding-the-python-executable>`__). Check your system environment variables, and add Python if necessary.
If you see an error indicating Python is not installed, Python may not be added to the PATH environment variable
(as described `here <https://docs.python.org/3/using/windows.html#finding-the-python-executable>`__).
Check your system environment variables, and add Python if necessary.
The environment variables are set. Continue to the next section if you want to download any additional components.
.. _model-optimizer-windows:
Step 3 (Optional): Install Additional Components
++++++++++++++++++++++++++++++++++++++++++++++++
OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models. It provides tools like Model Optimizer, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader. If you install OpenVINO Runtime using archive files, OpenVINO Development Tools must be installed separately.
See the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>` page for step-by-step installation instructions.
OpenCV is necessary to run demos from Open Model Zoo (OMZ). Some OpenVINO samples can also extend their capabilities when compiled with OpenCV as a dependency. To install OpenCV for OpenVINO, see the `instructions on GitHub <https://github.com/opencv/opencv/wiki/BuildOpenCV4OpenVINO>`__ .
.. _optional-steps-windows:
Step 4 (Optional): Configure Inference on non-CPU Devices
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
OpenVINO Runtime has a plugin architecture that enables you to run inference on multiple devices without rewriting your code. Supported devices include integrated GPUs, discrete GPUs and GNAs. See the instructions below to set up OpenVINO on these devices.
.. tab-set::
.. tab-item:: GPU
:sync: gpu
To enable the toolkit components to use processor graphics (GPU) on your system, follow the steps in :ref:`GPU Setup Guide <gpu guide windows>`.
.. tab-item:: GNA
:sync: gna
To enable the toolkit components to use Intel® Gaussian & Neural Accelerator (GNA) on your system, follow the steps in :ref:`GNA Setup Guide <gna guide windows>`.
.. _get-started-windows:
What's Next?
####################

1
docs/install_guides/installing-openvino-linux-header.md
View File

@ -17,6 +17,7 @@
Use APT <openvino_docs_install_guides_installing_openvino_apt>
Use YUM <openvino_docs_install_guides_installing_openvino_yum>
Use Conda Forge <openvino_docs_install_guides_installing_openvino_conda>
Use VCPKG <openvino_docs_install_guides_installing_openvino_vcpkg>
Use Homebrew <openvino_docs_install_guides_installing_openvino_brew>
Use Docker <openvino_docs_install_guides_installing_openvino_docker>

3
docs/install_guides/installing-openvino-macos-header.md
View File

@ -13,9 +13,10 @@
:hidden:
From Archive <openvino_docs_install_guides_installing_openvino_from_archive_macos>
Using Homebrew <openvino_docs_install_guides_installing_openvino_brew>
From PyPI <openvino_docs_install_guides_installing_openvino_pip>
Using Conda Forge <openvino_docs_install_guides_installing_openvino_conda>
Using Homebrew <openvino_docs_install_guides_installing_openvino_brew>
Use VCPKG <openvino_docs_install_guides_installing_openvino_vcpkg>
If you want to install OpenVINO™ Runtime on macOS, there are a few ways to accomplish this. We prepared following options for you:

58
docs/install_guides/installing-openvino-overview.md
View File

@ -3,9 +3,8 @@
@sphinxdirective
.. meta::
:description: You can choose to install OpenVINO Runtime package - a core set
of libraries or OpenVINO Development Tools - a set of utilities
for working with OpenVINO.
:description: install OpenVINO Runtime package, using the distribution channel
of your choice.
.. toctree::
@ -14,8 +13,8 @@
OpenVINO Runtime on Linux <openvino_docs_install_guides_installing_openvino_linux_header>
OpenVINO Runtime on Windows <openvino_docs_install_guides_installing_openvino_windows_header>
OpenVINO Runtime on macOS <openvino_docs_install_guides_installing_openvino_macos_header>
OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>
OpenVINO Runtime on macOS <openvino_docs_install_guides_installing_openvino_macos_header>
OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>
Create a Yocto Image <openvino_docs_install_guides_installing_openvino_yocto>
@ -25,26 +24,42 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<iframe id="selector" src="_static/selector-tool/selector-d0636ef.html" style="width: 100%; border: none" title="Download Intel® Distribution of OpenVINO™ Toolkit"></iframe>
.. warning::
The OpenVINO Development Tools package has been deprecated and removed from the default
installation options. For new projects, the OpenVINO runtime package now includes
all necessary components.
Different OpenVINO distributions may differ with regard to supported hardware or available APIs.
Read installation guides for particular distributions for more details.
The OpenVINO Development Tools is still available for older versions of OpenVINO,
as well as the current one, from the GitHub repository.
| **OpenVINO Runtime:**
| contains the core set of libraries for running inference on various processing units. It is recommended for users who already have an optimized model
and want to deploy it in an application using OpenVINO for inference on their devices.
| **OpenVINO Development Tools:**
| includes the OpenVINO Runtime for Python, as well as a set of utilities for optimizing models and validating performance.
It is recommended for users who want to optimize and verify their models before applying them in their applications.
For Python developers it is ready out-of-the-box, while for C++ development you need to install OpenVINO Runtime libraries separately.
| See the :ref:`For C++ Developers <cpp_developers>` section of the install guide for detailed instructions.
| Development Tools provides:
* Model conversion API
* Benchmark Tool
* Accuracy Checker and Annotation Converter
* Post-Training Optimization Tool
* Model Downloader and other Open Model Zoo tools
.. tip::
OpenVINO 2023.1, described here, is not a Long-Term-Support version!
All currently supported versions are:
* 2023.1 (development)
* 2022.3 (LTS)
* 2021.4 (LTS)
Moreover, different OpenVINO distributions may support slightly different sets of features.
Read installation guides for particular distributions for more details.
.. dropdown:: Distribution Comparison for OpenVINO 2023.1
=============== ========== ====== ========= ======== ============ ==========
Device Archives PyPI APT/YUM Conda Homebrew VCPKG
=============== ========== ====== ========= ======== ============ ==========
CPU V V V V V V
GPU V V V V V V
GNA V V V V V V
NPU V V V V V V
Auto V V V V V V
Auto-Batch V V V V V V
Hetero V n/a n/a n/a n/a n/a
Multi V n/a n/a n/a n/a n/a
=============== ========== ====== ========= ======== ============ ==========
| **Build OpenVINO from source**
| OpenVINO Toolkit source files are available on GitHub as open source. If you want to build your own version of OpenVINO for your platform,
@ -52,6 +67,5 @@ Read installation guides for particular distributions for more details.
@endsphinxdirective

42
docs/install_guides/installing-openvino-pip.md
View File

@ -7,27 +7,40 @@
macOS operating systems, using a PyPi package.
Using the PyPI repository, you can install either OpenVINO™ Runtime or OpenVINO Development Tools on Windows, Linux, and macOS systems.
This article focuses on OpenVINO™ Runtime.
.. note::
Note that the PyPi distribution:
* offers the Python API only
* does not offer support for GNA and NPU inference
* is dedicated to users of all major OSs: Windows, Linux, macOS
.. note
.. tab-set::
If you install OpenVINO Development Tools, OpenVINO Runtime will also be installed as a dependency, so you don't need to install it separately.
.. tab-item:: System Requirements
:sync: system-requirements
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
| 'PyPi OpenVINO page <https://pypi.org/project/openvino/>`__
.. tab-item:: Processor Notes
:sync: processor-notes
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
Installing OpenVINO Runtime
###########################
For system requirements and troubleshooting, see https://pypi.org/project/openvino/
Step 1. Set Up Python Virtual Environment
+++++++++++++++++++++++++++++++++++++++++
Use a virtual environment to avoid dependency conflicts.
To create a virtual environment, use the following command:
.. tab-set::
.. tab-item:: Windows
@ -100,7 +113,15 @@ Run the command below:
python -c "from openvino.runtime import Core; print(Core().available_devices)"
If installation was successful, you will see the list of available devices. Congratulations! You have finished installing OpenVINO Runtime.
If installation was successful, you will see the list of available devices.
Congratulations! You've just Installed OpenVINO! For some use cases you may still
need to install additional components. Check the
:doc:`list of additional configurations <openvino_docs_install_guides_configurations_header>`
to see if your case needs any of them.
What's Next?
@ -122,10 +143,7 @@ Visit the :doc:`Tutorials <tutorials>` page for more Jupyter Notebooks to get yo
* `Basic image classification program with Hello Image Classification <https://docs.openvino.ai/2023.1/notebooks/001-hello-world-with-output.html>`__
* `Convert a PyTorch model and use it for image background removal <https://docs.openvino.ai/2023.1/notebooks/205-vision-background-removal-with-output.html>`__
Run OpenVINO on accelerated devices
+++++++++++++++++++++++++++++++++++
OpenVINO Runtime has a plugin architecture that enables you to run inference on multiple devices without rewriting your code. Supported devices include integrated GPUs, discrete GPUs and GNAs. Visit the :doc:`Additional Configurations <openvino_docs_install_guides_configurations_header>` page for instructions on how to configure your hardware devices to work with OpenVINO.
Additional Resources
####################

95
docs/install_guides/installing-openvino-vcpkg.md Normal file
View File

@ -0,0 +1,95 @@
# Install OpenVINO™ Runtime via VCPKG {#openvino_docs_install_guides_installing_openvino_vcpkg}
@sphinxdirective
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Windows, Linux, and macOS
operating systems, using VCPKG.
.. note::
Note that the VCPKG distribution:
* offers C++ API only
* does not offer support for GNA and NPU inference
* is dedicated to users of all major OSs: Windows, Linux, macOS.
* may offer different hardware support under different operating systems.
.. tab-set::
.. tab-item:: System Requirements
:sync: system-requirements
| Full requirement listing is available in:
| `System Requirements Page <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
.. tab-item:: Processor Notes
:sync: processor-notes
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
.. tab-item:: Software Requirements
:sync: software-requirements
* `vcpkg <https://vcpkg.io/en/getting-started>`__
Installing OpenVINO Runtime
###########################
1. Make sure that you have installed VCPKG on your system. If not, follow the
`VCPKG installation instructions <https://vcpkg.io/en/getting-started>`__.
2. Install OpenVINO using the following terminal command:
.. code-block:: sh
vcpkg install openvino
VCPKG also enables you to install only selected components, by specifying them in the command.
See the list of `available features <https://vcpkg.link/ports/openvino>`__, for example:
.. code-block:: sh
vcpkg install openvino[cpu,ir]
Note that the VCPKG installation means building all packages and dependencies from source,
which means the compiler stage will require additional time to complete the process.
Congratulations! You've just Installed OpenVINO! For some use cases you may still
need to install additional components. Check the
:doc:`list of additional configurations <openvino_docs_install_guides_configurations_header>`
to see if your case needs any of them.
Uninstalling OpenVINO
#####################
To uninstall OpenVINO via VCPKG, use the following command:
.. code-block:: sh
vcpkg uninstall openvino
What's Next?
####################
Now that you've installed OpenVINO Runtime, you can try the following things:
* Learn more about :doc:`OpenVINO Workflow <openvino_workflow>`.
* To prepare your models for working with OpenVINO, see :doc:`Model Preparation <openvino_docs_model_processing_introduction>`.
* See pre-trained deep learning models in our :doc:`Open Model Zoo <model_zoo>`.
* Learn more about :doc:`Inference with OpenVINO Runtime <openvino_docs_OV_UG_OV_Runtime_User_Guide>`.
* See sample applications in :doc:`OpenVINO toolkit Samples Overview <openvino_docs_OV_UG_Samples_Overview>`.
* Check out the OpenVINO product home page: https://software.intel.com/en-us/openvino-toolkit.
@endsphinxdirective

2
docs/install_guides/installing-openvino-windows-header.md
View File

@ -15,9 +15,11 @@
Use Archive <openvino_docs_install_guides_installing_openvino_from_archive_windows>
Use PyPI <openvino_docs_install_guides_installing_openvino_pip>
Use Conda Forge <openvino_docs_install_guides_installing_openvino_conda>
Use VCPKG <openvino_docs_install_guides_installing_openvino_vcpkg>
Use Docker <openvino_docs_install_guides_installing_openvino_docker>
If you want to install OpenVINO™ Runtime on Windows, you have the following options:
* :doc:`Install OpenVINO Runtime from an Archive File <openvino_docs_install_guides_installing_openvino_from_archive_windows>`

3
docs/install_guides/installing-openvino-yocto.md
View File

@ -8,9 +8,6 @@
This document provides instructions for creating a Yocto image with Intel® Distribution of OpenVINO™ toolkit.
System Requirements
###################
Follow the `Yocto Project official documentation <https://docs.yoctoproject.org/brief-yoctoprojectqs/index.html#compatible-linux-distribution>`__ to set up and configure your host machine to be compatible with BitBake.
Step 1: Set Up Environment

68
docs/install_guides/installing-openvino-yum.md
View File

@ -1,35 +1,19 @@
# Install OpenVINO™ Runtime on Linux From YUM Repository {#openvino_docs_install_guides_installing_openvino_yum}
@sphinxdirective
.. meta::
:description: Learn how to install OpenVINO™ Runtime on Linux operating
system, using the YUM repository, which is a recommended
installation method for C++ developers.
system, using the YUM repository.
With the OpenVINO™ 2023.0 release, you can install OpenVINO Runtime on Linux using the YUM repository.
OpenVINO™ Development Tools can be installed via PyPI only. See
`Installing Additional Components <#step-3-optional-install-additional-components>`__ for more information.
See the `Release Notes <https://www.intel.com/content/www/us/en/developer/articles/release-notes/openvino/2023-0.html>`__
for more information on updates in the latest release.
Installing OpenVINO Runtime from YUM is recommended for C++ developers. If you are working with Python,
the PyPI package has everything needed for Python development and deployment on CPU and GPUs. Visit the
:doc:`Install OpenVINO from PyPI <openvino_docs_install_guides_installing_openvino_pip>`
page for instructions on how to install OpenVINO Runtime for Python using PyPI.
.. warning::
By downloading and using this container and the included software, you agree to the terms and conditions of the
`software license agreements <https://software.intel.com/content/dam/develop/external/us/en/documents/intel-openvino-license-agreements.pdf>`__.
Prerequisites
#############
.. note::
Note that the YUM distribution:
* offers both C++ and Python APIs
* does not offer support for GNA and NPU inference
* additionally includes code samples
* is dedicated to Linux users.
.. tab-set::
@ -46,8 +30,8 @@ Prerequisites
.. tab-item:: Processor Notes
:sync: processor-notes
Processor graphics are not included in all processors.
See `Product Specifications <https://ark.intel.com/>`__ for information about your processor.
| To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:
| `Product Specifications <https://ark.intel.com/>`__
.. tab-item:: Software
:sync: software
@ -146,27 +130,15 @@ Run the following command:
yum list installed 'openvino*'
Step 3 (Optional): Install Additional Components
+++++++++++++++++++++++++++++++++++++++++++++++++
OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models.
It provides tools like Model Optimizer, Benchmark Tool, Post-Training Optimization Tool, and
Open Model Zoo Downloader. If you installed OpenVINO Runtime using YUM, OpenVINO Development
Tools must be installed separately.
Congratulations! You've just Installed OpenVINO! For some use cases you may still
need to install additional components. Check the
:doc:`list of additional configurations <openvino_docs_install_guides_configurations_header>`
to see if your case needs any of them.
See **For C++ Developers** section on the :doc:`Install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>` page for instructions.
Step 4 (Optional): Configure Inference on Non-CPU Devices
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
To enable the toolkit components to use processor graphics (GPU) on your system, follow the steps in
:doc:`GPU Setup Guide <openvino_docs_install_guides_configurations_for_intel_gpu>`.
Step 5: Build Samples
++++++++++++++++++++++
To build the C++ or C sample applications for Linux, run the ``build_samples.sh`` script:
With the YUM distribution, you can build OpenVINO sample files, as explained in the
:doc:`guide for OpenVINO sample applications <openvino_docs_OV_UG_Samples_Overview>`.
For C++ and C, just run the ``build_samples.sh`` script:
.. tab-set::
@ -185,8 +157,6 @@ To build the C++ or C sample applications for Linux, run the ``build_samples.sh`
/usr/share/openvino/samples/c/build_samples.sh
For more information, refer to :doc:`Build the Sample Applications on Linux <openvino_docs_OV_UG_Samples_Overview>`.
Uninstalling OpenVINO Runtime
##############################
@ -245,8 +215,6 @@ You can also try the following things:
* Take a glance at the OpenVINO product home page: https://software.intel.com/en-us/openvino-toolkit.
@endsphinxdirective

9
docs/install_guides/troubleshooting.md
View File

@ -51,7 +51,7 @@ This guide provides general troubleshooting steps and solutions to possible issu
If you met proxy issues during the installation with Docker, you need set up proxy settings for Docker. See the `Docker guide <https://docs.docker.com/network/proxy/#set-proxy-using-the-cli>`__ for more details.
.. _yocto_install_issues:
.. _yocto_install_issues:
.. dropdown:: Issues with Creating a Yocto Image for OpenVINO
@ -170,12 +170,5 @@ This guide provides general troubleshooting steps and solutions to possible issu
For specific issues, see :ref:`Errors with Installing via PIP for Users in China <install_for_prc>` and :ref:`proxy issues with installing OpenVINO on Linux from Docker <proxy-issues>`.
.. dropdown:: Check if required external dependencies are installed (for pre-2022.2 releases)
For OpenVINO releases prior to 2022.2:
- If you are using Ubuntu or RHEL 8 systems, and installed OpenVINO Runtime via the archive file, APT, or YUM repository, and then decided to :doc:`install OpenVINO Development Tools <openvino_docs_install_guides_install_dev_tools>`, make sure that you **Install External Software Dependencies** first by following the steps in the corresponding installation pages.
- For C++ developers with Windows systems, make sure that Microsoft Visual Studio 2019 with MSBuild and CMake 3.14 or higher (64-bit) are installed. While installing Microsoft Visual Studio 2019, make sure that you have selected **Desktop development with C++** in the **Workloads** tab. If not, launch the installer again to select that option. For more information on modifying the installation options for Microsoft Visual Studio, see its `official support page <https://docs.microsoft.com/en-us/visualstudio/install/modify-visual-studio?view=vs-2019>`__ .
@endsphinxdirective

131
docs/notebooks-installation.md
View File

@ -3,35 +3,25 @@
@sphinxdirective
.. _notebooks installation:
.. meta::
:description: An installation guide for Jupyter notebooks on which Python
tutorials run. The tutorials serve as introduction to the
OpenVINO™ toolkit.
The notebooks run almost anywhere, from browsers and desktops to even a cloud VM or a Docker container.
Follow the guide below in order to run and manage the notebooks on your machine.
The notebooks can be run in various environments. This guide will show you
how to run and manage them on your local system.
--------------------
Contents:
- `Installation Guide <#-installation-guide>`__
- `Run the Notebooks <#-run-the-notebooks>`__
- `Manage the notebooks <#-manage-the-notebooks>`__
- `Troubleshooting <#-troubleshooting>`__
- `FAQ <#-faq>`__
- `Installation Guide <#installation-guide>`__
- `Run the Notebooks <#run-the-notebooks>`__
- `Manage the notebooks <#manage-the-notebooks>`__
- `Troubleshooting <#troubleshooting>`__
--------------------
.. raw:: html
<a name="-installation-guide">
`Installation Guide`_
=====================
Installation Guide
##################
The table below lists the supported operating systems and Python versions.
@ -57,8 +47,8 @@ The table below lists the supported operating systems and Python versions.
OpenVINO Notebooks also require Git. Follow the guide below for your
operating system or environment.
`Installing prerequisites`_
----------------------------
Installing prerequisites
+++++++++++++++++++++++++++
.. tab-set::
@ -258,8 +248,8 @@ operating system or environment.
CMD /tmp/scripts/run
`Installing notebooks`_
------------------------
Installing notebooks
++++++++++++++++++++
.. tab-set::
@ -469,8 +459,8 @@ operating system or environment.
4. **Start the browser**
Copy the URL printed in the terminal window and open in a browser. |br|
If it is a remote machine, replace 127.0.0.1 with the correct IP address.
| Copy the URL printed in the terminal window and open in a browser.
| If it is a remote machine, replace 127.0.0.1 with the correct IP address.
|docker-terminal-1|
@ -483,18 +473,11 @@ operating system or environment.
While running the container on Windows and macOS, only CPU devices can be used. To access the iGPU, install the notebooks locally, following the instructions above.
--------------------
.. raw:: html
<a name="-run-the-notebooks"/>
`Run the Notebooks`_
====================
Run the Notebooks
#################
Launch a Single Notebook
------------------------------
++++++++++++++++++++++++
If you want to launch only one notebook, such as the *Monodepth* notebook, run the command below.
@ -503,7 +486,7 @@ If you want to launch only one notebook, such as the *Monodepth* notebook, run t
jupyter lab notebooks/201-vision-monodepth/201-vision-monodepth.ipynb
Launch All Notebooks
--------------------------
++++++++++++++++++++
.. code:: bash
@ -514,23 +497,17 @@ In your browser, select a notebook from the file browser in Jupyter Lab, using t
|launch-jupyter|
--------------------
.. raw:: html
<a name="-manage-the-notebooks"/>
`Manage the Notebooks`_
========================
Manage the Notebooks
####################
Shut Down Jupyter Kernel
---------------------------
++++++++++++++++++++++++
To end your Jupyter session, press ``Ctrl-c``. This will prompt you to
``Shutdown this Jupyter server (y/[n])?`` enter ``y`` and hit ``Enter``.
Deactivate Virtual Environment
------------------------------------
++++++++++++++++++++++++++++++
First, make sure you use the terminal window where you activated ``openvino_env``. To deactivate your ``virtualenv``, simply run:
@ -541,7 +518,7 @@ First, make sure you use the terminal window where you activated ``openvino_env`
This will deactivate your virtual environment.
Reactivate Virtual Environment
------------------------------------
++++++++++++++++++++++++++++++
To reactivate your environment, run:
@ -572,7 +549,7 @@ To reactivate your environment, run:
Then type ``jupyter lab`` or ``jupyter notebook`` to launch the notebooks again.
Delete Virtual Environment
-------------------------------------
++++++++++++++++++++++++++
This operation is optional. However, if you want to remove your virtual environment, simply delete the ``openvino_env`` directory:
@ -601,7 +578,7 @@ This operation is optional. However, if you want to remove your virtual environm
Remove openvino_env Kernel from Jupyter
-------------------------------------------
+++++++++++++++++++++++++++++++++++++++
.. code:: bash
@ -611,65 +588,25 @@ Remove openvino_env Kernel from Jupyter
If you run into issues, check the `Troubleshooting <#-troubleshooting>`__, and `FAQs <#-faq>`__ sections or start a GitHub
`discussion <https://github.com/openvinotoolkit/openvino_notebooks/discussions>`__.
-------------------
.. raw:: html
Troubleshooting
###############
<a name="-troubleshooting"/>
For solutions to common issues during installation, refer to the `Troubleshooting <https://github.com/openvinotoolkit/openvino_notebooks#%EF%B8%8F-troubleshooting>`__ and
`FAQ <https://github.com/openvinotoolkit/openvino_notebooks#%EF%B8%8F-troubleshooting>`__ sections in `openvino_notebooks <https://github.com/openvinotoolkit/openvino_notebooks>`__ repository.
`Troubleshooting`_
====================
- To check some common installation problems, run
``python check_install.py``. This script is located in the
openvino_notebooks directory. Run it after activating the
``openvino_env`` virtual environment.
- If you get an ``ImportError``, doublecheck that you installed the
Jupyter kernel. If necessary, choose the ``openvino_env`` kernel from the
*Kernel->Change Kernel* menu) in Jupyter Lab or Jupyter Notebook
- If OpenVINO is installed globally, do not run installation commands
in a terminal where ``setupvars.bat`` or ``setupvars.sh`` are sourced.
- For Windows installation, it is recommended to use *Command Prompt
(cmd.exe)*, not *PowerShell*.
If the following tips do not solve your problem, feel free to open a `discussion
topic <https://github.com/openvinotoolkit/openvino_notebooks/discussions>`__
If the above tips do not solve your problem, feel free to open a
`discussion topic <https://github.com/openvinotoolkit/openvino_notebooks/discussions>`__
or create an
`issue <https://github.com/openvinotoolkit/openvino_notebooks/issues>`__! on Github.
`issue <https://github.com/openvinotoolkit/openvino_notebooks/issues>`__ on Github.
.. raw:: html
<a name="-faq"/>
`FAQ`_
========
- :doc:`Which devices does OpenVINO support? <openvino_docs_OV_UG_supported_plugins_Supported_Devices>`
- `What is the first CPU generation that OpenVINO supports? <https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html>`__
- `Are there any success stories about deploying real-world solutions with OpenVINO? <https://www.intel.com/content/www/us/en/internet-of-things/ai-in-production/success-stories.html>`__
--------------
`Additional Resources`_
-------------------------
Additional Resources
####################
* `OpenVINO™ Notebooks - Github Repository <https://github.com/openvinotoolkit/openvino_notebooks/blob/main/README.md>`_
* :doc:`Install OpenVINO™ Development Tools <openvino_docs_install_guides_install_dev_tools>`
.. |br| raw:: html
<br />
.. |launch-jupyter| image:: https://user-images.githubusercontent.com/15709723/120527271-006fd200-c38f-11eb-9935-2d36d50bab9f.gif
.. |Apache License Version 2.0| image:: https://img.shields.io/badge/license-Apache_2.0-green.svg
:target: https://github.com/openvinotoolkit/openvino_notebooks/blob/main/LICENSE
.. |nbval| image:: https://github.com/openvinotoolkit/openvino_notebooks/actions/workflows/nbval.yml/badge.svg
:target: https://github.com/openvinotoolkit/openvino_notebooks/actions/workflows/nbval.yml?query=branch%3Amain
.. |nbval-docker| image:: https://github.com/openvinotoolkit/openvino_notebooks/actions/workflows/docker.yml/badge.svg
:target: https://github.com/openvinotoolkit/openvino_notebooks/actions/workflows/nbval.yml?query=branch%3Amain
.. |binder logo| image:: https://mybinder.org/badge_logo.svg
:alt: Binder button
.. |ml-studio-1| image:: https://user-images.githubusercontent.com/15709723/117559437-17463180-b03a-11eb-9e8d-d4539d1502f2.png