OpenVINO(TM) Runtime

Project description

OpenVINO™

Intel® Distribution of OpenVINO™ toolkit is an open-source toolkit for optimizing and deploying AI inference. It can be used to develop applications and solutions based on deep learning tasks, such as: emulation of human vision, automatic speech recognition, natural language processing, recommendation systems, etc. It provides high-performance and rich deployment options, from edge to cloud.

If you have chosen a model, you can integrate it with your application through OpenVINO™ and deploy it on various devices. The OpenVINO™ Python package includes a set of libraries for easy inference integration with your products.

System Requirements

Before you start the installation, check the supported operating systems and required Python* versions. The complete list of supported hardware is available on the System Requirements page.

C++ libraries are also required for the installation on Windows*. To install that, you can download the Visual Studio Redistributable file (.exe).

NOTE: This package may work on other Linux and Windows versions but only the versions specified in system requirements are fully validated.

Install OpenVINO™

Step 1. Set Up Python Virtual Environment

Use a virtual environment to avoid dependency conflicts. To create a virtual environment, use the following commands:

On Windows:

python -m venv openvino_env

On Linux and macOS:

python3 -m venv openvino_env

NOTE: On Linux and macOS, you may need to install pip.

Step 2. Activate the Virtual Environment

On Windows:

openvino_env\Scripts\activate

On Linux and macOS:

source openvino_env/bin/activate

Step 3. Set Up and Update PIP to the Highest Version

Run the command below:

python -m pip install --upgrade pip

Step 4. Install the Package

Run the command below:

pip install openvino

Step 5. Verify that the Package Is Installed

Run the command below:

python -c "from openvino import Core; print(Core().available_devices)"

If installation was successful, you will see the list of available devices.

What's in the Package

Component	Content	Description
OpenVINO Runtime	`openvino package`	OpenVINO Runtime is a set of C++ libraries with C and Python bindings providing a common API to deliver inference solutions on the platform of your choice. Use the OpenVINO Runtime API to read PyTorch, TensorFlow, TensorFlow Lite, ONNX, and PaddlePaddle models and execute them on preferred devices. OpenVINO Runtime uses a plugin architecture and includes the following plugins: CPU, GPU, Auto Batch, Auto, Hetero,
OpenVINO Model Converter (OVC)	`ovc`	OpenVINO Model Converter converts models that were trained in popular frameworks to a format usable by OpenVINO components. Supported frameworks include ONNX, TensorFlow, TensorFlow Lite, and PaddlePaddle.
Benchmark Tool	`benchmark_app`	Benchmark Application** allows you to estimate deep learning inference performance on supported devices for synchronous and asynchronous modes.

Troubleshooting

For general troubleshooting steps and issues, see Troubleshooting Guide for OpenVINO Installation. The following sections also provide explanations to several error messages.

Errors with Installing via PIP for Users in China

Users in China may encounter errors while downloading sources via PIP during OpenVINO™ installation. To resolve the issues, try the following solution:

Add the download source using the -i parameter with the Python pip command. For example:
```
pip install openvino -i https://mirrors.aliyun.com/pypi/simple/
```
Use the --trusted-host parameter if the URL above is http instead of https.

ERROR:root:Could not find OpenVINO Python API.

On Windows, additional libraries may be necessary to run OpenVINO. To resolve this issue, install the C++ redistributable (.exe). You can also view a full download list on the official support page.

ImportError: libpython3.8.so.1.0: cannot open shared object file: No such file or directory

To resolve missing external dependency on Ubuntu*, execute the following command:

sudo apt-get install libpython3.8

Additional Resources

LEGAL NOTICE: Your use of this software and any required dependent software (the “Software Package”) is subject to the terms and conditions of the Apache 2.0 License for the Software Package, which may also include notices, disclaimers, or license terms for third party or open source software included in or with the Software Package, and your use indicates your acceptance of all such terms. Please refer to the “third-party-programs.txt” or other similarly-named text file included with the Software Package for additional details.

Intel is committed to the respect of human rights and avoiding complicity in human rights abuses, a policy reflected in the Intel Global Human Rights Principles. Accordingly, by accessing the Intel material on this platform you agree that you will not use the material in a product or application that causes or contributes to a violation of an internationally recognized human right.

Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.

Project details

Release history Release notifications | RSS feed

2024.5.0

Nov 20, 2024

2024.4.1.dev20240926 pre-release

Sep 26, 2024

This version

2024.4.0

Sep 19, 2024

2024.3.0

Jul 31, 2024

2024.2.0

Jun 17, 2024

2024.1.0

Apr 25, 2024

2024.0.0

Mar 6, 2024

2023.3.0

Jan 24, 2024

2023.2.0

Nov 16, 2023

2023.2.0.dev20230922 pre-release

Sep 27, 2023

2023.1.0

Sep 18, 2023

2023.1.0.dev20230811 pre-release

Aug 17, 2023

2023.1.0.dev20230728 pre-release

Aug 1, 2023

2023.1.0.dev20230623 pre-release

Jun 28, 2023

2023.0.2

Sep 4, 2023

2023.0.1

Jul 3, 2023

2023.0.0

May 31, 2023

2023.0.0.dev20230427 pre-release

May 4, 2023

2023.0.0.dev20230407 pre-release

Apr 12, 2023

2023.0.0.dev20230217 pre-release

Feb 23, 2023

2023.0.0.dev20230119 pre-release

Jan 25, 2023

2022.3.2

May 6, 2024

2022.3.1

Jun 19, 2023

2022.3.0

Dec 21, 2022

2022.2.0

Sep 21, 2022

2022.1.0

Mar 22, 2022

2021.4.2

Nov 16, 2021

2021.4.1

Sep 9, 2021

2021.4.0

Jun 29, 2021

2021.3.0

Mar 23, 2021

2021.2

Dec 16, 2020

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

openvino-2024.4.0-16579-cp312-cp312-win_amd64.whl (35.5 MB view details)

Uploaded Sep 19, 2024 CPython 3.12 Windows x86-64

openvino-2024.4.0-16579-cp312-cp312-manylinux_2_31_aarch64.whl (24.6 MB view details)

Uploaded Sep 19, 2024 CPython 3.12 manylinux: glibc 2.31+ ARM64

openvino-2024.4.0-16579-cp312-cp312-manylinux2014_x86_64.whl (42.6 MB view details)

Uploaded Sep 19, 2024 CPython 3.12

openvino-2024.4.0-16579-cp312-cp312-macosx_11_0_arm64.whl (28.3 MB view details)

Uploaded Sep 19, 2024 CPython 3.12 macOS 11.0+ ARM64

openvino-2024.4.0-16579-cp312-cp312-macosx_10_15_x86_64.whl (37.2 MB view details)

Uploaded Sep 19, 2024 CPython 3.12 macOS 10.15+ x86-64

openvino-2024.4.0-16579-cp311-cp311-win_amd64.whl (35.5 MB view details)

Uploaded Sep 19, 2024 CPython 3.11 Windows x86-64

openvino-2024.4.0-16579-cp311-cp311-manylinux_2_31_aarch64.whl (24.5 MB view details)

Uploaded Sep 19, 2024 CPython 3.11 manylinux: glibc 2.31+ ARM64

openvino-2024.4.0-16579-cp311-cp311-manylinux2014_x86_64.whl (42.6 MB view details)

Uploaded Sep 19, 2024 CPython 3.11

openvino-2024.4.0-16579-cp311-cp311-macosx_11_0_arm64.whl (28.3 MB view details)

Uploaded Sep 19, 2024 CPython 3.11 macOS 11.0+ ARM64

openvino-2024.4.0-16579-cp311-cp311-macosx_10_15_x86_64.whl (37.2 MB view details)

Uploaded Sep 19, 2024 CPython 3.11 macOS 10.15+ x86-64

openvino-2024.4.0-16579-cp310-cp310-win_amd64.whl (35.4 MB view details)

Uploaded Sep 19, 2024 CPython 3.10 Windows x86-64

openvino-2024.4.0-16579-cp310-cp310-manylinux_2_31_aarch64.whl (24.5 MB view details)

Uploaded Sep 19, 2024 CPython 3.10 manylinux: glibc 2.31+ ARM64

openvino-2024.4.0-16579-cp310-cp310-manylinux2014_x86_64.whl (42.6 MB view details)

Uploaded Sep 19, 2024 CPython 3.10

openvino-2024.4.0-16579-cp310-cp310-macosx_11_0_arm64.whl (28.3 MB view details)

Uploaded Sep 19, 2024 CPython 3.10 macOS 11.0+ ARM64

openvino-2024.4.0-16579-cp310-cp310-macosx_10_15_x86_64.whl (37.2 MB view details)

Uploaded Sep 19, 2024 CPython 3.10 macOS 10.15+ x86-64

openvino-2024.4.0-16579-cp39-cp39-win_amd64.whl (35.4 MB view details)

Uploaded Sep 19, 2024 CPython 3.9 Windows x86-64

openvino-2024.4.0-16579-cp39-cp39-manylinux_2_31_aarch64.whl (24.6 MB view details)

Uploaded Sep 19, 2024 CPython 3.9 manylinux: glibc 2.31+ ARM64

openvino-2024.4.0-16579-cp39-cp39-manylinux2014_x86_64.whl (42.6 MB view details)

Uploaded Sep 19, 2024 CPython 3.9

openvino-2024.4.0-16579-cp39-cp39-macosx_11_0_arm64.whl (28.3 MB view details)

Uploaded Sep 19, 2024 CPython 3.9 macOS 11.0+ ARM64

openvino-2024.4.0-16579-cp39-cp39-macosx_10_15_x86_64.whl (37.2 MB view details)

Uploaded Sep 19, 2024 CPython 3.9 macOS 10.15+ x86-64

openvino-2024.4.0-16579-cp38-cp38-win_amd64.whl (35.4 MB view details)

Uploaded Sep 19, 2024 CPython 3.8 Windows x86-64

openvino-2024.4.0-16579-cp38-cp38-manylinux_2_31_aarch64.whl (24.5 MB view details)

Uploaded Sep 19, 2024 CPython 3.8 manylinux: glibc 2.31+ ARM64

openvino-2024.4.0-16579-cp38-cp38-manylinux2014_x86_64.whl (42.6 MB view details)

Uploaded Sep 19, 2024 CPython 3.8

openvino-2024.4.0-16579-cp38-cp38-macosx_11_0_arm64.whl (28.3 MB view details)

Uploaded Sep 19, 2024 CPython 3.8 macOS 11.0+ ARM64

openvino-2024.4.0-16579-cp38-cp38-macosx_10_15_x86_64.whl (37.2 MB view details)

Uploaded Sep 19, 2024 CPython 3.8 macOS 10.15+ x86-64

File details

Details for the file openvino-2024.4.0-16579-cp312-cp312-win_amd64.whl.

File metadata

Download URL: openvino-2024.4.0-16579-cp312-cp312-win_amd64.whl
Upload date: Sep 19, 2024
Size: 35.5 MB
Tags: CPython 3.12, Windows x86-64
Uploaded using Trusted Publishing? No
Uploaded via: twine/5.1.1 CPython/3.8.10

File hashes

Hashes for openvino-2024.4.0-16579-cp312-cp312-win_amd64.whl
Algorithm	Hash digest
SHA256	`83af7df6f9b7e2a96dfc5d63a774e6ca3f87d64c7372d14f7ae339387474fc5c`
MD5	`2965a04750076f854d4547908cd47fd6`
BLAKE2b-256	`f96548822a4572f08b7ae06e199def4357906e44acd5d2f995743e3f8aeec822`

Algorithm	Hash digest
SHA256	`5c8ceeb537019280f69dbe86049c3136e648e94fa9f3da9ef0433975e479ad09`
MD5	`a45cd5965f401e857ed83efbc5ce9173`
BLAKE2b-256	`b806cc9666774df3120dcb6c3347b38c8e76ade1cb913fb5518d59aaaca27d8b`

Algorithm	Hash digest
SHA256	`d4cf229fb240b8af44d14686b5bdd94f9eabc70120b9808fc804252fac9ef615`
MD5	`0f98a5dd85ef436c5ed9cd64f8a8c10e`
BLAKE2b-256	`134dd3056f87f0a3cd74cda87a0e1687bffb459d1e4df65a6e807494e06a738b`

Algorithm	Hash digest
SHA256	`50e05d59a90f7950c205d95bb1559e9a8a7d655fe843449d3d426c579fe665f1`
MD5	`3864c8ce56b9986b5712103b1768de04`
BLAKE2b-256	`9686770a821d002b5d83d9830b2d0ee60d00924d6cb874e1a6395d201c6b4fa6`

Algorithm	Hash digest
SHA256	`d67d30f830fa3147eb37f31f53c9eaee424a4e93f33eed00d8288f304ef0250a`
MD5	`a21da8cb4d7afc741671a44357d46584`
BLAKE2b-256	`eaedfdd595c7f9d1bc065cea763398517d5e2ed7eb257008e35729b0f8a5f451`

Algorithm	Hash digest
SHA256	`ab42204c185a4f0df5600a0adb4a4a0c97cebdf630696f94f9d06732714385bc`
MD5	`04c0d201171911df32cc2a39546fd9bf`
BLAKE2b-256	`ea3a59b1f9c51632b3b415275c6a7e4d10159d2a5461bae4bde72e8e827c4bdc`

Algorithm	Hash digest
SHA256	`49b578c4d7325e4a519eb66ee5655871a2b7cd5be9d2de0d5109df23301d10a9`
MD5	`1bcd1bba63ab0c7bb5afdebfff1d8a88`
BLAKE2b-256	`ad48c1f1a9977413f764bb839648fddf08286861c3c80b0c5e36d3a0c64d2c10`

Algorithm	Hash digest
SHA256	`4bd3e21a70eff12166bae3b5ea824787b8c766f975f39e3f2d93729b47b74cb6`
MD5	`d1bf2cda30fbc2f5ccb772d59f2769b8`
BLAKE2b-256	`a7a1b6ea984fdfc8a824cbc61a7b9bf70e31e824f70b4fe148fcb8ca80d0e01a`

Algorithm	Hash digest
SHA256	`b59fb073da74c7ab6d89f2559e3024044f340750b3e519e25975426beb154942`
MD5	`b19adf70b51ef41886aa4e7df2d314d4`
BLAKE2b-256	`0d6e3564457bb4d311ae9d9183db2433693e7fe0ffd44926ef43aa093e936ca7`

Algorithm	Hash digest
SHA256	`e333a5f8155ae357f74e54b664d52d85fa4036a5ccea5da49a7df7f78826c1ce`
MD5	`2bf1ec0d6f8f6b069270f02f7cbd70ba`
BLAKE2b-256	`9f9f9880d89d9a1ed951d8faf0ded59328bb29518705821d2fa4ff0c90f108bb`

Algorithm	Hash digest
SHA256	`a5499d6daa91c358803441561b8792231dd964c5432e838df653c1e5df8de945`
MD5	`5761d409b66cfe40016901ff2f95060b`
BLAKE2b-256	`c0cffce49a283eb9b0f4dd84f80f21162d14504e7d76b1408cbcfd7bef0c01e2`

Algorithm	Hash digest
SHA256	`61f68366017262603be0d876e2e9b7015789ee6b319da8f1792da28b733193f8`
MD5	`3f5a591dc090da11783caa940a1d0a04`
BLAKE2b-256	`327c2bfac368ff87a0de827bac93106e7e327d532e6c69347415a90e380bb53f`

Algorithm	Hash digest
SHA256	`98325dec5ca8bd79f19ea10fd45ad4631a33d9ab50e30659a91a6239ae02d8f4`
MD5	`897966c6d00011c61da569211e2b8869`
BLAKE2b-256	`c34087461e7a59f0ae589603b12fed7bdb72a05b39bdab0fd4da8639050c8bcf`

Algorithm	Hash digest
SHA256	`4a1da4c8db12559bf2760c8a7c8455e0b4373a20364eaee2c9832a6bb23c88a9`
MD5	`b634a5475705b882add13949c901cc0f`
BLAKE2b-256	`249b9652a39411a3e1dec7a400715dd03863c65f4460dfa9425b4c799351c873`

Algorithm	Hash digest
SHA256	`8f19d4200ea04ab315a02f8279268851362f434beaa1a70b4f35d2eea1efa402`
MD5	`f52414e7a38cbb22976543802c832044`
BLAKE2b-256	`11a5adb62e480a7de765b8546e90baf7ba22e1b3b3a50b23f457751d93e357af`

Algorithm	Hash digest
SHA256	`be834d95405fe3724f104b54f3836e7053646d952c4f8a5dad2267665f55d88f`
MD5	`bba2f52c480b6c3f0d4360499e48bcb0`
BLAKE2b-256	`cee1f4a1af43a350ccedd2005f4cc08338340d63e0b6370af71a1c21cacb1950`

Algorithm	Hash digest
SHA256	`74094f8ad81c2ae8500d3361ac087455316a6583016f693d7e1dd1500217ceec`
MD5	`22d372d3c85b15183393ce18f34622a1`
BLAKE2b-256	`390a08c98fe868cf4fb647252057d3b2fa76874dc115aa50170061ab6e1e969b`

Algorithm	Hash digest
SHA256	`fb4781dd9691dc4cfbc6b69f56f724286699e309d4ddc7894fed3ee77b683e2f`
MD5	`060d4488f075be282da4a723a3ccf7d1`
BLAKE2b-256	`78004ba7437558bcecb2bcf34cd44f6bab141443bd2d8e226d7a614f10d51089`

Algorithm	Hash digest
SHA256	`0e01c22a9989470ebcbb7b05fd07e4297bf6c5ecdca202b05f5dc9d2b3186f39`
MD5	`820a04e6ad931d8d7de8d3b114a7179c`
BLAKE2b-256	`554d65a1c337d22452a1046b1734260f918e5a5e88f36be9687197a8a99b2a2c`

Algorithm	Hash digest
SHA256	`3b0834492ff5bc129debb506a705d26b640bca99a10e641af8f710bd081c9af0`
MD5	`aa7e12883acf5f99518ef0620003879b`
BLAKE2b-256	`f83dfd67357209f905ca91e11cf0621cb9db8c092a0debd565867b46f3cd3511`

Algorithm	Hash digest
SHA256	`0cccaa53a61629b44408fe0c7537db637be913697b0f3c54c78756e95dfc4498`
MD5	`e0201fd9950362b4aaf41242e365a0e6`
BLAKE2b-256	`a6b9d2dbe004176bdceb235fdb6dc88c56c8eb5ccbcce56542b99d2d730fe493`

openvino 2024.4.0

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Project description

OpenVINO™

System Requirements

Install OpenVINO™

Step 1. Set Up Python Virtual Environment

Step 2. Activate the Virtual Environment

Step 3. Set Up and Update PIP to the Highest Version

Step 4. Install the Package

Step 5. Verify that the Package Is Installed

What's in the Package

Troubleshooting

Errors with Installing via PIP for Users in China

ERROR:root:Could not find OpenVINO Python API.

ImportError: libpython3.8.so.1.0: cannot open shared object file: No such file or directory

Additional Resources

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Release history Release notifications | RSS feed

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

Algorithm	Hash digest
SHA256	`4ed049ab7a2ffb624690e6cf38366383630cd58736320953cc62c78e8b31eae5`
MD5	`f85dca3a9997cb950ed707dfda6368e9`
BLAKE2b-256	`64a70b6e50d5f2e1f2bdd8075e65ac44cc7e47529801b5fd7f8f1e8cd8ba6fa1`

Algorithm	Hash digest
SHA256	`24b28379bd8d43963829b0b4df957d659269fa647f4f842bd0b3d2f8db76782b`
MD5	`8fce9f372086c83fbab2a315b59e0186`
BLAKE2b-256	`fe18470c50a44e2d52015ceb587de154cc4a61a2c0faff2a3da2b728a1ac9687`

Algorithm	Hash digest
SHA256	`fa6e9fffd31c095e052f6cecb9ac3ff95e0c122418b81b9926b7687465475742`
MD5	`2190dcd40fd722f54e923b06bf9c7892`
BLAKE2b-256	`357226e792c69969885cb0dd5e3e93874976e61665a29764df351dc1ef84f526`

Algorithm	Hash digest
SHA256	`b23fd5114bf42f04773f293b16965a541d58e46e6847053f1417cd6e47acddf5`
MD5	`27942ce532d346421c180d38a7ee4afe`
BLAKE2b-256	`0d97fe9279a4d947445b523e6a816499991fae17d6fd52d471a12db1ef9e629d`