# **OpenVINO™ integration with TensorFlow**
[**OpenVINO™ integration with TensorFlow**](https://github.com/openvinotoolkit/openvino_tensorflow/) is a product designed for TensorFlow* developers who want to get started with [OpenVINO™](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) in their inferencing applications. This product delivers [OpenVINO™](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) inline optimizations which enhance inferencing performance with minimal code modifications. **OpenVINO™ integration with TensorFlow** accelerates inference across many [AI models](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/MODELS.md) on a variety of Intel<sup>®</sup> silicon such as:
- Intel<sup>®</sup> CPUs
- Intel<sup>®</sup> integrated and discrete GPUs
Note: Support for Intel Movidius™ MyriadX VPUs is no longer maintained. Consider previous releases for running on Myriad VPUs.
[Note: For maximum performance, efficiency, tooling customization, and hardware control, we recommend the developers to adopt native OpenVINO™ APIs and its runtime.]
## Installation
### Requirements
- Ubuntu 18.04, macOS 11.2.3 or Windows<sup>1</sup> 10 - 64 bit
- Python* 3.7, 3.8 or 3.9
- TensorFlow* v2.9.3
<sup>1</sup>Windows release supports only Python3.9
This **OpenVINO™ integration with TensorFlow** package comes with pre-built libraries of OpenVINO™ version 2022.3.0 meaning you do not have to install OpenVINO™ separately.
This package supports:
- Intel<sup>®</sup> CPUs
- Intel<sup>®</sup> integrated GPUs
pip3 install -U pip
pip3 install tensorflow==2.9.3
pip3 install openvino-tensorflow==2.3.0
For installation instructions on Windows please refer to [**OpenVINO™ integration with TensorFlow** for Windows ](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/INSTALL.md#windows)
For more details on installation please refer to [INSTALL.md](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/INSTALL.md), and for build from source options please refer to [BUILD.md](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/BUILD.md)
## Verify Installation
Once you have installed **OpenVINO™ integration with TensorFlow**, you can use TensorFlow to run inference using a trained model.
To check if **OpenVINO™ integration with TensorFlow** is properly installed, run
python3 -c "import tensorflow as tf; print('TensorFlow version: ',tf.__version__);\
import openvino_tensorflow; print(openvino_tensorflow.__version__)"
This should produce an output like:
TensorFlow version: 2.9.3
OpenVINO integration with TensorFlow version: b'2.3.0'
OpenVINO version used for this build: b'2022.3.0'
TensorFlow version used for this build: v2.9.3
CXX11_ABI flag used for this build: 1
## Usage
By default, Intel<sup>®</sup> CPU is used to run inference. However, you can change the default option to Intel<sup>®</sup> integrated or discrete GPUs (GPU, GPU.0, GPU.1 etc). Invoke the following function to change the hardware on which inferencing is done.
openvino_tensorflow.set_backend('<backend_name>')
Supported backends include 'CPU', 'GPU', 'GPU_FP16'.
To determine what processing units are available on your system for inference, use the following function:
openvino_tensorflow.list_backends()
For further performance improvements, it is advised to set the environment variable OPENVINO_TF_CONVERT_VARIABLES_TO_CONSTANTS=1. For more API calls and environment variables, see [USAGE.md](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/USAGE.md).
[Note: If a CUDA capable device is present in the system then set the environment variable CUDA_VISIBLE_DEVICES to -1]
## Examples
To see what you can do with **OpenVINO™ integration with TensorFlow**, explore the demos located in the [examples](https://github.com/openvinotoolkit/openvino_tensorflow/tree/master/examples) repository.
## Docker Support
Dockerfiles for Ubuntu* 18.04, Ubuntu* 20.04, and TensorFlow* Serving are provided which can be used to build runtime Docker* images for **OpenVINO™ integration with TensorFlow** on CPU, GPU.
For more details see [docker readme](https://github.com/openvinotoolkit/openvino_tensorflow/tree/master/docker/README.md).
### Prebuilt Images
- [Ubuntu18 runtime image on Docker* Hub](https://hub.docker.com/r/openvino/openvino_tensorflow_ubuntu18_runtime)
- [Ubuntu20 runtime image on Docker* Hub](https://hub.docker.com/r/openvino/openvino_tensorflow_ubuntu20_runtime)
- [Azure* Marketplace](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/intel_corporation.openvinotensorflow)
## Try it on Intel<sup>®</sup> DevCloud
Sample tutorials are also hosted on [Intel<sup>®</sup> DevCloud](https://software.intel.com/content/www/us/en/develop/tools/devcloud/edge/build/ovtfoverview.html). The demo applications are implemented using Jupyter Notebooks. You can interactively execute them on Intel<sup>®</sup> DevCloud nodes, compare the results of **OpenVINO™ integration with TensorFlow**, native TensorFlow and OpenVINO™.
## License
**OpenVINO™ integration with TensorFlow** is licensed under [Apache License Version 2.0](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/LICENSE).
By contributing to the project, you agree to the license and copyright terms therein
and release your contribution under these terms.
## Support
Please submit your questions, feature requests and bug reports via [**GitHub issues**](https://github.com/openvinotoolkit/openvino_tensorflow/issues).
## How to Contribute
We welcome community contributions to **OpenVINO™ integration with TensorFlow**. If you have an idea for improvement:
* Share your proposal via [GitHub issues](https://github.com/openvinotoolkit/openvino_tensorflow/issues).
* Submit a [pull request](https://github.com/openvinotoolkit/openvino_tensorflow/pulls).
We will review your contribution as soon as possible. If any additional fixes or modifications are necessary, we will guide you and provide feedback. Before you make your contribution, make sure you can build **OpenVINO™ integration with TensorFlow** and run all the examples with your fix/patch. If you want to introduce a large feature, create test cases for your feature. Upon the verification of your pull request, we will merge it to the repository provided that the pull request has met the above mentioned requirements and proved acceptable.
---
\* Other names and brands may be claimed as the property of others.
Raw data
{
"_id": null,
"home_page": "https://github.com/openvinotoolkit/openvino_tensorflow",
"name": "openvino-tensorflow",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "Intel Corporation",
"author_email": "",
"download_url": "",
"platform": "Ubuntu 18.04",
"description": "# **OpenVINO\u2122 integration with TensorFlow**\n\n[**OpenVINO\u2122 integration with TensorFlow**](https://github.com/openvinotoolkit/openvino_tensorflow/) is a product designed for TensorFlow* developers who want to get started with [OpenVINO\u2122](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) in their inferencing applications. This product delivers [OpenVINO\u2122](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) inline optimizations which enhance inferencing performance with minimal code modifications. **OpenVINO\u2122 integration with TensorFlow** accelerates inference across many [AI models](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/MODELS.md) on a variety of Intel<sup>\u00ae</sup> silicon such as:\n- Intel<sup>\u00ae</sup> CPUs\n- Intel<sup>\u00ae</sup> integrated and discrete GPUs\n\nNote: Support for Intel Movidius\u2122 MyriadX VPUs is no longer maintained. Consider previous releases for running on Myriad VPUs.\n\n[Note: For maximum performance, efficiency, tooling customization, and hardware control, we recommend the developers to adopt native OpenVINO\u2122 APIs and its runtime.]\n\n## Installation\n\n### Requirements\n\n- Ubuntu 18.04, macOS 11.2.3 or Windows<sup>1</sup> 10 - 64 bit\n- Python* 3.7, 3.8 or 3.9\n- TensorFlow* v2.9.3\n\n<sup>1</sup>Windows release supports only Python3.9 \n\nThis **OpenVINO\u2122 integration with TensorFlow** package comes with pre-built libraries of OpenVINO\u2122 version 2022.3.0 meaning you do not have to install OpenVINO\u2122 separately.\nThis package supports:\n- Intel<sup>\u00ae</sup> CPUs\n- Intel<sup>\u00ae</sup> integrated GPUs\n\n pip3 install -U pip\n pip3 install tensorflow==2.9.3\n pip3 install openvino-tensorflow==2.3.0\n\nFor installation instructions on Windows please refer to [**OpenVINO\u2122 integration with TensorFlow** for Windows ](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/INSTALL.md#windows)\n\nFor more details on installation please refer to [INSTALL.md](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/INSTALL.md), and for build from source options please refer to [BUILD.md](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/BUILD.md)\n\n## Verify Installation\n\nOnce you have installed **OpenVINO\u2122 integration with TensorFlow**, you can use TensorFlow to run inference using a trained model.\n\nTo check if **OpenVINO\u2122 integration with TensorFlow** is properly installed, run\n\n python3 -c \"import tensorflow as tf; print('TensorFlow version: ',tf.__version__);\\\n import openvino_tensorflow; print(openvino_tensorflow.__version__)\"\n\nThis should produce an output like:\n\n TensorFlow version: 2.9.3\n OpenVINO integration with TensorFlow version: b'2.3.0'\n OpenVINO version used for this build: b'2022.3.0'\n TensorFlow version used for this build: v2.9.3\n CXX11_ABI flag used for this build: 1\n\n## Usage\n\nBy default, Intel<sup>\u00ae</sup> CPU is used to run inference. However, you can change the default option to Intel<sup>\u00ae</sup> integrated or discrete GPUs (GPU, GPU.0, GPU.1 etc). Invoke the following function to change the hardware on which inferencing is done.\n\n openvino_tensorflow.set_backend('<backend_name>')\n\nSupported backends include 'CPU', 'GPU', 'GPU_FP16'.\n\nTo determine what processing units are available on your system for inference, use the following function:\n\n openvino_tensorflow.list_backends()\n\nFor further performance improvements, it is advised to set the environment variable OPENVINO_TF_CONVERT_VARIABLES_TO_CONSTANTS=1. For more API calls and environment variables, see [USAGE.md](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/USAGE.md).\n\n[Note: If a CUDA capable device is present in the system then set the environment variable CUDA_VISIBLE_DEVICES to -1] \n\n## Examples\n\nTo see what you can do with **OpenVINO\u2122 integration with TensorFlow**, explore the demos located in the [examples](https://github.com/openvinotoolkit/openvino_tensorflow/tree/master/examples) repository.\n\n## Docker Support\nDockerfiles for Ubuntu* 18.04, Ubuntu* 20.04, and TensorFlow* Serving are provided which can be used to build runtime Docker* images for **OpenVINO\u2122 integration with TensorFlow** on CPU, GPU. \nFor more details see [docker readme](https://github.com/openvinotoolkit/openvino_tensorflow/tree/master/docker/README.md).\n\n### Prebuilt Images\n\n- [Ubuntu18 runtime image on Docker* Hub](https://hub.docker.com/r/openvino/openvino_tensorflow_ubuntu18_runtime)\n- [Ubuntu20 runtime image on Docker* Hub](https://hub.docker.com/r/openvino/openvino_tensorflow_ubuntu20_runtime)\n- [Azure* Marketplace](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/intel_corporation.openvinotensorflow)\n\n## Try it on Intel<sup>\u00ae</sup> DevCloud\nSample tutorials are also hosted on [Intel<sup>\u00ae</sup> DevCloud](https://software.intel.com/content/www/us/en/develop/tools/devcloud/edge/build/ovtfoverview.html). The demo applications are implemented using Jupyter Notebooks. You can interactively execute them on Intel<sup>\u00ae</sup> DevCloud nodes, compare the results of **OpenVINO\u2122 integration with TensorFlow**, native TensorFlow and OpenVINO\u2122. \n\n## License\n**OpenVINO\u2122 integration with TensorFlow** is licensed under [Apache License Version 2.0](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/LICENSE).\nBy contributing to the project, you agree to the license and copyright terms therein\nand release your contribution under these terms. \n\n## Support\n\nPlease submit your questions, feature requests and bug reports via [**GitHub issues**](https://github.com/openvinotoolkit/openvino_tensorflow/issues).\n\n## How to Contribute\n\nWe welcome community contributions to **OpenVINO\u2122 integration with TensorFlow**. If you have an idea for improvement:\n\n* Share your proposal via [GitHub issues](https://github.com/openvinotoolkit/openvino_tensorflow/issues).\n* Submit a [pull request](https://github.com/openvinotoolkit/openvino_tensorflow/pulls).\n\nWe will review your contribution as soon as possible. If any additional fixes or modifications are necessary, we will guide you and provide feedback. Before you make your contribution, make sure you can build **OpenVINO\u2122 integration with TensorFlow** and run all the examples with your fix/patch. If you want to introduce a large feature, create test cases for your feature. Upon the verification of your pull request, we will merge it to the repository provided that the pull request has met the above mentioned requirements and proved acceptable.\n\n---\n\\* Other names and brands may be claimed as the property of others.\n",
"bugtrack_url": null,
"license": "Apache License, Version 2.0",
"summary": "OpenVINO\u2122 integration with TensorFlow",
"version": "2.3.0",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "6ca2d3eaea54b05aaa263ae58f500f2d401829fd9451404f7a33e17839f9eeb5",
"md5": "727fc2f78a0d10a603a457f1f5de71d1",
"sha256": "c91e3bf8caedf68ef02a5596f4e34ce253784fc2e40483201fa8bfbad319d82c"
},
"downloads": -1,
"filename": "openvino_tensorflow-2.3.0-cp37-cp37m-macosx_12_0_x86_64.whl",
"has_sig": false,
"md5_digest": "727fc2f78a0d10a603a457f1f5de71d1",
"packagetype": "bdist_wheel",
"python_version": "cp37",
"requires_python": null,
"size": 22058195,
"upload_time": "2023-01-23T13:14:05",
"upload_time_iso_8601": "2023-01-23T13:14:05.336270Z",
"url": "https://files.pythonhosted.org/packages/6c/a2/d3eaea54b05aaa263ae58f500f2d401829fd9451404f7a33e17839f9eeb5/openvino_tensorflow-2.3.0-cp37-cp37m-macosx_12_0_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "fdce9665f54eca583ed2c253750390bc724a7ed114b51fa1329a8b20e37b59ab",
"md5": "12b88fd8eabc94c53de9d58274049c3c",
"sha256": "4fd454a24713f8f87a46cf31ae7868a97667b1048cf2c15ec467fa82723f2582"
},
"downloads": -1,
"filename": "openvino_tensorflow-2.3.0-cp37-cp37m-manylinux_2_27_x86_64.whl",
"has_sig": false,
"md5_digest": "12b88fd8eabc94c53de9d58274049c3c",
"packagetype": "bdist_wheel",
"python_version": "cp37",
"requires_python": null,
"size": 27138001,
"upload_time": "2023-01-23T13:14:11",
"upload_time_iso_8601": "2023-01-23T13:14:11.399080Z",
"url": "https://files.pythonhosted.org/packages/fd/ce/9665f54eca583ed2c253750390bc724a7ed114b51fa1329a8b20e37b59ab/openvino_tensorflow-2.3.0-cp37-cp37m-manylinux_2_27_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "95a8686cbc4957953d20a7534daf84185bab0425219d922d3018c5b35603201e",
"md5": "163f3ef4f18cbbe34acf0871d1e5a79e",
"sha256": "33d9cf1e9bfaeb3e65ea5d45b2eacaa55763f6fb517de3842cbb63cad431e64c"
},
"downloads": -1,
"filename": "openvino_tensorflow-2.3.0-cp38-cp38-macosx_12_0_x86_64.whl",
"has_sig": false,
"md5_digest": "163f3ef4f18cbbe34acf0871d1e5a79e",
"packagetype": "bdist_wheel",
"python_version": "cp38",
"requires_python": null,
"size": 22058195,
"upload_time": "2023-01-23T13:14:16",
"upload_time_iso_8601": "2023-01-23T13:14:16.408475Z",
"url": "https://files.pythonhosted.org/packages/95/a8/686cbc4957953d20a7534daf84185bab0425219d922d3018c5b35603201e/openvino_tensorflow-2.3.0-cp38-cp38-macosx_12_0_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "775abca0953db18f1202dd5f68e578ad8df464464093498706fcb1b687a9ebfa",
"md5": "c301921ecc5d13b03b2ed595b434ca28",
"sha256": "085d8639eccb564b0cad1d567f8787f3f05b7fff053559ae99179e8840a13610"
},
"downloads": -1,
"filename": "openvino_tensorflow-2.3.0-cp38-cp38-manylinux_2_27_x86_64.whl",
"has_sig": false,
"md5_digest": "c301921ecc5d13b03b2ed595b434ca28",
"packagetype": "bdist_wheel",
"python_version": "cp38",
"requires_python": null,
"size": 27137999,
"upload_time": "2023-01-23T13:14:21",
"upload_time_iso_8601": "2023-01-23T13:14:21.774125Z",
"url": "https://files.pythonhosted.org/packages/77/5a/bca0953db18f1202dd5f68e578ad8df464464093498706fcb1b687a9ebfa/openvino_tensorflow-2.3.0-cp38-cp38-manylinux_2_27_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "f381d8b00210c57c3c7e81e7ac16833b6676dfd5ce0c58238027aa711a0bbc4a",
"md5": "01970d16959a9057eb498d72a4e1c89d",
"sha256": "61b41d74b37aa12c538b6301fa15cea7048e5c46b4ff55a1a5533a81265a40bf"
},
"downloads": -1,
"filename": "openvino_tensorflow-2.3.0-cp39-cp39-macosx_12_0_x86_64.whl",
"has_sig": false,
"md5_digest": "01970d16959a9057eb498d72a4e1c89d",
"packagetype": "bdist_wheel",
"python_version": "cp39",
"requires_python": null,
"size": 22058191,
"upload_time": "2023-01-23T13:14:27",
"upload_time_iso_8601": "2023-01-23T13:14:27.203662Z",
"url": "https://files.pythonhosted.org/packages/f3/81/d8b00210c57c3c7e81e7ac16833b6676dfd5ce0c58238027aa711a0bbc4a/openvino_tensorflow-2.3.0-cp39-cp39-macosx_12_0_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "436bb6c8026d244a1f6041d94d9ead79bbc88a3d1c3211cf71be5e3406cf8429",
"md5": "da7f7175f88286277fbe4a35b792c5cf",
"sha256": "74864a9e35fcd5a5f1ca928e7c2c832716851cf899accf5d06d27df441969ffc"
},
"downloads": -1,
"filename": "openvino_tensorflow-2.3.0-cp39-cp39-manylinux_2_27_x86_64.whl",
"has_sig": false,
"md5_digest": "da7f7175f88286277fbe4a35b792c5cf",
"packagetype": "bdist_wheel",
"python_version": "cp39",
"requires_python": null,
"size": 27138005,
"upload_time": "2023-01-23T13:14:31",
"upload_time_iso_8601": "2023-01-23T13:14:31.833708Z",
"url": "https://files.pythonhosted.org/packages/43/6b/b6c8026d244a1f6041d94d9ead79bbc88a3d1c3211cf71be5e3406cf8429/openvino_tensorflow-2.3.0-cp39-cp39-manylinux_2_27_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "8bfbb163a3fdff1495c58c9e8f8f1c88d835a27293b9f96b890132340dd770ad",
"md5": "37b7743ed2c1213cc591ff3551d44421",
"sha256": "5c40b7e97f8a7fb73440924d66421f878a277946e868dcebdcdb8a824a4bfada"
},
"downloads": -1,
"filename": "openvino_tensorflow-2.3.0-cp39-cp39-win_amd64.whl",
"has_sig": false,
"md5_digest": "37b7743ed2c1213cc591ff3551d44421",
"packagetype": "bdist_wheel",
"python_version": "cp39",
"requires_python": null,
"size": 25760150,
"upload_time": "2023-01-23T13:14:38",
"upload_time_iso_8601": "2023-01-23T13:14:38.178381Z",
"url": "https://files.pythonhosted.org/packages/8b/fb/b163a3fdff1495c58c9e8f8f1c88d835a27293b9f96b890132340dd770ad/openvino_tensorflow-2.3.0-cp39-cp39-win_amd64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-01-23 13:14:05",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "openvinotoolkit",
"github_project": "openvino_tensorflow",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "openvino-tensorflow"
}
JSON
