Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added migration for deployment #10800

Merged

Conversation

ilya-lavrenov
Copy link
Contributor

Details:

  • item1
  • ...

Tickets:

  • ticket-id

@ilya-lavrenov ilya-lavrenov force-pushed the deployment-migration branch 4 times, most recently from a2b8199 to 3efc22d Compare March 4, 2022 16:38
@ilya-lavrenov ilya-lavrenov requested a review from xu-yuan1 March 4, 2022 16:39
@ilya-lavrenov ilya-lavrenov added this to the 2022.1 milestone Mar 4, 2022
@ilya-lavrenov ilya-lavrenov added the category: docs OpenVINO documentation label Mar 4, 2022
@ilya-lavrenov ilya-lavrenov force-pushed the deployment-migration branch from 3efc22d to ba58a5e Compare March 4, 2022 16:42

"Easy to use" is one of the main points for OpenVINO 2.0 concept. This includes not only simplification of migration from frameworks to OpenVINO Toolkit, but also how OpenVINO is organized, how the development tools are used, how to develop and deploy OpenVINO-based applications.

Starting from OpenVINO 2.0, Model Optimizer, Post Training Optimization tool, Open Model Zoo tools and other Python-based Development tools are distributed via [PyPI](https://pypi.org/project/openvino-dev/) only. This simplifies user experience, because in older versions of OpenVINO development tools should be installed and used differently dependning on distribution type (debian packages vs. PyPi).
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think will be good to provide an example, how openvino-dev package can be installed.
pip install openvino-dev

Copy link
Contributor

@yury-gorbachev yury-gorbachev left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Generally good document


## Introduction

"Easy to use" is one of the main points for OpenVINO 2.0 concept. This includes not only simplification of migration from frameworks to OpenVINO Toolkit, but also how OpenVINO is organized, how the development tools are used, how to develop and deploy OpenVINO-based applications.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We cannot write OpenVINO 2.0, we can say OpenVINO API 2.0 or OpenVINO 22.1 release per marketing requirement. In this case I think OpenVINO API 2.0 makes more sense, in next paragraph I suggest to replace with 22.1 release...

Copy link
Contributor

@xu-yuan1 xu-yuan1 Mar 10, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi there, yes we have some guidelines from marketing:

  • For any features that require a designated version (e.g. API & IR format), please use v2 and so on, for example, OpenVINO API v2.
  • 2.0 is ok to use when there is clearly a distinction between release number and feature version, i.e. OpenVINO 2022.1 now supports API 2.0.
  • Do no use 2.0 as it relates to OpenVINO release, as it confuses the market around our product naming convention. So "OpenVINO 2.0" is not allowed.
  • For any reference to actual release, please use the full release number. So use OpenVINO 2022.1 only.


"Easy to use" is one of the main points for OpenVINO 2.0 concept. This includes not only simplification of migration from frameworks to OpenVINO Toolkit, but also how OpenVINO is organized, how the development tools are used, how to develop and deploy OpenVINO-based applications.

Starting from OpenVINO 2.0, Model Optimizer, Post Training Optimization tool, Open Model Zoo tools and other Python-based Development tools are distributed via [PyPI](https://pypi.org/project/openvino-dev/) only. This simplifies user experience, because in older versions of OpenVINO development tools should be installed and used differently dependning on distribution type (debian packages vs. PyPi).
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This not only simplifies due to different installation, but also ensures that dependencies are handled properly via PyPi as well as supports virtual environments for development tools.


Starting from OpenVINO 2.0, Model Optimizer, Post Training Optimization tool, Open Model Zoo tools and other Python-based Development tools are distributed via [PyPI](https://pypi.org/project/openvino-dev/) only. This simplifies user experience, because in older versions of OpenVINO development tools should be installed and used differently dependning on distribution type (debian packages vs. PyPi).

Moreover, we have tried further to reorganize package structure to have it in a good shape:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here, it is a little bit unclear shift from general description to IRC package. So, maybe I would clarify that it is applicable to installer package. Or am I missing something?

Moreover, we have tried further to reorganize package structure to have it in a good shape:

- `runtime` folder with OpenVINO Runtime include headers, libraries and CMake interfaces.
- `tools` folder with [compile_tool](../../../tools/compile_tool/README.md), [deployment manager](../../install_guides/deployment-manager-tool.md), `requirement.txt` files with `openvino-dev` package.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

requirement.txt file with link to corresponding version of openvino-dev package.

$ mo.py -h
```

In OpenVINO 2.0 users can install development tools only from [PyPI](https://pypi.org/project/openvino-dev/) repository:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Starting with OpenVINO 22.1...

target_link_libraries(ie_ngraph_app PRIVATE ${InferenceEngine_LIBRARIES} ${NGRAPH_LIBRARIES})
```

OpenVINO Runtine 2.0:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Runtime

- `openvino_onnx_frontend` to read ONNX models
- `openvino_paddle_frontend` to read Paddle models

So, to perform deployment steps - just take only required functionality: `openvino` or `openvino_c` depending on derired language plus plugins which are needed to solve your task. For example, `openvino_intel_cpu_plugin` and `openvino_ir_frontend` plugins to be able to load OpenVINO IRs and perform inference on CPU device.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

desired

@@ -77,5 +78,6 @@ Please look at next transition guides to understand how migrate Inference Engine
- [Preprocess your model](./preprocessing.md)
- [Configure device](./configure_devices.md)
- [OpenVINO™ Model Creation](graph_construction.md)
- [Install & deployment](deployment_migration.md)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm wondering if we should set this as first doc in list? Given that logically this is the first thing you do (aligned with Get Started)

@ilya-lavrenov ilya-lavrenov marked this pull request as ready for review March 5, 2022 11:28
@ilya-lavrenov ilya-lavrenov requested a review from a team as a code owner March 5, 2022 11:28
@ilya-lavrenov ilya-lavrenov requested review from avladimi and removed request for a team March 5, 2022 11:28
@ilya-lavrenov ilya-lavrenov added the port to master Required port to master from 2022.3 LTS label Mar 5, 2022
@ilya-lavrenov ilya-lavrenov requested review from a team March 5, 2022 11:28
@ilya-lavrenov ilya-lavrenov requested review from a team as code owners March 5, 2022 11:28
@ilya-lavrenov ilya-lavrenov requested review from a team March 5, 2022 11:28
@ilya-lavrenov ilya-lavrenov force-pushed the deployment-migration branch 2 times, most recently from 41dc109 to faa8168 Compare March 5, 2022 11:31
@azhogov azhogov merged commit db05e54 into openvinotoolkit:releases/2022/1 Mar 5, 2022
@ilya-lavrenov ilya-lavrenov deleted the deployment-migration branch March 5, 2022 12:18
@@ -0,0 +1,156 @@
# Install & Deployment {#openvino_2_0_deployment}
Copy link
Contributor

@xu-yuan1 xu-yuan1 Mar 10, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updates on Installation & Deployment


- `runtime` folder with OpenVINO Runtime include headers, libraries and CMake interfaces.
- `tools` folder with [compile_tool](../../../tools/compile_tool/README.md), [deployment manager](../../install_guides/deployment-manager-tool.md), `requirement.txt` files with link to corresponding version of `openvino-dev` package.
- `python` folder with OpenVINO Python Runtime.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is "OpenVINO Python Runtime"? I think it's a kind of incorporating the OpenVINO brand, which is not allowed. Is it "the Python version for OpenVINO Runtime"?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the Python version for OpenVINO Runtime - yes

ilya-lavrenov added a commit to ilya-lavrenov/openvino that referenced this pull request Mar 18, 2022
* Added migration for deployment

* Addressed comments
@ilya-lavrenov ilya-lavrenov added ported to master Ported from 2022.x branches to master and removed port to master Required port to master from 2022.3 LTS labels Mar 18, 2022
azhogov pushed a commit that referenced this pull request Mar 18, 2022
* Added migration for deployment (#10800)

* Added migration for deployment

* Addressed comments

* more info after the What's new Sessions' questions (#10803)

* more info after the What's new Sessions' questions

* generalizing the optimal_batch_size vs explicit value message

* Update docs/OV_Runtime_UG/automatic_batching.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/OV_Runtime_UG/automatic_batching.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/OV_Runtime_UG/automatic_batching.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/OV_Runtime_UG/automatic_batching.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/OV_Runtime_UG/automatic_batching.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/OV_Runtime_UG/automatic_batching.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Perf Hints docs and General Opt Guide refactoring (#10815)

* Brushed the general optimization page

* Opt GUIDE, WIP

* perf hints doc placeholder

* WIP

* WIP2

* WIP 3

* added streams and few other details

* fixed titles, misprints etc

* Perf hints

* movin the runtime optimizations intro

* fixed link

* Apply suggestions from code review

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* some details on the FIL and other means when pure inference time is not the only factor

* shuffled according to general->use-case->device-specifics flow, minor brushing

* next iter

* section on optimizing for tput and latency

* couple of links to the features support matrix

* Links, brushing, dedicated subsections for Latency/FIL/Tput

* had to make the link less specific (otherwise docs compilations fails)

* removing the Temp/Should be moved to the Opt Guide

* shuffled the tput/latency/etc info into separated documents. also the following docs moved from the temp into specific feature, general product desc or corresponding plugins

-   openvino_docs_IE_DG_Model_caching_overview
-   openvino_docs_IE_DG_Int8Inference
-   openvino_docs_IE_DG_Bfloat16Inference
-   openvino_docs_OV_UG_NoDynamicShapes

* fixed toc for ov_dynamic_shapes.md

* referring the openvino_docs_IE_DG_Bfloat16Inference to avoid docs compilation errors

* fixed main product TOC, removed ref from the second-level items

* reviewers remarks

* reverted the openvino_docs_OV_UG_NoDynamicShapes

* reverting openvino_docs_IE_DG_Bfloat16Inference and openvino_docs_IE_DG_Int8Inference

* "No dynamic shapes" to the "Dynamic shapes" as TOC

* removed duplication

* minor brushing

* Caching to the next level in TOC

* brushing

* more on the perf counters ( for latency and dynamic cases)

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Updated common IE pipeline infer-request section (#10844)

* Updated common IE pipeline infer-reqest section

* Update ov_infer_request.md

* Apply suggestions from code review

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com>
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* DOCS: Removed useless 4 spaces in snippets (#10870)

* Updated snippets

* Added link to encryption

* [DOCS] ARM CPU plugin docs (#10885)

* initial commit

ARM_CPU.md added
ARM CPU is added to the list of supported devices

* Update the list of supported properties

* Update Device_Plugins.md

* Update CODEOWNERS

* Removed quotes in limitations section

* NVIDIA and Android are added to the list of supported devices

* Added See Also section and reg sign to arm

* Added Preprocessing acceleration section

* Update the list of supported layers

* updated list of supported layers

* fix typos

* Added support disclaimer

* update trade and reg symbols

* fixed typos

* fix typos

* reg fix

* add reg symbol back

Co-authored-by: Vitaly Tuzov <vitaly.tuzov@intel.com>

* Try to fix visualization (#10896)

* Try to fix visualization

* New try

* Update Install&Deployment for migration guide to 22/1 (#10933)

* updates

* update

* Getting started improvements (#10948)

* Onnx updates (#10962)

* onnx changes

* onnx updates

* onnx updates

* fix broken anchors api reference (#10976)

* add ote repo (#10979)

* DOCS: Increase content width (#10995)

* fixes

* fix

* Fixed compilation

Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Co-authored-by: Aleksandr Voron <aleksandr.voron@intel.com>
Co-authored-by: Vitaly Tuzov <vitaly.tuzov@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
Co-authored-by: Victoria Yashina <victoria.yashina@intel.com>
Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: docs OpenVINO documentation ported to master Ported from 2022.x branches to master
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants