-
Notifications
You must be signed in to change notification settings - Fork 2.5k
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
Changes to the OpenVINO 2.0 Transition Guide #10936
Changes to the OpenVINO 2.0 Transition Guide #10936
Conversation
Let's merge #10933 first |
@andrew-zaytsev please, see the latest version and check whether some changes are still needed. |
…azaytsev/transition-guide-fixes # Conflicts: # docs/OV_Runtime_UG/migration_ov_2_0/intro.md
- Model Optimizer changed layouts for TensorFlow models (see [Layouts in OpenVINO](../layout_overview.md)). It leads to unexpected user behavior that a user needs to use a different layout for its input data with compare to the framework: | ||
![tf_openvino] | ||
- Inference Engine API (`InferenceEngine::CNNNetwork`) also applied some conversion rules for input and output precisions because of device plugins limitations. | ||
- Users need to specify input shapes during model conversions in Model Optimizer and work with static shapes in the application. | ||
|
||
OpenVINO API 2.0 is introduced to align logic of working with model as it is done in the frameworks - no layout and precision changes, operates with tensor names and indeces to address inputs and outputs. OpenVINO Runtime is composed of Inference Engine API used for inference and ngraph API targeted to work with models, operations. The API 2.0 has common structure, naming convention styles, namespaces, removes duplicated structures. See [How to migrate to API 2.0](./common_inference_pipeline.md) for details. | ||
OpenVINO™ introduces API 2.0 to align logic of working with model as it is done in the frameworks - no layout and precision changes, operates with tensor names and indices to address inputs and outputs. OpenVINO Runtime is composed of Inference Engine API used for inference and nGraph API targeted to work with models, operations. The API 2.0 has common structure, naming convention styles, namespaces, removes duplicated structures. See [How to migrate to OpenVINO API v2](common_inference_pipeline.md) for details. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why you changed to v2?? In other places of the document we have 2.0
CC @xu-yuan1 what is the proper name?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The approved names by marketing are "API 2.0", "OpenVINO API v2" and "OpenVINO 2022.1". I think "OpenVINO API 2.0" is in a grey area as it's not forbidden explicitly. @andrew-zaytsev Andrey may know better and confirm.
But I think on the same page we should keep consistent, having both "2.0" and "v2" can be confusing. Or maybe we can have a statement at the beginning to say that they are the same thing.
@andrew-zaytsev please, port these changes to master if needed |
Details:
Minor changes to the OpenVINO 2.0 Transition Guide
Tickets:
CVS-80835