22fe12fe9b
* restructure-mo-docs * apply-commits-18214 Applying commits from: https://github.com/openvinotoolkit/openvino/pull/18214 * update * Apply suggestions from code review Co-authored-by: Anastasiia Pnevskaia <anastasiia.pnevskaia@intel.com> * Apply suggestions from code review * Update model_introduction.md * Update docs/resources/tensorflow_frontend.md * Create MO_Python_API.md * Apply suggestions from code review Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com> * revert * Update Cutting_Model.md * serialize * serialize-in-image * Update Deep_Learning_Model_Optimizer_DevGuide.md * Apply suggestions from code review Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com> * Update model_conversion_diagram.svg --------- Co-authored-by: Anastasiia Pnevskaia <anastasiia.pnevskaia@intel.com> Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
1.1 KiB
1.1 KiB
OpenVINO TensorFlow Frontend Capabilities and Limitations
@sphinxdirective
.. meta:: :description: TensorFlow Frontend in OpenVINO Runtime is a C++ based frontend used by default for converting TensorFlow models to Intermediate Representation (IR).
TensorFlow Frontend is a C++ based Frontend for converting TensorFlow models. MO now uses the TensorFlow Frontend as the default path for conversion to IR.
Also, the frontend allows loading TensorFlow models in SavedModel, MetaGraph, and frozen Protobuf formats directly via the read_model() method.
The current limitations:
- IRs generated by new TensorFlow Frontend are compatible only with OpenVINO API 2.0
- There is no full parity between the legacy frontend and the new frontend in MO. Known limitations compared to the legacy approach are: TF1 Control flow, Complex types, models requiring config files and old python extensions. The solution detects unsupported functionalities and provides fallback. To force the use of the legacy frontend,
--use_legacy_frontendmust be specified.
@endsphinxdirective