IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
0cf95d26bf1a5abeb1fbba4e12547cbf215d1a3f
openvino/docs/resources/tensorflow_frontend.md
Roman Kazantsev 0cf95d26bf [TF FE] Add user guide about TF FE Capabilities and Limitations (#14622) 
* [TF FE] Add user guide about TF FE Capabilities and Limitations

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Update docs/resources/tensorflow_frontend.md

* Update docs/OV_Runtime_UG/protecting_model_guide.md

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* Update docs/OV_Runtime_UG/deployment/local-distribution.md

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2022-12-14 17:41:00 +04:00

1.2 KiB
Raw Blame History

OpenVINO TensorFlow Frontend Capabilities and Limitations

TensorFlow Frontend is C++ based Frontend for conversion of TensorFlow models and is available as a preview feature starting from 2022.3. That means that you can start experimenting with --use_new_frontend option passed to Model Optimizer to enjoy improved conversion time for limited scope of models or directly loading TensorFlow models through 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 yet between legacy Model Optimizer TensorFlow Frontend and new TensorFlow Frontend so primary path for model conversion is still legacy frontend
  • Model coverage and performance is continuously improving so some conversion phase failures, performance and accuracy issues might occur in case model is not yet covered. Known unsupported models: object detection models and all models with transformation configs, models with TF1/TF2 control flow, Complex type and training parts
  • read_model() method supports only *.pb format while Model Optimizer (or convert_model call) will accept other formats as well which are accepted by existing legacy frontend