ReverseV2 Error Converting/Optimizing ONNX Model

[mckittrick]

I converted a model from Tensorflow 2.2 to ONNX format without any issue.  When I tried to use the Model Optimizer to convert it to OpenVINO I get the following error:

Error('Exception occurred during running replacer "{}" ({}): {}'.format(
mo.utils.error.Error: Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "_tf_op_layer_ReverseV2/ReverseV2" node. 

It seems the issue is with the ReverseV2 function, but that is supported per the documentation:

https://software.intel.com/content/www/br/pt/develop/articles/openvino-relnotes-2019.html

TensorFlow*
Added support of the following TensorFlow* operations: ReverseSequence, ReverseV2, ZerosLike, Exp, Sum.

Does anyone have any suggestions on how I might resolve this?

Thanks

[Iffa_Intel]

Greetings,

Please help to ensure that you run setupvars each time you open a new terminal before proceeding with anything.

Besides, ensure that you are in correct directories and using the correct module optimizer and commands which you can cross check here: https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_ONNX.html

Check your topologies also since only listed in the documentations are supported.

Sincerely,

Iffa

[Iffa_Intel]

Greetings,

Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question.

Sincerely,

Iffa