[TensorFlow Frontend] Internal error

[vidithirve]

Hello,

I am trying to convert a TensorFlow model using

C:\Handwritten_OCR\SimpleHTR-master\SimpleHTR-master\model>mo --input_meta_graph snapshot-13.meta

but I am getting the following error as an output:

[libprotobuf ERROR C:\Jenkins\workspace\private-ci\ie\build-windows-vs2019\b\repos\openvino\thirdparty\protobuf\protobuf\src\google\protobuf\wire_format_lite.cc:618] String field 'tensorflow.NodeDef.op' contains invalid UTF-8 data when parsing a protocol buffer. Use the 'bytes' type if you intend to send raw bytes.
[ ERROR ]  -------------------------------------------------
[ ERROR ]  ----------------- INTERNAL ERROR ----------------
[ ERROR ]  Unexpected exception happened.
[ ERROR ]  Please contact Model Optimizer developers and forward the following information:
[ ERROR ]  Check 'is_conversion_successful' failed at C:\Jenkins\workspace\private-ci\ie\build-windows-vs2019\b\repos\openvino\src\frontends\tensorflow\src\frontend.cpp:263:
FrontEnd API failed with OpConversionFailure: :
[TensorFlow Frontend] Internal error, conversion is failed for CTCLoss operation with a message:
Check 'shape_rank.compatible(1)' failed at C:\Jenkins\workspace\private-ci\ie\build-windows-vs2019\b\repos\openvino\src\core\shape_inference\include\slice_shape_inference.hpp:70:
While validating node 'opset8::Slice Slice_60676 (ShapeOf_60672[0]:i64[3], Constant_60675[0]:i64[], Constant_60674[0]:i64[], Constant_60673[0]:i64[]) -> (dynamic[...])' with friendly_name 'Slice_60676':
Slice `start` input must be a 1D tensor. Got rank: 0

[TensorFlow Frontend] Internal error, conversion is failed for Conv2DBackpropInput operation with a message:
Accessing out-of-range dimension in Dimension[]
[TensorFlow Frontend] Internal error, no translator found for operation(s): AssignSubVariableOp, BiasAddGrad, BroadcastGradientArgs, ConcatOffset, Conv2DBackpropFilter, FusedBatchNormGradV3, InvertPermutation, MaxPoolGrad, OptionalFromValue, OptionalGetValue, ReluGrad, ResourceApplyAdam, ShapeN, SigmoidGrad, TanhGrad, TensorListPopBack

[ ERROR ]  Traceback (most recent call last):
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\openvino\tools\mo\convert_impl.py", line 915, in _convert
    ov_model, legacy_path = driver(argv, {"conversion_parameters": non_default_params})
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\openvino\tools\mo\convert_impl.py", line 591, in driver
    graph, ngraph_function = prepare_ir(argv)
                             ^^^^^^^^^^^^^^^^
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\openvino\tools\mo\convert_impl.py", line 404, in prepare_ir
    ngraph_function = moc_pipeline(argv, moc_front_end)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python311\Lib\site-packages\openvino\tools\mo\moc_frontend\pipeline.py", line 266, in moc_pipeline
    ov_model = moc_front_end.convert(input_model)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
openvino._pyopenvino.OpConversionFailure: Check 'is_conversion_successful' failed at C:\Jenkins\workspace\private-ci\ie\build-windows-vs2019\b\repos\openvino\src\frontends\tensorflow\src\frontend.cpp:263:
FrontEnd API failed with OpConversionFailure: :
[TensorFlow Frontend] Internal error, conversion is failed for CTCLoss operation with a message:
Check 'shape_rank.compatible(1)' failed at C:\Jenkins\workspace\private-ci\ie\build-windows-vs2019\b\repos\openvino\src\core\shape_inference\include\slice_shape_inference.hpp:70:
While validating node 'opset8::Slice Slice_60676 (ShapeOf_60672[0]:i64[3], Constant_60675[0]:i64[], Constant_60674[0]:i64[], Constant_60673[0]:i64[]) -> (dynamic[...])' with friendly_name 'Slice_60676':
Slice `start` input must be a 1D tensor. Got rank: 0

[TensorFlow Frontend] Internal error, conversion is failed for Conv2DBackpropInput operation with a message:
Accessing out-of-range dimension in Dimension[]
[TensorFlow Frontend] Internal error, no translator found for operation(s): AssignSubVariableOp, BiasAddGrad, BroadcastGradientArgs, ConcatOffset, Conv2DBackpropFilter, FusedBatchNormGradV3, InvertPermutation, MaxPoolGrad, OptionalFromValue, OptionalGetValue, ReluGrad, ResourceApplyAdam, ShapeN, SigmoidGrad, TanhGrad, TensorListPopBack


[ ERROR ]  ---------------- END OF BUG REPORT --------------
[ ERROR ]  -------------------------------------------------
[ INFO ] You can also try to use legacy TensorFlow Frontend by using argument --use_legacy_frontend.

I am unable to find a solution for this. I would really appreciate some help on this.