Unable to Run Model Inference with OpenVINO™ API Jupyter Notebook in DL Workbench

Encountered when converting model in Model Inference with OpenVINO™ API Jupyter Notebook:

[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID (<class 'openvino.tools.mo.load.caffe.loader.CaffeLoader'>)": Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:

1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

• Download and convert the model into Intermediate Representation (IR) format independently using OpenVINO™ Development Tools instead of DL Workbench.
• Upload the IR model into DL Workbench.
• Copy the path for the .xml and .bin file into the Model Inference with OpenVINO™ API Jupyter Notebook.