Workaround to convert model into Intermediate Representation (IR) format using Openvino-dev Python* package and uploading IR into DL Workbench 2022.1
Encountered error when converting model in DL Workbench 2022.1:
TypeError: 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If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc 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).
More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates
Protobuf release 4.21.0 were reported for breaking multiple libraries including TensorFlow libraries and needs to be restricted to lower versions.
- Convert the model using Openvino-dev Python* package into IR format for a workaround.
- Upload the IR to the DL Workbench