Model serving keep relaunching

[hulma]

Hello,

I tried to serve my model realtime. Model process keeps relaunching.

I am getting this error in the logs,

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If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc 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

how do i fix it?

[fsyshawn]

Have exact same issue. cannot figure out why either.

[hulma]

my workaround is to add protobuf<=3.20.1 in conda_env when i train the model in mlflow.

[kushan-gunaseke]

for anyone who is looking for a proper solution,

https://stackoverflow.com/a/72493690/6194097

[Anonymous]

Hey there @Hulma Abdul Rahman​ 

Hope you are well.

Just wanted to see if you were able to find an answer to your question and would you like to mark an answer as best? It would be really helpful for the other members too.

Cheers!