topic Re: Model serving keep relaunching in Machine Learning

Model serving keep relaunching

hulma — Thu, 26 May 2022 05:34:01 GMT

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If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc 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

Re: Model serving keep relaunching

fsyshawn — Thu, 26 May 2022 14:49:43 GMT

Have exact same issue. cannot figure out why either.

Re: Model serving keep relaunching

hulma — Fri, 27 May 2022 01:52:32 GMT

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

Re: Model serving keep relaunching

kushan-gunaseke — Tue, 14 Jun 2022 04:11:51 GMT

for anyone who is looking for a proper solution,

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

Re: Model serving keep relaunching

Anonymous — Mon, 25 Jul 2022 16:38:06 GMT

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!