This repository was archived by the owner on Nov 3, 2022. It is now read-only.
This repository was archived by the owner on Nov 3, 2022. It is now read-only.
Can't load pickle file (Keras Model) after deployment on the azure server #555
Open
Description
Describe the bug
I wanted to make the keras model pickable, so i used the solution from this issue: #34697 (comment)
it solved my problem perfectly in the local environment, but when I build the project from the docker container on Azure Server and while loading the pickle file it gives,
Can't get attribute 'unpack' on <module 'main' from '/opt/python/3.7.9/bin/gunicorn'>
it's like the gunicorn web server can't interpret or see the "unpack" function, I don't know exactly what's going on in the gunicorn server, any help please!
Environment:
- OS: linux - Azure server
- Python Version 3.7.9
- Tensorflow Version: 2.4
- Keras Version: 2.3.4
Metadata
Metadata
Assignees
Labels
No labels