C4 W3 Lab3 - Docker not starting

Course Q&A Machine Learning Engineering for Production(MLOps) Deploying Machine Learning Models in Production
1

Hi all,

I am experimenting a problem when trying to run docker on Windows 11. It seems like a mismatch related to the mounting of the disks but I cannot figure the solution.
Any help will be most appreciated.

The command:
docker run -t --rm -p 8501:8501
–mount type=bind,source="$(pwd)/models",target=/models/ tensorflow/serving
–model_config_file=/models/models.config
–model_config_file_poll_wait_seconds=60
–allow_version_labels_for_unavailable_models=true

The error message:
Failed to start server. Error: Not found: C:/Program Files/Git/models/models.config; No such file or directory

2

Hi Fernando. I think the problem is in this line –model_config_file=/models/models.config. It is assuming that you have the models directory under root (i.e. /) which it assumes is C:/Program Files/Git. Maybe you can place an absolute path there where the models.config file is located to avoid that error. Another way is to place the models directory under C:/Program Files/Git in your machine. That way, you won’t have to modify the command. Hope these help!