C4 W3 Ungraded Lab - Model Versioning with TF Serving (and Docker)

Hi! I followed the instruction in the README.md but got stuck with an error while trying the docker run command. I just copied and pasted the line of the command from the README.md in the PowerShell.

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

It generated the error as below:

docker: Error response from daemon: invalid mount config for type “bind”: invalid mount path: ‘/models’.
See ‘docker run --help’

Am I missing some steps?

Hi @kimdesok
first of all welcome to our Community.
Are you sure to have pulled the right docker image (tensorflow/serving:latest)?
In my case I see the following images (run ‘docker images’ from the shell)

docker images
REPOSITORY TAG IMAGE ID CREATED SIZE
locustio/locust latest 490c91721d75 5 weeks ago 985MB
mlepc4w2-ugl with-batch 05538f81ed79 5 weeks ago 521MB
mlepc4w2-ugl no-batch 52043ecf8b3e 5 weeks ago 521MB
tensorflow/serving latest e874bf5e4700 6 months ago 406MB
deeplearningai/mlepc1w1-ugl jupyternb bbb4b3565c40 9 months ago 2.31GB

If yes, have you successfully executed the setup.sh script?
After this step you should have a local folder named ‘models’
here below what I see from my shell

README.md dog_example.json models setup.sh

Please let me know
BR