mrdbourke / cs329s-ml-deployment-tutorial Goto Github PK

KeyError: "Failed to add concrete function 'b'__inference_model_1_layer_call_fn_61750'' to object-based SavedModel as it captures tensor <tf.Tensor: shape=(), dtype=resource, value=> which is unsupported or not reachable from root. One reason could be that a stateful object or a variable that the function depends on is not assigned to an attribute of the serialized trackable object (see SaveTest.test_captures_unreachable_variable)."

Hitting this error on a local instance trying to predict:

HttpError: <HttpError 403 when requesting https://us-west1-ml.googleapis.com/v1/projects/foodml/models/foodml_1:predict?alt=json returned "AI Platform Training & Prediction API has not been used in project 37288436933 before or it is disabled. Enable it by visiting https://console.developers.google.com/apis/api/ml.googleapis.com/overview?project=37288436933 then retry.

The API is enabled but the project number seems incorrect in the above message.

When I do this step:

3. Deploying the whole app to GCP
Okay, I've fixed the permissions error, how do I deploy my model/app?

I'm glad you asked...

run make gcloud-deploy... wait 5-10 mins and your app will be on App Engine (as long as you've activated the App Engine API)
...and you're done

I get this error in my Git Bash terminal:

ERROR: (gcloud.app.deploy) Error Response: [9] An internal error occurred while processing task /app-engine-flex/flex_await_healthy/flex_await_healthy>2022-11-25T13:25:59.323Z7873.jc.1: The region us-central1 does not have enough resources available to fulfill the request. Please try again later.
make: *** [Makefile:13: gcloud-deploy] Error 1

I did 'try again later' only to get the same error response.

What could I try?