CODEWITHSUNDEEP
google-cloud-ml
Harry Moreno
Harry Moreno

Reputation: 11603

No version was specified and no default version for the model was found

I uploaded my predictive model to Googles' ML Engine. When I run

gcloud ml-engine predict --model=earnings --json-instances=sample_input_prescaled.json

I get the error

ERROR: (gcloud.ml-engine.predict) HTTP request failed. Response: {
  "error": {
"code": 400,
"message": "Field: name Error: No version was specified and no default version for the model was found.",
"status": "INVALID_ARGUMENT",
"details": [
  {
    "@type": "type.googleapis.com/google.rpc.BadRequest",
    "fieldViolations": [
      {
        "field": "name",
        "description": "No version was specified and no default version for the model was found."
      }
    ]
  }
]
  }
}

How do I add a version to my model?

Upvotes: 0

Views: 303

Answers (1)

Harry Moreno
Harry Moreno

Reputation: 11603

If you bring up the model using the web interface you can add a version to your model. That is ML Engine > Models > [model name] > Create a version.

Google ML Engine interface

Also be sure that your variables files are still in a variables directory in the storage bucket. When I copied the model over (gsutil cp -R exported_model/* gs://keras-class-191806/earnings_v1) the model's directory structure was flattened. Restore the variables folder and move the variables files inside.

Upvotes: 1

Related Questions