The CREATE MODEL statement for importing TensorFlow Lite models

This document describes theCREATE MODEL statement for importingTensorFlow Lite models intoBigQuery by using SQL. Alternatively, you can use theGoogle Cloud console user interface tocreate a model by using a UI(Preview) instead of constructing the SQLstatement yourself.

For more information about supported SQL statements and functions for thismodel, seeEnd-to-end user journeys for imported models.

CREATE MODEL syntax

{CREATE MODEL |CREATE MODEL IF NOT EXISTS |CREATE OR REPLACE MODEL}model_nameOPTIONS(MODEL_TYPE = 'TENSORFLOW_LITE', MODEL_PATH =string_value  [, KMS_KEY_NAME =string_value ]);

CREATE MODEL

Creates and trains a new model in the specified dataset. If the model nameexists,CREATE MODEL returns an error.

CREATE MODEL IF NOT EXISTS

Creates and trains a new model only if the model doesn't exist in thespecified dataset.

CREATE OR REPLACE MODEL

Creates and trains a model and replaces an existing model with the same name inthe specified dataset.

model_name

The name of the model you're creating or replacing. The modelname must be unique in the dataset: no other model or table can have the samename. The model name must follow the same naming rules as aBigQuery table. A model name can:

• Contain up to 1,024 characters
• Contain letters (upper or lower case), numbers, and underscores

model_name is case-sensitive.

If you don't have a default project configured, then you must prepend theproject ID to the model name in the following format, including backticks:

`[PROJECT_ID].[DATASET].[MODEL]`

For example, `myproject.mydataset.mymodel`.

MODEL_TYPE

Syntax

MODEL_TYPE='TENSORFLOW_LITE'

Description

Specifies the model type. This option is required.

MODEL_PATH

Syntax

MODEL_PATH=string_value

Description

Specifies theCloud Storage URIof the TensorFlow Lite model to import. This option is required.

Arguments

ASTRING value specifying the URI of a Cloud Storage bucket that containsthe model to import.

BigQuery ML imports the model from Cloud Storage by using thecredentials of the user who runs theCREATE MODEL statement.

Example

MODEL_PATH='gs://bucket/path/to/tflite_model/*'

KMS_KEY_NAME

Syntax

KMS_KEY_NAME =string_value

Description

The Cloud Key Management Servicecustomer-managed encryption key (CMEK) touse to encrypt the model.

Arguments

ASTRING value containing the fully-qualified name of the CMEK. For example,

'projects/my_project/locations/my_location/keyRings/my_ring/cryptoKeys/my_key'

Supported data types for input and output columns

BigQuery ML converts some TensorFlow Lite modelinput and output columns to BigQuery ML types, and someTensorFlow Lite typesaren't supported. Supported data types for input and output columns includethe following:

Locations

For information about supported locations, seeLocations for non-remote models.

Limitations

Imported TensorFlow Lite models have the following limitations:

• The TensorFlow Lite model must exist before you can import itinto BigQuery.
• Models must be stored in Cloud Storage.
• TensorFlow Lite models must be in.tflite format.
• You can only use TensorFlow Lite models with theML.PREDICT function.
• Models are limited to 450 MB in size.
• OnlyTensorFlow core operationsandTensorFlow Text operationsare supported in BigQuery ML.
• SentencePiece operators are not supported.
• Sparse tensors are not supported.
• You can only use an imported TensorFlow Lite model with anobject table when you use capacity-based pricing through reservations.On-demand pricing isn't supported.

Example

The following example imports a TensorFlow Lite model intoBigQuery as a BigQuery ML model. The exampleassumes that there is an existing TensorFlow Lite model locatedatgs://bucket/path/to/tflite_model/*.

CREATEMODEL`project_id.mydataset.mymodel`OPTIONS(MODEL_TYPE='TENSORFLOW_LITE',MODEL_PATH="gs://bucket/path/to/tflite_model/*")