Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from http://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-tflite below:

The CREATE MODEL statement for importing TensorFlow Lite models | BigQuery

Stay organized with collections Save and categorize content based on your preferences.

This document describes the CREATE MODEL statement for importing TensorFlow Lite models into BigQuery by using SQL. Alternatively, you can use the Google Cloud console user interface to create a model by using a UI (Preview) instead of constructing the SQL statement yourself.

For information about the supported SQL statements and functions for each model type, see End-to-end user journey for each model.

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

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

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

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

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

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

model_name is not case-sensitive.

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

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

For example, `myproject.mydataset.mymodel`.

Syntax

MODEL_TYPE = 'TENSORFLOW_LITE'

Description

Specifies the model type. This option is required.

Syntax

MODEL_PATH = string_value

Description

Specifies the Cloud Storage URI of the TensorFlow Lite model to import. This option is required.

Arguments

A STRING value specifying the URI of a Cloud Storage bucket that contains the model to import.

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

Example

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

Syntax

KMS_KEY_NAME = string_value

Description

The Cloud Key Management Service customer-managed encryption key (CMEK) to use to encrypt the model.

Arguments

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

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

BigQuery ML converts some TensorFlow Lite model input and output columns to BigQuery ML types, and some TensorFlow Lite types aren't supported. Supported data types for input and output columns include the following:

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

Imported TensorFlow Lite models have the following limitations:

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

The following example imports a TensorFlow Lite model into BigQuery as a BigQuery ML model. The example assumes that there is an existing TensorFlow Lite model located at gs://bucket/path/to/tflite_model/*.

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

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-08-11 UTC.

[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-11 UTC."],[[["The `CREATE MODEL` statement imports TensorFlow Lite models into BigQuery, allowing for model creation, replacement, or creation only if a model of the same name doesn't exist."],["The `MODEL_TYPE` option must be set to `'TENSORFLOW_LITE'` and `MODEL_PATH` must specify a valid Cloud Storage URI containing the `.tflite` model to import."],["Imported TensorFlow Lite models have limitations, including requiring the models to be stored in Cloud Storage, be in `.tflite` format, use the `ML.PREDICT` function, and the model size must not exceed 450 MB."],["Only specific TensorFlow core and TensorFlow Text operations are supported for use, and only certain data types for input and output columns are compatible with BigQuery types."],["The `KMS_KEY_NAME` option can be used to specify a Cloud Key Management Service customer-managed encryption key (CMEK) for model encryption."]]],[]]

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4