Sign in

v1

latestOpenAPI 3.0.0Apache 2.0 License2026-07-143021,9861.6 MB

Starts a transform job. A transform job uses a trained model to get inferences on a dataset and saves these results to an Amazon S3 location that you specify.

To perform batch transformations, you create a transform job and use the data that you have readily available.

In the request body, you provide the following:

  • TransformJobName - Identifies the transform job. The name must be unique within an Amazon Web Services Region in an Amazon Web Services account.

  • ModelName - Identifies the model to use. ModelName must be the name of an existing Amazon SageMaker model in the same Amazon Web Services Region and Amazon Web Services account. For information on creating a model, see CreateModel.

  • TransformInput - Describes the dataset to be transformed and the Amazon S3 location where it is stored.

  • TransformOutput - Identifies the Amazon S3 location where you want Amazon SageMaker to save the results from the transform job.

  • TransformResources - Identifies the ML compute instances for the transform job.

For more information about how batch transformation works, see Batch Transform.

post/#X-Amz-Target=SageMaker.CreateTransformJob

Headers

X-Amz-Target'SageMaker.CreateTransformJob' required

Request body

TransformJobNamestring required

The name of the transform job. The name must be unique within an Amazon Web Services Region in an Amazon Web Services account.

ModelNamestring required

The name of the model that you want to use for the transform job. <code>ModelName</code> must be the name of an existing Amazon SageMaker model within an Amazon Web Services Region in an Amazon Web Services account.

MaxConcurrentTransformsinteger

The maximum number of parallel requests that can be sent to each instance in a transform job. If <code>MaxConcurrentTransforms</code> is set to <code>0</code> or left unset, Amazon SageMaker checks the optional execution-parameters to determine the settings for your chosen algorithm. If the execution-parameters endpoint is not enabled, the default value is <code>1</code>. For more information on execution-parameters, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-batch-code.html#your-algorithms-batch-code-how-containe-serves-requests">How Containers Serve Requests</a>. For built-in algorithms, you don't need to set a value for <code>MaxConcurrentTransforms</code>.

MaxPayloadInMBinteger
<p>The maximum allowed size of the payload, in MB. A <i>payload</i> is the data portion of a record (without metadata). The value in <code>MaxPayloadInMB</code> must be greater than, or equal to, the size of a single record. To estimate the size of a record in MB, divide the size of your dataset by the number of records. To ensure that the records fit within the maximum payload size, we recommend using a slightly larger value. The default value is <code>6</code> MB. </p> <p>The value of <code>MaxPayloadInMB</code> cannot be greater than 100 MB. If you specify the <code>MaxConcurrentTransforms</code> parameter, the value of <code>(MaxConcurrentTransforms * MaxPayloadInMB)</code> also cannot exceed 100 MB.</p> <p>For cases where the payload might be arbitrarily large and is transmitted using HTTP chunked encoding, set the value to <code>0</code>. This feature works only in supported algorithms. Currently, Amazon SageMaker built-in algorithms do not support HTTP chunked encoding.</p>
BatchStrategy'MultiRecord' | 'SingleRecord'
<p>Specifies the number of records to include in a mini-batch for an HTTP inference request. A <i>record</i> <i/> is a single unit of input data that inference can be made on. For example, a single line in a CSV file is a record. </p> <p>To enable the batch strategy, you must set the <code>SplitType</code> property to <code>Line</code>, <code>RecordIO</code>, or <code>TFRecord</code>.</p> <p>To use only one record when making an HTTP invocation request to a container, set <code>BatchStrategy</code> to <code>SingleRecord</code> and <code>SplitType</code> to <code>Line</code>.</p> <p>To fit as many records in a mini-batch as can fit within the <code>MaxPayloadInMB</code> limit, set <code>BatchStrategy</code> to <code>MultiRecord</code> and <code>SplitType</code> to <code>Line</code>.</p>
Environmentobject

The environment variables to set in the Docker container. We support up to 16 key and values entries in the map.

Response

Success

TransformJobArnstring required

The Amazon Resource Name (ARN) of the transform job.