ModelPackageTransformJobDefinition

data class ModelPackageTransformJobDefinition(val batchStrategy: ModelPackageTransformJobDefinitionBatchStrategy? = null, val environment: ModelPackageEnvironment? = null, val maxConcurrentTransforms: Int? = null, val maxPayloadInMb: Int? = null, val transformInput: ModelPackageTransformInput, val transformOutput: ModelPackageTransformOutput, val transformResources: ModelPackageTransformResources)

Defines the input needed to run a transform job using the inference specification specified in the algorithm.

Constructors

constructor(batchStrategy: ModelPackageTransformJobDefinitionBatchStrategy? = null, environment: ModelPackageEnvironment? = null, maxConcurrentTransforms: Int? = null, maxPayloadInMb: Int? = null, transformInput: ModelPackageTransformInput, transformOutput: ModelPackageTransformOutput, transformResources: ModelPackageTransformResources)

A string that determines the number of records included in a single mini-batch.

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

The maximum number of parallel requests that can be sent to each instance in a transform job. The default value is 1.

The maximum payload size allowed, in MB. A payload is the data portion of a record (without metadata).

A description of the input source and the way the transform job consumes it.

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

Identifies the ML compute instances for the transform job.