| Copyright | (c) 2013-2023 Brendan Hay |
|---|---|
| License | Mozilla Public License, v. 2.0. |
| Maintainer | Brendan Hay |
| Stability | auto-generated |
| Portability | non-portable (GHC extensions) |
| Safe Haskell | Safe-Inferred |
| Language | Haskell2010 |
Amazonka.SageMaker.Types.InferenceSpecification
Description
Synopsis
- data InferenceSpecification = InferenceSpecification' {}
- newInferenceSpecification :: NonEmpty ModelPackageContainerDefinition -> InferenceSpecification
- inferenceSpecification_supportedRealtimeInferenceInstanceTypes :: Lens' InferenceSpecification (Maybe [ProductionVariantInstanceType])
- inferenceSpecification_supportedTransformInstanceTypes :: Lens' InferenceSpecification (Maybe (NonEmpty TransformInstanceType))
- inferenceSpecification_containers :: Lens' InferenceSpecification (NonEmpty ModelPackageContainerDefinition)
- inferenceSpecification_supportedContentTypes :: Lens' InferenceSpecification [Text]
- inferenceSpecification_supportedResponseMIMETypes :: Lens' InferenceSpecification [Text]
Documentation
data InferenceSpecification Source #
Defines how to perform inference generation after a training job is run.
See: newInferenceSpecification smart constructor.
Constructors
| InferenceSpecification' | |
Fields
| |
Instances
newInferenceSpecification Source #
Arguments
| :: NonEmpty ModelPackageContainerDefinition | |
| -> InferenceSpecification |
Create a value of InferenceSpecification with all optional fields omitted.
Use generic-lens or optics to modify other optional fields.
The following record fields are available, with the corresponding lenses provided for backwards compatibility:
$sel:supportedRealtimeInferenceInstanceTypes:InferenceSpecification', inferenceSpecification_supportedRealtimeInferenceInstanceTypes - A list of the instance types that are used to generate inferences in
real-time.
This parameter is required for unversioned models, and optional for versioned models.
$sel:supportedTransformInstanceTypes:InferenceSpecification', inferenceSpecification_supportedTransformInstanceTypes - A list of the instance types on which a transformation job can be run or
on which an endpoint can be deployed.
This parameter is required for unversioned models, and optional for versioned models.
$sel:containers:InferenceSpecification', inferenceSpecification_containers - The Amazon ECR registry path of the Docker image that contains the
inference code.
$sel:supportedContentTypes:InferenceSpecification', inferenceSpecification_supportedContentTypes - The supported MIME types for the input data.
$sel:supportedResponseMIMETypes:InferenceSpecification', inferenceSpecification_supportedResponseMIMETypes - The supported MIME types for the output data.
inferenceSpecification_supportedRealtimeInferenceInstanceTypes :: Lens' InferenceSpecification (Maybe [ProductionVariantInstanceType]) Source #
A list of the instance types that are used to generate inferences in real-time.
This parameter is required for unversioned models, and optional for versioned models.
inferenceSpecification_supportedTransformInstanceTypes :: Lens' InferenceSpecification (Maybe (NonEmpty TransformInstanceType)) Source #
A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.
This parameter is required for unversioned models, and optional for versioned models.
inferenceSpecification_containers :: Lens' InferenceSpecification (NonEmpty ModelPackageContainerDefinition) Source #
The Amazon ECR registry path of the Docker image that contains the inference code.
inferenceSpecification_supportedContentTypes :: Lens' InferenceSpecification [Text] Source #
The supported MIME types for the input data.
inferenceSpecification_supportedResponseMIMETypes :: Lens' InferenceSpecification [Text] Source #
The supported MIME types for the output data.