Class: Aws::SageMaker::Types::InferenceSpecification
- Inherits:
-
Struct
- Object
- Struct
- Aws::SageMaker::Types::InferenceSpecification
- Includes:
- Aws::Structure
- Defined in:
- lib/aws-sdk-sagemaker/types.rb
Overview
When making an API call, you may pass InferenceSpecification data as a hash:
{
containers: [ # required
{
container_hostname: "ContainerHostname",
image: "Image", # required
image_digest: "ImageDigest",
model_data_url: "Url",
product_id: "ProductId",
},
],
supported_transform_instance_types: ["ml.m4.xlarge"], # required, accepts ml.m4.xlarge, ml.m4.2xlarge, ml.m4.4xlarge, ml.m4.10xlarge, ml.m4.16xlarge, ml.c4.xlarge, ml.c4.2xlarge, ml.c4.4xlarge, ml.c4.8xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.c5.xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.c5.18xlarge, ml.m5.large, ml.m5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.12xlarge, ml.m5.24xlarge
supported_realtime_inference_instance_types: ["ml.t2.medium"], # required, accepts ml.t2.medium, ml.t2.large, ml.t2.xlarge, ml.t2.2xlarge, ml.m4.xlarge, ml.m4.2xlarge, ml.m4.4xlarge, ml.m4.10xlarge, ml.m4.16xlarge, ml.m5.large, ml.m5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.c4.large, ml.c4.xlarge, ml.c4.2xlarge, ml.c4.4xlarge, ml.c4.8xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.c5.large, ml.c5.xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.c5.18xlarge
supported_content_types: ["ContentType"], # required
supported_response_mime_types: ["ResponseMIMEType"], # required
}
Defines how to perform inference generation after a training job is run.
Instance Attribute Summary collapse
-
#containers ⇒ Array<Types::ModelPackageContainerDefinition>
The Amazon ECR registry path of the Docker image that contains the inference code.
-
#supported_content_types ⇒ Array<String>
The supported MIME types for the input data.
-
#supported_realtime_inference_instance_types ⇒ Array<String>
A list of the instance types that are used to generate inferences in real-time.
-
#supported_response_mime_types ⇒ Array<String>
The supported MIME types for the output data.
-
#supported_transform_instance_types ⇒ Array<String>
A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.
Instance Attribute Details
#containers ⇒ Array<Types::ModelPackageContainerDefinition>
The Amazon ECR registry path of the Docker image that contains the inference code.
5900 5901 5902 5903 5904 5905 5906 5907 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 5900 class InferenceSpecification < Struct.new( :containers, :supported_transform_instance_types, :supported_realtime_inference_instance_types, :supported_content_types, :supported_response_mime_types) include Aws::Structure end |
#supported_content_types ⇒ Array<String>
The supported MIME types for the input data.
5900 5901 5902 5903 5904 5905 5906 5907 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 5900 class InferenceSpecification < Struct.new( :containers, :supported_transform_instance_types, :supported_realtime_inference_instance_types, :supported_content_types, :supported_response_mime_types) include Aws::Structure end |
#supported_realtime_inference_instance_types ⇒ Array<String>
A list of the instance types that are used to generate inferences in real-time.
5900 5901 5902 5903 5904 5905 5906 5907 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 5900 class InferenceSpecification < Struct.new( :containers, :supported_transform_instance_types, :supported_realtime_inference_instance_types, :supported_content_types, :supported_response_mime_types) include Aws::Structure end |
#supported_response_mime_types ⇒ Array<String>
The supported MIME types for the output data.
5900 5901 5902 5903 5904 5905 5906 5907 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 5900 class InferenceSpecification < Struct.new( :containers, :supported_transform_instance_types, :supported_realtime_inference_instance_types, :supported_content_types, :supported_response_mime_types) include Aws::Structure end |
#supported_transform_instance_types ⇒ Array<String>
A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.
5900 5901 5902 5903 5904 5905 5906 5907 |
# File 'lib/aws-sdk-sagemaker/types.rb', line 5900 class InferenceSpecification < Struct.new( :containers, :supported_transform_instance_types, :supported_realtime_inference_instance_types, :supported_content_types, :supported_response_mime_types) include Aws::Structure end |