Package software.amazon.awssdk.services.sagemaker.model

Interface RecommendationJobContainerConfig.Builder

    • Method Detail

      • domain

        RecommendationJobContainerConfig.Builder domain​(String domain)

        The machine learning domain of the model and its components.

        Valid Values: COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING

        Parameters:
        domain - The machine learning domain of the model and its components.

        Valid Values: COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING

        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • task

        RecommendationJobContainerConfig.Builder task​(String task)

        The machine learning task that the model accomplishes.

        Valid Values: IMAGE_CLASSIFICATION | OBJECT_DETECTION | TEXT_GENERATION | IMAGE_SEGMENTATION | FILL_MASK | CLASSIFICATION | REGRESSION | OTHER

        Parameters:
        task - The machine learning task that the model accomplishes.

        Valid Values: IMAGE_CLASSIFICATION | OBJECT_DETECTION | TEXT_GENERATION | IMAGE_SEGMENTATION | FILL_MASK | CLASSIFICATION | REGRESSION | OTHER

        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • framework

        RecommendationJobContainerConfig.Builder framework​(String framework)

        The machine learning framework of the container image.

        Valid Values: TENSORFLOW | PYTORCH | XGBOOST | SAGEMAKER-SCIKIT-LEARN

        Parameters:
        framework - The machine learning framework of the container image.

        Valid Values: TENSORFLOW | PYTORCH | XGBOOST | SAGEMAKER-SCIKIT-LEARN

        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • frameworkVersion

        RecommendationJobContainerConfig.Builder frameworkVersion​(String frameworkVersion)

        The framework version of the container image.

        Parameters:
        frameworkVersion - The framework version of the container image.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • payloadConfig

        RecommendationJobContainerConfig.Builder payloadConfig​(RecommendationJobPayloadConfig payloadConfig)

        Specifies the SamplePayloadUrl and all other sample payload-related fields.

        Parameters:
        payloadConfig - Specifies the SamplePayloadUrl and all other sample payload-related fields.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • nearestModelName

        RecommendationJobContainerConfig.Builder nearestModelName​(String nearestModelName)

        The name of a pre-trained machine learning model benchmarked by Amazon SageMaker Inference Recommender that matches your model.

        Valid Values: efficientnetb7 | unet | xgboost | faster-rcnn-resnet101 | nasnetlarge | vgg16 | inception-v3 | mask-rcnn | sagemaker-scikit-learn | densenet201-gluon | resnet18v2-gluon | xception | densenet201 | yolov4 | resnet152 | bert-base-cased | xceptionV1-keras | resnet50 | retinanet

        Parameters:
        nearestModelName - The name of a pre-trained machine learning model benchmarked by Amazon SageMaker Inference Recommender that matches your model.

        Valid Values: efficientnetb7 | unet | xgboost | faster-rcnn-resnet101 | nasnetlarge | vgg16 | inception-v3 | mask-rcnn | sagemaker-scikit-learn | densenet201-gluon | resnet18v2-gluon | xception | densenet201 | yolov4 | resnet152 | bert-base-cased | xceptionV1-keras | resnet50 | retinanet

        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • supportedInstanceTypes

        RecommendationJobContainerConfig.Builder supportedInstanceTypes​(Collection<String> supportedInstanceTypes)

        A list of the instance types that are used to generate inferences in real-time.

        Parameters:
        supportedInstanceTypes - A list of the instance types that are used to generate inferences in real-time.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • supportedInstanceTypes

        RecommendationJobContainerConfig.Builder supportedInstanceTypes​(String... supportedInstanceTypes)

        A list of the instance types that are used to generate inferences in real-time.

        Parameters:
        supportedInstanceTypes - A list of the instance types that are used to generate inferences in real-time.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • supportedEndpointType

        RecommendationJobContainerConfig.Builder supportedEndpointType​(String supportedEndpointType)

        The endpoint type to receive recommendations for. By default this is null, and the results of the inference recommendation job return a combined list of both real-time and serverless benchmarks. By specifying a value for this field, you can receive a longer list of benchmarks for the desired endpoint type.

        Parameters:
        supportedEndpointType - The endpoint type to receive recommendations for. By default this is null, and the results of the inference recommendation job return a combined list of both real-time and serverless benchmarks. By specifying a value for this field, you can receive a longer list of benchmarks for the desired endpoint type.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
        See Also:
        RecommendationJobSupportedEndpointType, RecommendationJobSupportedEndpointType

      • supportedEndpointType

        RecommendationJobContainerConfig.Builder supportedEndpointType​(RecommendationJobSupportedEndpointType supportedEndpointType)

        The endpoint type to receive recommendations for. By default this is null, and the results of the inference recommendation job return a combined list of both real-time and serverless benchmarks. By specifying a value for this field, you can receive a longer list of benchmarks for the desired endpoint type.

        Parameters:
        supportedEndpointType - The endpoint type to receive recommendations for. By default this is null, and the results of the inference recommendation job return a combined list of both real-time and serverless benchmarks. By specifying a value for this field, you can receive a longer list of benchmarks for the desired endpoint type.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
        See Also:
        RecommendationJobSupportedEndpointType, RecommendationJobSupportedEndpointType

      • dataInputConfig

        RecommendationJobContainerConfig.Builder dataInputConfig​(String dataInputConfig)

        Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. This field is used for optimizing your model using SageMaker Neo. For more information, see DataInputConfig.

        Parameters:
        dataInputConfig - Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. This field is used for optimizing your model using SageMaker Neo. For more information, see DataInputConfig.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • supportedResponseMIMETypes

        RecommendationJobContainerConfig.Builder supportedResponseMIMETypes​(Collection<String> supportedResponseMIMETypes)

        The supported MIME types for the output data.

        Parameters:
        supportedResponseMIMETypes - The supported MIME types for the output data.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • supportedResponseMIMETypes

        RecommendationJobContainerConfig.Builder supportedResponseMIMETypes​(String... supportedResponseMIMETypes)

        The supported MIME types for the output data.

        Parameters:
        supportedResponseMIMETypes - The supported MIME types for the output data.
        Returns:
        Returns a reference to this object so that method calls can be chained together.