Documentation

Specifies mandatory fields for running an Inference Recommender job directly in the CreateInferenceRecommendationsJob API. The fields specified in ContainerConfig override the corresponding fields in the model package. Use ContainerConfig if you want to specify these fields for the recommendation job but don't want to edit them in your model package.

See: newRecommendationJobContainerConfig smart constructor.

Create a value of RecommendationJobContainerConfig 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:domain:RecommendationJobContainerConfig', recommendationJobContainerConfig_domain - The machine learning domain of the model and its components.

Valid Values: COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING

$sel:framework:RecommendationJobContainerConfig', recommendationJobContainerConfig_framework - The machine learning framework of the container image.

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

$sel:frameworkVersion:RecommendationJobContainerConfig', recommendationJobContainerConfig_frameworkVersion - The framework version of the container image.

$sel:nearestModelName:RecommendationJobContainerConfig', recommendationJobContainerConfig_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

$sel:payloadConfig:RecommendationJobContainerConfig', recommendationJobContainerConfig_payloadConfig - Specifies the SamplePayloadUrl and all other sample payload-related fields.

$sel:supportedInstanceTypes:RecommendationJobContainerConfig', recommendationJobContainerConfig_supportedInstanceTypes - A list of the instance types that are used to generate inferences in real-time.

$sel:task:RecommendationJobContainerConfig', recommendationJobContainerConfig_task - The machine learning task that the model accomplishes.

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

The machine learning domain of the model and its components.

Valid Values: COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING

The machine learning framework of the container image.

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

The framework version of the container image.

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

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

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

The machine learning task that the model accomplishes.

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