RecommendationJobContainerConfig

import type { RecommendationJobContainerConfig } from "https://aws-api.deno.dev/v0.4/services/sagemaker.ts?docs=full";

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.

interface RecommendationJobContainerConfig {

DataInputConfig?: string | null;

Domain?: string | null;

Framework?: string | null;

FrameworkVersion?: string | null;

NearestModelName?: string | null;

PayloadConfig?: RecommendationJobPayloadConfig | null;

SupportedInstanceTypes?: string[] | null;

Task?: string | null;

}

§Properties

DataInputConfig?: string | null

[src]

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.

Domain?: string | null

[src]

The machine learning domain of the model and its components.

Valid Values: COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING

Framework?: string | null

[src]

The machine learning framework of the container image.

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

FrameworkVersion?: string | null

[src]

The framework version of the container image.

NearestModelName?: string | null