The harbor-tug wait model is a supported scikit-learn or XGBoost-class artifact. A contractor wants to spend a sprint writing a custom image for control. Which inference container should they use?
Select an answer to reveal the explanation.
Short Explanation
The harbor-tug wait model is already sklearn or XGBoost. Use a SageMaker provided inference container. A custom image is extra work when the framework already ships, Polly is not that container, and a trainer image is not the serving image.
Full Explanation
Use a SageMaker provided inference container when the framework is already supported. A custom image is not the default for sklearn or XGBoost-class artifacts. Polly is not that container, and a training image is not automatically the serving image.