easyMultiple Choice
MLA-C01 Practice Question: A machine learning engineer needs to deploy a…
A machine learning engineer needs to deploy a TensorFlow model to Amazon SageMaker and wants to use the built-in TensorFlow Serving container. What should the engineer provide in the model archive?
⚠ Common exam trap
AWS often tests the misconception that a frozen graph (Option A) is sufficient for TensorFlow Serving, but the exam expects candidates to know that TensorFlow Serving specifically requires the SavedModel format with its directory structure, not just a single protobuf file.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A tar.gz file containing the TensorFlow SavedModel.
The built-in TensorFlow Serving container in Amazon SageMaker expects a TensorFlow SavedModel packaged in a tar.gz archive. This is because TensorFlow Serving natively loads models from the SavedModel format, which includes the model's computational graph, weights, and assets in a standardized directory structure. Providing a tar.gz of the SavedModel ensures compatibility with the container's default serving stack without requiring custom inference code.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A frozen graph of the TensorFlow model.
Why it's wrong here
A frozen graph alone is insufficient: TensorFlow Serving requires the SavedModel directory format, containing the graph plus variables and assets, at a specific path in the archive. A frozen .pb graph suits TensorFlow Lite or custom loading code, not this container.
- ✓
A tar.gz file containing the TensorFlow SavedModel.
Why this is correct
The built-in TensorFlow Serving container expects a model.tar.gz archive whose contents are a TensorFlow SavedModel directory, including saved_model.pb and variables. Supplying that archive at model creation lets SageMaker load and serve the model without custom inference code.
- ✗
Model artifacts and a Python inference script.
Why it's wrong here
The built-in TensorFlow Serving container already provides the inference stack, so a custom Python inference script is not read or executed by it. Such a script belongs in a custom inference container, where the engineer controls the entrypoint and serving logic.
- ✗
A Dockerfile and model artifacts.
Why it's wrong here
A Dockerfile builds a custom inference container, which SageMaker would run instead of the built-in TensorFlow Serving image; the archive must instead contain the SavedModel artefacts at the expected path. Supplying a Dockerfile is correct when the framework version or dependencies fall outside the prebuilt containers and you must bring your own image.
Go deeper
Related to this question
About these practice questions
This MLA-C01 question is part of Courseiva's 665-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLA-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MLA-C01 exam.