mediumMultiple Choice
PMLE Practice Question: A data analyst wants to use Vision API to detect…
A data analyst wants to use Vision API to detect custom objects in manufacturing images, but the pre-trained API does not recognize their specific components. They have 1000 labeled images. Which path offers the fastest time-to-value with minimal coding?
⚠ Common exam trap
Google Cloud often tests the misconception that any cloud function or API call can be adapted to custom objects via post-processing, but the pre-trained Vision API's fixed label set cannot be extended without retraining, making AutoML the only low-code solution that actually learns new object classes.
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
✓
Use AutoML Vision for object detection
AutoML Vision for object detection is the fastest path because it requires no custom coding—users simply upload labeled images, and the platform automatically trains a model tailored to their custom components. This directly addresses the need to detect objects the pre-trained Vision API cannot recognize, while minimizing time-to-value compared to manual TensorFlow training or custom infrastructure setup.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Store images in BigQuery and use ML.PREDICT with a custom model
Why it's wrong here
BigQuery ML.PREDICT requires a model already trained and imported, and BigQuery ML does not natively train image object-detection models, so this path cannot produce the detector. It is tempting because ML.PREDICT gives SQL-based inference over stored data, which suits tabular models, not custom image detection.
- ✓
Use AutoML Vision for object detection
Why this is correct
AutoML Vision object detection trains on your labelled images and handles training infrastructure automatically, requiring no model code. With 1000 labelled images it satisfies the custom-component requirement while delivering the fastest time-to-value compared with building and tuning a custom model.
- ✗
Use a Cloud Function to call the Vision API and post-process results
Why it's wrong here
A Cloud Function calling the pre-trained Vision API still returns only the pre-trained labels, so the custom components remain undetected regardless of post-processing. It is tempting because serverless glue code is cheap and quick, and it would suit augmenting or routing Vision API output when the pre-trained classes already match the requirement.
- ✗
Train a custom object detection model using TensorFlow on Vertex AI
Why it's wrong here
Building a TensorFlow detector on Vertex AI demands model architecture, training pipelines and tuning, so time-to-value is long and coding heavy. It is tempting because Vertex AI supports full custom training, which suits teams needing bespoke architectures or control beyond AutoML's limits, but not a low-code analyst with 1000 labelled images.
Go deeper
Related to this question
About these practice questions
This PMLE question is part of Courseiva's 775-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 PMLE practice question is part of Courseiva's free Google Cloud 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 PMLE exam.