Answer-first summary for fast verification
Answer: Train the model by using AutoML Edge, and export it as a Core ML model. Configure your mobile application to use the .mlmodel file directly.
The correct answer is B. AutoML Edge provides a no-code interface for training models, and it allows the model to be exported as a Core ML model, which is optimized for iOS devices. This configuration minimizes latency by enabling the model to run directly on the device, thereby avoiding the latency and potential costs associated with network calls to a cloud endpoint. Core ML is specifically designed for iOS, ensuring efficient inference and low latency. Additionally, running the model locally helps minimize operational costs.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You are a machine learning engineer at a social media company tasked with developing a real-time image classification model for an iOS mobile application to identify fashion accessories. You have a pre-labeled dataset stored in Cloud Storage that you will use for training. Your objectives are to create the model using a no-code solution, ensure the solution minimizes operational costs, and achieve the lowest possible latency for predictions. What should you do?
A
Train the model by using AutoML, and register the model in Vertex AI Model Registry. Configure your mobile application to send batch requests during prediction.
B
Train the model by using AutoML Edge, and export it as a Core ML model. Configure your mobile application to use the .mlmodel file directly.
C
Train the model by using AutoML Edge, and export the model as a TFLite model. Configure your mobile application to use the .tflite file directly.
D
Train the model by using AutoML, and expose the model as a Vertex AI endpoint. Configure your mobile application to invoke the endpoint during prediction.