Answer-first summary for fast verification
Answer: Use the model's REST API to send image data and receive predictions.
The most appropriate way to integrate a custom vision model into a mobile application is by using the model's REST API. This allows the mobile application to send image data to the model and receive predictions in response. The REST API provides a standardized and secure way to interact with the model, without the need to expose the model's code or trained weights. Embedding the model's code directly into the mobile application or running inference locally on the mobile device may not be feasible or efficient due to resource constraints and security concerns. Re-training the model using the mobile application's data may not be necessary if the model has already been trained and evaluated for the desired task.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
Your team has developed a custom image classification model using Azure AI Vision to classify images of different types of fruits. You need to consume this model in a mobile application. Which of the following is the most appropriate way to integrate the custom vision model into the mobile application?
A
Embed the model's code directly into the mobile application.
B
Use the model's REST API to send image data and receive predictions.
C
Download the model's trained weights and run inference locally on the mobile device.
D
Re-train the model using the mobile application's data to improve its performance.