Professional Machine Learning Engineer

By Google · Question Mode

QuestionQ35

Automating and orchestrating ML pipelines

You work for a social media company and want to build a no-code image-classification model for an iOS mobile application that identifies fashion accessories. You have a labeled dataset in Cloud Storage. You need to configure a training workflow that minimizes cost and delivers predictions with the lowest possible latency. What should you do?

Explanation

AutoML Edge image-classification models can be exported as Core ML .mlmodel files for use on iOS devices. Running the exported model directly in the application performs inference on-device, eliminating network latency and managed online-endpoint serving costs.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!