What is custom model in ML?

ML Kit can use TensorFlow Lite models hosted remotely using Firebase, bundled with the app binary, or both . By hosting a model on Firebase, you can update the model without releasing a new app version, and you can use Remote Config and A/B Testing to dynamically serve different models to different sets of users.

You can configure ML Kit to automatically download model updates when the user’s device is idle or charging, or has a Wi-Fi connection. Use the TensorFlow Lite model for inference. Use ML Kit’s custom model APIs in your iOS or Android app to perform inference with your Firebase-hosted or app-bundled model.

Follow these steps.