Firebase Machine Learning is a mobile SDK that brings custom model deployment, AutoML Vision Edge, and Cloud Visions APIs to Android and iOS apps.
Firebase Machine Learning is a component of the Firebase suite of tools for cross-platform application development. Firebase Machine Learning was launched in June 2020, and grew out of firebase-mlkit. For ready-to-use on-device models, see google-mlkit.
Key capabilities
Host and deploy custom models
Use your own TensorFlow Lite models for on-device inference. Just deploy your model to Firebase, and we'll take care of hosting and serving it to your app. Firebase will dynamically serve the latest version of the model to your users, allowing you to regularly update them without having to push a new version of your app to users.
When you use Firebase ML with Remote Config, you can serve different models to different user segments, and with A/B Testing, you can run experiments to find the best performing model (see the iOS and Android guides).
Automatically train models
With Firebase ML and AutoML Vision Edge, you can easily train your own TensorFlow Lite image labeling models, which you can use in your app to recognize concepts in photographs. Upload training data—your own images and labels—and AutoML Vision Edge will use them to train a custom model in the cloud.
Production-ready for common use cases
Firebase ML comes with a set of ready-to-use APIs for common mobile use cases: recognizing text, labeling images, and identifying landmarks. Simply pass in data to the Firebase ML library and it gives you the information you need. These APIs leverage the power of Google Cloud Platform's machine learning technology to give you the highest level of accuracy.
Related tags
firebase firebase-mlkit firebase-remote-config firebase-ab-testing google-mlkit