ML codelabs

Stay organized with collections Save and categorize content based on your preferences.

Try these codelabs to learn hands-on how Firebase can help you use TensorFlowLite models more easily and effectively.

Digit classification (introduction to model deployment)

Screenshot of digit classification app

Learn how to use Firebase's model deployment features by building an app thatrecognizes handwritten digits. Deploy TensorFlow Lite models withFirebase ML, analyze model performance withPerformance Monitoring, and test modeleffectiveness withA/B Testing.

iOS+Android

Sentiment analysis

Screenshot of sentiment analysis app

In this codelab, you use your own training data to fine-tune an existing textclassification model that identifies the sentiment expressed in a passage oftext. Then, you deploy the model usingFirebase ML and compare the accuracyof the old and new models withA/B Testing.

iOS+Android

Content recommendation

Screenshot of content recommendation app

Recommendation engines let you personalize experiences to individual users,presenting them with more relevant and engaging content. Rather than buildingout a complex pipeline to power this feature, this codelab shows how you canimplement a content recommendation engine for an app by training and deployingan on-device ML model.

iOS+Android

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-03-04 UTC.