TensorFlow Lite is an open-source deep learning framework to run TensorFlow models on-device. If you are new to TensorFlow Lite, we recommend that you first explore the pre-trained models and run the example apps below on a real device to see what TensorFlow Lite can do.
Detect objects in real time from a camera feed with a MobileNet model.
Answer any questions related to a given text with a MobileBERT model.
If you are a mobile developer without much experience with machine learning and TensorFlow, you can start by learning how to train a model and deploy to a mobile app with TensorFlow Lite Model Maker.
A quick start tutorial for Android. Train a flower classification model and deploy it to an Android application.
A quick start tutorial for iOS. Train a flower classification model and deploy it to an iOS application.
If you are already familiar with TensorFlow and interested in deploying to edge devices, then you can start with the below tutorial to learn how to convert a TensorFlow model to TensorFlow Lite format and optimize it for on-device inference.
A quick start end-to-end tutorial on converting and optimizing a TensorFlow model for on-device inference, then deploy it to an Android app.
Learn how to use TensorFlow Lite Model Maker to quickly create image classification models.
If you are interested in deploying a TensorFlow model to Linux-based IoT devices such as Raspberry Pi, then you can try out these tutorials on how to implement computer vision tasks on IoT devices.
Perform real-time image classification using images streamed from the Pi Camera.
Perform real-time object detection using images streamed from the Pi Camera.
If you are interested in deploying a TensorFlow model to microcontrollers which are much more resource constrained, then you can start with these tutorials that demonstrate an end-to-end workflow from developing a TensorFlow model to converting to a TensorFlow Lite format and deploying to a microcontroller with TensorFlow Lite Micro.
Train a tiny speech model that can detect simple hotwords.
Train a model that can recognize different gestures using accelerometer data.

After you have familiarized yourself with the workflow of training a TensorFlow model, converting it to a TensorFlow Lite format, and deploying it to mobile apps, you can learn more about TensorFlow Lite with the below materials:

  • Try out the different domain tutorials (e.g. vision, speech) from the left navigation bar. They show you how to train a model for a specific machine learning task, such as object detection or sentiment analysis.
  • Learn more about the development workflow in the TensorFlow Lite Guide. You can find in-depth information about TensorFlow Lite features, such as model conversion or model optimization.
  • Check out this free e-learning course on TensorFlow Lite.

Subscribe to the TensorFlow blog, YouTube channel, and Twitter for the latest updates.