To import a TensorFlow Lite (TFLite) model: Use Android Studio ML Model Binding Note: Required Android Studio 4.1 or
The following sections contain some useful information for working with
To get started quickly writing your own Android code, we recommend using our To build the example in Android Studio, follow the instructions in Note: Additional Android applications demonstrating TensorFlow Lite in a variety Model, select the thread count, and decide whether to run on CPU, GPU, or via It allows the user to choose between a floating point or The demo app classifies frames in real-time, displaying the top most probableĬlassifications. Inference is performed using the TensorFlow Lite Java API and the The application can run either on device or emulator. To continuously classify whatever it sees from the device's rear-facing camera. TensorFlow Lite Android image classification To get started with TensorFlow Lite on Android, we recommend exploring the