1# TF Lite Android Image Classifier App Example 2 3A simple Android example that demonstrates image classification using the camera. 4 5## Building in Android Studio with TensorFlow Lite AAR from MavenCentral. 6The build.gradle is configured to use TensorFlow Lite's nightly build. 7 8If you see a build error related to compatibility with Tensorflow Lite's Java API (example: method X is 9undefined for type Interpreter), there has likely been a backwards compatible 10change to the API. You will need to pull new app code that's compatible with the 11nightly build and may need to first wait a few days for our external and internal 12code to merge. 13 14## Building from Source with Bazel 15 161. Follow the [Bazel steps for the TF Demo App](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#bazel): 17 18 1. [Install Bazel and Android Prerequisites](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#install-bazel-and-android-prerequisites). 19 It's easiest with Android Studio. 20 21 - You'll need at least SDK version 23. 22 - Make sure to install the latest version of Bazel. Some distributions 23 ship with Bazel 0.5.4, which is too old. 24 - Bazel requires Android Build Tools `28.0.0` or higher. 25 - You also need to install the Android Support Repository, available 26 through Android Studio under `Android SDK Manager -> SDK Tools -> 27 Android Support Repository`. 28 29 2. [Edit your `WORKSPACE`](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#edit-workspace) 30 to add SDK and NDK targets. 31 32 NOTE: As long as you have the SDK and NDK installed, the `./configure` 33 script will create these rules for you. Answer "Yes" when the script asks 34 to automatically configure the `./WORKSPACE`. 35 36 - Make sure the `api_level` in `WORKSPACE` is set to an SDK version that 37 you have installed. 38 - By default, Android Studio will install the SDK to `~/Android/Sdk` and 39 the NDK to `~/Android/Sdk/ndk-bundle`. 40 412. Build the app with Bazel. The demo needs C++11: 42 43 ```shell 44 bazel build -c opt //tensorflow/lite/java/demo/app/src/main:TfLiteCameraDemo 45 ``` 46 473. Install the demo on a 48 [debug-enabled device](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#install): 49 50 ```shell 51 adb install bazel-bin/tensorflow/lite/java/demo/app/src/main/TfLiteCameraDemo.apk 52 ``` 53