Skip to content
πŸ“± Custom Object Detection with Core ML (not Real-Time)
Java Python
Branch: master
Clone or download
bourdakos1 Merge pull request #2 from stspanho/fix/box-predictions-pointer-size
The size of the box predictions pointer size should be 4.
Latest commit 6197304 Jun 2, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
.idea fix up drawing Apr 13, 2019
app The size of the box predictions pointer size should be 4. Jun 1, 2019
gradle/wrapper initial commit Apr 12, 2019
.gitignore initial commit Apr 12, 2019
LICENSE Initial commit Apr 12, 2019 update readme Apr 12, 2019
build.gradle initial commit Apr 12, 2019
gradlew initial commit Apr 12, 2019
gradlew.bat initial commit Apr 12, 2019
settings.gradle initial commit Apr 12, 2019

Object Detection Android App

You can find an in depth walkthrough for training a TensorFlow lite model here.


git clone the repo and cd into it by running the following command:

git clone
cd object-detection-android

Install Android Studio

The recommended way to develop applications for Android is by using Android Studio, which can be downloaded here

Open the project with Android Studio

Launch Android Studio and choose Open an existing Android Studio project

In the file selector, choose object-detection-android.

You will get a Gradle Sync popup, the first time you open the project, asking about using gradle wrapper. Click OK.

Set up an Android device

You can't load the app from android studio onto your phone unless you activate developer mode and USB Debugging. This is a one time setup process.

Follow these instructions.

Add your model files to the project

Copy the model_android directory generated from the classification walkthrough and paste it into the object-detection-android/app/src/main/assets folder of this repo.

Run the app

In Android Studio run a Gradle sync so the build system can find your files.

Then hit play to start the build and install process.

You can’t perform that action at this time.