Using the image captioning model in Android

Following the same simplicity considerations, we'll develop a new Android app with a minimal UI and focus on how to use the model in Android:

1. Create a new Android app called Image2Text, add compile 'org.tensorflow:tensorflow-android:+' to the end of your app build.gradle file's dependencies, create an assets folder, and drag and drop to it the image2text_frozen_transformed.pb model file, the word_counts.txt file, and a few test image files.
2. Add an ImageView and a button to the activity_main.xml file:

<ImageView
    android:id="@+id/imageview"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    app:layout_constraintBottom_toBottomOf="parent"
    app:layout_constraintHorizontal_bias="0.0"
    app:layout_constraintLeft_toLeftOf="parent"
    app:layout_constraintRight_toRightOf="parent"
    app:layout_constraintTop_toTopOf="parent"
    app:layout_constraintVertical_bias="1.0"/>


<Button
    android:id="@+id/button...