Remember Intent/Camera?
     • We used implicit intent to take pictures and get 
      the image back. 
                                      We want to use 
                                      AI to detect 
                                      what’s in it!
     TensorFlow Lite
   TensorFlow Lite
   • Use a pre-trained model or train one.
      Using TF Lite in Android
      • Get a pre-trained model – Download and copy 
        (model and labels files) into the “app/assets” folder.
                     https://www.tensorflow.org/lite/models 
      • Gradle – edit build.gradle (module:app)
        dependencies {
            implementation('org.tensorflow:tensorflow-lite:0.0.0-nightly') { changing = true }
            implementation('org.tensorflow:tensorflow-lite-gpu:0.0.0-nightly') { changing = true }
            implementation('org.tensorflow:tensorflow-lite-support:0.0.0-nightly') { changing = true }
        }
        android {
            aaptOptions {
                noCompress "tflite"
                noCompress "lite"
            }
        }
     Android Code
     • Step 1 – Prepare the model “Interpreter”
    AssetFileDescriptor afd = 
    getAssets().openFd("mobilenet_v1_1.0_224_quant.tflite");
    FileInputStream fis = new FileInputStream(afd.getFileDescriptor());
    FileChannel fc = fis.getChannel();
    MappedByteBuffer mbb = fc.map(FileChannel.MapMode.READ_ONLY, 
    afd.getStartOffset(), afd.getLength());
    Interpreter interpreter = new Interpreter(mbb);