java - How to use a TensorFlow model in Android app

Question

I have trained an image recognition model in Python and I would like to use it in my Android app.

Currently, in Python, I use the model by providing the file path to the image and the model:

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", required=True,
    help="path to trained model model")
ap.add_argument("-i", "--image", required=True,
    help="path to input image")
args = vars(ap.parse_args())

# load the image
image = cv2.imread(args["image"])
orig = image.copy()

# pre-process the image for classification
image = cv2.resize(image, (28, 28))
image = image.astype("float") / 255.0
image = img_to_array(image)
image = np.expand_dims(image, axis=0)

I run this in the cmd. I would like to be able to use this model in my Java main after letting the user take a picture.

Currently, the image is saved in a Bitmap format, although I don't know how to send the image taken by the user to the model and use the prediction in my Java file later on. Here's the code to the Java part:

public class MainActivity extends Activity
{
    private static final int CAMERA_REQUEST = 1888;
    private ImageView imageView;
    private static final int MY_CAMERA_PERMISSION_CODE = 100;

    @Override
    public void onCreate(Bundle savedInstanceState)
    {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);
        this.imageView = (ImageView)this.findViewById(R.id.imageView1);
        Button photoButton = (Button) this.findViewById(R.id.button1);
        photoButton.setOnClickListener(new View.OnClickListener()
        {
            @Override
            public void onClick(View v)
            {
                if (checkSelfPermission(Manifest.permission.CAMERA) != PackageManager.PERMISSION_GRANTED)
                {
                    requestPermissions(new String[]{Manifest.permission.CAMERA}, MY_CAMERA_PERMISSION_CODE);
                }
                else
                {
                    Intent cameraIntent = new Intent(android.provider.MediaStore.ACTION_IMAGE_CAPTURE);
                    startActivityForResult(cameraIntent, CAMERA_REQUEST);
                }
            }
        });
    }

    @Override
    public void onRequestPermissionsResult(int requestCode, @NonNull String[] permissions, @NonNull int[] grantResults)
    {
        super.onRequestPermissionsResult(requestCode, permissions, grantResults);
        if (requestCode == MY_CAMERA_PERMISSION_CODE)
        {
            if (grantResults[0] == PackageManager.PERMISSION_GRANTED)
            {
                Toast.makeText(this, "camera permission granted", Toast.LENGTH_LONG).show();
                Intent cameraIntent = new Intent(android.provider.MediaStore.ACTION_IMAGE_CAPTURE);
                startActivityForResult(cameraIntent, CAMERA_REQUEST);
            }
            else
            {
                Toast.makeText(this, "camera permission denied", Toast.LENGTH_LONG).show();
            }
        }
    }

    @Override
    protected void onActivityResult(int requestCode, int resultCode, Intent data)
    {
        if (requestCode == CAMERA_REQUEST && resultCode == Activity.RESULT_OK)
        {
            Bitmap photo = (Bitmap) data.getExtras().get("data");
            imageView.setImageBitmap(photo);
        }
    }
}

I saw some examples of TensorFlow models being loaded in Java files, but none of them were about images.

question from:https://stackoverflow.com/questions/65646839/how-to-use-a-tensorflow-model-in-android-app

Answer 1

Waitting for answers