I can't run my deployed Tensorflow Lite Model in Android Studio due to customized model?

Question

I was deploying my Tensorflow Lite model into my Android Studio. The application does run but when after I took a picture and tried to predict the result, the app crashes. It seems that it is due to the model I use since I'm using a customized trained model ? Here is what the model looks like after I imported it to my project. It had like 4 outputFeatures rather than from what I'm seeing in some guides which has only 1. Can please someone help me how to resolve this issue that'll be a huge lend of a hand for me.

EDIT: I tried changing the imageSize value to 320 which matches with the createFixedSize values. The application does RUN, produced a result and did not crash after I entered the image. However, It only displays the same class as a result every time I run the prediction, . I tried inputting different images hoping to get different class result but it does not work at all. I also tried printing some values to see if I can debug it but Im not sure what to do after.

I also entered the code of the project below for you guys can see.

Note: I'm heavily relying on source codes around the internet right now and my level of understanding is not that high skilled as a programmer but I'm familiar how to code in Java.

try {
   Tflite model = Tflite.newInstance(context);

   // Creates inputs for reference.
   TensorBuffer inputFeature0 = TensorBuffer.createFixedSize(new int[]{1, 320, 320, 3}, DataType.FLOAT32);
   inputFeature0.loadBuffer(byteBuffer);

   // Runs model inference and gets result.
   Signlanguage.Outputs outputs = model.process(inputFeature0);
   TensorBuffer outputFeature0 = outputs.getOutputFeature0AsTensorBuffer();
   // TensorBuffer outputFeature1 = outputs.getOutputFeature1AsTensorBuffer();
   // TensorBuffer outputFeature2 = outputs.getOutputFeature2AsTensorBuffer();
   // TensorBuffer outputFeature3 = outputs.getOutputFeature3AsTensorBuffer();

   // Releases model resources if no longer used.
   model.close();
   } catch (IOException e) {
   // TODO Handle the exception
}

And this is what my object looks like in my MainActivity.java

public class MainActivity extends AppCompatActivity {

TextView result, demoTxt, classified, clickHere;
ImageView imageView, arrowImage;
Button picture;

int imageSize = 320; // default image size


@Override
protected void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);
    setContentView(R.layout.activity_main);

    result = findViewById(R.id.result);
    imageView = findViewById(R.id.imageView);
    picture = findViewById(R.id.button);

    demoTxt = findViewById(R.id.demoText);
    clickHere = findViewById(R.id.click_here);
    arrowImage = findViewById(R.id.demoArrow);
    classified = findViewById(R.id.classified);

    demoTxt.setVisibility(View.VISIBLE);
    clickHere.setVisibility(View.GONE);
    arrowImage.setVisibility(View.VISIBLE);
    classified.setVisibility(View.GONE);
    result.setVisibility(View.GONE);

    picture.setOnClickListener(new View.OnClickListener(){
        @RequiresApi(api = Build.VERSION_CODES.M)
        @Override
            public void onClick(View view){
            //launch camera if we have permission
                if(checkSelfPermission(Manifest.permission.CAMERA)== PackageManager.PERMISSION_GRANTED){
                    Intent cameraIntent = new Intent(MediaStore.ACTION_IMAGE_CAPTURE);
                    startActivityForResult(cameraIntent,1);
                }else {
                    //request camera permission if we don't have
                    requestPermissions(new String[]{Manifest.permission.CAMERA},100);
                }
        }
    });
}

@Override
protected void onActivityResult(int requestCode, int resultCode, @Nullable Intent data) {
    if (requestCode ==1 && resultCode == RESULT_OK){
        Bitmap image = (Bitmap) data.getExtras().get("data");
        int dimension = Math.min(image.getWidth(),image.getHeight());
        image = ThumbnailUtils.extractThumbnail(image,dimension,dimension);
        imageView.setImageBitmap(image);

        demoTxt.setVisibility(View.GONE);
        clickHere.setVisibility(View.VISIBLE);
        arrowImage.setVisibility(View.GONE);
        classified.setVisibility(View.VISIBLE);
        result.setVisibility(View.VISIBLE);

        image = Bitmap.createScaledBitmap(image, imageSize, imageSize, false);
        classifyImage(image);

        System.out.println("image.getWidth1: "+image.getWidth());
        System.out.println("image.getHeight1: "+image.getHeight());
        System.out.println("dimension: "+dimension);
    }
    super.onActivityResult(requestCode, resultCode, data);
}


private void classifyImage(Bitmap image) {
    try{
        Tflite model = Tflite.newInstance(getApplicationContext());

        //create input for reference
        TensorBuffer inputFeature0 = TensorBuffer.createFixedSize(new int[]{1,320,320,3}, DataType.FLOAT32);
        ByteBuffer byteBuffer = ByteBuffer.allocateDirect(4 * imageSize * imageSize * 3);
        byteBuffer.order(ByteOrder.nativeOrder());

        //get 1D array of 224 * 224 pixels in image
        int[] intValue = new int[imageSize * imageSize];
        image.getPixels(intValue,0,image.getWidth(),0,0,image.getWidth(),image.getHeight());

        //iterate over pixels and extract R, G, B values, add to bytebuffer
        int pixel = 0;
        for(int i = 0; i<imageSize; i++){
            for(int j =0;j<imageSize;j++){
                int val= intValue[pixel++]; // RGB
                byteBuffer.putFloat(((val >> 16) & 0xFF) * (1.f/255.f));
                byteBuffer.putFloat(((val >> 8) & 0xFF) * (1.f/255.f));
                byteBuffer.putFloat((val & 0xFF) * (1.f/255.f));
            }
        }

        inputFeature0.loadBuffer(byteBuffer);

        //run model interface and gets result
        Tflite.Outputs outputs = model.process(inputFeature0);
        //model inferences
        TensorBuffer outputFeatures0 = outputs.getOutputFeature0AsTensorBuffer();
        //THIS IS WHAT IAM TRYING TO WORK
        TensorBuffer outputFeatures1 = outputs.getOutputFeature1AsTensorBuffer();
        TensorBuffer outputFeatures2 = outputs.getOutputFeature2AsTensorBuffer();
        TensorBuffer outputFeatures3 = outputs.getOutputFeature3AsTensorBuffer();

        //Inferences
        float[] confidence = outputFeatures0.getFloatArray();

        //find the index of the class with the biggest confidence
        int maxPos = 0;
        float maxConfidence = 0;
        for (int i = 0; i < confidence.length; i++){
            if(confidence[i] > maxConfidence){
                maxConfidence = confidence[i];
                maxPos = i;
            }
        }
        String[] classes = {"A","B","C","Catch","D","E","Emergency","F","Fear","Feel","Fine","G","H",
            "Help","ILoveYou","IReallyLoveYou","I","It","J","K","L","LiveLong","Love","M","Mine","Myself",
            "N","O","Okay","P","Q","R","S","Sorry","Stop","T","ThankYou","This","Time","Tremble","U","V",
            "W","Where","X","Y","Yes","You","Yours","Z"};
        result.setText(classes[maxPos]);
        result.setOnClickListener(new View.OnClickListener() {
            @Override
            public void onClick(View view) {
                //to search the sign language on internet
                startActivity(new Intent(Intent.ACTION_VIEW,
                        Uri.parse("https://www.google.com/search?q=Signs+"+result.getText())));
            }
        });

        model.close();

        }catch(IOException e){
        //  TODO Handle the exception
    }
}

I have no idea how to involve these ?inferences? in finding the index of the classes with confidences to be able to get the result.

This is the error whenever I click the button for predicting the given image was this from LogCat:

EDIT: This resolves the issue after I set the imageSize value to 320 but the prediction always predicts the same no matter what the image is inserted.

    022-05-04 21:25:33.677 21148-21148/com.example.tflite E/AndroidRuntime: FATAL EXCEPTION: main
Process: com.example.tflite, PID: 21148
java.lang.RuntimeException: Failure delivering result ResultInfo{who=null, request=1, result=-1, data=Intent { act=inline-data (has extras) }} to activity {com.example.tflite/com.example.tflite.MainActivity}: java.lang.IllegalArgumentException: The size of byte buffer and the shape do not match.


    Caused by: java.lang.IllegalArgumentException: The size of byte buffer and the shape do not match.
    // THE LINE FOR 119 IS inputFeature0.loadBuffer(byteBuffer);
    at com.example.tflite.MainActivity.classifyImage(MainActivity.java:119)
   // THE LINE FOR 90 IS classifyImage(image); which is outside the function.
    at com.example.tflite.MainActivity.onActivityResult(MainActivity.java:90)
    

These 2 lines were in blue highlight so I put them here.