Can someone help me with the custom TF Lite model and Flutter using google_mlkit_object_detection: 0.13.0

Currently, I use the code below to try getting the detected objects and assign labels to them:

 Future<void> labelImage(File imageFile) async {
    final modelPath = await getModelPath('assets/ml/model.tflite');
    final InputImage inputImage = InputImage.fromFile(imageFile);
    const mode = DetectionMode.single;

    final options = LocalObjectDetectorOptions(
      mode: mode,
      modelPath: modelPath,
      classifyObjects: true,
      multipleObjects: true,
      maximumLabelsPerObject: 39,
    );

    final objectDetector = ObjectDetector(options: options);

    final List<DetectedObject> objects =
        await objectDetector.processImage(inputImage);
}

• In IOS, I can only see one object with an actual label Shorts while the rest of the objects have label with “Entitiy” as the text.
• In Android, all the detected objects have the empty list of labels.

Here’s the codes I made following the Google CodeLab with Model Maker

import tensorflow as tf
assert tf.__version__.startswith('2')

from tflite_model_maker import image_classifier
from tflite_model_maker.image_classifier import DataLoader
from tflite_model_maker.config import ExportFormat
from tflite_model_maker import model_spec

data_dir="D:\images_group_selected"

BATCH_SIZE = 4
EPOCHS = 8

data = DataLoader.from_folder(data_dir)

train_data, rest_data = data.split(0.8)
validation_data, test_data = rest_data.split(0.5)

model = image_classifier.create(
  train_data, 
  validation_data=validation_data, 
  epochs=EPOCHS, 
  train_whole_model=True, 
  batch_size=BATCH_SIZE,
  model_spec=model_spec.get('mobilenet_v2'),
  shuffle=True)

model.summary()

model.export(export_dir='.', export_format=ExportFormat.TFLITE)
model.export(export_dir='.', export_format=ExportFormat.LABEL)

model.evaluate_tflite('model.tflite', test_data)

In my data structure, each directory would contain all the data belongs to a class (a label)

class1
-- image_class1_1.jpg
-- image_class1_2.jpg
class2
-- image_class2_1.jpg
-- image_class2_2.jpg
...

I suspect that since I created an image classifier, it does not work well with the ObjectDetector in Flutter. I really appreciate any advice about this issue.