Caused by: java.lang.IllegalArgumentException: Cannot copy from a TensorFlowLite tensor (MobilenetV1/Predictions/Reshape_1) with shape [1, 1001] to a Java object with shape [1, 1001, 4].

[Sk-Mattes]

Body

I have a Flutter project in which an image is stored as a jpeg on the local storage. However, I always get an error as soon as I try to run the tflite model on the image. I would appreciate some help!
Kind regards!

Log with Error:
FATAL EXCEPTION: AsyncTask https://github.com/orgs/community/discussions/2
E/AndroidRuntime( 7781): Process: de.seekamp.security_system_software, PID: 7781
E/AndroidRuntime( 7781): java.lang.RuntimeException: An error occurred while executing doInBackground()
E/AndroidRuntime( 7781): at android.os.AsyncTask$3.done(AsyncTask.java:353)
E/AndroidRuntime( 7781): at java.util.concurrent.FutureTask.finishCompletion(FutureTask.java:383)
E/AndroidRuntime( 7781): at java.util.concurrent.FutureTask.setException(FutureTask.java:252)
E/AndroidRuntime( 7781): at java.util.concurrent.FutureTask.run(FutureTask.java:271)
E/AndroidRuntime( 7781): at android.os.AsyncTask$SerialExecutor$1.run(AsyncTask.java:245)
E/AndroidRuntime( 7781): at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1162)
E/AndroidRuntime( 7781): at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:636)
E/AndroidRuntime( 7781): at java.lang.Thread.run(Thread.java:764)
E/AndroidRuntime( 7781): Caused by: java.lang.IllegalArgumentException: Cannot copy from a TensorFlowLite tensor (MobilenetV1/Predictions/Reshape_1) with shape [1, 1001] to a Java object with shape [1, 1001, 4].
E/AndroidRuntime( 7781): at org.tensorflow.lite.TensorImpl.throwIfDstShapeIsIncompatible(TensorImpl.java:464)
E/AndroidRuntime( 7781): at org.tensorflow.lite.TensorImpl.copyTo(TensorImpl.java:226)
E/AndroidRuntime( 7781): at org.tensorflow.lite.NativeInterpreterWrapper.run(NativeInterpreterWrapper.java:278)
E/AndroidRuntime( 7781): at org.tensorflow.lite.InterpreterImpl.runForMultipleInputsOutputs(InterpreterImpl.java:101)
E/AndroidRuntime( 7781): at org.tensorflow.lite.Interpreter.runForMultipleInputsOutputs(Interpreter.java:95)
E/AndroidRuntime( 7781): at sq.flutter.tflite.TflitePlugin$RunSSDMobileNet.runTflite(TflitePlugin.java:710)
E/AndroidRuntime( 7781): at sq.flutter.tflite.TflitePlugin$TfliteTask.doInBackground(TflitePlugin.java:507)
E/AndroidRuntime( 7781): at sq.flutter.tflite.TflitePlugin$TfliteTask.doInBackground(TflitePlugin.java:481)
E/AndroidRuntime( 7781): at android.os.AsyncTask$2.call(AsyncTask.java:333)
E/AndroidRuntime( 7781): at java.util.concurrent.FutureTask.run(FutureTask.java:266)
E/AndroidRuntime( 7781): ... 4 more

My Code:

Future<bool> detectPeople(File file) async {

  initTFLite();
 
  var recognitions = await Tflite.detectObjectOnImage( //error coming up here!
    numBoxesPerBlock: 2,
    path: file.path,
    model: "SSDMobileNet",
    imageMean: 127.5,
    imageStd: 127.5,
    threshold: 0.4, 
    numResultsPerClass: 1,
  );


  for (var recog in recognitions!) {
    if (recog["detectedClass"] == "person") {
      return true;
    }
  }
  await Tflite.close();

  return false;
}

initTFLite() async{
  await Tflite.loadModel(
    model: "mobilenet_v1_1.0_224.tflite",
    labels: "mobilenet_v1_1.0_224.txt",
    isAsset: true,
    numThreads: 1,
    useGpuDelegate: false,
  );
}

Guidelines

• I have read and understood this category's guidelines before making this post.