Hi @umair13adil , I am new to flutter and working lo tflite andi prepared a app with detecting a leaf image through camera and gallery and i had converted the hdf5 model to tflite and using that tflite model with some label while testing/predicting the image i am getting an error like

Exception has occurred. PlatformException (PlatformException(error, Unsupported value: java.lang.IllegalArgumentException: Cannot copy between a TensorFlowLite tensor with shape [1, 38] and a Java object with shape [1, 40]., null)) in flutter Coulod any one help me

Thanks and Regards, Manikantha Sekhar.

I'm trying to use a custom model with the following properties:

The original model has these properties instead:

In theory, this should not be a problem as tflite is supposed to accept any TFLite model.

However, this error is thrown

E/AndroidRuntime(29968): Caused by: java.lang.IllegalArgumentException: Cannot copy from a TensorFlowLite tensor (Identity) with shape [1, 3, 6400, 85] to a Java object with shape [1, 80]

when I try to classify an image

Tflite.runModelOnFrame(
      bytesList: image.planes.map((plane) => plane.bytes).toList(),
    )

A similar error

E/AndroidRuntime( 2360): Caused by: java.lang.IllegalArgumentException: Cannot copy from a TensorFlowLite tensor (Identity) with shape [1, 3, 6400, 85] to a Java object with shape [1, 20, 20, 425]

is thrown when trying to detect an object

Tflite.detectObjectOnFrame(
      bytesList: image.planes.map((plane) => plane.bytes).toList(),
      model: "YOLO",
      imageHeight: 640,
      imageWidth: 640,
      imageMean: 0,
      imageStd: 255.0,
      anchors: [
        10,
        13,
        16,
        30,
        33,
        23,
        30,
        61,
        62,
        45,
        59,
        119,
        116,
        90,
        156,
        198,
        373,
        326
      ],
    )

Does anyone has any idea about why this could be happening?

Hi @umair13adil ,

I want to know some information regarding my app just i have created an app in flutter and i deployed a ml model into that app locally and working fine while taking the build its of more than 40 mb size in that my model is of 42mb size so its taking to large so i want to do i want to call my model from the server i was completed don't about that functionality could you help me in that .

Thanks & Regards, Manikantha Sekhar.