Cannot copy from a TensorFlowLite tensor (StatefulPartitionedCall:1) with shape [1, 10] to a Java object with shape [1, 10, 4].

[GiuseppeTallariti]

I’ve trained a custom TensorFlow Lite model and am using it through the tflite package. However, when I activate the camera, the app crashes after a while. The error message is: E/AndroidRuntime(31106): Caused by: java.lang.IllegalArgumentException: Cannot copy from a TensorFlowLite tensor (StatefulPartitionedCall:1) with shape [1, 10] to a Java object with shape [1, 10, 4].

I noticed that this is a common issue, as is reported in #180.

If it helps, below is a portion of the code I wrote,

Future<void> initializeCamera() async {
  controller = CameraController(
    widget.cameras[0], ResolutionPreset.low,
    enableAudio: false,
    imageFormatGroup: Platform.isAndroid
        ? ImageFormatGroup.yuv420
        : ImageFormatGroup.bgra8888, // for iOS
  );
  try {
    await controller.initialize();
    if (!mounted) return;

    setState(() {});

    String? res = await Tflite.loadModel(
      model: "assets/ssd_mobilenet_v2_320x320.tflite",
      labels: "assets/labels.txt",
      numThreads: 1,
      isAsset: true,
      useGpuDelegate: false,
    );

    controller.startImageStream((CameraImage img) {
      imageCount++;
      if (imageCount % 10 == 0) {
        imageCount = 0;
        Tflite.detectObjectOnFrame(
          bytesList: img.planes.map((plane) {
            return plane.bytes;
          }).toList(),
          model: "SSDMobileNet",
          imageHeight: img.height,
          imageWidth: img.width,
          imageMean: 127.5,
          imageStd: 127.5,
          rotation: 90,
          threshold: 0.5,
        ).then((value) {
          print('$value');
        });
      }
    });
  }
}