TypeError when using lung_nodule_ct_detection

Describe the bug
I have downloaded the lung_nodule_ct_detection bundle (0.5.9) and I try to follow the steps of https://docs.monai.io/projects/monai-deploy-app-sdk/en/latest/notebooks/tutorials/06_monai_bundle_app.html# to create a MAP using the downloaded bundle. Unfortunately, I fail already when trying to run the app locally, i.e., using something like:

app = LungNoduleDetectionApp()

app.run(
    input=str(input_dir),
    output=str(output_dir),
    model=str(model_dir),
)

This fails with the following error:

Going to initiate execution of operator MonaiBundleInferenceOperator
Executing operator MonaiBundleInferenceOperator (Process ID: 2193, Operator ID: 44d6d5d5-79ea-497e-bed5-469f23959f76)
/home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/monai/utils/deprecate_utils.py:321: FutureWarning: monai.transforms.io.dictionary LoadImaged.__init__:image_only: Current default value of argument `image_only=False` has been deprecated since version 1.1. It will be changed to `image_only=True` in version 1.3.
  warn_deprecated(argname, msg, warning_category)
/home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/monai/utils/deprecate_utils.py:221: FutureWarning: monai.transforms.utility.dictionary EnsureChannelFirstd.__init__:meta_key_postfix: Argument `meta_key_postfix` has been deprecated since version 0.9. not needed if image is type `MetaTensor`.
  warn_deprecated(argname, msg, warning_category)
Traceback (most recent call last):
  File "/home/da-for/code/byoai-workshop/workshops/monai-application-package/lung_nodule_ct_detection/run_model_locally.py", line 22, in <module>
    app.run(
  File "/home/da-for/code/byoai-workshop/workshops/monai-application-package/lung_nodule_ct_detection/app.py", line 52, in run
    super().run(*args, **kwargs)
  File "/home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/monai/deploy/core/application.py", line 429, in run
    executor_obj.run()
  File "/home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/monai/deploy/core/executors/single_process_executor.py", line 125, in run
    op.compute(op_exec_context.input_context, op_exec_context.output_context, op_exec_context)
  File "/home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/monai/deploy/operators/monai_bundle_inference_operator.py", line 579, in compute
    outputs: Any = self.predict(data=first_input, **other_inputs)  # Use type Any to quiet MyPy complaints.
  File "/home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/monai/deploy/operators/monai_bundle_inference_operator.py", line 604, in predict
    return self._inferer(inputs=data, network=self._model_network, *args, **kwargs)
  File "/home/da-for/code/byoai-workshop/workshops/monai-application-package/lung_nodule_ct_detection/scripts/detection_inferer.py", line 55, in __call__
    self.detector.network = network
  File "/home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1304, in __setattr__
    raise TypeError("cannot assign '{}' as child module '{}' "
TypeError: cannot assign 'monai.deploy.core.models.torch_model.TorchScriptModel' as child module 'network' (torch.nn.Module or None expected)

Environment
Windows 11 with WSL2 and Ubuntu 22.04

Ensuring you use the relevant python executable, please paste the output of:

MONAI version: 1.2.0
Numpy version: 1.22.2
Pytorch version: 1.13.1+cu117
MONAI flags: HAS_EXT = False, USE_COMPILED = False, USE_META_DICT = False
MONAI rev id: c33f1ba588ee00229a309000e888f9817b4f1934
MONAI __file__: /home/da-for/.pyenv/versions/monai/lib/python3.10/site-packages/monai/__init__.py

Optional dependencies:
Pytorch Ignite version: 0.4.9
ITK version: NOT INSTALLED or UNKNOWN VERSION.
Nibabel version: 4.0.1
scikit-image version: 0.21.0
Pillow version: 10.0.0
Tensorboard version: NOT INSTALLED or UNKNOWN VERSION.
gdown version: NOT INSTALLED or UNKNOWN VERSION.
TorchVision version: 0.14.1+cu117
tqdm version: 4.66.1
lmdb version: NOT INSTALLED or UNKNOWN VERSION.
psutil version: 5.9.5
pandas version: 2.0.3
einops version: NOT INSTALLED or UNKNOWN VERSION.
transformers version: NOT INSTALLED or UNKNOWN VERSION.
mlflow version: NOT INSTALLED or UNKNOWN VERSION.
pynrrd version: NOT INSTALLED or UNKNOWN VERSION.

For details about installing the optional dependencies, please visit:
    https://docs.monai.io/en/latest/installation.html#installing-the-recommended-dependencies

System: Linux
Linux version: Ubuntu 22.04.3 LTS
Platform: Linux-6.1.21.1-microsoft-standard-WSL2+-x86_64-with-glibc2.35
Processor: x86_64
Machine: x86_64
Python version: 3.10.4
Process name: python
Command: ['/home/da-for/.pyenv/versions/monai/bin/python', '-c', 'import monai; monai.config.print_debug_info()']
Open files: []
Num physical CPUs: 2
Num logical CPUs: 4
Num usable CPUs: 4
CPU usage (%): [7.8, 7.3, 8.2, 100.0]
CPU freq. (MHz): 2304
Load avg. in last 1, 5, 15 mins (%): [0.7, 1.1, 0.3]
Disk usage (%): 27.3
Avg. sensor temp. (Celsius): UNKNOWN for given OS
Total physical memory (GB): 15.6
Available memory (GB): 12.2
Used memory (GB): 3.1

Start with scripts/detection_inferer.py at the call method shown in the traceback, then trace how MonaiBundleInferenceOperator supplies the model to it. Reproduce the local lung_nodule_ct_detection run with the listed MONAI, PyTorch, and Python versions. Done means the app runs past model assignment without the TypeError and the documented local workflow completes.