MONAI bundle SwinUNETR failing with TypeError #1894
Description
Describe the bug
There seems to be an with the MONAI bundle swin_unetr_btcv_segmentation_v0.5.6 not matching the expected signature in the MONAI library and erroring out while starting the server.
0.5.6 is the latest version of the bundle: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/monaitoolkit/models/monai_swin_unetr_btcv_segmentation?version=0.5.6
Server logs
[2026-02-26 09:40:51,926] [13732] [MainThread] [INFO] (main:154) - +++ Adding Inferer:: segmentation => <lib.infers.segmentation.Segmentation object at 0x0000015B7CD7D490>
[2026-02-26 09:40:52,176] [13732] [MainThread] [ERROR] (uvicorn.error:121) - Traceback (most recent call last):
File "D:\monailabel\Lib\site-packages\monai\utils\module.py", line 243, in instantiate
return component(**kwargs)
^^^^^^^^^^^^^^^^^^^
TypeError: SwinUNETR.init() got an unexpected keyword argument 'img_size'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "D:\monailabel\Lib\site-packages\starlette\routing.py", line 694, in lifespan
async with self.lifespan_context(app) as maybe_state:
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\fastapi\routing.py", line 201, in merged_lifespan
async with original_context(app) as maybe_original_state:
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python312\Lib\contextlib.py", line 210, in aenter
return await anext(self.gen)
^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monailabel\app.py", line 49, in lifespan
instance = app_instance()
^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monailabel\interfaces\utils\app.py", line 49, in app_instance
app = c(app_dir=app_dir, studies=studies, conf=conf)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\workspace\radiology\main.py", line 129, in init
super().init(
File "D:\monailabel\Lib\site-packages\monailabel\interfaces\app.py", line 101, in init
self._infers = self.init_infers()
^^^^^^^^^^^^^^^^^^
File "D:\workspace\radiology\main.py", line 162, in init_infers
i = BundleInferTask(b, self.conf)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monailabel\tasks\infer\bundle.py", line 121, in init
network = self.bundle_config.get_parsed_content(self.const.key_network_def(), instantiate=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monai\bundle\config_parser.py", line 290, in get_parsed_content
return self.ref_resolver.get_resolved_content(id=id, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monai\bundle\reference_resolver.py", line 193, in get_resolved_content
return self._resolve_one_item(id=id, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monai\bundle\reference_resolver.py", line 171, in _resolve_one_item
self.resolved_content[id] = item.instantiate() if kwargs.get("instantiate", True) else item
^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monai\bundle\config_item.py", line 292, in instantiate
return instantiate(modname, mode, **args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\monailabel\Lib\site-packages\monai\utils\module.py", line 253, in instantiate
raise RuntimeError(
RuntimeError: Failed to instantiate component 'monai.networks.nets.swin_unetr.SwinUNETR' with keywords: spatial_dims,img_size,in_channels,out_channels,feature_size,use_checkpoint
set 'mode=debug' to enter the debugging mode.
[2026-02-26 09:40:52,176] [13732] [MainThread] [ERROR] (uvicorn.error:59) - Application startup failed. Exiting.
To Reproduce
Steps to reproduce the behavior:
- Install MONAI label from github: https://monai.readthedocs.io/projects/label/en/latest/installation.html#from-github
- https://github.com/Project-MONAI/MONAILabel/tree/6ed8f8c6113db723cc79ad71ac51b952bb860fac/sample-apps/radiology. Do the following:
monailabel start_server
--app workspace/radiology
--studies workspace/images
--conf models segmentation
--conf bundles swin_unetr_btcv_segmentation_v0.5.6
Expected behavior
A clear and concise description of what you expected to happen.
Environment
( I have a incompatible GPU compute at the moment but will upgrade to a different compute) This error however is independent of the compute.
Printing GPU config...
Found GPU0 Quadro P620 which is of cuda capability 6.1.
Minimum and Maximum cuda capability supported by this version of PyTorch is
(7.0) - (12.0)
Please install PyTorch with a following CUDA
configurations: 12.6 following instructions at
https://pytorch.org/get-started/locally/
Quadro P620 with CUDA capability sm_61 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_70 sm_75 sm_80 sm_86 sm_90 sm_100 sm_120.
If you want to use the Quadro P620 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
Num GPUs: 1
Has CUDA: True
CUDA version: 12.8
cuDNN enabled: True
NVIDIA_TF32_OVERRIDE: None
TORCH_ALLOW_TF32_CUBLAS_OVERRIDE: None
cuDNN version: 91002
Current device: 0
Library compiled for CUDA architectures: ['sm_70', 'sm_75', 'sm_80', 'sm_86', 'sm_90', 'sm_100', 'sm_120']
GPU 0 Name: Quadro P620
GPU 0 Is integrated: False
GPU 0 Is multi GPU board: False
GPU 0 Multi processor count: 4
GPU 0 Total memory (GB): 2.0
GPU 0 CUDA capability (maj.min): 6.1```
Additional context
I even tried older versions but they seem to be broken too.