can not find a suitable reader for file:

[caoshiwen1]

Loading dataset:   0%|          | 0/24 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\transforms\transform.py", line 92, in apply_transform
    return _apply_transform(transform, data, unpack_items)
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\transforms\transform.py", line 60, in _apply_transform
    return transform(parameters)
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\transforms\io\dictionary.py", line 128, in __call__
    data = self._loader(d[key], reader)
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\transforms\io\array.py", line 201, in __call__
    f"can not find a suitable reader for file: {filename}.\n"
RuntimeError: can not find a suitable reader for file: ('G:\\deep-learn\\deep-learning\\pytorch_classification\\WORK\\BTCV-3D-Unet-Transformer\\UNETR\\BTCV\\dataset\\dataset0\\imagesTr\\img0001.nii.gz',).
    Please install the reader libraries, see also the installation instructions:
    https://docs.monai.io/en/latest/installation.html#installing-the-recommended-dependencies.
   The current registered: [<monai.data.image_reader.ITKReader object at 0x00000110C8A42B48>, <monai.data.image_reader.NumpyReader object at 0x00000110C8A42BC8>, <monai.data.image_reader.PILReader object at 0x00000110C8A42C88>, <monai.data.image_reader.NibabelReader object at 0x00000110C8A3FFC8>].


The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "G:/deep-learn/deep-learning/pytorch_classification/WORK/BTCV-3D-Unet-Transformer/UNETR/BTCV/main.py", line 246, in <module>
    main()
  File "G:/deep-learn/deep-learning/pytorch_classification/WORK/BTCV-3D-Unet-Transformer/UNETR/BTCV/main.py", line 103, in main
    main_worker(gpu=0, args=args)
  File "G:/deep-learn/deep-learning/pytorch_classification/WORK/BTCV-3D-Unet-Transformer/UNETR/BTCV/main.py", line 120, in main_worker
    loader = get_loader(args)
  File "G:\deep-learn\deep-learning\pytorch_classification\WORK\BTCV-3D-Unet-Transformer\UNETR\BTCV\utils\data_utils.py", line 166, in get_loader
    num_workers=args.workers,
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\data\dataset.py", line 605, in __init__
    self._cache: List = self._fill_cache()
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\data\dataset.py", line 630, in _fill_cache
    desc="Loading dataset",
  File "C:\Users\Wu\AppData\Roaming\Python\Python37\site-packages\tqdm\std.py", line 1178, in __iter__
    for obj in iterable:
  File "C:\Users\Wu\anaconda3\lib\multiprocessing\pool.py", line 748, in next
    raise value
  File "C:\Users\Wu\anaconda3\lib\multiprocessing\pool.py", line 121, in worker
    result = (True, func(*args, **kwds))
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\data\dataset.py", line 646, in _load_cache_item
    item = apply_transform(_xform, item)
  File "C:\Users\Wu\anaconda3\lib\site-packages\monai\transforms\transform.py", line 116, in apply_transform
    raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.io.dictionary.LoadImaged object at 0x00000110C8A42E08>

进程已结束，退出代码为 1

[Nic-Ma]

Hi @caoshiwen1 ,

Thanks for your interest here.
I think maybe you need to add "\" in the filename?
G:\deep-learn\deep-learning\pytorch_classification\WORK\BTCV-3D-Unet-Transformer\UNETR\BTCV\dataset\dataset0\imagesTr\img0001.nii.gz
to be:
G:\\deep-learn\\deep-learning\\pytorch_classification\\WORK\\BTCV-3D-Unet-Transformer\\UNETR\\BTCV\\dataset\\dataset0\\imagesTr\\img0001.nii.gz

I verified it locally, seems it can be supported by NibabelReader.

Thanks.

[akansh12]

Try
pip install 'monai[all]'
and then restart your runtime if you are working on Jupyter Notebooks. Sometimes all the dependencies are not installed and hence MONAI cannot read many image formats.

Thanks
Akansh
(www.akansh12.github.io)

[ImranNust]

Thanks, Akansh12! Your suggested method solved my problem.

[vksastry]

This works !

[mahdics68]

Hi, I am using monai for UNET for 2D image segmentation. For training the model, I had a problem with reading and loading .tif format images, which I solved it by defining a class to open them and convert to numpy array.
now, for testing the model, I get an error with seems related to "saver" part which belongs to "SaveImage" as a transforms in monai. the error is this:

/scratch1/users/menayat/conda/mambaforg/envs/main/lib/python3.10/site-packages/monai/metrics/utils.py:219: UserWarning: y should be a binarized tensor.
warnings.warn(f"{name} should be a binarized tensor.")
Traceback (most recent call last):
File "/usr/users/menayat/code/UNET/UNET_livecell_test.py", line 85, in
test_UNET_2d((int(roi_w), int(roi_h)), model_name)
File "/usr/users/menayat/code/UNET/UNET_livecell_test.py", line 68, in test_UNET_2d
saver(val_output)
File "/scratch1/users/menayat/conda/mambaforg/envs/main/lib/python3.10/site-packages/monai/transforms/io/array.py", line 435, in call
kw = self.fname_formatter(meta_data, self)
File "/scratch1/users/menayat/conda/mambaforg/envs/main/lib/python3.10/site-packages/monai/data/folder_layout.py", line 22, in default_name_formatter
subject = metadict[monai.utils.ImageMetaKey.FILENAME_OR_OBJ] if metadict else getattr(saver, "_data_index", 0)
KeyError: 'filename_or_obj'

Do you have any idea what should I do here? thanks in advance

[KumoLiu]

Hi @mahdics68, I think you could try LoadImage to load .tif format and check metadata by using data.meta. Here is a simple example.

from monai.transforms import LoadImage

data = LoadImage(image_only=True)(data_path)
print(data.meta)
print(type(data)) --> <class 'monai.data.meta_tensor.MetaTensor'>

Thanks!

[mahdics68]

thank you so much for your help. but the issue is that I already tried LoadImage and got some error about suitable reader related to PIL reader. my impression was that LoadImage cannot read .tif images! now I am stucked! :D

[KumoLiu]

Hi @mahdics68, if you tried to load .tif format, maybe you should use WSIReader instead of PILReader. Could you please share your code and error message so I can take a deep look at it?

MONAI/monai/data/wsi_reader.py

Line 273 in eb6bbe8

class WSIReader(BaseWSIReader):

Thanks!

[XiShuFan]

This may be the unsuitable numpy version.

I change my numpy version from 1.24.4 to 1.21.4, and the error disappered

[763053441]

Try
pip install Nibabel

[yloufzzf]

it works, thx, :D