RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7fd33e7bcd60>

[poG515]

monai version:0.9.1

epoch 1/50
/opt/conda/lib/python3.8/site-packages/monai/data/utils.py:766: UserWarning: Modifying image pixdim from [1.2000012 0.9375 0.9375 0. ] to [ 1.20000124 0.9375 0.9375 442.02576912]
warnings.warn(f"Modifying image pixdim from {pixdim} to {norm}")
/opt/conda/lib/python3.8/site-packages/monai/data/utils.py:766: UserWarning: Modifying image pixdim from [1.2000012 0.9375 0.9375 0. ] to [ 1.20000124 0.9375 0.9375 452.94337004]
warnings.warn(f"Modifying image pixdim from {pixdim} to {norm}")
Traceback (most recent call last):
File "Densenet_ADvCN.py", line 147, in
main()
File "Densenet_ADvCN.py", line 92, in main
for batch_data in train_loader:
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 652, in next
data = self._next_data()
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1347, in _next_data
return self._process_data(data)
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1373, in _process_data
data.reraise()
File "/opt/conda/lib/python3.8/site-packages/torch/_utils.py", line 434, in reraise
raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/conda/lib/python3.8/site-packages/monai/transforms/transform.py", line 98, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/opt/conda/lib/python3.8/site-packages/monai/transforms/transform.py", line 62, in _apply_transform
return transform(parameters)
File "/opt/conda/lib/python3.8/site-packages/monai/transforms/intensity/array.py", line 450, in call
img = convert_to_tensor(img, track_meta=get_track_meta())
TypeError: convert_to_tensor() got an unexpected keyword argument 'track_meta'

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

Traceback (most recent call last):
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
data = fetcher.fetch(index)
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/lib/python3.8/site-packages/monai/apps/datasets.py", line 536, in getitem
img = apply_transform(self.transform, img)
File "/opt/conda/lib/python3.8/site-packages/monai/transforms/transform.py", line 122, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7fd33e7bcd60>

This is my code

file_x = "/user-data/CN/*/MP-RAGE/*/*/*.nii"
images_x = glob.glob(file_x)
file_y = "/user-data/AD/*/MP-RAGE/*/*/*.nii"
images_y = glob.glob(file_y)

x1 = round(0.7 * len(images_x))  # num_train_x
x2 = len(images_x) - x1  # num_val_x
y1 = round(0.7 * len(images_y))  # num_train_y
y2 = len(images_y) - y1  # num_val_y

train_images_x = images_x[:x1]
val_images_x = images_x[-x2:]

train_images_y = images_y[:y1]
val_images_y = images_y[-y2:]

train_images = train_images_x + train_images_y
val_images = val_images_x + val_images_y

train_labels = np.concatenate((np.zeros(x1, dtype=np.int64), np.ones(y1, dtype=np.int64)))
val_labels = np.concatenate((np.zeros(x2, dtype=np.int64), np.ones(y2, dtype=np.int64)))


# Define transforms
train_transforms = Compose([ScaleIntensity(), AsChannelFirst(), Resize((180, 180, 180)), RandRotate90(), EnsureType()])
val_transforms = Compose([ScaleIntensity(), AsChannelFirst(), Resize((180, 180, 180)), EnsureType()])

post_pred = Compose([EnsureType(), Activations(softmax=True)])
post_label = Compose([EnsureType(), AsDiscrete(to_onehot=2)])

#Define image dataset, data loader
check_dataset = NiftiDataset(image_files=train_images, labels=train_labels, transform=train_transforms)
check_loader = DataLoader(check_dataset,  batch_size=2, shuffle=True, num_workers=1, pin_memory=torch.cuda.is_available())
im, label = monai.utils.misc.first(check_loader)
print(type(im), im.shape, label)
os.system("pause")

[KumoLiu]

Hi @poG515, NiftiDataset had been removed from monai0.5.0, you can confirm it from CHANGELOG. So try to confirm your monai version?

from monai.config import print_config
print_config()