ValueError: Sequence must have length 2, got 3.

[laizhui]

I try to train a SwinUNETR model on my own MRI dataset, using the code and model.pt file given at:
https://githubfast.com/Project-MONAI/research-contributions/tree/main/SwinUNETR/BRATS21

However, I got errors as follows:
`Traceback (most recent call last):
File "main.py", line 229, in
main()
File "main.py", line 104, in main
main_worker(gpu=0, args=args)
File "main.py", line 210, in main_worker
accuracy = run_training(
File "/home/zwlai/BRATS21/trainer.py", line 157, in run_training
train_loss = train_epoch(
File "/home/zwlai/BRATS21/trainer.py", line 32, in train_epoch
for idx, batch_data in enumerate(loader):
File "/opt/Anaconda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/opt/Anaconda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
return self._process_data(data)
File "/opt/Anaconda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/opt/Anaconda/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 "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/transform.py", line 89, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/transform.py", line 53, in _apply_transform
return transform(parameters)
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/croppad/dictionary.py", line 889, in call
box_start, box_end = self.cropper.compute_bounding_box(img=d[self.source_key])
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/croppad/array.py", line 744, in compute_bounding_box
spatial_size = np.asarray(compute_divisible_spatial_size(orig_spatial_size.tolist(), k=self.k_divisible))
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/utils.py", line 1293, in compute_divisible_spatial_size
k = fall_back_tuple(k, (1,) * len(spatial_shape))
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/utils/misc.py", line 189, in fall_back_tuple
user = ensure_tuple_rep(user_provided, ndim)
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/utils/misc.py", line 146, in ensure_tuple_rep
raise ValueError(f"Sequence must have length {dim}, got {len(tup)}.")
ValueError: Sequence must have length 2, got 3.

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

Traceback (most recent call last):
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/transform.py", line 89, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/transform.py", line 53, in apply_transform
return transform(parameters)
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/compose.py", line 173, in call
input = apply_transform(transform, input, self.map_items, self.unpack_items, self.log_stats)
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/transform.py", line 113, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.croppad.dictionary.CropForegroundd object at 0x7f79d6a06130>

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

Traceback (most recent call last):
File "/opt/Anaconda/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/opt/Anaconda/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/Anaconda/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 "/home/zwlai/.local/lib/python3.8/site-packages/monai/data/dataset.py", line 97, in getitem
return self._transform(index)
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/data/dataset.py", line 83, in _transform
return apply_transform(self.transform, data_i) if self.transform is not None else data_i
File "/home/zwlai/.local/lib/python3.8/site-packages/monai/transforms/transform.py", line 113, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f79d6a71a30>`

How should I fix this error?

And I want to change output labels from 3 to 5, what should I do?

Any comments would be highly appreciated.
Thank you very much.

[KumoLiu]

Hi @laizhui, from the error message, seems you specified wrong type of k_divisible.
Should be:
k_divisible=1
instead of:
k_divisible=[1]

MONAI/monai/utils/misc.py

Lines 274 to 275 in 8212458

	>>> fall_back_tuple([0], (32, 32))
	ValueError: Sequence must have length 2, got length 1.

Hope it helps, thanks!

[KumoLiu]

Could you please show me how you initialize CropForegroundd?

[laizhui]

Hi @KumoLiu
I'm sorry for the uncertain reply before.
This is how I initialize CropForegroundd.
transforms.CropForegroundd( keys=["image", "label"], source_key="image", k_divisible=[args.roi_x, args.roi_y, args.roi_z] ),
Thank you very much!

[KumoLiu]

Hi @laizhui, sorry for the late response.
As you can see from your code, you specified a k_divisible of length 3 when initializing, but your spatial size should only be 2 in length from the error message.

[bolgoff]

Hi @KumoLiu, I have the same problem as @laizhui.

def get_loader(batch_size, data_dir, json_list, fold, roi):
    data_dir = data_dir
    datalist_json = json_list
    train_files, validation_files = datafold_read(datalist=datalist_json, basedir=data_dir, fold=fold)
    train_transform = transforms.Compose(
        [
            transforms.LoadImaged(keys=["image", "label"]),
            transforms.ConvertToMultiChannelBasedOnBratsClassesd(keys="label"),
            transforms.CropForegroundd(
                keys=["image", "label"],
                source_key="image",
                k_divisible=[roi[0], roi[1], roi[2]],
            ),
            transforms.RandSpatialCropd(
                keys=["image", "label"],
                roi_size=[roi[0], roi[1], roi[2]],
                random_size=False,
            ),
            transforms.RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=0),
            transforms.RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=1),
            transforms.RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=2),
            transforms.NormalizeIntensityd(keys="image", nonzero=True, channel_wise=True),
            transforms.RandScaleIntensityd(keys="image", factors=0.1, prob=1.0),
            transforms.RandShiftIntensityd(keys="image", offsets=0.1, prob=1.0),
        ]
    )
    val_transform = transforms.Compose(
        [
            transforms.LoadImaged(keys=["image", "label"]),
            transforms.ConvertToMultiChannelBasedOnBratsClassesd(keys="label"),
            transforms.NormalizeIntensityd(keys="image", nonzero=True, channel_wise=True),
        ]
    )

    train_ds = data.Dataset(data=train_files, transform=train_transform)

    train_loader = data.DataLoader(
        train_ds,
        batch_size=batch_size,
        shuffle=True,
        num_workers=8,
        pin_memory=True,
    )
    val_ds = data.Dataset(data=validation_files, transform=val_transform)
    val_loader = data.DataLoader(
        val_ds,
        batch_size=1,
        shuffle=False,
        num_workers=8,
        pin_memory=True,
    )

    return train_loader, val_loader

I'm trying to predict tumor for only T1 image, but get the error above. I also tried to train model only on T1 images from BraTS-2021, but it didn't help(the same error). Thanks for reply

[KumoLiu]

Hi @bolgoff, could you please paste the whole error message? Thanks.

[TrushalGulhane]

ValueError: Sequence must have length 2, got 3.

[LianZifeng]

Hello, I have the same problem as you. How did you solve it? Is there a problem with the dataset or some other reason?

[baba1587]

I met same.

[baba1587]

Maybe you need add one channel dimension.

[LianZifeng]

Thanks for your answer. I solved the problem using the same method you suggested.