RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f12920a50a0>

[medicalpeppa]

---

epoch 1/5
1/2, train_loss: 0.8549
2/2, train_loss: 0.7164
epoch 1 average loss: 0.7856

epoch 2/5
1/2, train_loss: 0.8476
2/2, train_loss: 0.6748
epoch 2 average loss: 0.7612

RuntimeError Traceback (most recent call last)
/home/yangzherui/chenjianan/3D语义分割-vnet3D及unet3D/3d分类(2).ipynb 单元格 10 line 3
31 y_pred = torch.tensor([], dtype=torch.float32, device=device)
32 y = torch.tensor([], dtype=torch.long, device=device)
---> 33 for val_data in val_loader:
34 val_images, val_labels = val_data["image"].to(device), val_data["label"].to(device)
35 y_pred = torch.cat([y_pred, model(val_images)], dim=0)

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:633, in _BaseDataLoaderIter.next(self)
630 if self._sampler_iter is None:
631 # TODO(pytorch/pytorch#76750)
632 self._reset() # type: ignore[call-arg]
--> 633 data = self._next_data()
634 self._num_yielded += 1
635 if self._dataset_kind == _DatasetKind.Iterable and
636 self._IterableDataset_len_called is not None and
637 self._num_yielded > self._IterableDataset_len_called:

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:1345, in _MultiProcessingDataLoaderIter._next_data(self)
1343 else:
1344 del self._task_info[idx]
-> 1345 return self._process_data(data)

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:1371, in _MultiProcessingDataLoaderIter._process_data(self, data)
...
return apply_transform(self.transform, data_i) if self.transform is not None else data_i
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 171, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f12920a50a0>

This is my code:

data_dir = "/home/yangzherui/chenjianan/10-seg/10-seg-data/images2/pre-image" class_names = sorted(x for x in os.listdir(data_dir) if os.path.isdir(os.path.join(data_dir, x)))

num_class = len(class_names)
image_files = [
[os.path.join(data_dir, class_names[i], x ) for x in os.listdir(os.path.join(data_dir, class_names[i]))]
for i in range(num_class)
]
num_each = [len(image_files[i]) for i in range(num_class)]
image_files_list = []
image_class = []
for i in range(num_class):
image_files_list.extend(image_files[i])
image_class.extend([i] * num_each[i])
image_class = np.array(image_class, dtype=np.int64)

random.seed(2023)
templist = [i for i in zip(image_files_list, image_class)]
random.shuffle(templist)
image_files_list[:], image_class[:] = zip(*templist)
print(f"Total image count: {len(image_files_list)}")
print(f"Label names: {class_names}")
print(f"Label counts: {num_each}")
num_class = 2
train_transform = Compose(
[
LoadImageD(keys="image", image_only=True),
EnsureChannelFirstD(keys="image"),
ScaleIntensityRangeD(
keys="image",
a_min=-17.3,
a_max=1280.5,
b_min=0.0,
b_max=1.0,
clip=True,
),
OrientationD(keys="image", axcodes="RAS"),
SpacingD(keys="image", pixdim=(1, 1, 1), mode="bilinear"),
ResizeD(keys="image",spatial_size=(96,96,96)),
RandRotate90D(keys="image", prob=0.8, spatial_axes=[0, 2]),
]
)

val_transforms = Compose(
[
LoadImageD(keys="image", image_only=True),
EnsureChannelFirstD(keys="image"),
ScaleIntensityRangeD(
keys="image",
a_min=-17.3,
a_max=1280.5,
b_min=0.0,
b_max=1.0,
clip=True,
),
OrientationD(keys="image", axcodes="RAS"),
SpacingD(keys="image", pixdim=(1, 1, 1), mode="bilinear"),
ResizeD(keys="image",spatial_size=(96,96,96)),

]

)
post_pred = Compose([Activations(softmax=True)])
post_label = Compose([AsDiscrete(to_onehot=num_class)]) val_frac = 0.2
slicer = int(len(image_files_list)*val_frac)
train_files = [{"image": img, "label": label} for img, label in zip(image_files_list[:slicer], image_class[:slicer])]
val_files = [{"image": img, "label": label} for img, label in zip(image_files_list[-slicer:], image_class[-slicer:])]

tra_ds = Dataset(data=train_files, transform=train_transform)
tra_loader = DataLoader(tra_ds, batch_size=2, num_workers=4, pin_memory=torch.cuda.is_available())
val_ds = monai.data.Dataset(data=val_files, transform=val_transforms)
val_loader = DataLoader(val_ds, batch_size=2, num_workers=4, pin_memory=torch.cuda.is_available()) device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
#model = densenet121(spatial_dims=3, in_channels=1, out_channels=num_class).to(device)
model = resnet50(spatial_dims=3,n_input_channels=1,num_classes=num_class).to(device)
loss_function = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), 1e-5)
auc_metric = ROCAUCMetric()
max_epochs = 5
val_interval = 2
best_metric = -1
best_metric_epoch = -1
writer = SummaryWriter()
for epoch in range(max_epochs):
print("-" * 10)
print(f"epoch {epoch + 1}/{max_epochs}")
model.train()
epoch_loss = 0
step = 0
for batch_data in tra_loader:
step += 1
inputs, labels = batch_data["image"].to(device), batch_data["label"].to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_len = len(tra_ds) // tra_loader.batch_size
print(f"{step}/{epoch_len}, train_loss: {loss.item():.4f}")
writer.add_scalar("train_loss", loss.item(), epoch_len * epoch + step)
epoch_loss /= step
print(f"epoch {epoch + 1} average loss: {epoch_loss:.4f}")

if (epoch + 1) % val_interval == 0:
    model.eval()
    with torch.no_grad():
        y_pred = torch.tensor([], dtype=torch.float32, device=device)
        y = torch.tensor([], dtype=torch.long, device=device)
        for val_data in val_loader:
            val_images, val_labels = val_data["image"].to(device), val_data["label"].to(device)
            y_pred = torch.cat([y_pred, model(val_images)], dim=0)
            y = torch.cat([y, val_labels], dim=0)

        acc_value = torch.eq(y_pred.argmax(dim=1), y)
        acc_metric = acc_value.sum().item() / len(acc_value)
        y_onehot = [post_label(i) for i in decollate_batch(y, detach=False)]
        y_pred_act = [post_pred(i) for i in decollate_batch(y_pred)]
        auc_metric(y_pred_act, y_onehot)
        auc_result = auc_metric.aggregate()
        auc_metric.reset()
        del y_pred_act, y_onehot
        if acc_metric > best_metric:
            best_metric = acc_metric
            best_metric_epoch = epoch + 1
            torch.save(model.state_dict(), "best_metric_model_classification3d_dict.pth")
            print("saved new best metric model")
        print(
            "current epoch: {} current accuracy: {:.4f} current AUC: {:.4f} best accuracy: {:.4f} at epoch {}".format(
                epoch + 1, acc_metric, auc_result, best_metric, best_metric_epoch
            )
        )
        writer.add_scalar("val_accuracy", acc_metric, epoch + 1)

print(f"train completed, best_metric: {best_metric:.4f} at epoch: {best_metric_epoch}")
writer.close()

What's wrong with my code, and my monai version is 1.3.0.
Thank you very much.

[KumoLiu]

Hi @medicalpeppa, could you please paste the whole error message? Thanks!

[medicalpeppa]

Thank you for your response. And the whole error message is below:
epoch 1/5
1/2, train_loss: 0.8549
2/2, train_loss: 0.7164
epoch 1 average loss: 0.7856
epoch 2/5
1/2, train_loss: 0.8476
2/2, train_loss: 0.6748
epoch 2 average loss: 0.7612
RuntimeError Traceback (most recent call last)
/home/yangzherui/chenjianan/3D语义分割-vnet3D及unet3D/3d分类(2).ipynb 单元格 10 line 3
31 y_pred = torch.tensor([], dtype=torch.float32, device=device)
32 y = torch.tensor([], dtype=torch.long, device=device)
---> 33 for val_data in val_loader:
34 val_images, val_labels = val_data["image"].to(device), val_data["label"].to(device)
35 y_pred = torch.cat([y_pred, model(val_images)], dim=0)

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:633, in _BaseDataLoaderIter.next(self)
630 if self._sampler_iter is None:
631 # TODO(pytorch/pytorch#76750)
632 self._reset() # type: ignore[call-arg]
--> 633 data = self._next_data()
634 self._num_yielded += 1
635 if self._dataset_kind == _DatasetKind.Iterable and
636 self._IterableDataset_len_called is not None and
637 self._num_yielded > self._IterableDataset_len_called:

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:1345, in _MultiProcessingDataLoaderIter._next_data(self)
1343 else:
1344 del self._task_info[idx]
-> 1345 return self._process_data(data)

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:1371, in _MultiProcessingDataLoaderIter._process_data(self, data)
...
return apply_transform(self.transform, data_i) if self.transform is not None else data_i
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 171, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f12920a50a0>

[KumoLiu]

Hi @medicalpeppa, I don't see the most direct cause of the error in your error message, perhaps in the ellipses. Could you please help check it?

[medicalpeppa]

Thank you for your response. The whole error message is below:
RuntimeError Traceback (most recent call last)
/home/yangzherui/chenjianan/3D语义分割-vnet3D及unet3D/3d分类(2).ipynb 单元格 10 line 3
31 y_pred = torch.tensor([], dtype=torch.float32, device=device)
32 y = torch.tensor([], dtype=torch.long, device=device)
---> 33 for val_data in val_loader:
34 val_images, val_labels = val_data["image"].to(device), val_data["label"].to(device)
35 y_pred = torch.cat([y_pred, model(val_images)], dim=0)

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:633, in _BaseDataLoaderIter.next(self)
630 if self._sampler_iter is None:
631 # TODO(pytorch/pytorch#76750)
632 self._reset() # type: ignore[call-arg]
--> 633 data = self._next_data()
634 self._num_yielded += 1
635 if self._dataset_kind == _DatasetKind.Iterable and
636 self._IterableDataset_len_called is not None and
637 self._num_yielded > self._IterableDataset_len_called:

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:1345, in _MultiProcessingDataLoaderIter._next_data(self)
1343 else:
1344 del self._task_info[idx]
-> 1345 return self._process_data(data)

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/dataloader.py:1371, in _MultiProcessingDataLoaderIter._process_data(self, data)
1369 self._try_put_index()
1370 if isinstance(data, ExceptionWrapper):
-> 1371 data.reraise()
1372 return data

File ~/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/_utils.py:644, in ExceptionWrapper.reraise(self)
640 except TypeError:
641 # If the exception takes multiple arguments, don't try to
642 # instantiate since we don't know how to
643 raise RuntimeError(msg) from None
--> 644 raise exception

RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 141, in apply_transform
return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 98, in _apply_transform
return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/io/dictionary.py", line 162, in call
data = self._loader(d[key], reader)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/io/array.py", line 274, in call
raise RuntimeError(
RuntimeError: LoadImage cannot find a suitable reader for file: /home/yangzherui/chenjianan/10-seg/10-seg-data/images2/pre-image/freash/mask.
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.NumpyReader object at 0x7f12b221b670>, <monai.data.image_reader.PILReader object at 0x7f12b221b9d0>, <monai.data.image_reader.NibabelReader object at 0x7f12b221b790>].

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

Traceback (most recent call last):
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 141, in apply_transform
return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 98, in _apply_transform
return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/compose.py", line 335, in call
result = execute_compose(
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/compose.py", line 111, in execute_compose
data = apply_transform(
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 171, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.io.dictionary.LoadImaged object at 0x7f10c2d2e5b0>

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

[medicalpeppa]

I am sorry to disturb you. I try pip install 'monai[all]', and now I have another question: My data is in nii.gz format. The error message is below:
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 141, in apply_transform
return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 98, in _apply_transform
return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/io/dictionary.py", line 162, in call
data = self._loader(d[key], reader)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/io/array.py", line 255, in call
img = reader.read(filename)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/data/image_reader.py", line 241, in read
raise FileNotFoundError(f"no DICOMs in: {name}.")
FileNotFoundError: no DICOMs in: /home/yangzherui/chenjianan/10-seg/10-seg-data/images2/pre-image/freash/mask.

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

Traceback (most recent call last):
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 141, in apply_transform
return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 98, in _apply_transform
return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/compose.py", line 335, in call
result = execute_compose(
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/compose.py", line 111, in execute_compose
data = apply_transform(
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 171, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.io.dictionary.LoadImaged object at 0x7f90153db040>

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

Traceback (most recent call last):
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/data/dataset.py", line 112, in getitem
return self._transform(index)
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/data/dataset.py", line 98, in _transform
return apply_transform(self.transform, data_i) if self.transform is not None else data_i
File "/home/yangzherui/miniconda3/envs/yangzherui/lib/python3.9/site-packages/monai/transforms/transform.py", line 171, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f9015350340>

[KumoLiu]

Hi @medicalpeppa, from this error message, seems you didn't put the right path.

FileNotFoundError: no DICOMs in: /home/yangzherui/chenjianan/10-seg/10-seg-data/images2/pre-image/freash/mask.

You could specify the path to the file for "img" and "label", such as "/workspace/data/mask1.nii.gz"
train_files = [{"image": img, "label": label} for img, label in zip(image_files_list[:slicer], image_class[:slicer])]

Thanks!