transform.Invertd raise error

[YingdiZhang]

thanks for the great job.
I am using monai in a 3d segmentation task. In my test code, When I want to save the network prediction result in original data spacing and orientation, an error occured. And I have no idea how it comes:

Traceback (most recent call last):
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/transform.py", line 89, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/transform.py", line 53, in _apply_transform
return transform(parameters)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/spatial/dictionary.py", line 555, in inverse
transform = self.get_most_recent_transform(d, key)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/inverse.py", line 148, in get_most_recent_transform
self.check_transforms_match(transform)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/inverse.py", line 138, in check_transforms_match
raise RuntimeError(f"Error inverting the most recently applied invertible transform {xform_name} {xform_id}.")
RuntimeError: Error inverting the most recently applied invertible transform Spacingd 139908762272528.

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

Traceback (most recent call last):
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/transform.py", line 89, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/transform.py", line 53, in _apply_transform
return transform(parameters)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/post/dictionary.py", line 648, in call
inverted = self.transform.inverse(input_dict)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/compose.py", line 183, in inverse
data = apply_transform(t.inverse, data, self.map_items, self.unpack_items, self.log_stats)
File "/home/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/transform.py", line 113, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <bound method Spacingd.inverse of <monai.transforms.spatial.dictionary.Spacingd object at 0x7f3f0c138bb0>>

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

Traceback (most recent call last):
File "/data/zyd/beifen_xinsuoqu_/MedSeg/MedSeg/test/Task906Tester.py", line 804, in
t906_tester.test(
File "/data/zyd/beifen_xinsuoqu_/MedSeg/MedSeg/test/Task906Tester.py", line 193, in test
test_data = [self.post_trans_save(i) for i in decollate_batch(test_data)] # 保存原尺度
File "/data/zyd/beifen_xinsuoqu_/MedSeg/MedSeg/test/Task906Tester.py", line 193, in
test_data = [self.post_trans_save(i) for i in decollate_batch(test_data)] # 保存原尺度
File "/home/zyd/anaconda3/envs/med/lib/python3.9/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/zyd/anaconda3/envs/med/lib/python3.9/site-packages/monai/transforms/transform.py", line 113, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.post.dictionary.Invertd object at 0x7f3f0c1488b0>

And my test code is like this:
test_transform = Compose([
LoadImaged(keys=["image", "label"]),
EnsureChannelFirstd(keys=["image", "label"]),
Spacingd(
keys=["image", "label"],
pixdim=(1.0, 1.0, 1.0),
mode=("bilinear", "nearest")
),
Orientationd(keys=["image", "label"], axcodes="RAS"),
ScaleIntensityRanged(keys=["image"], a_min=-324, a_max=1453,
b_min=0.0, b_max=1.0, clip=True),
CastToTyped(
keys=["image", "label"],
dtype=(np.float32, np.uint8)
),
EnsureTyped(keys=["image", "label"])
]
)
post_trans_save = Compose(
[
EnsureTyped(keys="pred"), #
Invertd(
keys="pred", # invert the pred data field, also support multiple fields
transform=transform, # self.transform,
orig_keys="image", # "label", # # get the previously applied self.transforms information on the image data field,
# then invert pred based on this information. we can use same info
# for multiple fields, also support different orig_keys for different fields
meta_keys="pred_meta_dict", # key field to save inverted meta data, every item maps to keys
orig_meta_keys="image_meta_dict", # "label_meta_dict", # # get the meta data from image_meta_dict field when inverting,
# for example, may need the affine to invert Spacingd transform,
# multiple fields can use the same meta data to invert
meta_key_postfix="meta_dict", # if meta_keys=None, use "{keys}{meta_key_postfix}" as the meta key,
# if orig_meta_keys=None, use "{orig_keys}{meta_key_postfix}",
# otherwise, no need this arg during inverting
nearest_interp=False, # don't change the interpolation mode to "nearest" when inverting transforms
# to ensure a smooth output, then execute AsDiscreted transform
to_tensor=True # convert to PyTorch Tensor after inverting
),
AsDiscreted(keys="pred", argmax=True, to_onehot=None),
SaveImaged(keys="pred", meta_keys="pred_meta_dict", output_dir=self.pred_output_folder,
output_postfix="seg", resample=False, output_ext='.nii.gz',
separate_folder=False)
]
)
with torch.no_grad():
for (idx, test_data) in enumerate(tqdm(self.test_loader)):
inputs = test_data["image"].to(device)
test_data["pred"] = sliding_window_inference(
inputs, roi_size, sw_batch_size, self.model, overlap=overlap,
mode='gaussian',
device='cpu'
)
test_outputs = [self.post_trans_pred(i) for i in decollate_batch(pred_for_dice)]
test_labels = [self.post_trans_label(i) for i in decollate_batch(label_for_dice)]
test_data = [self.post_trans_save(i) for i in decollate_batch(test_data)] # 保存原尺度

[Nic-Ma]

Hi @YingdiZhang ,

I think you can try to run this tutorial example:
https://github.com/Project-MONAI/tutorials/blob/main/3d_segmentation/torch/unet_inference_dict.py#L70
Then adapt to your program to see where is not correct?

Thanks.