RuntimeError: Error Resize getting the most recently applied invertible transform Orientation #1035

neerajamaha · 2022-10-03T13:11:24Z

neerajamaha
Oct 3, 2022

Hi all,

I have trained a model for lung segmentation using MONAI Label, where inputs are MRI exams, and the model is a DeepEdit application. When I try to run inferences on a new lung MRI dataset for model validation, I am getting the following error:

I have gotten this error before but thought the issue was because I was trying to run an inference on an image that the model was already trained on, so there were duplicate IDs for the same exam. However, this current trained model has not been exposed to this new dataset, so I'm not sure what the issue is. Any help with this is appreciated!

Thank you so much,
Neeraja

tangy5 · 2022-10-03T16:35:51Z

tangy5
Oct 3, 2022
Maintainer

Hi @neerajamaha , based on the logs, the errors are caused by the inverse transform after prediction. The code tries to recover the prediction back to its original image space with invert transformation, those transform are determined accordingly by pre-transforms.

It seems the Resize transform inverse has some issue, e.g., data orientation.
The problem might be related to the data, since it's MRI, the original deepedit transforms might be changed. You could dig into the pre-transforms in the infer task, or post the transform and we can investigate more.
Thank you for using MONAI Label!

0 replies

Hirriririir · 2023-05-26T15:00:08Z

Hirriririir
May 26, 2023

Hi @tangy5, I have encountered the same problem here. Could you please help me?

Basically, I am trying to use my own pretrained model for auto-segmentation in MONAIlabel. The preprocessing, postprocessing, and sliding window inference methods worked very well in the conventional Jupyter Notebook approach. However, this same code does not work in MONAIlabel.

def pre_transforms(self, data=None) -> Sequence[Callable]:
        return [
            LoadImaged(keys="image", reader="ITKReader"),
            EnsureTyped(keys="image", device=data.get("device") if data else None),
            EnsureChannelFirstd(keys="image"),
            Spacingd(keys="image", mode="bilinear", pixdim=[0.7813000082969666, 0.7813000082969666, 4.0], dtype=torch.float32, allow_missing_keys=True),
            NormalizeIntensityd(keys="image", nonzero=True, channel_wise=True),
        ]

def inferer(self, data=None) -> Inferer:
        return SlidingWindowInfererAdapt(roi_size=(336, 336, 88),
                                    sw_batch_size=1,
                                    overlap=0.625,
                                    mode="gaussian",
                                    cache_roi_weight_map=False,
                                    progress=False)
        

def post_transforms(self, data=None) -> Sequence[Callable]:
        
        train_transforms = Compose([
            LoadImaged(keys="image", reader="ITKReader"),
            EnsureTyped(keys="image", dtype=torch.float32),
            EnsureChannelFirstd(keys="image"),
            Spacingd(keys="image", mode="bilinear", pixdim=[0.7813000082969666, 0.7813000082969666, 4.0], allow_missing_keys=True),
            NormalizeIntensityd(keys="image", nonzero=True, channel_wise=True),

        ])
        
        
        return [
            EnsureTyped(keys="pred", device=data.get("device") if data else None),
            Activationsd(keys="pred", softmax=True),
            AsDiscreted(keys="pred", argmax=True),  
            #Restored(keys="pred", ref_image="image"),       
            Invertd(keys="pred", orig_keys="image", transform=train_transforms, nearest_interp=False, meta_key_postfix="meta_dict")
            
        ]

The terminal always stopped at the 'Invertd' step (invertible transform SpatialResample 139624824560896 != 139623799946544.). I have tried your suggestions, such as adding Orientationd(keys='img', axcodes='RAS') or using different MRI scans, but the process still corrupts.

If I replace 'Invertd' with 'Restored(keys='pred', ref_image='image')', I get very weird results.

[2023-05-26 22:32:32,850] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.app:37) - Initializing App from: /home/hua/Muscle_seg/apps/radiology; studies: /home/hua/Muscle_seg/datasets/Thigh_muscles; conf: {'models': 'segmentation_muscle', 'skip_trainers': 'true'}
[2023-05-26 22:32:33,046] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for MONAILabelApp Found: <class 'main.MyApp'>
[2023-05-26 22:32:33,049] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_3d.Deepgrow3D'>
[2023-05-26 22:32:33,049] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_spine.LocalizationSpine'>
[2023-05-26 22:32:33,049] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation.Segmentation'>
[2023-05-26 22:32:33,050] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_vertebra.LocalizationVertebra'>
[2023-05-26 22:32:33,051] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation_spleen.SegmentationSpleen'>
[2023-05-26 22:32:33,051] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation_vertebra.SegmentationVertebra'>
[2023-05-26 22:32:33,052] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_2d.Deepgrow2D'>
[2023-05-26 22:32:33,052] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation_muscle.SegmentationMuscle'>
[2023-05-26 22:32:33,052] [1610] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepedit.DeepEdit'>
[2023-05-26 22:32:33,052] [1610] [MainThread] [INFO] (main:93) - +++ Adding Model: segmentation_muscle => lib.configs.segmentation_muscle.SegmentationMuscle
[2023-05-26 22:32:33,427] [1610] [MainThread] [INFO] (main:96) - +++ Using Models: ['segmentation_muscle']
[2023-05-26 22:32:33,427] [1610] [MainThread] [INFO] (monailabel.interfaces.app:135) - Init Datastore for: /home/hua/Muscle_seg/datasets/Thigh_muscles
[2023-05-26 22:32:33,428] [1610] [MainThread] [INFO] (monailabel.datastore.local:130) - Auto Reload: True; Extensions: ['*.nii.gz', '*.nii', '*.nrrd', '*.jpg', '*.png', '*.tif', '*.svs', '*.xml']
[2023-05-26 22:32:33,429] [1610] [MainThread] [INFO] (monailabel.datastore.local:577) - Invalidate count: 0
[2023-05-26 22:32:33,429] [1610] [MainThread] [INFO] (monailabel.datastore.local:151) - Start observing external modifications on datastore (AUTO RELOAD)
[2023-05-26 22:32:33,472] [1610] [MainThread] [INFO] (main:126) - +++ Adding Inferer:: segmentation_muscle => <lib.infers.segmentation_muscle.SegmentationMuscle object at 0x7efcfd371f40>
[2023-05-26 22:32:33,472] [1610] [MainThread] [INFO] (main:191) - {'segmentation_muscle': <lib.infers.segmentation_muscle.SegmentationMuscle object at 0x7efcfd371f40>, 'Histogram+GraphCut': <monailabel.scribbles.infer.HistogramBasedGraphCut object at 0x7efcfd371dc0>, 'GMM+GraphCut': <monailabel.scribbles.infer.GMMBasedGraphCut object at 0x7efcf0105220>}
[2023-05-26 22:32:33,472] [1610] [MainThread] [INFO] (monailabel.utils.sessions:51) - Session Path: /home/hua/.cache/monailabel/sessions
[2023-05-26 22:32:33,472] [1610] [MainThread] [INFO] (monailabel.utils.sessions:52) - Session Expiry (max): 3600
[2023-05-26 22:32:33,473] [1610] [MainThread] [INFO] (monailabel.interfaces.app:469) - App Init - completed
[2023-05-26 22:32:33,473] [timeloop] [INFO] Starting Timeloop..
[2023-05-26 22:32:33,473] [1610] [MainThread] [INFO] (timeloop:60) - Starting Timeloop..
[2023-05-26 22:32:33,473] [timeloop] [INFO] Registered job <function MONAILabelApp.on_init_complete.<locals>.run_scheduler at 0x7efcf010e160>
[2023-05-26 22:32:33,473] [1610] [MainThread] [INFO] (timeloop:42) - Registered job <function MONAILabelApp.on_init_complete.<locals>.run_scheduler at 0x7efcf010e160>
[2023-05-26 22:32:33,474] [timeloop] [INFO] Timeloop now started. Jobs will run based on the interval set
[2023-05-26 22:32:33,474] [1610] [MainThread] [INFO] (timeloop:63) - Timeloop now started. Jobs will run based on the interval set
[2023-05-26 22:32:33,474] [1610] [MainThread] [INFO] (uvicorn.error:62) - Application startup complete.
[2023-05-26 22:32:33,474] [1610] [MainThread] [INFO] (uvicorn.error:217) - Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
[2023-05-26 22:32:36,674] [1610] [MainThread] [INFO] (monailabel.endpoints.infer:161) - Infer Request: {'model': 'segmentation_muscle', 'image': 'THIGH_013_0002', 'device': 'NVIDIA GeForce RTX 3080 Laptop GPU', 'result_extension': '.nrrd', 'result_dtype': 'uint8', 'client_id': 'user-xyz'}
[2023-05-26 22:32:36,675] [1610] [MainThread] [INFO] (monailabel.tasks.infer.basic_infer:277) - Infer Request (final): {'device': 'cuda', 'model': 'segmentation_muscle', 'image': '/home/hua/Muscle_seg/datasets/Thigh_muscles/THIGH_013_0002.nii.gz', 'result_extension': '.nrrd', 'result_dtype': 'uint8', 'client_id': 'user-xyz', 'description': 'A pre-trained model for volumetric (3D) segmentation of the spleen from CT image'}
monai.transforms.io.dictionary LoadImaged.__init__:image_only: Current default value of argument `image_only=False` has been deprecated since version 1.1. It will be changed to `image_only=True` in version 1.3.
[2023-05-26 22:32:36,676] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:76) - PRE - Run Transform(s)
[2023-05-26 22:32:36,676] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:77) - PRE - Input Keys: ['device', 'model', 'image', 'result_extension', 'result_dtype', 'client_id', 'description', 'image_path']
[2023-05-26 22:32:38,593] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - PRE - Transform (LoadImaged): Time: 1.9161; image: torch.Size([512, 512, 16])(torch.float32)
[2023-05-26 22:32:39,512] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - PRE - Transform (EnsureTyped): Time: 0.919; image: torch.Size([512, 512, 16])(torch.float32)
[2023-05-26 22:32:39,512] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - PRE - Transform (EnsureChannelFirstd): Time: 0.0002; image: torch.Size([1, 512, 512, 16])(torch.float32)
[2023-05-26 22:32:40,191] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - PRE - Transform (Spacingd): Time: 0.6782; image: torch.Size([1, 538, 538, 91])(torch.float32)
[2023-05-26 22:32:40,254] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - PRE - Transform (NormalizeIntensityd): Time: 0.0627; image: torch.Size([1, 538, 538, 91])(torch.float32)
[2023-05-26 22:32:40,254] [1610] [MainThread] [INFO] (monailabel.tasks.infer.basic_infer:480) - Inferer:: cuda => SlidingWindowInfererAdapt => {'roi_size': (336, 336, 88), 'sw_batch_size': 1, 'overlap': 0.625, 'mode': gaussian, 'sigma_scale': 0.125, 'padding_mode': constant, 'cval': 0.0, 'sw_device': None, 'device': None, 'progress': False, 'cpu_thresh': None, 'buffer_steps': None, 'buffer_dim': -1, 'roi_weight_map': None}
[2023-05-26 22:32:40,254] [1610] [MainThread] [INFO] (monailabel.tasks.infer.basic_infer:418) - Infer model path: /home/hua/Muscle_seg/apps/radiology/model/pretrained_segmentation_muscle.pt
[2023-05-26 22:33:01,637] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:76) - POST - Run Transform(s)
[2023-05-26 22:33:01,638] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:77) - POST - Input Keys: ['device', 'model', 'image', 'result_extension', 'result_dtype', 'client_id', 'description', 'image_path', 'image_meta_dict', 'latencies', 'pred']
[2023-05-26 22:33:01,638] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - POST - Transform (EnsureTyped): Time: 0.0001; image: torch.Size([1, 538, 538, 91])(torch.float32); pred: torch.Size([12, 538, 538, 91])(torch.float32)
[2023-05-26 22:33:01,646] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - POST - Transform (Activationsd): Time: 0.0076; image: torch.Size([1, 538, 538, 91])(torch.float32); pred: torch.Size([12, 538, 538, 91])(torch.float32)
[2023-05-26 22:33:01,649] [1610] [MainThread] [INFO] (monailabel.interfaces.utils.transform:122) - POST - Transform (AsDiscreted): Time: 0.003; image: torch.Size([1, 538, 538, 91])(torch.float32); pred: torch.Size([1, 538, 538, 91])(torch.float32)
[2023-05-26 22:33:01,652] [1610] [MainThread] [ERROR] (uvicorn.error:434) - Exception in ASGI application
Traceback (most recent call last):
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/transform.py", line 103, in apply_transform
    return _apply_transform(transform, data, unpack_items)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/transform.py", line 67, in _apply_transform
    return transform(parameters)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/spatial/dictionary.py", line 452, in inverse
    d[key] = self.spacing_transform.inverse(cast(torch.Tensor, d[key]))
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/spatial/array.py", line 505, in inverse
    return self.sp_resample.inverse(data)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/spatial/array.py", line 218, in inverse
    transform = self.pop_transform(data)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/inverse.py", line 321, in pop_transform
    return self.get_most_recent_transform(data, key, check, pop=True)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/inverse.py", line 303, in get_most_recent_transform
    self.check_transforms_match(all_transforms[-1])
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/inverse.py", line 270, in check_transforms_match
    raise RuntimeError(
RuntimeError: Error SpatialResample getting the most recently applied invertible transform SpatialResample 139624824560896 != 139623799946544.

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

Traceback (most recent call last):
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/uvicorn/protocols/http/h11_impl.py", line 429, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/uvicorn/middleware/proxy_headers.py", line 78, in __call__
    return await self.app(scope, receive, send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/fastapi/applications.py", line 276, in __call__
    await super().__call__(scope, receive, send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/applications.py", line 122, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/middleware/errors.py", line 184, in __call__
    raise exc
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/middleware/errors.py", line 162, in __call__
    await self.app(scope, receive, _send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/middleware/cors.py", line 84, in __call__
    await self.app(scope, receive, send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
    raise exc
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
    await self.app(scope, receive, sender)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/fastapi/middleware/asyncexitstack.py", line 21, in __call__
    raise e
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
    await self.app(scope, receive, send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/routing.py", line 718, in __call__
    await route.handle(scope, receive, send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/routing.py", line 276, in handle
    await self.app(scope, receive, send)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/starlette/routing.py", line 66, in app
    response = await func(request)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/fastapi/routing.py", line 237, in app
    raw_response = await run_endpoint_function(
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/fastapi/routing.py", line 163, in run_endpoint_function
    return await dependant.call(**values)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monailabel/endpoints/infer.py", line 180, in api_run_inference
    return run_inference(background_tasks, model, image, session_id, params, file, label, output)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monailabel/endpoints/infer.py", line 162, in run_inference
    result = instance.infer(request)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monailabel/interfaces/app.py", line 307, in infer
    result_file_name, result_json = task(request)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monailabel/tasks/infer/basic_infer.py", line 317, in __call__
    data = self.run_post_transforms(data, self.post_transforms(data))
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monailabel/tasks/infer/basic_infer.py", line 411, in run_post_transforms
    return run_transforms(data, transforms, log_prefix="POST")
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monailabel/interfaces/utils/transform.py", line 106, in run_transforms
    data = t(data)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/post/dictionary.py", line 702, in __call__
    inverted = self.transform.inverse(input_dict)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/compose.py", line 478, in inverse
    data = apply_transform(t.inverse, data, self.map_items, self.unpack_items, self.log_stats)
  File "/home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monai/transforms/transform.py", line 130, 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 0x7efcb2ff7ee0>>

0 replies

tangy5 · 2023-05-26T16:45:09Z

tangy5
May 26, 2023
Maintainer

Thanks for post the question in monailabel repo as well @Hirriririir , I read through your logs and tried to find anything different with our prior apps and models. It's very likely the transforms' issues.

First, if the problem is caused by the Invertd or Restored transforms, the error is probably caused by an incorrect reference pre-transform, as you defined a new transform group instead of using the pre-transform, since no meta info is saved. Except for this one, I did not find other wrong items. If this doesn't work, you could double-check the following as denugging reference.

You can double check whether training used the Orientationd transform, if so, you will need to add the Orientationd(keys='image', axcodes='RAS') in the inference pipeline.
If the orientations are correct, You could try to place the Invertd ahead of AsDiscreted.
If you think the Inverted or Restored caused the problem, you could first try disabling them and save the un-inverted label, and see whether the prediction is making sense, at least not the noisy masks.
If disabling Invertd still cause the issue, you can check whether the model, pre-transform follows the same configuration to your prior working Jupyter notebook version.

Thanks, I believe once you figured out the way of using monailabel, you will love it.
Hope above helps.

1 reply

Hirriririir May 27, 2023

Hi tangy5, many many thanks for your help!

Following your suggestion, I started using SaveImage to debug and check the outputs during the transformation. It seems that the problem occurs after the pre-transformations and before the post-transformations. Since this indicates an issue with the model, I checked the model configuration code, and it is exactly the same as what I used in Jupyter Notebook. Therefore, I suspected that the problem might be related to the model loading.

I found this loading snippet in /home/hua/miniconda3/envs/monai_w/lib/python3.8/site-packages/monailabel/tasks/infer/basic_infer.py and ran it in my notebook. It produced just the same weird output as I mentioned. So, I replaced the three # lines with network.load_state_dict(torch.load(path)["state_dict"]), and the MONAI label starts successfully generating accurate results.

if network is None:
            if self.network:
                network = copy.deepcopy(self.network)
                network.to(torch.device(device))

                if path:
                    #checkpoint = torch.load(path, map_location=torch.device(device))
                    #model_state_dict = checkpoint.get(self.model_state_dict, checkpoint)
                    #network.load_state_dict(model_state_dict, strict=self.load_strict)
                    network.load_state_dict(torch.load(path)["state_dict"])
            else:
                network = torch.jit.load(path, map_location=torch.device(device))

SachidanandAlle · 2023-05-27T07:08:22Z

SachidanandAlle
May 27, 2023
Maintainer

you have saved the stat_dict with a different key..
otherwise by default monailablel InferTask is looking into: model_state_dict: str = "model"

https://github.com/Project-MONAI/MONAILabel/blob/main/monailabel/tasks/infer/basic_infer.py#L55
you don't need to change the code for this.. in your segmentation_muscle model..
you can pass that in your init arg..

example: https://github.com/Project-MONAI/MONAILabel/blob/main/sample-apps/radiology/lib/configs/segmentation.py#L93-L101

2 replies

SachidanandAlle May 27, 2023
Maintainer

Also you can enable load_strict: bool = True in the init arg.. that would have easily caught the torch load errors due to key missing etc..

Hirriririir May 28, 2023

Hi SachidanandAlle, you are right. Many thanks!

The method you provided also worked. I think I need to read more pytorch tutorials.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

RuntimeError: Error Resize getting the most recently applied invertible transform Orientation #1035

{{title}}

Replies: 4 comments 3 replies

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

Select a reply

RuntimeError: Error Resize getting the most recently applied invertible transform Orientation #1035

neerajamaha Oct 3, 2022

Replies: 4 comments · 3 replies

tangy5 Oct 3, 2022 Maintainer

Hirriririir May 26, 2023

tangy5 May 26, 2023 Maintainer

Hirriririir May 27, 2023

SachidanandAlle May 27, 2023 Maintainer

SachidanandAlle May 27, 2023 Maintainer

Hirriririir May 28, 2023

neerajamaha
Oct 3, 2022

Replies: 4 comments 3 replies

tangy5
Oct 3, 2022
Maintainer

Hirriririir
May 26, 2023

tangy5
May 26, 2023
Maintainer

SachidanandAlle
May 27, 2023
Maintainer

SachidanandAlle May 27, 2023
Maintainer