deepedit workflow transforms documentation #820

artony35 · 2022-07-21T19:28:20Z

artony35
Jul 21, 2022

It seems like the deepedit workflow is using several transforms that has no documentation, especially for the ones that are from
monai.apps.deepedit.transforms. Are these transforms deprecated or they are still a bit too new? Thank you

Nic-Ma · 2022-07-22T02:49:30Z

Nic-Ma
Jul 22, 2022
Maintainer

Hi @SachidanandAlle ,

Could you please help take a look at this ticket?

Thanks.

2 replies

SachidanandAlle Jul 22, 2022
Collaborator

@diazandr3s is our key contributor for deepedit solution.. @artony35 please feel free to reach to Andres for more questions and understanding on deepedit and related transforms...

Some wiki can be found at: https://github.com/Project-MONAI/MONAILabel/wiki/DeepEdit

artony35 Jul 25, 2022
Author

Thank you @SachidanandAlle!

diazandr3s · 2022-07-25T11:27:17Z

diazandr3s
Jul 25, 2022
Collaborator

Hi @artony35,

Thanks for opening this discussion.
The DeepEdit transforms are quite new. Here you can find a tutorial showing how the DeepEdit transforms work for both training and inference: https://github.com/Project-MONAI/tutorials/tree/main/deepedit/ignite
In addition to this, a paper showing how DeepEdit works will be published soon. It's been accepted to the DALI workshop in MICCAI.

If you have any questions regarding these, please don't hesitate to ask. More than happy to help

5 replies

artony35 Jul 25, 2022
Author

Hi Andres @diazandr3s!

Thank you for reaching out! Really appreciate your tutorial. I have been going over it but I am having issues with some of the deepedit transform. That's why I was digging for documentation. I am guessing the issue roots from here since I am trying to train a multiclass model.

For line 441, would you mind clarifying what we should edit in get_loader? It seems like line 151-152 is within get_post_transforms

On my end, the error indeed seems to come from get_post_transforms

Would really appreciate your insight on how to transition from single label training to multi-label training. Thank you!

diazandr3s Jul 25, 2022
Collaborator

Hi @artony35,

It seems you're using an outdated monailabel version. Please update it to the latest version.

The DeepEdit model can be used for multiple label segmentation without major changes. You just need to define the labels (https://github.com/Project-MONAI/MONAILabel/blob/main/sample-apps/radiology/lib/configs/deepedit.py#L46-L55) and deactivate the use of the pretrained model (https://github.com/Project-MONAI/MONAILabel/blob/main/sample-apps/radiology/lib/configs/deepedit.py#L75)

Here I explained the same two steps using the segmentation model: https://www.youtube.com/watch?v=3HTh2dqZqew&list=PLtoSVSQ2XzyD4lc-lAacFBzOdv5Ou-9IA&index=3

Please let me know how that goes

abhishekmarkad May 5, 2023

i am working with
MONAILabel version: 0.7.0rc6+1.g737a581
Numpy version: 1.23.5
Pytorch version: 2.0.0+cu118
MONAILabel rev id: 737a581fade1d473fa6892703a605544ec48a367

i want ro train a deepedit model on custom dataset ( lung lobe segmentation )
i follow the steps from https://www.youtube.com/watch?v=3HTh2dqZqew&list=PLtoSVSQ2XzyD4lc-lAacFBzOdv5Ou-9IA&index=3
for deepedit
when i click trian button from slicer (version 5.2.2)
i got the followiing error . follwing is the server log

__Using PYTHONPATH=/home/vayu:

[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: version = False
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: app = /data4/apps/radiology
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: studies = /data4/lndb_37/lndb_nifti_37
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: verbose = INFO
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: conf = [['models', 'deepedit']]
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: host = 0.0.0.0
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: port = 8000
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: uvicorn_app = monailabel.app:app
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: ssl_keyfile = None
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: ssl_certfile = None
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: ssl_keyfile_password = None
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: ssl_ca_certs = None
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: workers = None
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: limit_concurrency = None
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: access_log = False
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: root_path = /
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: log_level = info
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: log_config = None
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: dryrun = False
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:285) - USING:: action = start_server
[2023-05-05 05:06:39,726] [682493] [MainThread] [INFO] (main:296) -
Allow Origins: ['']
[2023-05-05 05:06:39,870] [682493] [MainThread] [INFO] (uvicorn.error:74) - Started server process [682493]
[2023-05-05 05:06:39,870] [682493] [MainThread] [INFO] (uvicorn.error:48) - Waiting for application startup.
[2023-05-05 05:06:39,870] [682493] [MainThread] [INFO] (monailabel.interfaces.utils.app:37) - Initializing App from: /data4/apps/radiology; studies: /data4/lndb_37/lndb_nifti_37; conf: {'models': 'deepedit'}
[2023-05-05 05:06:39,895] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for MONAILabelApp Found: <class 'main.MyApp'>
[2023-05-05 05:06:39,898] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation_spleen.SegmentationSpleen'>
[2023-05-05 05:06:39,898] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_vertebra.LocalizationVertebra'>
[2023-05-05 05:06:39,898] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_3d.Deepgrow3D'>
[2023-05-05 05:06:39,898] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_2d.Deepgrow2D'>
[2023-05-05 05:06:39,898] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_spine.LocalizationSpine'>
[2023-05-05 05:06:39,898] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation_vertebra.SegmentationVertebra'>
[2023-05-05 05:06:39,899] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepedit.DeepEdit'>
[2023-05-05 05:06:39,899] [682493] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation.Segmentation'>
[2023-05-05 05:06:39,899] [682493] [MainThread] [INFO] (main:93) - +++ Adding Model: deepedit => lib.configs.deepedit.DeepEdit
[2023-05-05 05:06:40,229] [682493] [MainThread] [INFO] (lib.configs.deepedit:147) - EPISTEMIC Enabled: False; Samples: 5
[2023-05-05 05:06:40,229] [682493] [MainThread] [INFO] (main:96) - +++ Using Models: ['deepedit']
[2023-05-05 05:06:40,229] [682493] [MainThread] [INFO] (monailabel.interfaces.app:135) - Init Datastore for: /data4/lndb_37/lndb_nifti_37
[2023-05-05 05:06:40,229] [682493] [MainThread] [INFO] (monailabel.datastore.local:130) - Auto Reload: True; Extensions: ['.nii.gz', '.nii', '.nrrd', '.jpg', '.png', '.tif', '.svs', '.xml']
[2023-05-05 05:06:40,231] [682493] [MainThread] [INFO] (monailabel.datastore.local:577) - Invalidate count: 0
[2023-05-05 05:06:40,232] [682493] [MainThread] [INFO] (monailabel.datastore.local:151) - Start observing external modifications on datastore (AUTO RELOAD)
[2023-05-05 05:06:40,241] [682493] [MainThread] [INFO] (main:126) - +++ Adding Inferer:: deepedit => <lib.infers.deepedit.DeepEdit object at 0x7fda4fa84160>
[2023-05-05 05:06:40,241] [682493] [MainThread] [INFO] (main:126) - +++ Adding Inferer:: deepedit_seg => <lib.infers.deepedit.DeepEdit object at 0x7fda48005540>
[2023-05-05 05:06:40,241] [682493] [MainThread] [INFO] (main:191) - {'deepedit': <lib.infers.deepedit.DeepEdit object at 0x7fda4fa84160>, 'deepedit_seg': <lib.infers.deepedit.DeepEdit object at 0x7fda48005540>, 'Histogram+GraphCut': <monailabel.scribbles.infer.HistogramBasedGraphCut object at 0x7fda480056c0>, 'GMM+GraphCut': <monailabel.scribbles.infer.GMMBasedGraphCut object at 0x7fda480067d0>}
[2023-05-05 05:06:40,241] [682493] [MainThread] [INFO] (main:206) - +++ Adding Trainer:: deepedit => <lib.trainers.deepedit.DeepEdit object at 0x7fda48006800>
[2023-05-05 05:06:40,241] [682493] [MainThread] [INFO] (monailabel.utils.sessions:51) - Session Path: /home/vayu/.cache/monailabel/sessions
[2023-05-05 05:06:40,241] [682493] [MainThread] [INFO] (monailabel.utils.sessions:52) - Session Expiry (max): 3600
[2023-05-05 05:06:40,241] [682493] [MainThread] [INFO] (monailabel.interfaces.app:469) - App Init - completed
[2023-05-05 05:06:40,242] [timeloop] [INFO] Starting Timeloop..
[2023-05-05 05:06:40,242] [682493] [MainThread] [INFO] (timeloop:60) - Starting Timeloop..
[2023-05-05 05:06:40,242] [timeloop] [INFO] Registered job <function MONAILabelApp.on_init_complete..run_scheduler at 0x7fda4facb370>
[2023-05-05 05:06:40,242] [682493] [MainThread] [INFO] (timeloop:42) - Registered job <function MONAILabelApp.on_init_complete..run_scheduler at 0x7fda4facb370>
[2023-05-05 05:06:40,242] [timeloop] [INFO] Timeloop now started. Jobs will run based on the interval set
[2023-05-05 05:06:40,242] [682493] [MainThread] [INFO] (timeloop:63) - Timeloop now started. Jobs will run based on the interval set
[2023-05-05 05:06:40,242] [682493] [MainThread] [INFO] (uvicorn.error:62) - Application startup complete.
[2023-05-05 05:06:40,242] [682493] [MainThread] [INFO] (uvicorn.error:217) - Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
[2023-05-05 05:07:10,607] [682493] [MainThread] [INFO] (monailabel.utils.async_tasks.task:41) - Train request: {'model': 'deepedit', 'name': 'train_01', 'pretrained': True, 'device': 'NVIDIA GeForce RTX 4090', 'max_epochs': 50, 'early_stop_patience': -1, 'val_split': 0.2, 'train_batch_size': 1, 'val_batch_size': 1, 'multi_gpu': True, 'gpus': 'all', 'dataset': 'SmartCacheDataset', 'dataloader': 'ThreadDataLoader', 'tracking': 'mlflow', 'tracking_uri': '', 'tracking_experiment_name': '', 'client_id': 'user-xyz'}
[2023-05-05 05:07:10,607] [682493] [ThreadPoolExecutor-2_0] [INFO] (monailabel.utils.async_tasks.utils:49) - Before:: /home/vayu::/data4/apps/radiology
[2023-05-05 05:07:10,607] [682493] [ThreadPoolExecutor-2_0] [INFO] (monailabel.utils.async_tasks.utils:53) - After:: /home/vayu::/data4/apps/radiology
[2023-05-05 05:07:10,607] [682493] [ThreadPoolExecutor-2_0] [INFO] (monailabel.utils.async_tasks.utils:65) - COMMAND:: /usr/bin/python -m monailabel.interfaces.utils.app -m train -r {"model":"deepedit","name":"train_01","pretrained":true,"device":"NVIDIA GeForce RTX 4090","max_epochs":50,"early_stop_patience":-1,"val_split":0.2,"train_batch_size":1,"val_batch_size":1,"multi_gpu":true,"gpus":"all","dataset":"SmartCacheDataset","dataloader":"ThreadDataLoader","tracking":"mlflow","tracking_uri":"","tracking_experiment_name":"","client_id":"user-xyz"}
[2023-05-05 05:07:10,667] [682747] [MainThread] [INFO] (main:37) - Initializing App from: /data4/apps/radiology; studies: /data4/lndb_37/lndb_nifti_37; conf: {'models': 'deepedit'}
[2023-05-05 05:07:11,302] [682747] [MainThread] [INFO] (torch.distributed.nn.jit.instantiator:21) - Created a temporary directory at /tmp/tmpvzm9ykc5
[2023-05-05 05:07:11,302] [682747] [MainThread] [INFO] (torch.distributed.nn.jit.instantiator:76) - Writing /tmp/tmpvzm9ykc5/_remote_module_non_scriptable.py
[2023-05-05 05:07:12,230] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for MONAILabelApp Found: <class 'main.MyApp'>
[2023-05-05 05:07:12,233] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation_spleen.SegmentationSpleen'>
[2023-05-05 05:07:12,233] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_vertebra.LocalizationVertebra'>
[2023-05-05 05:07:12,233] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_3d.Deepgrow3D'>
[2023-05-05 05:07:12,233] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_2d.Deepgrow2D'>
[2023-05-05 05:07:12,233] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_spine.LocalizationSpine'>
[2023-05-05 05:07:12,233] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation_vertebra.SegmentationVertebra'>
[2023-05-05 05:07:12,234] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepedit.DeepEdit'>
[2023-05-05 05:07:12,234] [682747] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation.Segmentation'>
[2023-05-05 05:07:12,234] [682747] [MainThread] [INFO] (main:93) - +++ Adding Model: deepedit => lib.configs.deepedit.DeepEdit
[2023-05-05 05:07:12,563] [682747] [MainThread] [INFO] (lib.configs.deepedit:147) - EPISTEMIC Enabled: False; Samples: 5
[2023-05-05 05:07:12,563] [682747] [MainThread] [INFO] (main:96) - +++ Using Models: ['deepedit']
[2023-05-05 05:07:12,563] [682747] [MainThread] [INFO] (monailabel.interfaces.app:135) - Init Datastore for: /data4/lndb_37/lndb_nifti_37
[2023-05-05 05:07:12,563] [682747] [MainThread] [INFO] (monailabel.datastore.local:130) - Auto Reload: False; Extensions: ['.nii.gz', '.nii', '.nrrd', '.jpg', '.png', '.tif', '.svs', '*.xml']
[2023-05-05 05:07:12,566] [682747] [MainThread] [INFO] (monailabel.datastore.local:577) - Invalidate count: 0
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (main:126) - +++ Adding Inferer:: deepedit => <lib.infers.deepedit.DeepEdit object at 0x7f3cc20b2260>
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (main:126) - +++ Adding Inferer:: deepedit_seg => <lib.infers.deepedit.DeepEdit object at 0x7f3cbb578a60>
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (main:191) - {'deepedit': <lib.infers.deepedit.DeepEdit object at 0x7f3cc20b2260>, 'deepedit_seg': <lib.infers.deepedit.DeepEdit object at 0x7f3cbb578a60>, 'Histogram+GraphCut': <monailabel.scribbles.infer.HistogramBasedGraphCut object at 0x7f3cbb579d80>, 'GMM+GraphCut': <monailabel.scribbles.infer.GMMBasedGraphCut object at 0x7f3cbb579de0>}
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (main:206) - +++ Adding Trainer:: deepedit => <lib.trainers.deepedit.DeepEdit object at 0x7f3cbb579c90>
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (monailabel.utils.sessions:51) - Session Path: /home/vayu/.cache/monailabel/sessions
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (monailabel.utils.sessions:52) - Session Expiry (max): 3600
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:432) - Train Request (input): {'model': 'deepedit', 'name': 'train_01', 'pretrained': True, 'device': 'NVIDIA GeForce RTX 4090', 'max_epochs': 50, 'early_stop_patience': -1, 'val_split': 0.2, 'train_batch_size': 1, 'val_batch_size': 1, 'multi_gpu': True, 'gpus': 'all', 'dataset': 'SmartCacheDataset', 'dataloader': 'ThreadDataLoader', 'tracking': 'mlflow', 'tracking_uri': '', 'tracking_experiment_name': '', 'client_id': 'user-xyz', 'local_rank': 0}
[2023-05-05 05:07:12,575] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:445) - CUDA_VISIBLE_DEVICES: None
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:450) - Distributed/Multi GPU is limited
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:465) - Distributed Training = FALSE
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:492) - 0 - Train Request (final): {'name': 'train_01', 'pretrained': True, 'device': 'cuda', 'max_epochs': 50, 'early_stop_patience': -1, 'val_split': 0.2, 'train_batch_size': 1, 'val_batch_size': 1, 'multi_gpu': False, 'gpus': 'all', 'dataset': 'SmartCacheDataset', 'dataloader': 'ThreadDataLoader', 'tracking': 'mlflow', 'tracking_uri': '', 'tracking_experiment_name': '', 'model': 'deepedit', 'client_id': 'user-xyz', 'local_rank': 0, 'run_id': '20230505_050712'}
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:625) - 0 - Using Device: cuda; IDX: None
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:518) - Run/Output Path: /data4/apps/radiology/model/deepedit_dynunet/train_01
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:534) - Tracking: mlflow
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:535) - Tracking URI: file:///data4/apps/radiology/model/deepedit_dynunet/train_01/mlruns;
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:536) - Tracking Experiment Name: deepedit; Run Name: run_20230505_050712
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:410) - Total Records for Training: 24
[2023-05-05 05:07:12,576] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:411) - Total Records for Validation: 6
monai.handlers.stats_handler StatsHandler.init:name: Current default value of argument name=None has been deprecated since version 1.1. It will be changed to name=StatsHandler in version 1.3.
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.
Loading dataset: 0%| | 0/6 [00:00<?, ?it/s]
Loading dataset: 17%|█▋ | 1/6 [00:05<00:26, 5.20s/it]
Loading dataset: 33%|███▎ | 2/6 [00:08<00:16, 4.17s/it]
Loading dataset: 50%|█████ | 3/6 [00:09<00:08, 2.82s/it]
Loading dataset: 67%|██████▋ | 4/6 [00:14<00:07, 3.60s/it]
Loading dataset: 83%|████████▎ | 5/6 [00:18<00:03, 3.62s/it]
Loading dataset: 100%|██████████| 6/6 [00:19<00:00, 2.86s/it]
Loading dataset: 100%|██████████| 6/6 [00:19<00:00, 3.28s/it]
cache_num is greater or equal than dataset length, fall back to regular monai.data.CacheDataset.
[2023-05-05 05:07:32,331] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:328) - 0 - Records for Validation: 6
[2023-05-05 05:07:32,334] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:318) - 0 - Adding Validation to run every '1' interval
Loading dataset: 0%| | 0/24 [00:00<?, ?it/s]
Loading dataset: 4%|▍ | 1/24 [00:05<01:57, 5.12s/it]
Loading dataset: 8%|▊ | 2/24 [00:07<01:22, 3.74s/it]
Loading dataset: 12%|█▎ | 3/24 [00:10<01:06, 3.14s/it]
Loading dataset: 17%|█▋ | 4/24 [00:13<01:04, 3.22s/it]
Loading dataset: 21%|██ | 5/24 [00:17<01:03, 3.35s/it]
Loading dataset: 25%|██▌ | 6/24 [00:20<01:01, 3.43s/it]
Loading dataset: 29%|██▉ | 7/24 [00:24<00:58, 3.42s/it]
Loading dataset: 33%|███▎ | 8/24 [00:28<00:56, 3.53s/it]
Loading dataset: 38%|███▊ | 9/24 [00:31<00:51, 3.45s/it]
Loading dataset: 42%|████▏ | 10/24 [00:34<00:45, 3.25s/it]
Loading dataset: 46%|████▌ | 11/24 [00:37<00:43, 3.31s/it]
Loading dataset: 50%|█████ | 12/24 [00:40<00:40, 3.34s/it]
Loading dataset: 54%|█████▍ | 13/24 [00:44<00:38, 3.46s/it]
Loading dataset: 58%|█████▊ | 14/24 [00:47<00:31, 3.12s/it]
Loading dataset: 62%|██████▎ | 15/24 [00:50<00:29, 3.27s/it]
Loading dataset: 67%|██████▋ | 16/24 [00:54<00:28, 3.53s/it]
Loading dataset: 71%|███████ | 17/24 [00:57<00:22, 3.21s/it]
Loading dataset: 75%|███████▌ | 18/24 [00:59<00:17, 3.00s/it]
Loading dataset: 79%|███████▉ | 19/24 [01:02<00:14, 2.89s/it]
Loading dataset: 83%|████████▎ | 20/24 [01:04<00:11, 2.77s/it]
Loading dataset: 88%|████████▊ | 21/24 [01:07<00:07, 2.63s/it]
Loading dataset: 92%|█████████▏| 22/24 [01:09<00:04, 2.47s/it]
Loading dataset: 96%|█████████▌| 23/24 [01:12<00:02, 2.81s/it]
Loading dataset: 100%|██████████| 24/24 [01:14<00:00, 2.33s/it]
Loading dataset: 100%|██████████| 24/24 [01:14<00:00, 3.09s/it]
[2023-05-05 05:08:46,423] [682747] [MainThread] [INFO] (monailabel.tasks.train.basic_train:264) - 0 - Records for Training: 24
[2023-05-05 05:08:46,424] [682747] [MainThread] [INFO] (ignite.engine.engine.SupervisedTrainer:876) - Engine run resuming from iteration 0, epoch 0 until 50 epochs
[2023-05-05 05:08:47,495] [682747] [MainThread] [ERROR] (ignite.engine.engine.SupervisedTrainer:1086) - Current run is terminating due to exception: applying transform <monai.transforms.compose.Compose object at 0x7f3c31b73640>
[2023-05-05 05:08:47,495] [682747] [MainThread] [ERROR] (ignite.engine.engine.SupervisedTrainer:202) - Exception: applying transform <monai.transforms.compose.Compose object at 0x7f3c31b73640>
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 103, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 67, in apply_transform
return transform(parameters)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/apps/deepedit/transforms.py", line 729, in call
d[f"pred{key_label}"] = d[key][idx + 1, ...][None]
File "/home/vayu/.local/lib/python3.10/site-packages/monai/data/meta_tensor.py", line 276, in torch_function
ret = super().torch_function(func, types, args, kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/torch/_tensor.py", line 1295, in torch_function
ret = func(*args, **kwargs)
IndexError: index 6 is out of bounds for dimension 0 with size 6
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 103, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 67, in _apply_transform
return transform(parameters)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/compose.py", line 451, in call
return execute_compose(
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/compose.py", line 199, in execute_compose
data = apply_transform(_transform, data, map_items, unpack_items, log_stats)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 130, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.apps.deepedit.transforms.SplitPredsLabeld object at 0x7f3c31b73700>
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 1068, in _run_once_on_dataset_as_gen
self.state.output = self._process_function(self, self.state.batch)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/apps/deepedit/interaction.py", line 100, in call
return engine._iteration(engine, batchdata) # type: ignore[arg-type]
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/trainer.py", line 238, in _iteration
engine.fire_event(IterationEvents.MODEL_COMPLETED)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 449, in fire_event
return self._fire_event(event_name)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 425, in _fire_event
func(*first, *(event_args + others), **kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/workflow.py", line 226, in _run_postprocessing
engine.state.batch[i], engine.state.output[i] = engine_apply_transform(b, o, posttrans)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/utils.py", line 261, in engine_apply_transform
transformed_data = apply_transform(transform, data)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 130, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f3c31b73640>
[2023-05-05 05:08:47,602] [682747] [MainThread] [ERROR] (ignite.engine.engine.SupervisedTrainer:992) - Engine run is terminating due to exception: applying transform <monai.transforms.compose.Compose object at 0x7f3c31b73640>
[2023-05-05 05:08:47,603] [682747] [MainThread] [ERROR] (ignite.engine.engine.SupervisedTrainer:202) - Exception: applying transform <monai.transforms.compose.Compose object at 0x7f3c31b73640>
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 103, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 67, in apply_transform
return transform(parameters)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/apps/deepedit/transforms.py", line 729, in call
d[f"pred{key_label}"] = d[key][idx + 1, ...][None]
File "/home/vayu/.local/lib/python3.10/site-packages/monai/data/meta_tensor.py", line 276, in torch_function
ret = super().torch_function(func, types, args, kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/torch/_tensor.py", line 1295, in torch_function
ret = func(*args, **kwargs)
IndexError: index 6 is out of bounds for dimension 0 with size 6
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 103, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 67, in _apply_transform
return transform(parameters)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/compose.py", line 451, in call
return execute_compose(
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/compose.py", line 199, in execute_compose
data = apply_transform(_transform, data, map_items, unpack_items, log_stats)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 130, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.apps.deepedit.transforms.SplitPredsLabeld object at 0x7f3c31b73700>
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 959, in _internal_run_as_gen
epoch_time_taken += yield from self._run_once_on_dataset_as_gen()
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 1087, in _run_once_on_dataset_as_gen
self._handle_exception(e)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 636, in _handle_exception
self._fire_event(Events.EXCEPTION_RAISED, e)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 425, in _fire_event
func(*first, *(event_args + others), **kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/handlers/stats_handler.py", line 203, in exception_raised
raise e
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 1068, in _run_once_on_dataset_as_gen
self.state.output = self._process_function(self, self.state.batch)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/apps/deepedit/interaction.py", line 100, in call
return engine._iteration(engine, batchdata) # type: ignore[arg-type]
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/trainer.py", line 238, in _iteration
engine.fire_event(IterationEvents.MODEL_COMPLETED)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 449, in fire_event
return self._fire_event(event_name)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 425, in _fire_event
func(*first, *(event_args + others), **kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/workflow.py", line 226, in _run_postprocessing
engine.state.batch[i], engine.state.output[i] = engine_apply_transform(b, o, posttrans)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/utils.py", line 261, in engine_apply_transform
transformed_data = apply_transform(transform, data)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 130, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f3c31b73640>
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 103, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 67, in apply_transform
return transform(parameters)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/apps/deepedit/transforms.py", line 729, in call
d[f"pred{key_label}"] = d[key][idx + 1, ...][None]
File "/home/vayu/.local/lib/python3.10/site-packages/monai/data/meta_tensor.py", line 276, in torch_function
ret = super().torch_function(func, types, args, kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/torch/_tensor.py", line 1295, in torch_function
ret = func(*args, **kwargs)
IndexError: index 6 is out of bounds for dimension 0 with size 6
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 103, in apply_transform
return _apply_transform(transform, data, unpack_items)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 67, in _apply_transform
return transform(parameters)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/compose.py", line 451, in call
return execute_compose(
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/compose.py", line 199, in execute_compose
data = apply_transform(_transform, data, map_items, unpack_items, log_stats)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 130, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.apps.deepedit.transforms.SplitPredsLabeld object at 0x7f3c31b73700>
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/home/vayu/.local/lib/python3.10/site-packages/monailabel/interfaces/utils/app.py", line 128, in
run_main()
File "/home/vayu/.local/lib/python3.10/site-packages/monailabel/interfaces/utils/app.py", line 113, in run_main
result = a.train(request)
File "/home/vayu/.local/lib/python3.10/site-packages/monailabel/interfaces/app.py", line 423, in train
result = task(request, self.datastore())
File "/home/vayu/.local/lib/python3.10/site-packages/monailabel/tasks/train/basic_train.py", line 466, in call
res = self.train(0, world_size, req, datalist)
File "/home/vayu/.local/lib/python3.10/site-packages/monailabel/tasks/train/basic_train.py", line 555, in train
context.trainer.run()
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/trainer.py", line 53, in run
super().run()
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/workflow.py", line 283, in run
super().run(data=self.data_loader, max_epochs=self.state.max_epochs)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 892, in run
return self._internal_run()
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 935, in _internal_run
return next(self._internal_run_generator)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 993, in _internal_run_as_gen
self._handle_exception(e)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 636, in _handle_exception
self._fire_event(Events.EXCEPTION_RAISED, e)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 425, in _fire_event
func(*first, *(event_args + others), **kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/handlers/stats_handler.py", line 203, in exception_raised
raise e
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 959, in _internal_run_as_gen
epoch_time_taken += yield from self._run_once_on_dataset_as_gen()
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 1087, in _run_once_on_dataset_as_gen
self._handle_exception(e)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 636, in _handle_exception
self._fire_event(Events.EXCEPTION_RAISED, e)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 425, in _fire_event
func(*first, *(event_args + others), **kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/handlers/stats_handler.py", line 203, in exception_raised
raise e
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 1068, in _run_once_on_dataset_as_gen
self.state.output = self._process_function(self, self.state.batch)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/apps/deepedit/interaction.py", line 100, in call
return engine._iteration(engine, batchdata) # type: ignore[arg-type]
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/trainer.py", line 238, in _iteration
engine.fire_event(IterationEvents.MODEL_COMPLETED)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 449, in fire_event
return self._fire_event(event_name)
File "/home/vayu/.local/lib/python3.10/site-packages/ignite/engine/engine.py", line 425, in fire_event
func(*first, *(event_args + others), **kwargs)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/workflow.py", line 226, in run_postprocessing
engine.state.batch[i], engine.state.output[i] = engine_apply_transform(b, o, posttrans)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/engines/utils.py", line 261, in engine_apply_transform
transformed_data = apply_transform(transform, data)
File "/home/vayu/.local/lib/python3.10/site-packages/monai/transforms/transform.py", line 130, in apply_transform
raise RuntimeError(f"applying transform {transform}") from e
RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7f3c31b73640>
[2023-05-05 05:08:48,591] [682493] [ThreadPoolExecutor-2_0] [INFO] (monailabel.utils.async_tasks.utils:83) - Return code: 1

please have a look at apps/radiology/lib/config/deepedit.py
following is the content of deepedit.py

import logging
import os
from typing import Any, Dict, Optional, Union

import lib.infers
import lib.trainers
from monai.networks.nets import UNETR, DynUNet

from monailabel.interfaces.config import TaskConfig
from monailabel.interfaces.tasks.infer_v2 import InferTask, InferType
from monailabel.interfaces.tasks.scoring import ScoringMethod
from monailabel.interfaces.tasks.strategy import Strategy
from monailabel.interfaces.tasks.train import TrainTask
from monailabel.tasks.activelearning.epistemic import Epistemic
from monailabel.tasks.scoring.dice import Dice
from monailabel.tasks.scoring.epistemic import EpistemicScoring
from monailabel.tasks.scoring.sum import Sum
from monailabel.utils.others.generic import download_file, strtobool

logger = logging.getLogger(name)

class DeepEdit(TaskConfig):
def init(self, name: str, model_dir: str, conf: Dict[str, str], planner: Any, **kwargs):
super().init(name, model_dir, conf, planner, **kwargs)

    self.epistemic_enabled = None
    self.epistemic_samples = None

    # Multilabel
    '''  "spleen": 1,
        "right kidney": 2,
        "left kidney": 3,
        "liver": 6,
        "stomach": 7,
        "aorta": 8,
        "inferior vena cava": 9,
        "background": 0,
        '''
    self.labels = {
      "background": 0,
        "lung_upper_lobe_left": 1,
        "lung_lower_lobe_left": 2,
        "lung_upper_lobe_right": 3,
        "lung_middle_lobe_right": 4,
        "lung_lower_lobe_right": 5,
    }
    # Single label
    # self.labels = {
    #     "spleen": 1,
    #     "background": 0,
    # }

    # Number of input channels - 4 for BRATS and 1 for spleen
    self.number_intensity_ch = 1

    network = self.conf.get("network", "dynunet")

    # Model Files
    self.path = [
        os.path.join(self.model_dir, f"pretrained_{self.name}_{network}.pt"),  # pretrained
        os.path.join(self.model_dir, f"{self.name}_{network}.pt"),  # published
    ]

    # Download PreTrained Model
    if strtobool(self.conf.get("use_pretrained_model", "false")):
        url = f"{self.conf.get('pretrained_path', self.PRE_TRAINED_PATH)}"
        url = f"{url}/radiology_deepedit_{network}_multilabel.pt"
        download_file(url, self.path[0])

    self.target_spacing = (1.0, 1.0, 1.0)  # target space for image
    self.spatial_size = (128, 128, 128)  # train input size

    # Network
    self.network = (
        UNETR(
            spatial_dims=3,
            in_channels=len(self.labels) + self.number_intensity_ch,
            out_channels=len(self.labels),
            img_size=self.spatial_size,
            feature_size=64,
            hidden_size=1536,
            mlp_dim=3072,
            num_heads=48,
            pos_embed="conv",
            norm_name="instance",
            res_block=True,
        )
        if network == "unetr"
        else DynUNet(
            spatial_dims=3,
            in_channels=len(self.labels) + self.number_intensity_ch,
            out_channels=len(self.labels),
            kernel_size=[3, 3, 3, 3, 3, 3],
            strides=[1, 2, 2, 2, 2, [2, 2, 1]],
            upsample_kernel_size=[2, 2, 2, 2, [2, 2, 1]],
            norm_name="instance",
            deep_supervision=False,
            res_block=True,
        )
    )

    self.network_with_dropout = (
        UNETR(
            spatial_dims=3,
            in_channels=len(self.labels) + self.number_intensity_ch,
            out_channels=len(self.labels),
            img_size=self.spatial_size,
            feature_size=64,
            hidden_size=1536,
            mlp_dim=3072,
            num_heads=48,
            pos_embed="conv",
            norm_name="instance",
            res_block=True,
            dropout_rate=0.2,
        )
        if network == "unetr"
        else DynUNet(
            spatial_dims=3,
            in_channels=len(self.labels) + self.number_intensity_ch,
            out_channels=len(self.labels),
            kernel_size=[3, 3, 3, 3, 3, 3],
            strides=[1, 2, 2, 2, 2, [2, 2, 1]],
            upsample_kernel_size=[2, 2, 2, 2, [2, 2, 1]],
            norm_name="instance",
            deep_supervision=False,
            res_block=True,
            dropout=0.2,
        )
    )

    # Others
    self.epistemic_enabled = strtobool(conf.get("epistemic_enabled", "false"))
    self.epistemic_samples = int(conf.get("epistemic_samples", "5"))
    logger.info(f"EPISTEMIC Enabled: {self.epistemic_enabled}; Samples: {self.epistemic_samples}")

def infer(self) -> Union[InferTask, Dict[str, InferTask]]:
    return {
        self.name: lib.infers.DeepEdit(
            path=self.path,
            network=self.network,
            labels=self.labels,
            preload=strtobool(self.conf.get("preload", "false")),
            spatial_size=self.spatial_size,
            target_spacing=self.target_spacing,
            config={"cache_transforms": True, "cache_transforms_in_memory": True, "cache_transforms_ttl": 300},
        ),
        f"{self.name}_seg": lib.infers.DeepEdit(
            path=self.path,
            network=self.network,
            labels=self.labels,
            preload=strtobool(self.conf.get("preload", "false")),
            spatial_size=self.spatial_size,
            target_spacing=self.target_spacing,
            number_intensity_ch=self.number_intensity_ch,
            type=InferType.SEGMENTATION,
        ),
    }

def trainer(self) -> Optional[TrainTask]:
    output_dir = os.path.join(self.model_dir, f"{self.name}_" + self.conf.get("network", "dynunet"))
    load_path = self.path[0] if os.path.exists(self.path[0]) else self.path[1]

    task: TrainTask = lib.trainers.DeepEdit(
        model_dir=output_dir,
        network=self.network,
        load_path=load_path,
        publish_path=self.path[1],
        spatial_size=self.spatial_size,
        target_spacing=self.target_spacing,
        number_intensity_ch=self.number_intensity_ch,
        config={"pretrained": strtobool(self.conf.get("use_pretrained_model", "true"))},
        labels=self.labels,
        debug_mode=False,
        find_unused_parameters=True,
    )
    return task

def strategy(self) -> Union[None, Strategy, Dict[str, Strategy]]:
    strategies: Dict[str, Strategy] = {}
    if self.epistemic_enabled:
        strategies[f"{self.name}_epistemic"] = Epistemic()
    return strategies

def scoring_method(self) -> Union[None, ScoringMethod, Dict[str, ScoringMethod]]:
    methods: Dict[str, ScoringMethod] = {
        "dice": Dice(),
        "sum": Sum(),
    }

    if self.epistemic_enabled:
        methods[f"{self.name}_epistemic"] = EpistemicScoring(
            model=self.path,
            network=self.network_with_dropout,
            transforms=lib.infers.DeepEdit(
                type=InferType.DEEPEDIT,
                path=self.path,
                network=self.network,
                labels=self.labels,
                preload=strtobool(self.conf.get("preload", "false")),
                spatial_size=self.spatial_size,
            ).pre_transforms(),
            num_samples=self.epistemic_samples,
        )
    return methods

Any help for above error. Thank you .

diazandr3s May 5, 2023
Collaborator

Hi @abhishekmarkad,

Thanks for the detailed information.
The logs show that the error comes from the label indexing.

In the config file, you declared these labels:

    "background": 0,
    "lung_upper_lobe_left": 1,
    "lung_lower_lobe_left": 2,
    "lung_upper_lobe_right": 3,
    "lung_middle_lobe_right": 4,
    "lung_lower_lobe_right": 5,

But the label files have index numbers bigger than 5:

IndexError: index 6 is out of bounds for dimension 0 with size 6

Are you sure the segment called "lung_lower_lobe_right" is represented by 5 in all the labels you have?

You should make sure the indexes used in the DeepEdit config file are the ones representing the different lobes in the NIfTI/NRRD label files. Similar to what is done in the Segmentation model: https://github.com/Project-MONAI/MONAILabel/blob/main/sample-apps/radiology/lib/configs/segmentation.py#L37-L63

BTW, have you tried the Segmentation model? I'd recommend you check it out. It works great and you can combine it with the Total Segmentator dataset that has lung lobes segmentation: https://zenodo.org/record/6802614#.ZFTp3M7MJEY

Hope this helps

abhishekmarkad May 8, 2023

Thank you for reply ,
Same dataset and similar config file works for segmentation model .
segmentation config file contains
self.labels = {
"lung_upper_lobe_left": 1,
"lung_lower_lobe_left": 2,
"lung_upper_lobe_right": 3,
"lung_middle_lobe_right": 4,
"lung_lower_lobe_right": 5,

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

deepedit workflow transforms documentation #820

{{title}}

{{editor}}'s edit

{{editor}}'s edit

Replies: 2 comments 7 replies

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

Select a reply

deepedit workflow transforms documentation #820

artony35 Jul 21, 2022

Replies: 2 comments · 7 replies

Nic-Ma Jul 22, 2022 Maintainer

SachidanandAlle Jul 22, 2022 Collaborator

artony35 Jul 25, 2022 Author

diazandr3s Jul 25, 2022 Collaborator

artony35 Jul 25, 2022 Author

diazandr3s Jul 25, 2022 Collaborator

abhishekmarkad May 5, 2023

diazandr3s May 5, 2023 Collaborator

abhishekmarkad May 8, 2023

artony35
Jul 21, 2022

Replies: 2 comments 7 replies

Nic-Ma
Jul 22, 2022
Maintainer

SachidanandAlle Jul 22, 2022
Collaborator

artony35 Jul 25, 2022
Author

diazandr3s
Jul 25, 2022
Collaborator

artony35 Jul 25, 2022
Author

diazandr3s Jul 25, 2022
Collaborator

diazandr3s May 5, 2023
Collaborator