Using one Bundle generated model in Auto3DSeg in MONAI Label #1591

rfrs · 2023-11-05T10:50:15Z

rfrs
Nov 5, 2023

Dear all,
I recently started using Auto3DSeg and would like to import the generated models into MONAI Label.
I successfully trained a model and have the .pt models from the different Auto3DSeg networks.

I selected the best model (best metrics) for use. I followed the tutorial here [https://github.com/Project-MONAI/MONAILabel/tree/main/sample-apps#radiology](url) and created the files in lib: train, infer, config, yet, i get the error message stating lib.configs.spine4.py'; 'lib.configs.spine4 is not a package.

I would highly appreciate your input.

Best wishes
Rui

KumoLiu · 2023-11-07T02:59:12Z

KumoLiu
Nov 7, 2023
Maintainer

Hi @rfrs, hope this can help you, thanks!

0 replies

rfrs · 2023-11-13T07:40:57Z

rfrs
Nov 13, 2023
Author

HI @KumoLiu, thanks for the suggestion.
Despite having different names between folders and files it still fails...

Thanks

1 reply

KumoLiu Nov 13, 2023
Maintainer

Hi @rfrs, did you add init file in lib.configs?

rfrs · 2023-11-13T10:20:12Z

rfrs
Nov 13, 2023
Author

Dear @KumoLiu, yes there is such a file in the config, infer and trainers subfolders.

Thanks

1 reply

KumoLiu Nov 13, 2023
Maintainer

Could you please share the whole error message?

Could you please share some comments on this one? cc @SachidanandAlle @tangy5
Thanks in advance!

rfrs · 2023-11-13T10:39:48Z

rfrs
Nov 13, 2023
Author

My last attempt follows. I duplicated the radiology app and simply modified the segmentation config file by adding the labels i need and that were used for the training in auto3Dseg. Also in the config file i added the path for a trained model in Auto3DSeg..

Here is the log/error (i used ... just as replacement for private info).

Thanks a lot for the help.

Best

(monailabel) azureuser@rs-a100:~/cloudfiles/code/Users/...$ monailabel start_server --app monai-apps/spine --studies ... --conf models segmentation
Using PYTHONPATH=/anaconda/envs:

[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: version = False
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: app = /mnt/batch/tasks/shared/LS_root/mounts/clusters/.../monai-apps/spine
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: studies = ...
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: verbose = INFO
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: conf = [['models', 'segmentation']]
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: host = 0.0.0.0
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: port = 8000
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: uvicorn_app = monailabel.app:app
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: ssl_keyfile = None
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: ssl_certfile = None
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: ssl_keyfile_password = None
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: ssl_ca_certs = None
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: workers = None
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: limit_concurrency = None
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: access_log = False
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: root_path = /
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: log_level = info
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: log_config = None
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: dryrun = False
[2023-11-13 10:34:34,073] [10613] [MainThread] [INFO] (__main__:285) - USING:: action = start_server
[2023-11-13 10:34:34,074] [10613] [MainThread] [INFO] (__main__:296) - 
Allow Origins: ['*']
[2023-11-13 10:34:36,014] [10613] [MainThread] [INFO] (uvicorn.error:74) - Started server process [10613]
[2023-11-13 10:34:36,014] [10613] [MainThread] [INFO] (uvicorn.error:48) - Waiting for application startup.
[2023-11-13 10:34:36,014] [10613] [MainThread] [INFO] (monailabel.interfaces.utils.app:37) - Initializing App from: /mnt/batch/tasks/shared/LS_root/mounts/clusters/.../monai-apps/spine; studies: ...; conf: {'models': 'segmentation'}
[2023-11-13 10:34:37,913] [10613] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for MONAILabelApp Found: <class 'main.MyApp'>
[2023-11-13 10:34:38,315] [10613] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepedit.DeepEdit'>
[2023-11-13 10:34:38,366] [10613] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_2d.Deepgrow2D'>
[2023-11-13 10:34:38,421] [10613] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.deepgrow_3d.Deepgrow3D'>
[2023-11-13 10:34:38,477] [10613] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_spine.LocalizationSpine'>
[2023-11-13 10:34:38,528] [10613] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.localization_vertebra.LocalizationVertebra'>
[2023-11-13 10:34:38,574] [10613] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for TaskConfig Found: <class 'lib.configs.segmentation.Segmentation'>
[2023-11-13 10:34:38,640] [10613] [MainThread] [ERROR] (uvicorn.error:123) - Traceback (most recent call last):
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/starlette/routing.py", line 677, in lifespan
    async with self.lifespan_context(app) as maybe_state:
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/starlette/routing.py", line 566, in __aenter__
    await self._router.startup()
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/starlette/routing.py", line 654, in startup
    await handler()
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/monailabel/app.py", line 108, in startup_event
    instance = app_instance()
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/monailabel/interfaces/utils/app.py", line 50, in app_instance
    app = c(app_dir=app_dir, studies=studies, conf=conf)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/.../monai-apps/spine/main.py", line 49, in __init__
    for c in get_class_names(lib.configs, "TaskConfig"):
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/monailabel/utils/others/class_utils.py", line 164, in get_class_names
    module = importlib.import_module("." + name, package=current_module_name)
  File "/anaconda/envs/monailabel/lib/python3.9/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1030, in _gcd_import
  File "<frozen importlib._bootstrap>", line 1007, in _find_and_load
  File "<frozen importlib._bootstrap>", line 981, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'lib.configs.segmentation.py'; 'lib.configs.segmentation' is not a package

1 reply

KumoLiu Nov 13, 2023
Maintainer

Hi @rfrs, one more question, did you follow these steps?
And did you import lib.configs in the main.py?

MONAILabel/sample-apps/radiology/main.py

Line 17 in 071dc52

import lib.configs

rfrs · 2023-11-13T10:54:19Z

rfrs
Nov 13, 2023
Author

Dear @KumoLiu , what steps do you refer to?

Yes, the main.py imports the lib.configs. I did not alter its content (see the first lines bellow)-

import json
import logging
import os
from typing import Dict

import lib.configs
from lib.activelearning import Last
from lib.infers.deepgrow_pipeline import InferDeepgrowPipeline
from lib.infers.vertebra_pipeline import InferVertebraPipeline

import monailabel
from monailabel.interfaces.app import MONAILabelApp
from monailabel.interfaces.config import TaskConfig
from monailabel.interfaces.datastore import Datastore
from monailabel.interfaces.tasks.infer_v2 import InferTask
from monailabel.interfaces.tasks.scoring import ScoringMethod
from monailabel.interfaces.tasks.strategy import Strategy
from monailabel.interfaces.tasks.train import TrainTask
from monailabel.scribbles.infer import GMMBasedGraphCut, HistogramBasedGraphCut
from monailabel.tasks.activelearning.first import First
from monailabel.tasks.activelearning.random import Random

# bundle
from monailabel.tasks.infer.bundle import BundleInferTask
from monailabel.tasks.train.bundle import BundleTrainTask
from monailabel.utils.others.class_utils import get_class_names
from monailabel.utils.others.generic import get_bundle_models, strtobool
from monailabel.utils.others.planner import HeuristicPlanner

logger = logging.getLogger(__name__)

2 replies

KumoLiu Nov 13, 2023
Maintainer

This steps: https://github.com/Project-MONAI/MONAILabel/tree/main/sample-apps#creating-a-custom-app
(forget to put the link :))

rfrs Nov 13, 2023
Author

Yes i followed that and it failed

rfrs · 2023-11-13T14:44:20Z

rfrs
Nov 13, 2023
Author

HI everyone, so i tried something different and got a different error. I was checking here https://github.com/Project-MONAI/MONAILabel/tree/main/sample-apps/radiology#hybrid-radiology-app-with-models-and-bundles on how to use bundles.

Thus i did the following:

downloaded monaibundle
made a copy and renamed it to monaibundle_spine
Made a copy of the SegResNet model from Auto3dSeg (model generated with fold 1) and called that folder spine_segresnet_1
placed the folder inside the Model folder of monaibundle
ran the code monailabel start_server --app monai-apps/monaibundle_spine --studies ... --conf bundles spine_segresnet_1

and got the following error:

Using PYTHONPATH=/anaconda/envs:

[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: version = False
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: app = /mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../monai-apps/monaibundle_spine
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: studies = ...
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: verbose = INFO
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: conf = [['bundles', 'spine_segresnet_1']]
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: host = 0.0.0.0
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: port = 8000
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: uvicorn_app = monailabel.app:app
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: ssl_keyfile = None
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: ssl_certfile = None
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: ssl_keyfile_password = None
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: ssl_ca_certs = None
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: workers = None
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: limit_concurrency = None
[2023-11-13 14:35:12,277] [7782] [MainThread] [INFO] (__main__:285) - USING:: access_log = False
[2023-11-13 14:35:12,278] [7782] [MainThread] [INFO] (__main__:285) - USING:: root_path = /
[2023-11-13 14:35:12,278] [7782] [MainThread] [INFO] (__main__:285) - USING:: log_level = info
[2023-11-13 14:35:12,278] [7782] [MainThread] [INFO] (__main__:285) - USING:: log_config = None
[2023-11-13 14:35:12,278] [7782] [MainThread] [INFO] (__main__:285) - USING:: dryrun = False
[2023-11-13 14:35:12,278] [7782] [MainThread] [INFO] (__main__:285) - USING:: action = start_server
[2023-11-13 14:35:12,278] [7782] [MainThread] [INFO] (__main__:296) - 
Allow Origins: ['*']
[2023-11-13 14:35:12,587] [7782] [MainThread] [INFO] (uvicorn.error:74) - Started server process [7782]
[2023-11-13 14:35:12,588] [7782] [MainThread] [INFO] (uvicorn.error:48) - Waiting for application startup.
[2023-11-13 14:35:12,588] [7782] [MainThread] [INFO] (monailabel.interfaces.utils.app:37) - Initializing App from: /mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../monai-apps/monaibundle_spine; studies: ...; conf: {'bundles': 'spine_segresnet_1'}
[2023-11-13 14:35:12,797] [7782] [MainThread] [INFO] (monailabel.utils.others.class_utils:57) - Subclass for MONAILabelApp Found: <class 'main.MyApp'>
[2023-11-13 14:35:12,826] [7782] [MainThread] [ERROR] (uvicorn.error:123) - Traceback (most recent call last):
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/starlette/routing.py", line 677, in lifespan
    async with self.lifespan_context(app) as maybe_state:
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/starlette/routing.py", line 566, in __aenter__
    await self._router.startup()
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/starlette/routing.py", line 654, in startup
    await handler()
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/monailabel/app.py", line 108, in startup_event
    instance = app_instance()
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/monailabel/interfaces/utils/app.py", line 50, in app_instance
    app = c(app_dir=app_dir, studies=studies, conf=conf)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../monai-apps/monaibundle_spine/main.py", line 36, in __init__
    self.models = get_bundle_models(app_dir, conf)
  File "/anaconda/envs/monailabel/lib/python3.9/site-packages/monailabel/utils/others/generic.py", line 350, in get_bundle_models
    models = models.split(",")
AttributeError: 'NoneType' object has no attribute 'split'

3 replies

KumoLiu Nov 13, 2023
Maintainer

Hi @rfrs, according to the error message, seems no model was found.
Now it looks more like a modellabel usage issue, I will convert this one to MONAI Label repo.
Thanks!

rfrs Nov 13, 2023
Author

So is there something i need to change in mz directories or else?

KumoLiu Nov 13, 2023
Maintainer

I think you missed specify conf_key="bundles" in your get_bundle_models.
https://github.com/Project-MONAI/MONAILabel/blob/071dc527dd129f66c6c42752c06e87e46b9a8467/sample-apps/radiology/main.py#L101C24-L101C41

Thanks!

rfrs · 2023-11-14T09:51:18Z

rfrs
Nov 14, 2023
Author

Hey

I could fix it by adapting

monailabel start_server --app monai-apps/monaibundle_spine --studies ... --conf models spine_segresnet_1

Best
Rui

1 reply

diazandr3s Nov 15, 2023
Maintainer

Hi @rfrs,

Did you make any changes to the generated folder/model by Auto3D?

Let us know,

rfrs · 2023-11-23T18:44:58Z

rfrs
Nov 23, 2023
Author

Dear @diazandr3s and @KumoLiu

I am not advancing to generate a model in Auto3DSeg with a large dataset. Nonetheless during the data analysis step i am getting the following error:

Traceback (most recent call last):
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/data_analyzer.py", line 19, in <module>
    datastat = analyser.get_all_case_stats()
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/apps/auto3dseg/data_analyzer.py", line 230, in get_all_case_stats
    result_bycase = self._get_all_case_stats(0, 1, None, key, transform_list)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/apps/auto3dseg/data_analyzer.py", line 333, in _get_all_case_stats
    for batch_data in tqdm(dataloader) if (has_tqdm and rank == 0) else dataloader:
  File "/anaconda/envs/monai/lib/python3.9/site-packages/tqdm/std.py", line 1182, in __iter__
    for obj in iterable:
  File "/anaconda/envs/monai/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 633, in __next__
    data = self._next_data()
  File "/anaconda/envs/monai/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data
    return self._process_data(data)
  File "/anaconda/envs/monai/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data
    data.reraise()
  File "/anaconda/envs/monai/lib/python3.9/site-packages/torch/_utils.py", line 644, in reraise
    raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 2.
Original Traceback (most recent call last):
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/transform.py", line 141, in apply_transform
    return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/transform.py", line 98, in _apply_transform
    return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/io/dictionary.py", line 162, in __call__
    data = self._loader(d[key], reader)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/io/array.py", line 282, in __call__
    img_array, meta_data = reader.get_data(img)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/data/image_reader.py", line 938, in get_data
    data = self._get_array_data(i)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/data/image_reader.py", line 1012, in _get_array_data
    return np.asanyarray(img.dataobj, order="C")
  File "/anaconda/envs/monai/lib/python3.9/site-packages/nibabel/arrayproxy.py", line 439, in __array__
    arr = self._get_scaled(dtype=dtype, slicer=())
  File "/anaconda/envs/monai/lib/python3.9/site-packages/nibabel/arrayproxy.py", line 406, in _get_scaled
    scaled = apply_read_scaling(self._get_unscaled(slicer=slicer), scl_slope, scl_inter)
  File "/anaconda/envs/monai/lib/python3.9/site-packages/nibabel/arrayproxy.py", line 376, in _get_unscaled
    return array_from_file(
  File "/anaconda/envs/monai/lib/python3.9/site-packages/nibabel/volumeutils.py", line 465, in array_from_file
    n_read = infile.readinto(data_bytes)
  File "/anaconda/envs/monai/lib/python3.9/gzip.py", line 300, in read
    return self._buffer.read(size)
  File "/anaconda/envs/monai/lib/python3.9/_compression.py", line 68, in readinto
    data = self.read(len(byte_view))
  File "/anaconda/envs/monai/lib/python3.9/gzip.py", line 478, in read
    self._read_eof()
  File "/anaconda/envs/monai/lib/python3.9/gzip.py", line 524, in _read_eof
    raise BadGzipFile("CRC check failed %s != %s" % (hex(crc32),
gzip.BadGzipFile: CRC check failed 0x5ab25329 != 0x84f031a9

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

Traceback (most recent call last):
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/transform.py", line 141, in apply_transform
    return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/transform.py", line 98, in _apply_transform
    return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/compose.py", line 335, in __call__
    result = execute_compose(
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/transforms/compose.py", line 111, in execute_compose
    data = apply_transform(
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/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 0x7fae34f6cd30>

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

Traceback (most recent call last):
  File "/anaconda/envs/monai/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
    data = fetcher.fetch(index)
  File "/anaconda/envs/monai/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 "/anaconda/envs/monai/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/monai/data/dataset.py", line 112, in __getitem__
    return self._transform(index)
  File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/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 "/mnt/batch/tasks/shared/LS_root/mounts/clusters/rs-a100/code/Users/.../Auto3DSeg/MONAI-git/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 0x7fae34f6c640>

I understand there is some corrupted file that is being evaluated during the data analysis step. Out of the 912 images, the analysis crashes at step/image 210.
I loaded all images using both nibabel and simpleITK but all images open. Yet, there is this failure with the data analysis from monai... any way you can help me pinpoint which files are corrupted?
Any way to get a report from monai which images are not loading?

Thank you so much.
Best
Rui

17 replies

caolonghao Mar 6, 2024

@diazandr3s Hello there, I just need to segment one region (a tumor near cerebellum). Do you have some suggestions for the choice of model?

diazandr3s Mar 6, 2024
Maintainer

On which MR sequence (i.e. T1, T2, FLAIR or T1+C)? Is it mutlisequence?

caolonghao Mar 6, 2024

No, it's not mutlisequence, just T1 MRI.

diazandr3s Mar 6, 2024
Maintainer

Yes, I'd recommend trying with a DeepEdit model and see how that goes.

Yasna-frn Sep 27, 2024

Hi @caolonghao,

Thanks for clarifying. Yes, while we solve the issue of Bundle incompatibility between Auto3D and MONAI Label, I'd recommend the same - train a MONAI Label model for that (segmentation or deepedit) How many regions are you segmenting?

Let us know,

Hi @diazandr3s
I wanted to follow up on the issue you mentioned regarding the Bundle incompatibility between Auto3D and MONAI Label. Has this been resolved yet? If not, is there an expected timeline or release date for a fix?

rfrs · 2024-03-05T07:32:24Z

rfrs
Mar 5, 2024
Author

Dear Tony, I still have no found a way. I have been in contact with Nvidia personal responsible for the matter and so far, it appears MONAI-Label and Auto3DSeg have not been made to communicate and operate with each other unfortunately... Also the architectures of each monai label model and auto3Dseg are different... I am sorry. So far i cannot be of further help. Best regards

…

On Tue, 5 Mar 2024 at 06:37, Tony Cao ***@***.***> wrote: @rfrs <https://github.com/rfrs> Hello, I also want to use my pre-trained AutoSeg3D model as the base model of MONAI Lable but I feel confused about the process. Did you find the problem? Thanks a lot. — Reply to this email directly, view it on GitHub <#1591 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AL74AI2YRCENX7WAYYQAEE3YWVKZHAVCNFSM6AAAAAA7JLFDV6VHI2DSMVQWIX3LMV43SRDJONRXK43TNFXW4Q3PNVWWK3TUHM4DMNZVGA2DK> . You are receiving this because you were mentioned.Message ID: ***@***.*** com>

1 reply

caolonghao Mar 5, 2024

Thank you for your reply. Then it seems that training a deepedit model based on unetr(or other model) and deploying it in monai label could be a better choice. Maybe we can utilize the data augmentation module of auto3dseg seperately for training. I will try that then.

rfrs · 2024-03-05T08:07:38Z

rfrs
Mar 5, 2024
Author

I am interested in knowing if that works :) Keep me in the loop please. Also, i have been successful in training a monai label model from scratch within the monai label framework and the metrics are really nice. I just had to adapt the segmentation.py task across the lib app.

…

On Tue, 5 Mar 2024 at 08:39, Tony Cao ***@***.***> wrote: Thank you for your reply. Then it seems that training a deepedit model based on unetr(or other model) and deploying it in monai label could be a better choice. Maybe we can utilize the data augmentation module of auto3dseg seperately for training. I will try that then. — Reply to this email directly, view it on GitHub <#1591 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AL74AI6FVBHXA3G77TZPPQTYWVZCJAVCNFSM6AAAAAA7JLFDV6VHI2DSMVQWIX3LMV43SRDJONRXK43TNFXW4Q3PNVWWK3TUHM4DMNZWGA2DK> . You are receiving this because you were mentioned.Message ID: ***@***.*** com>

0 replies

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Using one Bundle generated model in Auto3DSeg in MONAI Label #1591

{{title}}

Replies: 10 comments 27 replies

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

Select a reply

Using one Bundle generated model in Auto3DSeg in MONAI Label #1591

rfrs Nov 5, 2023

Replies: 10 comments · 27 replies

KumoLiu Nov 7, 2023 Maintainer

rfrs Nov 13, 2023 Author

KumoLiu Nov 13, 2023 Maintainer

rfrs Nov 13, 2023 Author

KumoLiu Nov 13, 2023 Maintainer

rfrs Nov 13, 2023 Author

KumoLiu Nov 13, 2023 Maintainer

rfrs Nov 13, 2023 Author

KumoLiu Nov 13, 2023 Maintainer

rfrs Nov 13, 2023 Author

rfrs Nov 13, 2023 Author

KumoLiu Nov 13, 2023 Maintainer

rfrs Nov 13, 2023 Author

KumoLiu Nov 13, 2023 Maintainer

rfrs Nov 14, 2023 Author

diazandr3s Nov 15, 2023 Maintainer

rfrs Nov 23, 2023 Author

caolonghao Mar 6, 2024

diazandr3s Mar 6, 2024 Maintainer

caolonghao Mar 6, 2024

diazandr3s Mar 6, 2024 Maintainer

Yasna-frn Sep 27, 2024

rfrs Mar 5, 2024 Author

caolonghao Mar 5, 2024

rfrs Mar 5, 2024 Author

rfrs
Nov 5, 2023

Replies: 10 comments 27 replies

KumoLiu
Nov 7, 2023
Maintainer

rfrs
Nov 13, 2023
Author

KumoLiu Nov 13, 2023
Maintainer

rfrs
Nov 13, 2023
Author

KumoLiu Nov 13, 2023
Maintainer

rfrs
Nov 13, 2023
Author

KumoLiu Nov 13, 2023
Maintainer

rfrs
Nov 13, 2023
Author

KumoLiu Nov 13, 2023
Maintainer

rfrs Nov 13, 2023
Author

rfrs
Nov 13, 2023
Author

KumoLiu Nov 13, 2023
Maintainer

rfrs Nov 13, 2023
Author

KumoLiu Nov 13, 2023
Maintainer

rfrs
Nov 14, 2023
Author

diazandr3s Nov 15, 2023
Maintainer

rfrs
Nov 23, 2023
Author

diazandr3s Mar 6, 2024
Maintainer

diazandr3s Mar 6, 2024
Maintainer

rfrs
Mar 5, 2024
Author

rfrs
Mar 5, 2024
Author