gift-surg / monaifbs Goto Github PK

Hello,

I'm trying to rebuild a new singularity container embeding MONAIfbs but.
no matter the way I try to get the models archive it fails.

+ zenodo_get 10.5281/zenodo.4282679
Title: MONAI dynUNet model for fetal brain segmentation
Keywords: fetal brain segmentation, MONAI, dynUNet
Publication date: 2020-11-20
DOI: 10.5281/zenodo.4282679
Total size: 324.5 MB

Link: https://zenodo.org/api/files/ba541695-648a-4f20-9995-ee86cb1ccb6a/models.tar.gz   size: 324.5 MB
  Download error. Original link: https://zenodo.org/api/files/ba541695-648a-4f20-9995-ee86cb1ccb6a/models.tar.gz
  Too many errors.
  Download is aborted.

wget https://zenodo.org/api/files/ba541695-648a-4f20-9995-ee86cb1ccb6a/models.tar.gz
also fail

is there another way or URL source to get the archive ?

Eric

Dear .
I gave a try to the docker version of the great fetal brain segmentation tool you provide. I ran the fetal brain segmentation of 3 stacks using niftymic segmentation command. I should precise I ran the docker with singularity on a high performance computing cluster (slurm interface). When launching the segmentation I obtained the error below:

File "fetal_brain_seg.py", line 86, in
run_inference(input_data=img, config_info=config)
File "/app/NiftyMIC/MONAIfbs/monaifbs/src/inference/monai_dynunet_inference.py", line 273, in run_inference
evaluator.run()
File "/usr/local/lib/python3.6/site-packages/monai/engines/evaluator.py", line 91, in run
super().run()
File "/usr/local/lib/python3.6/site-packages/monai/engines/workflow.py", line 157, in run
super().run(data=self.data_loader, max_epochs=self.state.max_epochs)
File "/usr/local/lib/python3.6/site-packages/ignite/engine/engine.py", line 691, in run
return self._internal_run()
File "/usr/local/lib/python3.6/site-packages/ignite/engine/engine.py", line 762, in _internal_run
self._handle_exception(e)
File "/usr/local/lib/python3.6/site-packages/ignite/engine/engine.py", line 465, in _handle_exception
self._fire_event(Events.EXCEPTION_RAISED, e)
File "/usr/local/lib/python3.6/site-packages/ignite/engine/engine.py", line 423, in _fire_event
func(*first, *(event_args + others), **kwargs)
File "/usr/local/lib/python3.6/site-packages/monai/handlers/stats_handler.py", line 145, in exception_raised
raise e
File "/usr/local/lib/python3.6/site-packages/ignite/engine/engine.py", line 722, in _internal_run
self._fire_event(Events.STARTED)
File "/usr/local/lib/python3.6/site-packages/ignite/engine/engine.py", line 423, in _fire_event
func(*first, *(event_args + others), **kwargs)
File "/usr/local/lib/python3.6/site-packages/monai/handlers/checkpoint_loader.py", line 82, in call
checkpoint = torch.load(self.load_path, map_location=self.map_location)
File "/usr/local/lib/python3.6/site-packages/torch/serialization.py", line 525, in load
with _open_file_like(f, 'rb') as opened_file:
File "/usr/local/lib/python3.6/site-packages/torch/serialization.py", line 212, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/usr/local/lib/python3.6/site-packages/torch/serialization.py", line 193, in init
super(_open_file, self).init(open(name, mode))
PermissionError: [Errno 13] Permission denied: '/app/NiftyMIC/MONAIfbs/monaifbs/models/checkpoint_dynUnet_DiceXent.pt'

The .pt file seems to exist (at least when I run the singularity image) but the script serialization.py can not read it.

Do you have any hint ?
Have a good day
Alex

Hello! I saw a typo in requirements.txt: the last sentence ends with a colon: tensorboard>=2.2.1:, where it shouldn't.

This thows an error when trying to install it using pip install -e .

Cheers!