An error is reported for downsampling

[Madeypo]

Dear Mart,

Hooknettls is a very good article, and I really appreciate your contribution. I encountered some issues when trying to reproduce it using Docker.

1.Is there any hidden code inside the Docker container after creation? For example, I noticed that the 'IOPaths' defined in hooknettls/io.py is not being used. I also couldn't find the file containing the complete code for the dataloader, and some parameters seem to be undefined as well.

2.When I'm testing with my own data, I encounter the following error. How should I resolve it.

Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/user/pathology-hooknet-tls/hooknettls/main.py", line 8, in
objects = build_config(config_reader.read()["default"])
File "/usr/local/lib/python3.8/dist-packages/dicfg/factory.py", line 124, in build_config
return _ObjectFactory(deepcopy(config)).build_config()
File "/usr/local/lib/python3.8/dist-packages/dicfg/factory.py", line 26, in build_config
return self._build(self._configuration)
File "/usr/lib/python3.8/functools.py", line 912, in _method
return method.get(obj, cls)(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/dicfg/factory.py", line 38, in _build_dict
config[key] = self._build_object(value)
File "/usr/local/lib/python3.8/dist-packages/dicfg/factory.py", line 67, in _build_object
return attribute(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/wholeslidedata/iterators/patchiterator.py", line 46, in create_patch_iterator
commander = commander_class(
File "/usr/local/lib/python3.8/dist-packages/wholeslidedata/buffer/patchcommander.py", line 50, in init
self.reset()
File "/usr/local/lib/python3.8/dist-packages/wholeslidedata/buffer/patchcommander.py", line 68, in reset
messages = self.get_patch_messages()
File "/usr/local/lib/python3.8/dist-packages/wholeslidedata/buffer/patchcommander.py", line 91, in get_patch_messages
self._mask = WholeSlideImage(self._mask_path, backend=self._backend, auto_resample=True)
File "/usr/local/lib/python3.8/dist-packages/wholeslidedata/image/wholeslideimage.py", line 39, in init
self._spacings = self._backend._init_spacings(self._downsamplings)
File "/usr/local/lib/python3.8/dist-packages/wholeslidedata/interoperability/asap/backend.py", line 43, in _init_spacings
return [
File "/usr/local/lib/python3.8/dist-packages/wholeslidedata/interoperability/asap/backend.py", line 44, in
self.getSpacing()[0] * downsampling for downsampling in downsamplings

[martvanrijthoven]

Dear Madeypo,

Thank you for your kind words and interest in hooknet-tls!

1)

I understand that the code could be a bit confusing, i will try to explain a bit:
The hooknet-tls pipeline is defined via this config file:

• https://github.com/DIAGNijmegen/pathology-hooknet-tls/blob/f28c65b2c7ba8816fd5027097c439d0702561378/hooknettls/configs/config.yml
  Here also the IOPaths are created on this line:

  pathology-hooknet-tls/hooknettls/configs/config.yml

  Lines 56 to 61 in f28c65b

  	io_paths:
  	"*object": hooknettls.io.get_io_paths
  	image_path: ${image_path}
  	model_name: ${model_name}
  	output_folder: ${output_folder}

  
  This is possible due to the use of dicfg python package: https://martvanrijthoven.github.io/dicfg/
  The data loading is also done via another library, namely wholeslidedata: https://github.com/DIAGNijmegen/pathology-whole-slide-data. And it is defined here in the config file:

• pathology-hooknet-tls/hooknettls/configs/config.yml

  Lines 18 to 33 in f28c65b

  	patch_configuration:
  	"*object": wholeslidedata.iterators.PatchConfiguration
  	patch_shape: [1244, 1244, 3]
  	center: True
  	spacings: [0.5, 2.0]
  	overlap: [220, 220]
  	offset: [-512, -512]
  	iterator:
  	"*object": wholeslidedata.iterators.create_patch_iterator
  	image_path: ${image_path}
  	mask_path: ${mask_path}
  	patch_configuration: ${patch_configuration}
  	cpus: 8
  	backend: asap

  
  However please note that a user, normally, should not need to touch the config file.

2)

By looking at the error trace it seems something goes wrong when loading the mask file. However, could please also provide me the actual error? I hope it will allow me to give you more information what actual goes wrong.

Best wishes,
Mart