KanielDatz

So, if understood you well, in my case it should look like this: ``` { "channel_names": { "0": "channel0" }, "labels": { "background": 0, "catheter": [1,6,7,9], "deflated_device": 2, "inflated_device": 3,...

I've trained a classifier on the encoder deep outputs with the pretrained nnunet encoder. maybe this approach can be useful for you.

I'm in the process with [PlotNeuralNet](https://github.com/HarisIqbal88/PlotNeuralNet ) I will share when ready

same here, appreciate your help and effort ``` run_preprocessing preprocessor_class = recursive_find_python_class([join(nnunet_mednext.__path__[0], "preprocessing")], File "/home/cathalert/mednext/nnunet_mednext/training/model_restore.py", line 28, in recursive_find_python_class m = importlib.import_module(current_module + "." + modname) File "/usr/lib/python3.10/importlib/__init__.py", line 126,...