Closed FriedaSmith closed 11 months ago
I used the Python command and also reported an error. The dataset path is as follows:
(MedNeXt) zw@T640:~/myData/Code/study/MedNeXt$ ls "/home/zw/myData/Code/study/nnUNet_raw_data_base/nnUNet_raw_data/Dataset001_Tr"
dataset.json imagesTr imagesTs infers labelsTr
(MedNeXt) zw@T640:~/myData/Code/study/MedNeXt$ python "/home/zw/myData/Code/study/MedNeXt/nnunet_mednext/experiment_planning/nnUNet_plan_and_preprocess.py" -t 1
Traceback (most recent call last):
File "/home/zw/myData/Code/study/MedNeXt/nnunet_mednext/experiment_planning/nnUNet_plan_and_preprocess.py", line 170, in <module>
main()
File "/home/zw/myData/Code/study/MedNeXt/nnunet_mednext/experiment_planning/nnUNet_plan_and_preprocess.py", line 102, in main
task_name = convert_id_to_task_name(i)
File "/home/zw/myData/Code/study/MedNeXt/nnunet_mednext/utilities/task_name_id_conversion.py", line 51, in convert_id_to_task_name
raise RuntimeError("Could not find a task with the ID %d. Make sure the requested task ID exists and that "
RuntimeError: Could not find a task with the ID 1. Make sure the requested task ID exists and that nnU-Net knows where raw and preprocessed data are located (see Documentation - Installation). Here are your currently defined folders:
nnUNet_preprocessed=/home/zw/myData/Code/study/nnUNet_preprocessed
RESULTS_FOLDER=/home/zw/myData/Code/study/nnUNet_trained_models
nnUNet_raw_data_base=/home/zw/myData/Code/study/nnUNet_raw_data_base
If something is not right, adapt your environemnt variables.
Hey @FriedaSmith. I haven't had the time to clean the preprocessing or nnunet training yet - or even release all the code for to do the preprocessing.
But maybe I can add something I notice in your code. Your code seems to be processed based on nnUNet (v2) format. This is what the main branch of nnUNet supports at the moment. My model was trained using nnUNet (v1) which you will find in a branch of the nnUNet repo (https://github.com/MIC-DKFZ/nnUNet/tree/nnunetv1).
You are free to use my model inside nnunet v2 if you have experience with replacing the model inside an nnUNetTrainer. Or wait a little more for me to clean/release code for data preparation and training as part of this repository.
There is code and instructions now to recreate the MICCAI2023 experiments in nnUNet(v1). Please reopen this issue if you have more questions.
python version: 3.9.13 pytorch version: 1.12.1+cu113