MIC-DKFZ
nnUNet post processing
Hello everyone. I am trying to train nnUNet using another pretained model. I am using Model Genesis pretrained model and I want to retrain the model with nnUNet. At the end of the training, I received the following warning.
WARNING! Cannot run postprocessing because the postprocessing file is missing. Make sure to run consolidate_folds in the output folder of the model first!
The folder you need to run this in is nnUNet_trained_models/nnUNet/3d_fullres/Task006_Lung/nnUNetTrainer_Experimental__nnUNetPlansv2.1
I didn't here about any command like consolidate_folds.
if I ignore this warning, the predictions are not good.
Can someone help ?
No, but I saw somewhere that post processing did not considerably improve the results.
No, but I saw somewhere that post processing did not considerably improve the results.
I guess you can run the /postprecessing/consolidate_postprecessing.py first? I'm not sure about this. Maybe you can have a try... :)
