'--ndet' flag

[abergsneider]

Hi Jun,

Thank you so much for sharing this with everyone. I'm coming from the nnU-Net repository after researching some of the issues posted.

I'm getting ready to implement your repository but noticed the --ndet flag at the end of the suggested run command python run/run_training.py 3d_fullres nnUNetTrainer_Dice TaskXX_MY_DATASET FOLD --ndet. I'm not familiar with what this flag does, and I can't seem to find any information about it anywhere. My best guess is that it is for non-deterministic training but I think nnU-Net does this by default.

Any info is much appreciated. Take care!

Andres

[JunMa11]

Hi @abergsneider ,

Thanks for your interest very much.

I guess you are using the nnU-Net V2. However, my repo was developed with nnU-Net V1.

If you want to use the Dice loss to train your model, I would recommend nnUNetTrainerV2_Loss_Dice.py.

nnUNet_train 3d_lowres nnUNetTrainerV2_Loss_Dice TaskXXX_MYTASK FOLD

Hope this answer can help you. Also, please feel free to raise any questions.

Best regards,
Jun

[abergsneider]

Thanks @JunMa11, I will go ahead and play around with those loss functions. And thanks for kindly pointing me in the right direction.

Best,

Andres