maggie2209

Hi, I have the same problem! The first week when I used the driver the backlight switched off after a while, but came back on as soon as I started...

I don't have access to my machine at the moment, but will get the information on the mismatching shape as soon as possible. In the mean time, attaching the plans...

> Hi it looks like your source and your new plan are matching. Did your pretrain using the nnUNetPlans_target.json? I think it might have done the pretraining with the source...

> > Hi it looks like your source and your new plan are matching. Did your pretrain using the nnUNetPlans_target.json? > > Thank you for your early reply! I solved...

> and maybe add a ".shape" [here](https://github.com/MIC-DKFZ/nnUNet/blob/2eee620844e0b67300d9a6226405012fe20a3687/nnunetv2/run/load_pretrained_weights.py#L45C63-L45C79) to see the actual mismatching shape :D Also, I've now got the info on the mismatching shapes: `AssertionError: The shape of the parameters...

When I ran the finetuning I used this command: `nnUNetv2_train 733 2d 0 -pretrained_weights nnunet/nnUNet_trained_models/Dataset731_CT-EID-E094/nnUNetTrainer__newPlans__2d/fold_all/checkpoint_final.pth` So I didn't select a specific json file for this, but I guess it would...

Okay, maybe I did mix them up. What does target dataset refer to in this function then?

Thanks, I'll try it again

Thank you, the assertion error is now solved. However, I am getting a cuda runtime error now. I attached the output log. Have you come across this before in the...

Unfortunately, I still get the error even after changing it to False