Chris Xiao

> Hello @mikami520 Can you please post the command you've used? Hi @duytq99 Thanks for your response. I use "nnUNet_plan_and_preprocess -t 004 --verify_dataset_integrity" for preprocessing dataset, where 004 is the...

> Hi, Could you insert the line `print(data.shape)` to inspect data dimension at > > https://github.com/MIC-DKFZ/nnUNet/blob/a7d1d875e8fc3f4e93ca7b51b1ba206711844d92/nnunet/preprocessing/cropping.py#L94 > > and provide the output? > Thank you. When I insert that line,...

> @zhiweigong75, unfortunately iso2mesh does not include any pre-compiled binaries for M1 processors. I expect that not only meshresample.m does not work, many other functions such as meshcheckrepair and s2m/surf2mesh...

@CadyWang Hi Cady, I have a quick question about your generator. I compared your generator to the original one, you add atlas as an input argument and to the generator,...

> Can you describe in more detail your 256x256x128 runs? > > * How did you normalize data? what loss did you use? how much data did you use to...

> you should probably take the mean and std after the clip, but otherwise that looks fine (ish). What was the loss hyperparameter balancing loss and grad? I think I...

> ok, and what does it mean that the results are very bad?   The moved image is the registered result, you can clearly see that there are many...

> you should probably take the mean and std after the clip, but otherwise that looks fine (ish). What was the loss hyperparameter balancing loss and grad? Btw here is...

> I see, some training curves might help. Is that a training subject? yes, do you have any suggestions to improve the result?

> @adalca Here is the training curves