Mikael Brudfors

Hi @elisim I ended up using a MATLAB function for doing this -- my code is below. It could hopefully be ported to Python without too much effort. ```matlab %...

Hi @Defuse3 What function are you calling in order to see this error message, is it `spm_CTseg`? It looks like perhaps the deformation file `C:\Users\Dawn\Desktop\science\spm12-CTseg\y_*.nii` is not correctly specified, maybe...

Glad to hear you solved it! CTseg returns total brain (GM + WM) and total intracranial (GM + WM + CSF) volume. If you want the individual volumes, perhaps look...

Hi Paul, Wouldn't the deformation field be subject-specific, so why would you want to apply the same field to different subjects? Or maybe I am missing something :)

Ah, I see! I think it might be possible to give a list of paths at, for example, line 68. If you want, you could try that, and make as...

Hello @arturjpaulo I suspect you are giving CTseg a large image, which means that the RAM usage will be high. Unfortuntaly, there are no tricks available for decreasing memory use...

Hello @wendy-xiaozong , Appologies it took me some time to get back to you on this. I have now added a demo notebook that shows how to apply the forward...

I think the header looks OK, and setting `correct_header=true` should take care of any affine matrix related issues regardless. Are you sure the scan is not of a young child?...

Hi @SophieOstmeier, Do you ensure that your local CUDA version is the same as the one that was used to build the pytorch version you are using?

Are you familiar with Docker? If so, you could try to build a Docker image from a `Dockerfile` with the following content: ```sh FROM nvidia/cuda:11.1.1-cudnn8-devel-ubuntu20.04 RUN apt-get update --fix-missing &&...