robert-graf

Yes, just concatenate your image to the noised-image input and change the input-channel size.

@huseyin-karaca This Google paper introduced this [https://iterative-refinement.github.io/palette/](https://iterative-refinement.github.io/palette/). I did it before the forward call of the U-Net and only updated the input size of the first Con-Block. ```python # Conditional...

1: Step 4 from Algorithm, but using equivalence from formula 9,7. Equation 9 right side of mean_tilde_t( ... , HERE) and replacing mean_tilde_t with 7 I tested equation 11 and...

I missed a ants_mni.to_nibabel(), which used the 0.4 version. And then, I noticed the given nifti_to_ants were not invariant. The get_ras_affine_from_ants form Torchio assumes that the axis is mirrored and...

I figured it out; The reshape removes spatial dimensions: `source = source.reshape(source.shape[0], -1).float()` will reshape to (batch,-1) The mean will collapse the second dimension, even if you set keepdim=True This...

This change crashes our downstream. And the replaced function does not work. The function uses get_data() and has been deprecated since version 3 (current version 5) and crashes. It should...

Oh, you probably use the SimpleITK definition of affines. Then the above code is not yet functioning. As you already figured out in the other issues, you must mirror the...