Egor Panfilov

Use JSON or YAML for configuration and transformation files

3

Currently, the configuration of the registration method is performed using a text file of the custom syntax. Same applies for the file with the estimated transformation parameters. This causes severe...

Registration fails for signed images

1

Hi, I've discovered that the registration doesn't work if the images are preliminarily normalized by mean-std. MSE loss immediately falls to nan, NCC - to 0, and they do not...

Use `plane, row, col` notation in all docstrings

30

## References Closes https://github.com/scikit-image/scikit-image/issues/2276. ## For reviewers (Don't remove the checklist below.) - [ ] Check that the PR title is short, concise, and will make sense 1 year later....

I've faced some troubles making this this tool work in Archlinux. Consider adding more details or even a separate ARCHLINUX.md file to facilitate installation for the new users. See https://gist.github.com/soupault/9ffd5035891657a9f1499b12d15f32c6.

Add Identity layer handling to LRP

2

This is one of the better implementations I have come up with. Let me know your thoughts. Closes https://github.com/pytorch/captum/issues/792.

Support for Identity layer in LRP

2

## 🐛 Bug Hi! Thank you for the great tool! It appears that LRP fails if the model includes `Identity` layer (https://pytorch.org/docs/stable/generated/torch.nn.Identity.html): ```python File "???.py", line 523, in my_fn attrs...

Fix the broken link

2

In the README - http://mipt-ml.oulu.fi/datasets/OAProgression

Use `plane, row, col` dimensions ordering as specified in the `skimage` conventions page

5

## Description I've discovered that the declared recommended order of 3D image dimensions is `plane, row, col` (see the table in http://scikit-image.org/docs/dev/user_guide/numpy_images.html#coordinate-conventions). In `skimage` there are couple of places, where...

### Description: With 3D[+C] and higherD images being widely used, [skimage.restoration.denoise_bilateral](https://scikit-image.org/docs/stable/api/skimage.restoration.html#skimage.restoration.denoise_bilateral) is currently limited to 2D/2D+C inputs, same is MATLAB's [imbilatfilt](https://se.mathworks.com/help/images/ref/imbilatfilt.html), OpenCV's [bilateralFilter](https://docs.opencv.org/4.x/d4/d86/group__imgproc__filter.html#ga9d7064d478c95d60003cf839430737ed), kornia's [bilateral_blur](https://kornia.readthedocs.io/en/latest/filters.html#kornia.filters.bilateral_blur), etc. It would be great...

E.g., from https://ieeexplore.ieee.org/abstract/document/9169719/ .