Effect of resizing image & mask without keeping width-height ratio in the data augmentation

[rose-jinyang]

Hello
How are you?
Thanks for contribution to this project.
I'm NOT sure if this RMI loss would work well in case that we resize the image & mask to input size(NxN in pixels) without keeping width-height ratio in the data augmentation step.
I am working on image segmentation project.
There are many images & masks with different sizes in my dataset.
The data by dataloader are resized to input size(ex: 256x256) and feed into the model.
So the original width-height ratio of image & mask are NOT kept.
Even in such case, does this RMI loss work well?

[rose-jinyang]

Hello
Could u reply to the above question?
Thanks

[mzhaoshuai]

Well, I think different w-h ratios will have no effect on RMI.
RMI only cares about the relationship of neighbors, and resizing does not change it.

Sorry for this late reply.
This repo is old and I am busy with other projects.

[rose-jinyang]

Thanks