YosuaMichael

I have talked with @oke-aditya in slack and he seems interested to add swin3d and I will help to support him on this. cc @datumbox

Thanks a lot @oke-aditya for the help!

Hi @ain-soph, thanks a lot for the PR! As of now, I am still reading SwinTransformerV2 paper and original code, and I will try to review afterwards. Meanwhile, let me...

@xiaohu2015 could you elaborate more on the bug detail that you mention: > we should fix the problem in https://github.com/pytorch/vision/pull/6222 ( for input size=256 window size=8, it works well, but...

I close this PR since it is replaced by few other smaller PRs already

This seems to be related to https://github.com/pytorch/vision/issues/5863 cc @datumbox, Do you know who can review this PR?

Hi @vadimkantorov , from my understanding the answer is yes. The swin_transformer implementation in TorchVision dont restrict the input_resolution. However take note that the accuracy may changes depending on your...

> well, resize_size makes think that it's resizing the input instead and always gives a fixed output resolution > > from what I understand, the two impl I mentioned above...

Hi @vadimkantorov , I can confirm that swin transformer model on torchvision can support different input size. Here is the code to show this: ``` mport torchvision import torch m...

> We already have a PR for that: #5009. Closing this to avoid duplicates. Hi @pmeier , this PR is a bit different from #5009 as it monitor `release/0.13` branch...