Aleksei Shabanov

Hey, @stoensin ! Thank you for the interest in OML. I think we need some tests for this. As an input you can use this url: `https://i.ibb.co/wsmD5r4/photo-2022-06-06-17-40-52.jpg`. You can put...

Hey, @stoensin ! Let's move on with this PR. Please, see the comment above: https://github.com/OML-Team/open-metric-learning/pull/548#discussion_r1596831798

@stoensin please, re-open this PR, when you ready to continue

@PapaMadeleine2022 , it's a good idea. Unfortunately, I don't have time to work on this issue right now, so, contributions are welcome!

If someone wants to work on this, [here](https://github.com/OML-Team/open-metric-learning/pull/403) is the checklist of needed steps for adding a model & example of model adding PR

Swin: https://github.com/microsoft/Swin-Transformer [Contribution instruction](https://github.com/OML-Team/open-metric-learning/blob/main/CONTRIBUTING.md#contributing-to-models-zoo).

@armored-guitar are you still going to implement this?

@leoromanovich great, waiting for it

Let's start with the first PR, where we don't add texts support, but refactor the way of processing images datasets. Particularly, we had `get_retrieval_datasets` function that was hardcoded, but now...

responded in DM :)