Object Detection/ Instance Segmentation config details and pre-trained models

[abbasmammadov]

I was wondering when the pre-trained models (checkpoints) and corresponding config files for Swin Transformer V2(object detection/ instance segmentation) will be released? In the github repo, only V1 was provided. Also, if it is not planned to release soon, then it would be great if the config files for Swin V2 HTC++ (the ones achieved SOTA) will be provided in order to train and replicate the results in paper.

All in all, will there be any clear guidelines to replicate the results?

[Robotatron]

I would also be interested on how to train a Swin V2 HTC++