RT-DETR icon indicating copy to clipboard operation
RT-DETR copied to clipboard

Published 20 hours ago • verified publisher icon lyuwenyu

Non-square training

Open videscar opened this issue 10 months ago • 1 comments

Hello! First of all, thanks for you work on the RT-DETR and RT-DETRv2, looks really good.

I have a question, I want to fine-tune the model on my custom dataset, but my images are 1920x768 (wxh), which doesn't much the pretrained weights expected input. I want to avoid resizing my images so I don't loss details.

Is there a way to still use the pretrained weights on my non-square custom resolution? Or the only option I have is training the model from scratch?

Thank you very much for the support!

videscar avatar Jan 21 '25 09:01 videscar

You can reference this issue/discussion

https://github.com/lyuwenyu/RT-DETR/issues/13

lyuwenyu avatar Jan 22 '25 08:01 lyuwenyu