ViTDet changing img_size

[austinmw]

📚 Documentation Issue

Hi, I'm curious if I could get more information on MAE/ViT input size and ViTDet img_size.

I'd like to train a ViT 'b' backbone with MAE and use it to create a ViTDet model for size 448 images. Should the MAE pertaining also ideally be at size 448? And if I change img_size from 1024 to 448, what else needs to be changed?

Edit: Solved. I no longer have any errors changing the image size now that I've moved to the latest ViTDet PR.