Hi, thank you for your excellent work !
I have a question regarding the implementation of CAE on COCO segmentation tasks. Since the pre-trained model has a fixed img_size=224, how do you handle the fixed position embedding issue during inference, given that the resolution of COCO images varies and the resolutions are not always fixed?
I'm looking forward to your response. Thank you !
Hi, thank you for your excellent work !
I have a question regarding the implementation of CAE on COCO segmentation tasks. Since the pre-trained model has a fixed img_size=224, how do you handle the fixed position embedding issue during inference, given that the resolution of COCO images varies and the resolutions are not always fixed?
I'm looking forward to your response. Thank you !