ViT-Adapter
ViT-Adapter copied to clipboard
img_norm_config for maskrcnn dinov2 large seems to be accidentally default
https://github.com/czczup/ViT-Adapter/blob/94ffa6b6134b99d838312e2e042d6ac3a52a7ef8/detection/configs/mask_rcnn/dinov2/mask_rcnn_dinov2_adapter_large_fpn_3x_coco.py#L47
has all 127.5 values rather than the values in small and base
Hello, this should be my typo, it may slightly damage the performance.
Was it also intended to have image size 592 for small, base, and large variants?