evaluation with different data_loader_val batch size leads to different results

[cdluminate]

At https://github.com/IDEA-Research/DINO/blob/main/main.py#L182 , the batchsize for the validation set is fixed to 1. Using the same ckpt, same hardware and the same environment, increasing the validation batch size will simply lead to worse AP.
For instance, with batchsize=1 I may get 49.3, but with batchsize=4 I get 49.0. Any idea on how to fix this issue?