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?
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 withbatchsize=4
I get 49.0. Any idea on how to fix this issue?