Giters

baidut / paq2piq

PaQ2PiQ in PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The performance difference between the validation set and the test validation set

sunguwei opened this issue · comments

commented

In your released paper, I find that the performance difference between the validation set and the test validation set is quite large, which is not normal. Could you explain why?

commented

Thank you! Good question. The test set contains images bigger than 640x640 while the validation set contains images that have a width or height smaller than 640 and have similar size distribution with the training set.