Thanks for the great repo! Just found out that transformation was applied prior to train val split, effectively augmenting validation set. I don't have a neat solution for this but maybe this gist https://gist.github.com/kevinzakka/d33bf8d6c7f06a9d8c76d97a7879f5cb could be a way out, although it has to load twice the same data.
Thanks for the great repo! Just found out that transformation was applied prior to train val split, effectively augmenting validation set. I don't have a neat solution for this but maybe this gist https://gist.github.com/kevinzakka/d33bf8d6c7f06a9d8c76d97a7879f5cb could be a way out, although it has to load twice the same data.