About training auto-ps task on Fivek dataset
YinengXiong opened this issue · comments
Hello, I'm a beginer and I have some questions:
have you tried to train auto-ps task on fivek dataset at original image size?
the implementation in paper is resize to 512s and random resized from 512 to 1672 without data augmentation(e.g. random crop & random rotate) and you set fine-size = -1 in your default setting.
If i wanna train auto-ps task on the original image size, is it better to apply data augmentation(random crop, random flip & rotate) strategy?
thank you very much
I didn't try this. But I think rand crop
is necessary.