loss increase in custom dataset
maichm opened this issue · comments
My dataset is imbalance and long tail, this will affect the policy search?
And the more epoch train in the same experiment! Why my loss looks so strange?
albumentations-team / autoalbument
AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/