FixMatch-pytorch icon indicating copy to clipboard operation
FixMatch-pytorch copied to clipboard

When fix patch is applied to my dataset, the dataset is unbalanced. Why does the training set perform well, but the loss of verification set first decreases and then keeps rising?

Open a571-op opened this issue 5 years ago • 3 comments

When fix patch is applied to my dataset, the dataset is unbalanced. Why does the training set perform well, but the loss of verification set first decreases and then keeps rising?

a571-op avatar Dec 22 '20 00:12 a571-op

Same thing is happening to me.

arfeen93 avatar Apr 15 '21 18:04 arfeen93

When fix patch is applied to my dataset, the dataset is unbalanced. Why does the training set perform well, but the loss of verification set first decreases and then keeps rising?

Friend,I meet the problem too,have you ever solved?

15510112867 avatar Dec 08 '21 12:12 15510112867

same here.

jingyang2017 avatar Apr 07 '22 10:04 jingyang2017