loss를 OCRnet에서 어떤 방식으로 계산하는 걸까요? #24
Unanswered
kmouleejunhyuk
asked this question in
Q&A
Replies: 2 comments 3 replies
-
|
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
shape가 아예 다른데, 픽셀 별로 onehot하는 걸까요?
만약 그렇다면 mask에 "가려지는"(경재님이 말씀하신 mask label 순서 문제) 부분은, 겹쳐 있으면 어떻게 되는 걸까요?
ex: 한 픽셀의 seg 결과
pred: 00000000001
mask(gt): 5, 11
Beta Was this translation helpful? Give feedback.
All reactions