ChoiDM
commented
4 years ago Thank you for your question.
The output channel doesn’t effect to computing dice score because before the value is calculated, the tensor is flattened.
I hope my answer was helpful. Thank you.
2019년 11월 5일 (화) 오후 11:43, zz10001 notifications@github.com님이 작성:
Hi, Thanks for your awesomework, I notice that your network output channel is 1 in train.ipynb, Is it have some problem when compute dice? [image: image] https://user-images.githubusercontent.com/39954774/68214311-25b42700-0018-11ea-9313-4e5308787571.png, It the sum of 0 and 1, not compute 0 and 1 Seperately .
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/ChoiDM/LiTS-Liver-Tumor-Segmentaton-Challenge/issues/1?email_source=notifications&email_token=AINKZ4OTCCWDNMKMBQC7D2TQSGBCDA5CNFSM4JJDDCTKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HW45VAQ, or unsubscribe https://github.com/notifications/unsubscribe-auth/AINKZ4ML7TGDLMFAYO25RPLQSGBCDANCNFSM4JJDDCTA .
zz10001
Hi, Thanks for your awesomework, I notice that your network output channel is 1 in train.ipynb, Is it have some problem when compute dice?
, It the sum of 0 and 1, not compute 0 and 1 Seperately .