HiLab-git / SSL4MIS

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

metric

smallkaka opened this issue · comments

commented

Thank you so much for your work.
Why are my test.py results and the results given in the papers far different on HD95?
metric:
[array([ 0.85472167, 1.11961011, 22.76351007]), array([ 0.83855158, 1.44890421, 24.67442546]), array([ 0.89453618, 2.88821746, 19.81192052])]
(metric[0]+metric[1]+metric[2])/3:
[ 0.86260314 1.81891059 22.41661868]
your paper
2023-04-13_194749

我跑的结果是[0.85657412 6.39942719 1.68263292],我是dice值差距有点大,而且这是batch size 16的情况,如果是8的情况结果就变成[0.8665116 8.17052963 2.290688 ]。方便的话可以交流一下吗?谢谢!(swagyypg@gmail.com