Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

hi~ #1

Open
louielu1027 opened this issue Jan 11, 2019 · 1 comment
Open

hi~ #1

louielu1027 opened this issue Jan 11, 2019 · 1 comment

Comments

@louielu1027
Copy link

你好,我看了你dcnv1,v2对比实验结果,那我想问一下,你有没有做没加dcn的结果呢?

@zhanglonghao1992
Copy link
Owner

@louielu1027 以前跑过,会比这个低1-2个点左右。不过我观察了v1学习的offset和v2学到的offset+mask,offset普遍偏小(1e-1~1e-3)
个人感觉voc上不是很能体现出deformable的优势。因为在stage3、stage4加入dcn会使性能下降,但是在coco上就不一样了,更多的dcn会使性能提升。(从论文实验结果可以看出来,其实v2比v1的提升主要因为使用了更多的dcn,而不是mdcn本身。。)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants