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.

Sign up for GitHub

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

Jump to bottom

evalcallback和get_map 中的confidence设置 #117

Open
epistimi22 opened this issue Nov 16, 2023 · 1 comment
Open

evalcallback和get_map 中的confidence设置 #117

epistimi22 opened this issue Nov 16, 2023 · 1 comment

Comments

@epistimi22
Copy link

您好，我把验证集在get_map.py上跑了一遍，发现结果和训练过程中报的validation 的map值出入很大，get_map上的结果高了近5个点。
我检查了代码，发现验证过程中计算map用的是evalcallback类下的代码，这里的confidence是0.05，而get_map 单独写了get_map_txt，其中confidence设置为0.001。作者解释为confidence的值应当设置的尽量小进而获得全部可能的预测框
我有一个疑问，为什么同样是报结果，get_map的confidence就要设置得更小？毕竟训练过程中map的大小对模型的优化是没有影响的。
谢谢！
@epistimi22
Copy link
Author

还有就是best_epoch的选择也不看map，只看loss，这里的confidence为什么不能设置成统一值，确实不太理解

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@epistimi22