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

请问一下，PiecewiseDecay对训练COCO数据集最终的mAP影响大吗？ #2147

Open
songyuc opened this issue Jan 30, 2021 · 2 comments
Open

请问一下，PiecewiseDecay对训练COCO数据集最终的mAP影响大吗？ #2147

songyuc opened this issue Jan 30, 2021 · 2 comments
Labels
config question Further information is requested

Comments

@songyuc
Copy link

songyuc commented Jan 30, 2021

尊敬的开发者，你好，
我自己复现了一下CenterNet，不过在COCO128上mAP只有22左右；
我在训练设置中没有使用lr的PiecewiseDecay，请问一下，这个设置对训练COCO128数据集的最终结果影响大吗？

期待您的回复！
@heavengate
Copy link
Collaborator

影响很大的，训练到一定阶段需要衰减一下学习率达到更好的收敛效果，可以参考下 https://blog.csdn.net/lvchunyang66/article/details/80090708

@songyuc
Copy link
Author

songyuc commented Mar 19, 2021

@heavengate ，你好，请问一下，milestones的迭代轮数一般是怎么计算的呢？

@thinkthinking thinkthinking added question Further information is requested config labels Mar 15, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
config question Further information is requested
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@heavengate @songyuc @thinkthinking