-
Notifications
You must be signed in to change notification settings - Fork 7
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
代码训练问题,权重最优,图像融合 #12
Comments
Hey, 非常感谢关注,以下是我们的回答:
|
你好!谢谢你的回复,我还想问一个问题。
如果不保存权重最优的话,请问你们是选择哪一轮权重来进行测试,如何选择?
在 2023-08-07 06:23:21,"Shiyu Zhao" ***@***.***> 写道:
Hey, 非常感谢关注,以下是我们的回答:
我们并没有保存最优权重。并且不建议根据测试结果挑选最优权重,那可能会导致过拟合
我们的图像融合方法是一个离线过程,不需要和特定的训练过程绑定
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
Hey, 我们总是使用训练结束得到的最后一个模型权重进行测试。训练iterations一般detectron2默认的90k。如果您想选择更优的权重,可以考虑使用验证集进行选择。 |
您好,
非常感谢您耐心的回复!受益颇深。
在 2023-08-08 02:01:19,"Shiyu Zhao" ***@***.***> 写道:
Hey,
我们总是使用训练结束得到的最后一个模型权重进行测试。训练iterations一般detectron2默认的90k。如果您想选择更优的权重,可以考虑使用验证集进行选择。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
您好!
我看了您的代码,想请问您下面两个问题:
期待您的回复。
The text was updated successfully, but these errors were encountered: