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

验证集指标问题 #19

Open
gejutaixiao22 opened this issue Nov 2, 2024 · 6 comments
Open

验证集指标问题 #19

gejutaixiao22 opened this issue Nov 2, 2024 · 6 comments

Comments

@gejutaixiao22
Copy link

作者您好,我再尝试更改您的网络结构并在跑模型的时候,发现验证集指标略高一点的时候测试出来的结果并没有和验证集相同,Outdoor_Rain数据集大概差了0.3左右,请问这是正常现象么。再者您在训练的时候训练了多少epoch呢?谢谢

@sunshangquan
Copy link
Owner

sunshangquan commented Nov 2, 2024

Hi @gejutaixiao22 , 谢谢您的关注,验证的时候为了时间考虑,在这里添加了一个early stop,就是只验证了验证集的前60张图片的结果,所以测试的时候会有一些差别,不过验证和测试的总体趋势应该是一样的;训练了一共300000个iteration

@xiaoshuai0719
Copy link

Hello author, I would like to ask if the 60 validation results mentioned here refer to the models generated every 1000 iterations during our training process when running test.py, and that we use test_histoformer to calculate and manually select the best model (best.pth)?

@sunshangquan
Copy link
Owner

Hi @xiaoshuai0719, yes.

@hhhhhhalf
Copy link

作者您好!您论文中提到的在"RainDrop 测试数据集"上进行指标评估,我发现RainDrop官方数据集上有'testA”和‘’testB"两个测试集,请问您是使用testA用于训练时的val,最终测试指标是在testb数据集上吗?
ce6a16793792f59dc547588b6780d1e

@sunshangquan
Copy link
Owner

Hi @hhhhhhalf ,指标用的是testa集,b这个集不用做数值比较

@hhhhhhalf
Copy link

Hi @hhhhhhalf ,指标用的是testa集,b这个集不用做数值比较

好嘞!感谢您的解答!

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

4 participants