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

#测试Quantification_Results和Verification_data数据结果均接近于0?? #4

Open
tan90du-sx opened this issue Feb 10, 2023 · 8 comments

Comments

@tan90du-sx
Copy link

利用网盘的uiunet.pth测试代码的数据,实验指标分别为
Quantification_Results
0.00200256328099968 0.004197722567287785
0.040051265619993594 0.0839544513457557
Verification_data
0.0 0.0
0.0

@tan90du-sx
Copy link
Author

盼回复

@BLUE-coconut
Copy link

我之前一开始碰到这个问题,后来发现是直接用作者的dataloader可能image和label没有对齐,我改了loader的方法就解决了,和原论文对的上的。你可以看看是不是这个问题。

@Li-Haoqing
Copy link

麻烦您能具体的说一下吗?谢谢!
@BLUE-coconut

@BLUE-coconut
Copy link

就是它SalObjDataset构造数据集时是根据传入的img_name_list和lbl_name_list 的顺序来构造的,而它test.py中img_name_list = glob.glob(image_dir + os.sep + '')和label_name_list = glob.glob(label_dir + os.sep + '')不能保证img_name_list[i]和label_name_list [i]是同一张图像的原图和mask,导致你实际上SalObjDataset中的‘image’和‘label’也是不对应的,所以计算出来的实验指标有问题。

@Li-Haoqing
Copy link

谢谢 @BLUE-coconut

@Joazs
Copy link

Joazs commented May 19, 2023

您好,请问为什么在测试中要经过一个normPRED?网络中不是已经经过了Sigmoid了吗?

@Web-AK

This comment was marked as outdated.

@BLUE-coconut
Copy link

BLUE-coconut commented Nov 10, 2023 via email

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

5 participants