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

Mistake #2

Closed
Xi-Mu-Yu opened this issue Sep 4, 2024 · 3 comments
Closed

Mistake #2

Xi-Mu-Yu opened this issue Sep 4, 2024 · 3 comments

Comments

@Xi-Mu-Yu
Copy link

Xi-Mu-Yu commented Sep 4, 2024

Hello, there seems to be an error with val.list and test.list in the MS-CMRSEG19 dataset. For example, test.list in mscmrseg19_split1 has only one file name. The test.list of mscmrseg19_split2 is the same as the val.list

@xinyuliu-jeffrey
Copy link
Contributor

Hi @BeiZhiRen, thanks for your interest in our work!

Different from ACDC that have both val and test, in MS-CMRSEG19 dataset and Decathlon Prostate, we actually only split the dataset into training and validation dataset. The performance are reported as the average of performance on the validation sets of two different splits. The test list are not used for these two datasets.

Hope this helps!

@Xi-Mu-Yu
Copy link
Author

Xi-Mu-Yu commented Sep 4, 2024

您好,感谢您对我们的工作感兴趣!

与 ACDC 同时具有 val 和 test 不同,在 MS-CMRSEG19 数据集和迪卡侬前列腺中,我们实际上只将数据集拆分为训练数据集和验证数据集。性能报告为两个不同拆分的验证集上的平均性能。测试列表不用于这两个数据集。

希望这有帮助!
Ok, I see, thanks for your answers and contributions in semi-supervised semantic segmentation, I will do my best to quote and promote your article

@xinyuliu-jeffrey
Copy link
Contributor

@BeiZhiRen Thanks again for bring this to our attention!

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

2 participants