Does MSE and SAD eval metrics works for binary classification (Sematic segmentation)?

[Sanath1998]

问题确认 Search before asking

• [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

Hi @jzhang533 @ZeyuChen @llxxxll @QingshuChen,

Thanks for this wonderful repository. But I have 1 question will MSE (Mean Squared Error) and SAD (Sum of Absolute Difference) works for Binary Classification where I have only background and foreground class while doing this Sematic Training? If yes could you please give your understanding on it which helps us a lot?

Reference from the code:- https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.9/Matting/ppmatting/metrics/metric.py

Thanks and reply is much appreciated.