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

--features==MS vs --features==M #46

Open
XIANZHAOGUO opened this issue Jan 4, 2025 · 0 comments
Open

--features==MS vs --features==M #46

XIANZHAOGUO opened this issue Jan 4, 2025 · 0 comments

Comments

@XIANZHAOGUO
Copy link

XIANZHAOGUO commented Jan 4, 2025

  1. 对于代码中的--features==MS 与 --features==M的情况下我想知道在这两种情况模型输出是怎么样,例如在MS情况是否是只对目标列生成预测,在exp_forecast.py文件中加入一行调试代码
    屏幕截图 2025-01-04 183504(1)
    2.采用ETTh1数据集,在本地进行测试关注test阶段的维度
    3.步骤1设置为M,test阶段输出如下:
    屏幕截图 2025-01-04 183021(1)
    屏幕截图 2025-01-04 183146(1)
    4.步骤2设置为MS,test阶段输出如下:
    屏幕截图 2025-01-04 183252(1)
    屏幕截图 2025-01-04 183355(1)
    5.test阶段的数据长度为如下:
    屏幕截图 2025-01-04 184912
    test阶段读取数据总长度为2976,共有7维,根据data_loade中计算方法,数据长度为2976-96(seq_len)-96(pred_len)+1=2785
    数据共有7维,batch_size为32,故可以得到的总的batch个数为(2785*7)/32=610
    经过上面思路,并未发现在这两个情况下有什么区别?
    由于对这方面专业知识不强,对作者团队结果深表赞叹,不知上述想法是否正确,希望得到作者回复
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

1 participant