Giters

PaddlePaddle / PaddleTS

Awesome Easy-to-Use Deep Time Series Modeling based on PaddlePaddle, including comprehensive functionality modules like TSDataset, Analysis, Transform, Models, AutoTS, and Ensemble, etc., supporting versatile tasks like time series forecasting, representation learning, and anomaly detection, etc., featured with quick tracking of SOTA deep models.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

TFT方法有办法修改损失函数为MAE、MSE之类的其他函数么

IgnoranceSmile opened this issue · comments

commented

我希望通过修改损失函数的方式，让tft模型支持AutoTS，这可行么

commented

您好，tft由于是概率预测模型，暂时不支持。可以修改成mse，但可能涉及网络输出层结构变化，可能无法保证效果。

commented

您好，由于问题超过一周，将自动关闭。若有问题可以重新打开，或者重新提issue。感谢理解。