search

yuqinie98 / PatchTST

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
Apache License 2.0
1.51k stars 262 forks source link

PatchTST as a Classifier #74

Closed vitor-rolla closed 1 year ago

vitor-rolla commented 1 year ago

Do you have any tips for using PatchTST as a binary classifier?

          As mentioned in the paper, we provide another framework for multivariate time series forecasting/regression/classification where channels can go into the Transformer in parallel instead of mixing...

Originally posted by @namctin in https://github.com/yuqinie98/PatchTST/issues/29#issuecomment-1482653015

Lindanhan commented 11 months ago

Excuse me. I have similar problems and you close this issue. Do you know how to transfer this forecasting task to classification task? I don’t see the another framework in this code. Could you help me with that? Thanks!

Brandy-L commented 6 months ago 
          As mentioned in the paper, we provide another framework for multivariate time series forecasting/regression/classification where channels can go into the Transformer in parallel instead of mixing...

Excuse me. Have you solved this problem? I have the same problem but I haven't found a solution yet. Could you please tell me how you did it?

RoelofKuipers commented 5 months ago

Same issue :)