Problems with experimental data in the paper about itransformer HOT 3 CLOSED

Hello, thanks for your concen. There's a lot of difference here:

• Enlarged lookback window: PatchTST paper adopts tunable lookback length in {336, 512}, while ours adopts the unified length of 96, following the unified long-term forecasting protocol of TimesNet.
• More epochs to train: PatchTST paper trains the PatchTST model with 100 epochs, while we train all models with 10 epochs.
• Learning rate: PatchTST paper adapts a carefully designed learning rate strategy.

Related issue: #30

from itransformer.

I would like to test a new backbone architecture that replaces the Transformer in your code experiment setup. What are the things I should be aware of?

Thanks in advance!

from itransformer.

Hello, you can refer to this repo, since iTransformer in built on this!

from itransformer.