Closed elisim closed 1 year ago
PatchTST is in Gluon, thanks to @kashif . Closing here :) https://github.com/awslabs/gluonts/pull/2748
Oh I apologize that I just notice this issue. Somehow I haven't seen it previously... And I appreciate so much for your attention on the PatchTST! Anything I could do for it? Also, glad to see the Gluonts application!
@yuqinie98 not a problem... i will get PatchTST added to transformers next
@yuqinie98 also note that the model on gluonts is not exactly the patchTST implementation as your paper (or the implementations in tsai and neuralforecast):
it doesn't carry the multivariate time series around but rather each entry in the batch is some random time series from the data
torch.unfold
) based on the freq
is also implementedthe points I raised in my email to you still stand with respect to the paper
Model description
"time-series patching" refers to the process of segmentation the series into subseries-level patches which are served as input tokens to the transformer. It's really similar to what's done in ViT, but for time-series. This idea was first propsed in a recent ICLR paper:
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers code: https://github.com/yuqinie98/PatchTST
@kashif @NielsRogge
Open source status
Provide useful links for the implementation
@yuqinie98
Edit: I think that "new model" is not the best label to this issue, maybe there is a better label for this?