This is the repo for a time-series classification model based on the transformer architecture. It uses a number of different encoder blocks to perform classification on a timeseries dataset. Linear attention works but windowed attention is not properly implemented.
-
Notifications
You must be signed in to change notification settings - Fork 0
Transformer model for timeseries classification with different attention mechanisms
License
taihim/timeseries-transformer
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Transformer model for timeseries classification with different attention mechanisms
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published