Closed suojifeng closed 4 months ago
Hi, SegRNN is designed for long-term time series forecasting tasks. If you wish to use it for multivariate time series classification, some adjustments are necessary. For instance, you could replace the PMF module directly with a linear classification head.
Furthermore, I suggest referring to this framework (https://github.com/thuml/Time-Series-Library), which includes comprehensive implementations for forecasting, classification, anomaly detection, and other tasks. You might consider migrating the SegRNN to this repository to facilitate multivariate time series classification.
Hi author, Is it just encoder?thank you