Decide the mode of the model. Train model for each machine dataset, 28 of them. Farecasting seems 30k steps works. RECONSTRUCTING and BOTH - it took 300k. Models sometimes deviate to NaN during ...

Our implementation of MTAD-GAT: Multivariate Time-series Anomaly Detection (MTAD) via Graph Attention Networks (GAT) by Zhao et al. (2020). This repo includes a complete framework for multivariate ...