This is a pytorch-based implementation of DeepAR (DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks).
Based on the works of TimeSeries, this implementation is developed to provide more easy-reading API for training and testing single variable as well as multi-variable time sries.
- Xinze Zhang (Xinze@hust.edu.cn) - Huazhong University of Science and Technology.
- Acknowledgement: Thanks, Yunkai Zhang, Qiao Jianga, and Xueying Ma who are the authors of TimeSeries.