Due to the involvement of subsequent paper work, only the core code has been open-sourced.
[1] Dataset. (Opened source)
[2] Raster feature preprocessing method. (Opened source)
[3] Model architecture (Simplify raster features). (Opened source)
[4] Model architecture (Original raster features). (Not open source)
- PyTorch
- Matplotlib
- Pandas
- Numpy
- Time
- OS
- et al.
PeMS03,PeMS04,PeMS07,PeMS08 and SZ-taxi (flow, speed, occupancy, weather, news)
We would like to thank the following individuals and organizations for their contributions to this project:
This work was supported in part by the National Natural Science Foundation of China under Grant 61771265; in part by the Funding for the 6th "333 Talent" Project in Jiangsu Province under Grant 2022044; in part by the Postgraduate Research & Practice Innovation Program of Jiangsu Province under Grant KYCX22_3341, and Grant KYCX23_3396.