stgt-traffic-twin – AI Model by anupam1897 | AlphaNeural AI

You can deploy this model and start earning money today!

anupam1897/
stgt-traffic-twin

like

0

traffic-prediction

graph-neural-network

urban-digital-twin

Views

No views yet

STGT Traffic Digital Twin

Koramangala, Bangalore

Spatio-Temporal Graph Transformer for urban traffic impact assessment.

Performance

MAE: 2.763 veh/5min
R2: 0.97
Coverage: 2,107 junctions in Koramangala

Files

File	Size	Description
`best_stgt_v2.pth`	1.8 MB	Main GCN model
`best_stgt_gat.pth`	0.7 MB	GAT variant
`graph_dict.pkl`	0.3 MB	Road network
`config.json`	-	Model config

Usage

python

from huggingface_hub import hf_hub_download
import torch

ckpt_path = hf_hub_download(
    repo_id="anupam1897/stgt-traffic-twin",
    filename="best_stgt_v2.pth"
)
ckpt = torch.load(ckpt_path, map_location='cpu')

Citation

@misc{stgt-twin-2024,
  title={STGT: Traffic Digital Twin for Bangalore},
  author=anupam1897,
  year={2024},
  url=https://huggingface.co/anupam1897/stgt-traffic-twin
}