Downloads · 30 days
5
10% of all-time downloads
stgt-traffic-twin
anupam1897/stgt-traffic-twin
stgt-traffic-twin is a machine learning model from anupam1897. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Spatio-Temporal Graph Transformer for urban traffic impact assessment.
All-time downloads
51
Public
Repo size
2.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth2.5 MB · 89%
At a glance
- License
- mit
- Access
- Public
- Created
- Apr 4, 2026
- Updated
- Apr 4, 2026
- SHA
- 017af22b
Model card
From the Hugging Face model README
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
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
}
- License
- mit
- Created
- Apr 4, 2026
- Updated
- Apr 4, 2026