flowmatic-traffic-stgcn-forecaster

Forecast graph-structured traffic sensor states using spatial correlations.

Model summary

Field	Value
Architecture	stgcn_forecast
Dataset	hf_traffic
Source checkpoint	q1_hf_traffic_stgcn_forecaster
Test metrics	{"test_loss": 0.2541641902743721, "test_mae": 0.2853931188583374, "test_rmse": 0.5041469931602478}

Files

• model.safetensors — primary weights
• model.torchscript.pt — TorchScript export (when present)
• metadata.json — schema, scaler, metrics
• model_card.md — training card

Usage in Flowmatic

Deploy in the Core Unit with model ID flowmatic-traffic-stgcn-forecaster (prefixed by your Hugging Face username in the UI).

Inference is routed through Flowmatic's model-inference service using your organization Hugging Face token.