Tools · MarkTechPost ·
A Coding Implementation on Spatial Graph Neural Networks for Urban Function Inference Using city2graph, OSMnx, and PyTorch Geometric
The post describes an end-to-end spatial graph learning pipeline built with city2graph, OSMnx, and PyTorch Geometric. It uses OpenStreetMap POI and street network data, creates multiple graph types, and trains a GraphSAGE model to predict POI categories from urban spatial structure.