Urban trees play a critical role in mitigating heat, enhancing climate resilience, and advancing environmental equity in cities. While a wide range of remote sensing imagery and deep learning approaches have been used to map urban tree cover, several barriers limit their full operationalization, including the cost of imagery, lack of integrated workflows, and limited practical training in model development and deployment. This study presents an open, reproducible, and transferable framework that leverages publicly available USDA NAIP imagery within the I-GUIDE platform. The training modules are designed for students, instructors, professionals, and municipal practitioners, and cover the full workflow, including training data preparation, model development using open-source image segmentation methods, comparison with pre-trained models, and model retraining for knowledge transfer. This approach provides hands-on learning in remote sensing and GeoAI while enabling consistent and scalable urban tree canopy mapping across cities, supporting planners and decision-makers in managing and expanding urban forests.