EuroSAT Training Sample Application

.NET Core Console App that classifies aerial / satellite images between 1 of 10 classes using ML.NET Image Classification API / Model Builder. Both API and Model Builder use ResNet50.

Projects

• EuroSATTrainSample: Console application using ML.NET Image Classification API
• EuroSATTrainSampleML.ConsoleApp: Auto-generated Model Builder Image Classification project
• EuroSATTrainSampleML.Model: Auto-generated Model Builder Image Classification project

Data Source

EuroSAT https://github.com/phelber/eurosat

[1] Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. Patrick Helber, Benjamin Bischke, Andreas Dengel, Damian Borth. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019.

[2] Introducing EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification. Patrick Helber, Benjamin Bischke, Andreas Dengel. 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018.