torchgeo/torchgeo
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
This data set includes Landsat 8 images and their manually extracted pixel-level ground truths for cloud detection.
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Training images for geostastical simulation
Water Detect Algorithm
Cube++ is a novel dataset collected for illumination estimation problem. It has 4890 raw 18-megapixel images, each containing a SpyderCube color target in their scenes, manually labelled categories, and ground truth illumination chromaticities.
Earth observation processing framework for machine learning in Python
Analysis of land use and cover change using satellite imagery
2 captures since 2026-05-23