TorchGeo
unknown · United StatesScores
1 product on the map — 1 open.
Openness
5 high confidence- license
- MIT (OSI)
- source
- public (github.com/torchgeo/torchgeo)
- core features withheld
- no — maintainer-governed community project; nothing sold
- pretrained-weights-terms
- per-weight licenses, among them CC-BY-4.0, Apache-2.0, MIT, ODC-BY and OpenRAIL (optional pretrained weights the user selects; they do not govern the MIT library)
The library is MIT-licensed, builds from the public repository and is run by its maintainers by consensus, with nothing sold. Its pretrained weights come from many research groups under their own licenses, but a user picks them one by one, and none is needed to use the library.
- https://pypi.org/pypi/torchgeo/json recorded 2026-11-12
PyPI record for torchgeo 0.10.1, uploaded 2026-09-29, License-Expression "MIT", Homepage github.com/torchgeo/torchgeo.
- https://raw.githubusercontent.com/torchgeo/torchgeo/HEAD/.github/GOVERNANCE.md recorded 2026-11-12
Governance policy: "Projects make decisions through consensus of the Maintainers"; "There shall be no undue financial barriers to participation."
- https://raw.githubusercontent.com/torchgeo/torchgeo/HEAD/docs/api/weights/sentinel2.csv recorded 2026-11-12
Sentinel-2 weights table with a License column per weight, including "CC-BY-4.0", "Apache-2.0", "MIT", ODC-BY and OpenRAIL.
- https://raw.githubusercontent.com/torchgeo/torchgeo/HEAD/LICENSE recorded 2026-11-12
LICENSE is the MIT License, "Copyright (c) TorchGeo Contributors."
- https://ungh.cc/repos/torchgeo/torchgeo/files/main recorded 2026-11-12
Repository tree of 4,245 paths with no ee, enterprise, commercial or proprietary directory.
Adoption
2 high confidenceMeasured on monthly PyPI downloads of the torchgeo package.
- https://pypistats.org/api/packages/torchgeo/recent recorded 2026-11-12
last_month 39,822 downloads of torchgeo
Capability
3 high confidenceTorchGeo bundles the datasets, pretrained backbones and training tasks to fit and compare models on satellite imagery, as torchvision does for ordinary photographs. Its pretrained weights are starting points for fine-tuning, so a prediction on a new labeling task still needs a training run.
- https://docs.torchgeo.org/en/stable/api/models.html recorded 2026-11-12
Models API page: pretrained weights grouped under "Sensor-Agnostic Landsat NAIP Sentinel-1 Sentinel-2 Aerial Atmospheric"; "These weights can be used with imagery from any satellite/sensor" for the sensor-agnostic group.
- https://raw.githubusercontent.com/torchgeo/torchgeo/HEAD/README.md recorded 2026-11-12
README: "TorchGeo is a PyTorch domain library, similar to torchvision, providing datasets, samplers, transforms, and pre-trained models specific to geospatial data"; Lightning datamodules "and tasks for various tasks like classification, regression, and semantic segmentation".