#139139th of 214 in ML frameworks and libraries
segment-geospatial
Python package for segmenting satellite imagery and GeoTIFFs with SAM models
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.2k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Aug 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
SamGeo wraps Meta's Segment Anything Model (SAM, SAM 2, SAM 3), HQ-SAM and Fast SAM for geospatial rasters. It downloads TMS map tiles to GeoTIFF, segments with point, box or text prompts (text via Grounding DINO), and exports masks as GeoPackage, Shapefile or GeoJSON. It also offers an optional FastAPI REST server and a separate QGIS plugin.
Who it is for: GIS and remote sensing practitioners segmenting imagery in Python or QGIS
Strengths
- Exports results to GeoPackage, Shapefile and GeoJSON for use in GIS tools
- Optional pip extras (samgeo2, samgeo3, hq, fast, text, api) keep installs smaller
- Supports text prompts, box prompts, interactive markers and timeseries imagery
- Also available as a QGIS plugin and an ArcGIS toolbox
Weaknesses
- Large rasters need a GPU; README recommends at least 8 GB of GPU memory
- SAM 3 install on Windows needs manual steps, including triton-windows
- Interactive mapping and examples assume Jupyter; no standalone web UI
- Bulk tile downloads may require permission from the basemap provider
What it needs
- GPU optional
- Docker
- Needs PyTorch, Grounding DINO (text prompts), FastAPI and Uvicorn (REST API), Jupyter (examples)
- Models: SAM, SAM 2, SAM 3, HQ-SAM, Fast SAM
Also in ML frameworks and libraries
See all 214| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 94 out of 100 |
| #4 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |