terrastackai/terratorch
A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
This tool helps geospatial professionals customize powerful AI models for tasks like image segmentation or land classification. You provide your specialized geospatial data and a chosen large pre-trained model, and it produces a fine-tuned model ready for your specific analytical needs. It's for data scientists, GIS analysts, and remote sensing specialists working with satellite imagery or other geospatial datasets.
749 stars. Actively maintained with 35 commits in the last 30 days. Available on PyPI.
Use this if you need to adapt an existing geospatial AI model to accurately perform tasks on your unique or niche geospatial dataset.
Not ideal if you're looking for pre-trained models ready for immediate use without any customization or training.
Stars
749
Forks
141
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
35
Dependencies
31
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/terrastackai/terratorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
torchgeo/torchgeo
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
DataverseLabs/pyinterpolate
Kriging | Poisson Kriging | Variogram Analysis
OSGeo/grass
GRASS - free and open-source geospatial processing engine
sentinel-hub/eo-learn
Earth observation processing framework for machine learning in Python
fatiando/verde
Processing and gridding spatial data, machine-learning style