Doodleverse/segmentation_gym
A neural gym for training deep learning models to carry out geoscientific image segmentation. Works best with labels generated using https://github.com/Doodleverse/dash_doodler
This project helps geoscientists, environmental researchers, and remote sensing specialists analyze satellite, aerial, or other geoscientific images by automatically identifying and outlining specific features like coastlines, rivers, or land cover. You feed it your geoscientific images (like JPGs or PNGs) along with corresponding human-labeled examples, and it outputs a trained model capable of segmenting new, unlabeled images. This is for practitioners who need to efficiently process large volumes of imagery for environmental monitoring, mapping, or other geographical analyses.
No commits in the last 6 months.
Use this if you need to train robust deep learning models to automatically delineate features within geoscientific imagery, especially when working with multispectral or Earth Observation data.
Not ideal if your primary need is general image classification or object detection rather than precise pixel-level segmentation within geographical contexts.
Stars
53
Forks
14
Language
Python
License
MIT
Category
Last pushed
Jul 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Doodleverse/segmentation_gym"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
WHU-Sigma/HyperSIGMA
The official repo for [TPAMI'25] "HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model"
manideep2510/eye-in-the-sky
Satellite Image Classification using semantic segmentation methods in deep learning
motokimura/spacenet_building_detection
Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite...
rogerxujiang/dstl_unet
Dstl Satellite Imagery Feature Detection
Paulymorphous/skeyenet
Road and Building Segmentation in Satellite Imagery