obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
This tool helps computer vision practitioners accurately detect small objects within very large images, a common challenge in fields like aerial imagery or medical imaging. It takes in large images and an object detection model, then outputs more precise detection results, even for tiny objects. Researchers, data scientists, and engineers working with high-resolution image analysis will find this useful.
5,160 stars. Used by 1 other package. Actively maintained with 19 commits in the last 30 days. Available on PyPI.
Use this if you need to reliably find small items in large, high-resolution images, where traditional object detection struggles.
Not ideal if your images are small or medium-sized and the objects you need to detect are generally large or medium-sized.
Stars
5,160
Forks
735
Language
Python
License
MIT
Last pushed
Mar 12, 2026
Commits (30d)
19
Dependencies
11
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/obss/sahi"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related frameworks
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...
interpretml/interpret
Fit interpretable models. Explain blackbox machine learning.