# liwenxi/SWIFT-AI

A fast gigapixel processing system

Repository: https://github.com/liwenxi/SWIFT-AI
Canonical: https://ross.abutalabs.com/products/liwenxi-swift-ai
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2024-12-10T12:24:32+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 82
- inputs: {"age_days": 1149, "days_push": 631, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1334, forks 176 (observed 2026-08-28T04:04:25.204930+00:00)

## What it is
SWIFT-AI is a deep learning system for extremely fast gigapixel-level visual understanding in scientific applications, such as detecting strong gravitational lenses for the LSST project. It includes models, code, and links to gigapixel datasets like PANDA.

## Use cases
- process gigapixel images with deep learning
- detect strong gravitational lenses in astronomy surveys
- analyze large field-of-view scientific imagery
- run object detection on gigapixel video like PANDA
- speed up visual understanding of huge scientific images

## When to choose
- you need to analyze gigapixel-scale images or video quickly
- you work in astronomy or scientific imaging with very large fields of view
- you want a research-ready pipeline with pretrained models and datasets

## When to avoid
- you only need standard-resolution image processing
- you need a production-grade supported product rather than research code
- you work outside Python/GPU environments

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, deep-learning, machine-learning
- domain: computer-vision, artificial-intelligence, astronomy, data-science
- platform: python
- tags: gigapixel-imaging, scientific-imaging, gravitational-lensing, visual-understanding, jupyter-notebooks, gpu, linux

## Member repositories
- liwenxi/SWIFT-AI (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.204930+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:44:33.221638+00:00, confidence not recorded.
  - readme: https://github.com/liwenxi/SWIFT-AI (fetched 2026-08-28T04:04:25.204930+00:00, sha db5a89524e75)
- Data as of 2026-08-30T08:39:29.467469+00:00.