# tryolabs/luminoth

Deep Learning toolkit for Computer Vision.

Repository: https://github.com/tryolabs/luminoth
Canonical: https://ross.abutalabs.com/products/luminoth
Homepage: https://tryolabs.com
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: tensorflow, sonnet, deep-learning, computer-vision, object-detection, python, machine-learning, toolkit, faster-rcnn
Last push: 2023-03-24T23:52:00+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3485, "days_push": 1258, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2402, forks 391 (observed 2026-08-28T04:06:43.854914+00:00)

## What it is
Luminoth is an open-source Python toolkit for computer vision built on TensorFlow and Sonnet, focused on object detection with Faster R-CNN and SSD models. It provides a CLI ('lumi') for training, evaluating, and running predictions with pre-trained checkpoints, but is no longer maintained.

## Use cases
- detect objects in images with faster rcnn
- train a custom object detection model in python
- run pretrained object detection on my photos
- tensorflow object detection toolkit
- ssd object detection inference
- train object detector on google cloud ml engine

## When to choose
- you need a simple Python CLI for Faster R-CNN or SSD object detection on legacy TensorFlow 1.x setups
- you want to study or fork a readable object detection implementation

## When to avoid
- starting a new project - the project is officially unmaintained; use Detectron2 or similar instead
- you need modern models like Mask R-CNN, RetinaNet, or YOLO
- you use TensorFlow 2.x or recent Python versions

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing, cli
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, faster-rcnn, ssd, tensorflow, sonnet, pretrained-models, unmaintained, linux, macos, gpu

## Member repositories
- tryolabs/luminoth (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:43.854914+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 2026-08-30T02:34:14.236066+00:00, confidence not recorded.
  - readme: https://github.com/tryolabs/luminoth (fetched 2026-08-28T04:06:43.854914+00:00, sha 830fecd2ef6e)
  - homepage: https://tryolabs.com (fetched 2026-08-29T10:14:40.696904+00:00, sha 7229b16e374f)
- Data as of 2026-08-30T08:39:29.467469+00:00.