# KichangKim/DeepDanbooru

AI based multi-label girl image classification system, implemented by using TensorFlow.

Repository: https://github.com/KichangKim/DeepDanbooru
Canonical: https://ross.abutalabs.com/products/deepdanbooru
Language: Python
License: MIT
License Family: permissive
Topics: danbooru, tensorflow, machine-learning
Last push: 2026-07-04T00:17:04+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 8, longevity 100
- inputs: {"age_days": 2448, "days_push": 61, "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 2937, forks 266 (observed 2026-08-28T04:07:30.930704+00:00)

## What it is
DeepDanbooru is a Python/TensorFlow system that estimates Danbooru-style tags for anime-style girl images using multi-label classification. It includes a CLI for training custom projects on your own datasets and evaluating images.

## Use cases
- tag anime images automatically
- estimate danbooru tags for an image
- train a multi-label image classifier on my own dataset
- auto-tag artwork for booru-style image boards
- generate tags from anime pictures for dataset labeling

## When to choose
- you need Danbooru-style tag prediction for anime images
- you want to train a custom multi-label image tagging model with TensorFlow
- you want a simple CLI to evaluate images against a trained tag model

## When to avoid
- you need general-purpose (non-anime) image classification
- you prefer PyTorch-based tooling
- you need a hosted GUI service rather than a local Python tool

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, image-processing, cli
- domain: machine-learning, computer-vision, image-processing
- platform: python, cross-platform, cli
- tags: anime-image-tagging, multi-label-classification, tensorflow, danbooru-tags, image-tag-estimation

## Member repositories
- KichangKim/DeepDanbooru (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.930704+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 2026-08-30T07:33:06.154676+00:00, confidence not recorded.
  - readme: https://github.com/KichangKim/DeepDanbooru (fetched 2026-08-28T04:07:30.930704+00:00, sha b5ab184a6026)
  - registry_pypi: https://pypi.org/pypi/deepdanbooru/json (fetched 2026-08-29T09:48:19.843921+00:00, sha 1e5735bccb6d)
- Data as of 2026-08-30T08:39:29.467469+00:00.