# devzwy/open_nsfw_android

🔥🔥🔥色情图片离线识别，基于TensorFlow实现。识别只需20ms,可断网测试，成功率99%，调用只要一行代码，从雅虎的开源项目open_nsfw移植，该模型文件可用于iOS、java、C++等平台

Repository: https://github.com/devzwy/open_nsfw_android
Canonical: https://ross.abutalabs.com/products/open_nsfw_android
Language: Java
License Family: other
Topics: nsfw, nsfw-android, tensorflowlite, tensorflow-lite, tensorflow-lite-nsfw, tensorflow, photographs-to-discern-yellow, yellow-chart, pornography, picture-recognition, picture-recognition-sdk, photo-recognition-sdk, photo-recognition, photo-identification, tensorflow-android, tensorflow-examples, tensorflow-models, tensorflow-gpu, nsfw-filter
Archived: true
Last push: 2023-04-08T03:58:38+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2668, "days_push": 1243, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1957, forks 344 (observed 2026-08-28T04:05:59.157780+00:00)

## What it is
An Android library for offline NSFW (pornographic) image detection, ported from Yahoo's open_nsfw project using TensorFlow Lite. It classifies images in ~20ms with a single-line API, and the model file can also be used on iOS, Java, C++, and other platforms.

## Use cases
- detect pornographic images offline on android
- moderate user-uploaded photos for nsfw content
- filter inappropriate images in a chat or feed app
- scan image files for adult content without a server
- integrate open_nsfw model into a mobile app
- classify images as safe or unsafe on device

## When to choose
- you need fast, fully offline NSFW image classification on Android with minimal integration effort
- you want a portable tflite/pb model reusable across iOS, Java, or C++

## When to avoid
- you need actively maintained, highly accurate NSFW detection
- you need video or live-stream moderation
- you require a licensed, supported SDK with guarantees

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, computer-vision
- domain: machine-learning, image-processing, mobile-development, security
- platform: cross-platform
- tags: nsfw-detection, tensorflow-lite, offline-inference, content-moderation, image-classification, android

## Member repositories
- devzwy/open_nsfw_android (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:59.157780+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 2026-08-30T03:06:00.759776+00:00, confidence not recorded.
  - readme: https://github.com/devzwy/open_nsfw_android (fetched 2026-08-28T04:05:59.157780+00:00, sha afa70e0b7ac2)
- Data as of 2026-08-30T08:39:29.467469+00:00.