NSFWJS is a client-side JavaScript library for detecting NSFW (Not Safe For Work) content in images using TensorFlow.js. It provides a simple API to load pre-trained models (MobileNetV2, MobileNetV2Mid, InceptionV3) and classify images into five categories: Drawing, Hentai, Neutral, Porn, and Sexy. The library is designed for both browser and Node.js environments, with backend selection guidance for optimal performance (WebGL, WebGPU, WASM, CPU). The core architecture consists of a lightweight `NSFWJS` class that handles model loading, inference, classification, and disposal, with support for tree-shaking via separate model imports. The repository also includes several demo applications: a full-featured React + Vite demo with Web Worker offloading, camera support, and file drop; a Node.js Express server example; and a minimal HTML/script tag demo. While primarily an application library, it is hybrid in nature as it bundles pre-trained model weights (quantized and base64-encoded) and includes model conversion scripts, making it both a software tool and a model distribution package. The library relies on TensorFlow.js as a peer dependency and uses IndexedDB for model caching in the browser.
This repository is a large model zoo (500+ models) focused on converting and quantizing pre-trained computer vision models for edge deployment across multiple frameworks (TFLite, ONNX, OpenVINO, CoreML, TensorRT). It provides hundreds of download scripts for pre-converted model files, conversion pipelines (PyTorch/ TensorFlow to ONNX/TFLite), and a modest set of inference demo scripts for real-time video processing. The repo is primarily a research/engineering resource for edge AI practitioners, not a software application. It exhibits heavy duplication across model directories, relies on an external S3 bucket for model distribution, and uses older framework versions (TensorFlow 1.x/2.x, ONNX opset 11-13). Despite these maintenance concerns, the systematic conversion workflow and post-processing ONNX subgraph generators (e.g., NMS, box decoding) represent reusable patterns for anyone building end-to-end inference pipelines. The repo is hybrid in nature: while classified as data_research due to its focus on pre-trained model artifacts and lack of original training code, it also contains application-like demo code and CLI entry points.
This repository is a web component library focused on accessibility, providing custom HTML elements for building inclusive web applications. It implements alternative input methods including standard mouse/keyboard/touch and pose/body tracking using TensorFlow's PoseNet model. The architecture follows web component principles using LitElement and Polymer, with a clear hierarchy of base classes (AbstractInputElement, AbstractUIElement) and specialized components for various UI patterns. The library emphasizes accessibility features like ARIA support, keyboard navigation, and screen reader compatibility. The codebase demonstrates strong craftsmanship in its utility implementations, particularly in coordinate transformation handling (mouse-position.ts), vector mathematics (vec2.ts), and general-purpose helper functions (utils.ts). The webcam integration (webcam.ts) shows proper resource management and lifecycle handling. However, the library suffers from significant technical drift due to outdated dependencies (lit-element 0.5.2, tfjs 0.13.0, typescript 3.1.6), which would require substantial updates for modern use. While the core architectural patterns are sound, the dependency versions limit practical reusability without migration work.