Features

NSFW Classifications - Ships a pre-trained model that classifies images into five NSFW categories for content moderation.
NSFW Classifiers - Classifies images as porn, hentai, sexy, neutral, or drawing using a TensorFlow.js model running in the browser.
Client-Side Inference - Executes a pre-trained convolutional neural network entirely in the browser using TensorFlow.js.
NSFW Classifiers - Classifies images as safe or not safe for work directly in the browser using a pre-trained TensorFlow.js model.
TensorFlow.js Models - A pre-trained neural network that categorizes images into NSFW and safe content classes using TensorFlow.js.
Image Classification - Provides a pre-trained neural network that assigns NSFW category labels to images with confidence scores.
Image Data Preprocessing - Converts raw image data into normalised tensor inputs with resizing and channel reordering for the neural network.
Bundled Weight Embeddings - Ships pre-trained model weights embedded in the package for instant offline classification.
Client-Side Model Loading - Loads a pre-trained neural network model from bundled definitions, hosted URLs, or local paths for classification.
Content Moderation Tools - Moderates image content directly in the browser without sending images to a server for analysis.
NSFW Classifiers - Classifies images for NSFW content on the server side using TensorFlow.js Node backend.
NSFW Classification - Runs NSFW image classification on a Node.js backend for API or server-side content moderation workflows.
Model Lifecycle Management - Provides explicit load, predict, and dispose methods to control memory and tensor resource allocation.
Model Architecture Selection - Offers multiple bundled model architectures like MobileNetV2 and InceptionV3 for users to choose from.
NSFW Content Filters - Integrates NSFW image classification into React Native mobile apps for on-device content filtering.
Pre-trained Models - Loads and selects between different pre-trained model architectures like MobileNetV2 or InceptionV3 for image classification.
Model Weight Caching - Caches loaded model artifacts in IndexedDB to skip re-downloading on subsequent page visits.
Server-Side Image Processing - Runs NSFW classification model on the server using TensorFlow.js Node backend for API workflows.
NSFW Detection Libraries - Detects adult content in images on mobile devices using TensorFlow.js for React Native applications.
On-Device Classifications - Integrates the NSFW classifier into React Native mobile apps for on-device content filtering.
Confidence Scoring - Returns a ranked list of category labels with floating-point confidence values from the softmax output layer.
Deep Learning Frameworks - Client-side NSFW detection using TensorFlow.js.

Istoric stele

infiniterednsfwjs

Name: infinitered/nsfwjs
Author: infinitered

View on GitHub

8,908 stele590 fork-uriTypeScriptMIT4 vizualizărinsfwjs.com

Nsfwjs

NSFW detection on the client-side via TensorFlow.js

Features

NSFW Classifications - Ships a pre-trained model that classifies images into five NSFW categories for content moderation.
NSFW Classifiers - Classifies images as porn, hentai, sexy, neutral, or drawing using a TensorFlow.js model running in the browser.
Client-Side Inference - Executes a pre-trained convolutional neural network entirely in the browser using TensorFlow.js.
NSFW Classifiers - Classifies images as safe or not safe for work directly in the browser using a pre-trained TensorFlow.js model.
TensorFlow.js Models - A pre-trained neural network that categorizes images into NSFW and safe content classes using TensorFlow.js.
Image Classification - Provides a pre-trained neural network that assigns NSFW category labels to images with confidence scores.
Image Data Preprocessing - Converts raw image data into normalised tensor inputs with resizing and channel reordering for the neural network.
Bundled Weight Embeddings - Ships pre-trained model weights embedded in the package for instant offline classification.
Client-Side Model Loading - Loads a pre-trained neural network model from bundled definitions, hosted URLs, or local paths for classification.
Content Moderation Tools - Moderates image content directly in the browser without sending images to a server for analysis.
NSFW Classifiers - Classifies images for NSFW content on the server side using TensorFlow.js Node backend.
NSFW Classification - Runs NSFW image classification on a Node.js backend for API or server-side content moderation workflows.
Model Lifecycle Management - Provides explicit load, predict, and dispose methods to control memory and tensor resource allocation.
Model Architecture Selection - Offers multiple bundled model architectures like MobileNetV2 and InceptionV3 for users to choose from.
NSFW Content Filters - Integrates NSFW image classification into React Native mobile apps for on-device content filtering.
Pre-trained Models - Loads and selects between different pre-trained model architectures like MobileNetV2 or InceptionV3 for image classification.
Model Weight Caching - Caches loaded model artifacts in IndexedDB to skip re-downloading on subsequent page visits.
Server-Side Image Processing - Runs NSFW classification model on the server using TensorFlow.js Node backend for API workflows.
NSFW Detection Libraries - Detects adult content in images on mobile devices using TensorFlow.js for React Native applications.
On-Device Classifications - Integrates the NSFW classifier into React Native mobile apps for on-device content filtering.
Confidence Scoring - Returns a ranked list of category labels with floating-point confidence values from the softmax output layer.
Deep Learning Frameworks - Client-side NSFW detection using TensorFlow.js.

Alternative open-source pentru Nsfwjs

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Nsfwjs.

tensorflow/tfjs-models
tensorflow/tfjs-models
14,791Vezi pe GitHub
This project is a collection of pre-trained machine learning models and conversion pipelines designed for running inference directly in the browser using TensorFlow.js. It provides a library of ready-to-use models for computer vision, audio classification, and natural language processing tasks. The suite includes specialized tools for transforming Python-based Keras models into JSON formats compatible with web environments. It enables the deployment of these models by fetching architectures and weight shards via HTTP for client-side execution. The project covers a broad range of capabilities
TypeScript
Vezi pe GitHub14,791
tensorflow/tfjs-core
tensorflow/tfjs-core
8,437Vezi pe GitHub
TensorFlow.js is a JavaScript machine learning library and browser-based runtime used to build, train, and execute models. It functions as a WebGL accelerated tensor engine, providing a foundation for high-performance linear algebra operations and an automatic differentiation framework for computing gradients. The project distinguishes itself through its ability to run machine learning directly in web environments, supporting both client-side inference and browser-based training. It enables the deployment of Python-based models by converting Keras or TensorFlow models into compatible formats
TypeScriptdeep-learningdeep-neural-networksgpu-acceleration
Vezi pe GitHub8,437
tensorflow/tfjs
tensorflow/tfjs
19,134Vezi pe GitHub
TensorFlow.js is a JavaScript machine learning library used for training and deploying models in web browsers and server-side environments. It functions as a browser-based model trainer, a WebAssembly inference engine, and a WebGPU accelerated tensor library for low-level linear algebra. The project also includes a model converter to transform Python-based models into optimized formats for JavaScript execution. The library distinguishes itself through a pluggable backend architecture that allows mathematical operations to be executed via CPU, WebGL, or WebGPU. It supports the conversion of Py
TypeScript
Vezi pe GitHub19,134

Întrebări frecvente

Ce face infinitered/nsfwjs?

NSFW detection on the client-side via TensorFlow.js

Care sunt principalele funcționalități ale infinitered/nsfwjs?

Principalele funcționalități ale infinitered/nsfwjs sunt: NSFW Classifications, NSFW Classifiers, Client-Side Inference, TensorFlow.js Models, Image Classification, Image Data Preprocessing, Bundled Weight Embeddings, Client-Side Model Loading.

Care sunt câteva alternative open-source pentru infinitered/nsfwjs?

Alternativele open-source pentru infinitered/nsfwjs includ: tensorflow/tfjs-models — This project is a collection of pre-trained machine learning models and conversion pipelines designed for running… tensorflow/tfjs — TensorFlow.js is a JavaScript machine learning library used for training and deploying models in web browsers and… tensorflow/tfjs-core — TensorFlow.js is a JavaScript machine learning library and browser-based runtime used to build, train, and execute… yahoo/open_nsfw — Open NSFW is a deep learning image classifier and content filter designed to identify explicit or unsafe visual… xenova/transformers.js — Transformers.js is a JavaScript library and web machine learning framework designed to run pretrained transformer… harthur/brain — Brain is a JavaScript library for building, training, and running feed-forward neural networks. It implements a…