awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
transcranial avatar

transcranial/keras-js

0
View on GitHub↗
4,963 stars·493 forks·JavaScript·MIT·18 viewstranscranial.github.io/keras-js↗

Keras Js

Keras-js is a JavaScript inference engine and browser-based machine learning framework designed to execute pre-trained Keras neural networks. It allows for client-side model inference in web browsers or Node.js environments without the requirement of a backend server.

The library utilizes a WebGL tensor accelerator to map mathematical operations to the graphics processor for hardware acceleration. To maintain user interface responsiveness during heavy computations, it incorporates a web worker inference runtime that executes neural network processing in background threads.

The system supports loading models via JSON configuration files and weight tensors. It manages large numerical arrays using WebGL texture storage to facilitate high-speed memory access during tensor execution.

Features

  • Keras Model Execution - A JavaScript library for running pre-trained Keras neural networks directly in the browser or Node.js environment.
  • Web-Based Machine Learning - Provides a framework for integrating and executing machine learning models directly within web browsers.
  • Client-Side Inference - Enables the execution of pre-trained machine learning models directly within the web browser.
  • Browser-Based Frameworks - Implements a deep learning framework specifically designed to run within web browser environments.
  • GPU-Accelerated Computation - Offloads mathematical tensor operations to graphics hardware for high-performance numerical processing.
  • WebGL Tensor Acceleration - Accelerates tensor operations by mapping mathematical computations to WebGL shaders and textures.
  • Inference Execution - Implements the execution of inference tasks on trained models to generate outputs.
  • External Model Loading - Imports and initializes pre-trained Keras models using JSON configuration files and weight tensors.
  • Tensor Texture Storage - Utilizes WebGL texture storage to manage large numerical arrays for high-speed memory access during tensor execution.
  • Inference Runtimes - Provides a background execution system that runs heavy machine learning computations in separate threads.
  • Inference Threading - Executes neural network processing in background web worker threads to maintain user interface responsiveness.
  • Responsive Interface Threading - Offloads heavy neural network computations to background threads to prevent the browser interface from freezing.
  • Deep Learning Frameworks - Run Keras models in the browser using WebGL.
  • Machine Learning Frameworks - Browser-based execution of Keras models with WebGL acceleration.
  • Developer Tools - Engine for running trained models in web browsers.
  • Frameworks and Libraries - Browser-based execution for Keras models.

Star history

Star history chart for transcranial/keras-jsStar history chart for transcranial/keras-js

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does transcranial/keras-js do?

Keras-js is a JavaScript inference engine and browser-based machine learning framework designed to execute pre-trained Keras neural networks. It allows for client-side model inference in web browsers or Node.js environments without the requirement of a backend server.

What are the main features of transcranial/keras-js?

The main features of transcranial/keras-js are: Keras Model Execution, Web-Based Machine Learning, Client-Side Inference, Browser-Based Frameworks, GPU-Accelerated Computation, WebGL Tensor Acceleration, Inference Execution, External Model Loading.

Which projects share features with transcranial/keras-js?

Projects with overlapping indexed features include: tensorflow/tfjs — TensorFlow.js is a JavaScript machine learning library used for training and deploying models in web browsers and… harthur/brain — Brain is a JavaScript library for building, training, and running feed-forward neural networks. It implements a… lasagne/lasagne — Lasagne is a modular neural network framework and symbolic computation engine used for building and training deep… graal-research/poutyne — A simplified framework and utilities for PyTorch. cornellius-gp/gpytorch — GPyTorch is a GPU-accelerated probabilistic framework and PyTorch library for implementing scalable Gaussian process… deepmind/sonnet — Sonnet is a modular machine learning framework and TensorFlow library used for building, training, and managing deep…

Projects sharing features with Keras Js

These projects share indexed features with Keras Js. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • tensorflow/tfjstensorflow avatar

    tensorflow/tfjs

    19,134View on 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
    View on GitHub↗19,134
  • harthur/brainharthur avatar

    harthur/brain

    7,991View on GitHub↗

    Brain is a JavaScript library for building, training, and running feed-forward neural networks. It implements a multilayer perceptron model designed for pattern recognition and function approximation. The library includes a standalone inference engine that converts trained models into portable JavaScript functions. This allows predictions to be executed in browser or Node.js environments without requiring the original library dependencies. The system supports persistent model management through JSON serialization for saving and loading network weights. It also provides a streaming mechanism

    JavaScript
    View on GitHub↗7,991
  • lasagne/lasagneLasagne avatar

    Lasagne/Lasagne

    3,863View on GitHub↗

    Lasagne is a modular neural network framework and symbolic computation engine used for building and training deep learning architectures. Built as a library on top of Theano, it utilizes symbolic expression graphs and lazy evaluation to automate gradient calculations for parameter optimization. The framework emphasizes modularity by allowing the construction of complex neural networks through the composition of independent and reusable layers. It is designed as a hardware-accelerated machine learning library that offloads intensive linear algebra operations to graphics processors to increase

    Python
    View on GitHub↗3,863
  • deepmind/sonnetdeepmind avatar

    deepmind/sonnet

    9,920View on GitHub↗

    Sonnet is a modular machine learning framework and TensorFlow library used for building, training, and managing deep learning models. It functions as a system for composing neural networks from reusable modules and layers that encapsulate their own parameters and internal states. The project provides specialized tools for distributed model training, enabling the synchronization of gradients across multiple hardware devices. It also serves as a model state management system, allowing for the persistence of neural network weights and the export of portable models that separate the computation g

    Python
    View on GitHub↗9,920
Compare all 30 related projects→