Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
- autodiff
- deep-learning
- machine-learning
- rust
99,825 visible repositories in the index
1–13 of 13 · Most stars
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learn...
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
[IEEE TMI Best Paper Award] Official Implementation for UNet++
UnrealCV: Connecting Computer Vision to Unreal Engine
Shadow is a discrete-event network simulator that directly executes real application code, enabling you to simulate distributed systems with thousands of network-connected processes in realistic and scalable private network experiments using your laptop, desktop, or server running Linux.
Machine learning for NeuroImaging in Python
Formula Recognition & Office Editing | Handwriting & PDF to LaTeX/Markdown | Secure API Integrations.
A 3D fruit fly living on your macOS desktop, driven by a live spiking simulation of the real FlyWire connectome
Wrapper for RDKit's RunReactants to improve stereochemistry handling
Translated天气战士 (Weather Fighter, "weather warrior") Weather Fighter —— Just honestly looking at the weather is boring, isn't it?
NeuroAnatomy Toolbox: An R package for the (3D) visualisation and analysis of biological image data, especially tracings of single neurons.
Coq formalization of algorithms due to Tarjan and Kosaraju for finding strongly connected graph components using Mathematical Components and SSReflect [maintainers=@CohenCyril,@palmskog]