Open-source alternatives to Graph Learn

DGL is a Python library for building and training graph neural networks. It functions as a graph message passing framework and a geometric deep learning tool, enabling the development of models that analyze graph-structured data. The library is designed for large-scale graph processing, utilizing distributed training and neighbor sampling to handle datasets with billions of edges. It provides specialized support for heterogeneous graph modeling, allowing for the representation of complex real-world entities with multiple node and edge types. Its capabilities cover a wide range of graph tasks

Angel is a distributed machine learning framework and graph computation engine designed to train predictive models and execute algorithms across a cluster of servers. It functions as a distributed parameter server that synchronizes model weights and gradients across multiple machines to handle massive datasets. The system provides a production environment for model inference deployment to provide real-time predictions for end users. It integrates with Spark to run machine learning workflows and data processing pipelines through a compatible interface. The framework covers distributed graph c

pygcn is a PyTorch library and framework for implementing graph convolutional networks. It provides tools for semi-supervised node classification and the generation of node embeddings from graph-structured data. The system converts graph nodes into low-dimensional vectors based on neighborhood patterns and local similarities. It enables the prediction of node labels by leveraging both a small set of labeled examples and the overall graph topology. The library covers relational data analysis and semi-supervised graph learning. It includes computational primitives for message passing, adjacenc

graph_nets is a graph-structured deep learning framework and library for building message-passing neural networks. It provides tools for designing architectures that operate on nodes and edges to process and reason about data structured as graphs using TensorFlow. The framework implements a message-passing paradigm for iterative information exchange between nodes. This approach enables the development of models that can reason about complex graph-structured inputs for tasks such as path-finding and sorting, or serve as a predictor for the future states and trajectories of physical systems.

GraphCast is a machine learning model that uses graph neural networks to produce global weather forecasts up to ten days ahead at high spatial resolution. The system represents the Earth's surface as an icosahedral mesh, enabling message passing between mesh nodes to capture atmospheric dynamics, and combines this with a learned multiscale processor that operates across coarse-to-fine mesh resolutions. The model is trained on historical ERA5 reanalysis data through a supervised learning objective, and its autoregressive rollout loop feeds predictions back as input to generate multi-step forec

This project is a collection of neural network models and geometric tools designed for image feature matching, spatial alignment, and visual localization. It provides a pre-trained neural network model for identifying high-accuracy correspondences between sparse image features without requiring local training. The system utilizes a graph neural network matcher that employs attention mechanisms and message passing to learn spatial relationships between image feature points. It integrates a RANSAC camera pose estimator to filter feature matches and calculate the relative spatial transformation

This project provides a comprehensive educational curriculum and research resource for deep learning, focusing on the theoretical and technical foundations of neural network implementation. It serves as a structured academic guide for building and training complex models from scratch, covering the essential mathematical primitives, computational graph construction, and automatic differentiation mechanisms required for modern machine learning. The repository distinguishes itself through its extensive coverage of generative modeling and specialized neural architectures. It includes practical im

This project is a collection of TensorFlow 2.x machine learning tutorials and practical code examples. It serves as a deep learning implementation guide for constructing diverse neural network architectures, including convolutional, recurrent, and generative networks. The repository provides templates and examples for several specialized domains, including computer vision for image classification and object detection, natural language processing for text generation and language understanding, and generative AI for synthesizing data using adversarial networks and autoencoders. It also includes

This repository provides a comprehensive educational framework for mastering machine learning and deep learning through a structured curriculum. It integrates theoretical mathematical foundations—including calculus, probability, and linear algebra—with hands-on laboratory implementations that require learners to build algorithms and neural network architectures from scratch. The project distinguishes itself by emphasizing first-principles development, ensuring that students understand the underlying mechanics of backpropagation, layer-wise computation, and model optimization. It covers a broa

Nebula is a distributed graph database designed for storing and querying massive volumes of interconnected vertices and edges across a horizontally scalable cluster. It functions as a Kubernetes-native database and a distributed graph analytics engine, utilizing a Raft-based distributed store to ensure strong consistency and high availability. The system features an OpenCypher query engine for performing complex graph traversals and pattern matching. It distinguishes itself with a decoupled compute-storage architecture and a shared-nothing distributed design, allowing query processing and dat

This project is a collection of deep learning research implementations and a reproduction kit designed to translate theoretical AI papers into working code. It provides a library of neural network architectures and reference implementations for reproducing seminal research concepts through interactive notebooks. The repository distinguishes itself through the implementation of AI theory and scaling laws, covering complexity dynamics, information theory, and the simulation of universal AI agents. It also includes a benchmarking suite for synthetic reasoning, allowing for the evaluation of mode

This project is a comprehensive machine learning educational resource and tutorial series delivered as a collection of interactive Jupyter Notebooks. It provides practical Python implementations for the end-to-end machine learning lifecycle, covering supervised and unsupervised learning, deep learning, and reinforcement learning. The resource distinguishes itself by providing detailed implementation guides for complex architectures, including transformers, generative adversarial networks, and convolutional neural networks. It also features specialized courseware for developing reinforcement l

Huatuo-Llama-Med-Chinese is a medical large language model specialized in processing and generating natural language text in Chinese. It is an instruction-tuned system designed to answer professional healthcare questions by leveraging a dedicated medical knowledge base. The model integrates structured medical literature and knowledge graphs to ensure clinical accuracy during response generation. It employs knowledge-graph augmented inference to combine structured entity relationships with neural network outputs. The system is developed through domain-specific weight adaptation, cross-lingual

This repository serves as the central hub for the Rime input method engine, functioning as a home for the open source community and a repository for input method schemata. It provides a collaborative space for users and developers to coordinate the development of the framework and manage a collection of customizable input rules and keyboard layouts. The project focuses on custom input method development and linguistic schema design. It enables the creation of tailored text entry rules and layouts to support specific languages or personal typing preferences. The framework is supported by a C+

This toolkit serves as a framework for interpreting the decision-making processes of graph neural networks. It functions as a library for analyzing how these models process complex network data, providing methods to identify the specific node attributes and structural patterns that influence predictive outcomes. The project distinguishes itself by employing mask-optimized subgraph extraction and gradient-based attribution mapping to isolate the minimal components of a graph that preserve a model's original prediction. By separating graph processing layers from explanation logic, the architect

WickedEngine is a C++ 3D game engine and framework designed for building high-fidelity three-dimensional applications and graphics projects. It features a modern graphics renderer that implements current standards to produce complex geometry and lighting across different hardware. The engine includes a standalone visual scene editor for designing environments and configuring properties without writing code. It also provides an integrated Lua scripting environment to manage runtime logic and automate engine tasks. The framework covers 3D graphics rendering and application development, includi

Feast is an open-source feature store for machine learning that provides a central platform for defining, storing, and serving features across both training and inference workflows. It operates as a declarative system where feature definitions are written as code in Python files, synchronized to a central registry, and made available for low-latency online retrieval or point-in-time correct historical joins for training datasets. The project abstracts storage behind a pluggable architecture, allowing offline and online backends to be swapped without changing retrieval logic, and coordinates ma

This project is a distributed machine learning platform and sparse deep learning framework designed for training and serving models with high-dimensional sparse data. It functions as an online model serving infrastructure and recommendation system engine, enabling real-time item retrieval and scoring using deep tree matching and neural networks. The system distinguishes itself through a multi-task learning framework that optimizes multiple objective functions within a shared representation space. It features a specialized online serving infrastructure that supports dynamic model hot-loading a

RawTherapee is a professional raw photo processing software and image developer designed to convert raw camera files and high dynamic range data into high quality standard image formats. It functions as a raw format converter and image processor, providing tools for fine-tuning color, exposure, and detail across multiple operating systems. The software utilizes a non-destructive editing model, applying a sequence of reversible transformations to photos without altering the original source files. This approach preserves image quality throughout the digital photo development workflow. The appl

Boost is a collection of portable, high-performance source libraries that extend the C++ standard library. It provides a wide range of reusable components, data structures, and algorithms designed to add capabilities to the base language across different platforms. The project is distinguished by its extensive focus on compile-time template metaprogramming and generic programming. It implements advanced architectural patterns such as policy-based design, concept-based type validation, and the use of SFINAE for conditional template resolution to minimize runtime overhead. The library covers a

Deep Java Library is a Java deep learning framework and JVM model inference engine. It provides a high-level API for building and deploying deep learning models within the Java ecosystem, acting as a cross-platform runtime for executing models across CPUs, GPUs, and mobile devices. The library is engine-agnostic, allowing users to switch between different deep learning engines such as PyTorch, TensorFlow, and MXNet while maintaining a single unified API. This enables the deployment of the same model across different backends without changing the application code. The framework supports the f

LÖVE is a cross-platform game engine and framework for developing two-dimensional games using the Lua programming language. It provides a 2D graphics API for rendering shapes, images, and sprites across multiple desktop and mobile platforms. The framework enables the development of a single codebase that can be deployed to Windows, macOS, Linux, Android, and iOS. It utilizes a Lua-based scripting interface to control internal engine systems. The project covers 2D game development, mobile game development, and cross-platform game deployment.

Yoga is a cross-platform layout engine and embeddable core that determines the dimensions and offsets of hierarchical element trees. It provides a C++ implementation of the Flexbox layout model to calculate element positions and sizes based on web standards, ensuring a uniform appearance across diverse devices and operating systems. The engine is designed for portability via a C API, allowing the layout logic to be integrated into various host languages and platforms. It utilizes an incremental layout system that identifies modified subtrees and recalculates positions only for changed nodes a

Sorbet is a static analysis tool and type checker designed for Ruby codebases. It identifies type inconsistencies, potential bugs, and logic errors by examining source code without execution, helping to improve software reliability and maintainability in large-scale projects. The system employs a constraint-based type inference engine that evaluates expressions against defined annotations to validate data structures. To support rapid development, it utilizes incremental analysis and caching to provide feedback by processing only modified files and their dependencies. Beyond static analysis,

kphp-kdb is a NoSQL database engine and PHP extension designed for high-throughput read and write operations. It functions as a persistence layer integrated directly into the PHP runtime, providing a non-relational storage system for high-load environments. The project incorporates a compiler that translates dynamic PHP source code into statically typed C++ code. This process eliminates runtime interpretation overhead to achieve native execution speeds and lower resource consumption. The system leverages native C++ bindings and a schema-less storage engine to ensure low-latency data access.

This project is a deep learning text classification framework and neural text analysis library. It provides tools for categorizing textual data, adapting large language models through fine-tuning, and treating classification tasks as sequence generation problems using transformer architectures. The framework distinguishes itself through the implementation of ensemble learning, using boosting to combine predictions from multiple architectures to increase accuracy. It also includes a toolkit for fine-tuning pre-trained models via layer updates and the ability to restore model sessions for real-

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥