Projects sharing features with Tensorspace

This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene

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

This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum

This project is a collection of educational resources and reference implementations for neural network development using TensorFlow. It serves as a comprehensive learning course, machine learning curriculum, and practical implementation guide for building deep learning architectures. The codebase provides instructional materials and examples covering a wide range of model types, including convolutional neural networks for image classification, recurrent networks and long short-term memory cells for sequential data, and autoencoders for generative modeling. It also includes implementations for

Lucid is a TensorFlow interpretability toolkit and visualization library designed to analyze the internal representations of neural networks. It functions as a gradient-based optimization framework that generates images and atlases to reveal the features learned by specific neurons and layers. The library enables the creation of activation atlases and the mapping of high-dimensional neural activations into lower-dimensional spaces to study model behavior. It utilizes differentiable image parametrization to optimize visual inputs that maximally activate network components. The system covers a

This project is a comprehensive educational resource and tutorial handbook for building, training, and deploying machine learning models using TensorFlow 2. It serves as a structured learning guide covering core deep learning concepts, including neural network architectures, automatic differentiation, and tensor operations. The handbook provides technical guidance on optimizing execution efficiency through GPU memory management, distributed training, and model quantization. It also includes detailed manuals for constructing high-performance data pipelines and exporting models for production s

mmocr is a PyTorch-based optical character recognition framework designed for training and deploying text detection, recognition, and key information extraction models. It serves as a comprehensive toolbox for scene text detection and recognition, providing specialized libraries for locating text regions and converting visual text into machine-encoded strings. The project distinguishes itself through a research framework for key information extraction and advanced text spotting capabilities. These include point-based spotting using transformers and the use of parameterized Bezier curves to id

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

Pannellum is a WebGL panorama viewer and virtual tour framework used to render equirectangular or cubemap images as immersive 360-degree environments. It functions as a multiresolution image renderer and a panoramic video player, supporting both static images and spherical video playback. The project distinguishes itself by its ability to handle extremely large, high-resolution panoramas through multiresolution tile generation and loading. It enables the creation of interactive virtual tours by linking multiple panoramic scenes together using transition fades and interactive hotspots. The sy

ogl is a WebGL graphics library and 3D scene graph engine designed for rendering three-dimensional scenes. It provides a lightweight framework for managing geometries and coordinating spatial transformations within a hierarchical system. The project includes a PBR shader system for creating realistic materials and a GPGPU computation framework for performing large-scale general-purpose calculations and particle simulations on the graphics processor. It also features a post-processing suite for applying visual filters to rendered scenes via frame buffers. The library covers broader capabiliti

Vanta is a browser-based engine and library for rendering real-time, interactive 3D animations and stylized visual effects. It initializes and manages WebGL graphics within the HTML5 Canvas element to create animated digital art and dynamic backgrounds for web pages. The engine focuses on interactivity, mapping mouse and touch inputs to real-time visual changes. It provides configuration tools to adjust visual parameters, such as colors and animation properties, to align with specific branding and aesthetic requirements. The system handles the full animation lifecycle, including GPU renderin

This project is a three-dimensional developer portfolio template and web application. It uses Three.js to render interactive 3D models, animations, and environmental effects directly within the browser to create an immersive professional showcase. The application integrates artificial intelligence to provide automated responses to visitor inquiries and includes a community forum where authenticated users can share knowledge. It also features a system for generating personalized learning roadmaps based on user profile data and an algorithmic content recommendation system to improve post discov

Cesium is a JavaScript library designed for rendering high-precision 3D globes and 2D maps within web browsers. It functions as a visualization engine that leverages hardware-accelerated graphics to display complex geographic data, terrain, and imagery. The library distinguishes itself through a modular architecture that supports the streaming of massive geographic datasets. By employing tiled data delivery and hierarchical level-of-detail optimization, it maintains performance while navigating large-scale environments. It also includes a time-dynamic state management system, which synchroniz

This project is a web-based prize drawing tool and raffle manager that uses a 3D sphere-based interface to execute randomized winner selections. It combines a Three.js visualization layer with an Express backend to simulate a lottery drawing process within a browser. The application allows for the configuration of prize tiers, quantities, and drawing rules through JSON files, while managing winner eligibility and restrictions. It facilitates the coordination of event giveaways by importing participant lists and exporting final results via Excel files for auditing and record-keeping. The syst

OpenSC2K is an open-source JavaScript city builder engine designed as a recreation of SimCity 2000. It functions as a web-based simulation that uses the Phaser 3 framework to implement game loops and entity management. The project utilizes WebGL and Canvas rendering to visualize large-scale urban environments. It includes a coordinate-based camera system that enables panning and zooming across the reconstructed game world. The engine incorporates a data pipeline to parse legacy city files and graphics assets, allowing it to reconstruct and display urban layouts within a modern web browser.

This project is a web-based 3D experience and interactive gallery designed as a personal portfolio. It uses a virtual room simulation to create a spatial representation of a physical environment where users can navigate and explore digital art and creative work. The environment is rendered directly in the browser as an interactive 3D gallery, allowing users to engage with a spatial showcase through first-person navigation. The project utilizes WebGL-based GPU rendering and custom shader-based lighting to display complex spatial environments. It incorporates asynchronous asset loading and an

SandDance is a hardware-accelerated visualization library and web-based data explorer designed for the interactive analysis of large, non-aggregated datasets. It functions as an interactive data visualization tool that renders complex datasets and intricate visuals within a browser. The project provides an embeddable data canvas consisting of web components and tags, allowing for the integration of full visualization interfaces and interactive charts into external web applications. It utilizes WebGL hardware acceleration to efficiently render large volumes of data as interactive graphics. Th

This project is a creative coding showcase and interactive 3D portfolio template. It utilizes JavaScript and ThreeJS to render a navigable browser environment for presenting professional projects and digital artwork. The project implements a WebGL interactive gallery and immersive digital showcases. These environments use hardware-accelerated graphics to provide 3D navigation and creative web animations. The technical implementation includes a 3D scene with camera movement and lighting, supported by GLTF model loading and raycaster-based interaction. The architecture employs an entity-compon

noclip.website is a web-based interactive repository and viewer for archived 3D game geometry. It functions as a digital game level museum and archive, providing a browser-based interface to explore the visual and structural history of video game levels. The platform enables users to interact with extracted game scenes through a free-roaming camera and a temporal timeline. These tools allow for scrubbing through game events, freezing specific scene states, and analyzing the layout and design of archived environments. The system manages 3D scene visualization through WebGL rendering and stati

Blockbench is a specialized low-poly 3D modeler and texture painter designed for creating models and pixel art textures. It functions as an extensible 3D editor that allows for the production of assets intended for game engines and rendering software. The editor is distinguished by its plugin-based architecture, which enables the development of custom scripts to automate design workflows and add specialized tools. It further integrates a texture painting system that applies pixel art directly onto 3D meshes to achieve a stylized aesthetic. The software covers high-quality 3D rendering for pr

MUI X is a collection of advanced React UI components for building data-rich applications, including a data grid, charting library, date and time pickers, scheduler, and tree view. The library is built with accessibility as a core principle, ensuring all components meet WCAG and WAI-ARIA standards for keyboard navigation and screen reader announcements. The components are designed for extensibility and performance. The data grid offers comprehensive data management with sorting, filtering, pagination, column pinning, row grouping, inline editing, and Excel export. The charting library support

webgl-globe is a WebGL globe visualization library and geospatial renderer used to display latitude and longitude spatial data on an interactive 3D globe. It functions as a 3D data visualization tool that maps coordinate-based datasets into a three-dimensional environment. The library provides capabilities for interactive geographic visualization and spatial data animation, allowing for the rendering of geographic coordinates and the creation of automated motion sequences to illustrate trends or movements over time. It utilizes hardware acceleration to implement a web-based map interface, em

This project is a cross-platform graphics wrapper and translation layer that implements the OpenGL ES and EGL specifications. It functions as a graphics API bridge, mapping OpenGL ES calls and WebGL content to platform-specific hardware APIs such as Vulkan and Metal to ensure consistent rendering across different operating systems. The system features a shader translation service that validates shading language code and transpiles it into multiple target languages, including HLSL, SPIR-V, and Metal SL. It employs a pluggable backend architecture to select the appropriate hardware rendering AP

VivaGraphJS is a JavaScript graph visualization library used to render interactive network diagrams and relational data in web browsers. It features a force-directed layout engine that employs physics-based simulations, using spring and charge models to calculate balanced spatial distributions for nodes and links. The library utilizes a modular rendering architecture that decouples mathematical layout logic from the visual output. This allows for interchangeable rendering pipelines, supporting both vector-based SVG diagrams and hardware-accelerated WebGL rendering for large-scale visualizatio

Vizceral is a web-based interactive graph visualization tool and network topology analytics dashboard. It functions as a WebGL network traffic visualizer designed to render animated graphs that display data flow and connection volumes between network nodes. The tool focuses on distributed system monitoring and real-time traffic analysis. It maps network topologies through interactive tiered views, allowing users to navigate from global summaries down to individual node interactions to identify dependencies and communication patterns. The system handles network traffic visualization and topol

webgl-fundamentals is a comprehensive educational resource and graphics tutorial for learning hardware-accelerated 2D and 3D rendering using the WebGL API. It serves as a structured 3D graphics curriculum and GPU programming reference, guiding users through the graphics pipeline from basic geometry to advanced rendering techniques. The project provides detailed guides on GLSL shader development, including the creation of vertex and fragment shaders. It specifically focuses on the implementation of real-time lighting models—such as directional, point, and spot lighting—and the application of s

The Book of Shaders is an interactive educational guide and curriculum for learning GLSL fragment shader programming to create procedural graphics and visual effects. It provides a structured learning path and a categorized reference guide for data types, built-in functions, and mathematical operations used in shader development. The project features a web-based shader sandbox and interactive editor that allows for real-time iteration and visualization of GLSL code. Users can experiment with procedural art and share their results via unique URLs. The curriculum covers a wide range of graphic