Open-source alternatives to Sketch Code

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

This is a structured deep learning curriculum for programmers, delivered as a collection of Jupyter notebooks. It teaches the fundamentals of training neural networks for computer vision, natural language processing, tabular data analysis, and collaborative filtering using PyTorch and the fastai library. The course is designed to be hands-on, guiding learners from building a training loop from scratch to fine-tuning pretrained models for a variety of practical tasks. The curriculum distinguishes itself by covering the full lifecycle of a deep learning project, from data preparation and augmen

This project is a TensorFlow and Keras implementation of the Mask R-CNN architecture. It provides a framework for performing simultaneous object detection and instance segmentation, transforming raw images into segmented masks and bounding boxes for individual object identification. The toolset enables custom computer vision training through fine-tuning pre-trained weights and integrating user-provided datasets. It includes capabilities for distributed GPU training to accelerate the optimization of large vision models. The framework covers model evaluation using standard precision metrics an

bert4keras is a lightweight reimplementation of the BERT transformer architecture for the Keras deep learning framework. It serves as a natural language processing toolkit and transformer model library used for text classification, sequence labeling, and semantic embedding extraction. The framework includes a sequence-to-sequence model system for question answering and text generation, as well as a model inference server to deploy trained transformers as web APIs for real-time predictions. Capabilities cover a broad range of natural language understanding tasks, including reading comprehensi

This project is a time series forecasting model implemented in Python and Keras. It is a deep learning system designed to predict future values in sequential datasets by training long short-term memory neural networks on historical numerical data. The implementation focuses on sequential data analysis, specifically applying these models to financial market prediction to forecast price movements and trends. The architecture covers data preprocessing through min-max feature scaling and sliding-window transformations. It utilizes recurrent neural network cells with gating mechanisms for long-te

This project is a structured educational curriculum designed to teach the fundamentals of building and training deep learning models. It provides a comprehensive guide for implementing neural networks using high-level machine learning frameworks and the Python programming language, focusing on practical, hands-on exercises for beginners. The tutorial distinguishes itself by covering the full lifecycle of model development, from initial construction to production-ready optimization. It includes specific modules on refining model performance through weight quantization and addressing data bias

This project is a deep learning face classification system that detects human faces and classifies gender and emotion. It utilizes convolutional neural networks and computer vision tools to analyze facial attributes in both static images and live video streams. The system includes specialized classifiers for emotions based on the FER2013 dataset and gender based on IMDB datasets. These models are integrated into a containerized web service, allowing the classification logic to be exposed as an API that processes image data via network requests. The technical surface covers the entire pipelin

This repository serves as an educational resource for learning deep learning and neural network development through the Keras framework. It provides a collection of interactive tutorials and documented code samples designed to guide users through the construction, training, and evaluation of machine learning models. The project focuses on practical implementations across several domains, including computer vision, natural language processing, and sequential data analysis. Users can explore workflows for image classification, object detection, and facial recognition, as well as techniques for

This project is an object detection framework implementing the YOLOv3 architecture using Keras and TensorFlow. It functions as a deep learning vision model and computer vision toolset designed to locate and classify multiple entities within images and video streams using bounding boxes. The system includes a multi-GPU inference engine to distribute computational loads across several graphics processing units. It also provides a pipeline for creating custom object detectors by retraining pre-trained weights on annotated datasets to recognize user-defined object classes. The framework covers m

keras-rl is a reinforcement learning library that enables the training of neural agents using Keras. It serves as a framework for implementing deep reinforcement learning agents that interact with simulated environments to discover optimal behaviors and maximize cumulative rewards. The library provides a system for configuring, training, and managing neural network agents. It handles the interaction loop between agents and environments, allowing models to learn through direct experience and gradient-based optimization. The framework includes capabilities for model weight management, allowing

This project is a collection of interactive notebooks for a TensorFlow deep learning course. It provides guided learning resources and practical tutorials for implementing neural network architectures, supervised learning, and transfer learning. The materials feature a computer vision learning path and specific guides for transfer learning, demonstrating how to adapt pre-trained models to new tasks. It includes tutorials for building regression models and image classifiers using the Keras high-level API. The scope covers supervised learning pipelines for binary and multiclass classification,

This project is a collection of interactive instructional documents and practical code samples designed as a machine learning educational resource. It consists of Jupyter notebooks that provide runnable examples and guided exercises for learning deep learning and model development. The repository features Keras model implementations that demonstrate how to build and train neural network architectures for processing images, objects, and natural language. It includes capabilities for executing the same model code across different computation engines to compare framework behavior and performance

Screenshot-to-code is an AI visual frontend generator that translates images, design mockups, and screenshots into structured HTML, CSS, and Tailwind markup. It functions as a design-to-code converter that uses large language models and neural networks to transform visual elements into functional web page layouts. The tool automates the frontend design process by converting static mockups into website code, facilitating rapid UI prototyping and the generation of static website structures. It bridges the gap between visual design assets and frontend development by translating image-based layou

This project is a CSS theme for the Firefox web browser designed to integrate its user interface with the GNOME desktop environment. It implements a visual layer that aligns browser elements with the typography, spacing, and overall design language of the GTK system. The theme provides multiple color palettes, including standard dark mode and high-contrast OLED black variants. It also includes system icon integration, allowing the browser to replace internal images with system-level icons to match the host operating system's aesthetics. Beyond color and iconography, the project covers interf

This project is an artificial intelligence-powered frontend generator that translates visual design inputs into functional source code. It functions as a workflow engine that interprets graphical user interfaces, mapping layout structures and styling rules to structured markup and programming language syntax. The tool distinguishes itself by supporting both static design mockups and dynamic video recordings. It processes temporal and spatial information from screen captures to reconstruct interaction flows and state transitions, enabling the creation of functional software prototypes from vis

This is a comprehensive educational curriculum designed to teach machine learning fundamentals using the Python programming language. It provides a structured course covering the implementation and theory of supervised learning, unsupervised learning, and deep learning. The curriculum is delivered through interactive notebooks that combine executable code with technical tutorials. It includes dedicated guides for building neural network architectures, implementing classification and regression models, and utilizing clustering techniques for pattern discovery in unlabeled data. The materials

Detectron2 is a PyTorch computer vision framework and visual recognition platform designed for training and deploying models for object detection, image segmentation, and visual recognition. It provides a research-oriented environment for training complex vision models with multi-GPU acceleration. The project includes a specialized object detection library for identifying and locating multiple objects via bounding boxes, as well as an image segmentation toolkit for creating pixel-level masks through instance, semantic, and panoptic segmentation. Additionally, it features a human pose estimati

xtuner is a comprehensive training engine for large language models, offering a toolkit for pre-training, supervised fine-tuning, and the optimization of vision-language multimodal models. It serves as a distributed training accelerator and a specialized framework for scaling Mixture-of-Experts models and aligning model behavior through reinforcement learning from human feedback. The project distinguishes itself through advanced memory and compute optimizations, such as sequence parallelism for ultra-long context windows and interleaved pipeline parallelism to reduce GPU idle time. It provide

This project is a collection of scalable vector graphics designed for web interfaces. It is distributed as an SVG icon library available through package managers as a Node.js package and a Ruby gem. The set provides plug-and-play vector graphics that can be imported into web applications and styled using CSS to adjust size, color, and layout. The library supports integration via task-runner plugins and template-based rendering to manage assets within development pipelines.

This project is a Python bio-imaging toolkit and analysis suite designed for processing and analyzing microscopy and medical images. It provides a collection of tools for image quantification, medical image segmentation, and general bio-imaging workflows. The suite includes specialized capabilities for quantifying biological data, such as measuring neuron branching complexity via Sholl analysis, calculating particle size distributions, and tracking wound area in scratch assays. It also features a medical image segmentation library that implements U-Net architectures for isolating anatomical s

Lettering.js is a JavaScript typography library that divides text strings into granular HTML elements. It wraps individual characters, words, and lines in tags to enable precise CSS control and advanced visual styling. The library includes an accessible text wrapper system that maintains screen reader compatibility. It manages text accessibility by mirroring the original content into ARIA labels on containers and hiding fragmented elements from assistive technologies. The tool provides capabilities for granular text manipulation and DOM-based decomposition. These mechanisms facilitate web ty

Corenet is a deep learning training framework and computer vision model library designed for developing neural networks across vision, text, and audio modalities. It functions as a distributed training orchestrator for scaling workloads across multiple compute nodes and provides a multimodal data pipeline for processing image, text, and video data. The project includes a model conversion toolkit for transforming weights and architectures between different machine learning frameworks. It also provides tools for optimizing model performance on Apple Silicon and reducing response latency in gene

BewlyBewly is a browser extension that customizes the Bilibili homepage, modifying its layout and appearance to deliver a personalized browsing experience without altering the core functionality of the site. It functions as a frontend customization utility, injecting custom CSS and scripts directly into the page context to override default styles and dynamically reapply changes as content loads. The extension is built as a Manifest V3 Chrome extension, using a content script injection system and a DOM mutation observer to ensure customizations persist even as the page updates. It includes a u

Flat-UI is a collection of responsive UI toolkits and CSS libraries used to build websites and interactive web components with a flat design aesthetic. It provides a responsive frontend toolkit and a web component library based on the Bootstrap framework to create adaptive layouts. The library focuses on implementing a consistent flat design through predefined hex color palettes and typography styles. It replaces standard browser elements with customized visual styles to remove skeuomorphic depth. The toolkit covers a broad range of interface capabilities, including customized form elements

GrapesJS is a framework for creating no-code visual editors that produce HTML and CSS templates. It provides a browser-based interface for designing website and newsletter structures using a drag-and-drop page editor. The project functions as a web builder framework, enabling the development of custom design environments. It includes a system for managing nested HTML elements, modifying layout properties via a graphical interface, and organizing components through a page layer hierarchy. The toolset covers digital asset management for organizing images and files, as well as the ability to pe

jupyter-themes is a Jupyter Notebook theme manager and CSS interface customizer. It provides a command line tool to apply custom color schemes, fonts, and layout styles to notebook environments. The project includes a data visualization styling tool that synchronizes the aesthetic properties and color schemes of plotting libraries with the active interface theme. This ensures that data charts and figures remain visually consistent with the overall workspace theme.

Azul is a native desktop application builder and UI toolkit for creating high-performance graphical user interfaces. It utilizes a functional and reactive programming model for managing layout and state, enabling the development of native software through a CSS-based toolkit. The framework is distinguished by its use of the WebRender engine to provide GPU-accelerated rendering. This allows the system to display complex user interface elements with high efficiency and speed by leveraging hardware acceleration. The project enables the design of desktop interfaces using a document object model