Projects sharing features with DeepLabCut

This is a real-time object detection framework built on the YOLOv3 architecture, implemented in PyTorch. It provides a complete pipeline for identifying and localizing objects in images and video using a single neural network pass, combining a Darknet-53 backbone with multi-scale feature pyramids and anchor-based bounding box prediction. The framework extends beyond basic detection to include instance segmentation, human pose estimation, and multi-object tracking across video frames. It offers a model export toolkit that converts trained models through ONNX to CoreML, TensorFlow Lite, and Ten

This project is a deep learning framework built for detecting and tracking human body keypoints in images and video streams. It functions as both a real-time motion tracking system and a machine learning environment for training and evaluating pose estimation models. The system utilizes a two-branch convolutional neural network to predict body part locations and their directional connections simultaneously. It employs multi-stage feature refinement to improve keypoint localization accuracy and uses greedy parsing and bipartite matching algorithms to associate detected parts into individual sk

PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti

EasyMocap is a markerless 3D human motion capture system that recovers body, hand, and face poses from single or multi-view video without physical markers or suits. It uses parametric body models like SMPL, SMPL-X, and MANO, and leverages mirror reflections to resolve depth ambiguity in single-view pose estimation, improving accuracy by computing mirror surface normals from vanishing points. The system distinguishes itself through mirror-assisted depth disambiguation, enabling accurate 3D pose reconstruction from a single RGB image or video that includes a mirror reflection. It also supports

sam-3d-body is a machine learning framework for 3D human mesh recovery and pose estimation. It utilizes a 3D human mesh recovery model to reconstruct full-body meshes, including the body, hands, and feet, from a single image. The project implements a specialized extension of the Segment Anything Model to guide the extraction and refinement of human body shapes. This integration allows for prompt-guided mesh recovery, where 2D masks and keypoints constrain the inference of 3D pose and shape parameters. The system covers a range of computer vision capabilities, including 3D spatial alignment t

AlphaPose is a deep learning pose estimation framework and PyTorch computer vision library designed for detecting and tracking human body, face, hand, and foot keypoints in images and videos. It provides a system for skeletal posture estimation and multi-person pose tracking. The project implements tools for three-dimensional human pose reconstruction, generating joint positions and body mesh shapes from two-dimensional image data. It also includes a multi-person pose tracker capable of maintaining the identity of multiple people across consecutive video frames. The framework covers a broad

GoCV is a computer vision library and Go language binding for OpenCV. It serves as an image processing toolkit and deep learning inference engine, providing programmatic access to a wide range of algorithms for image manipulation, object detection, and video analysis. The project differentiates itself through high-performance native bindings and hardware acceleration. It utilizes a foreign function interface to map Go calls to C++ functions and includes a hardware-agnostic backend dispatch to route neural network tasks to computation engines such as CUDA and OpenVINO. The library covers a br

OpenPose is a real-time pose estimation engine designed to detect and track human body, face, hand, and foot landmarks. It functions as a multi-person motion tracker, identifying the spatial coordinates of multiple individuals simultaneously within video streams or static images. Beyond two-dimensional detection, the software acts as a three-dimensional kinematics processor, reconstructing spatial movement data from single or multiple synchronized camera perspectives. The system distinguishes itself through a bottom-up approach that utilizes part-affinity fields to associate body parts across

ESPnet is a comprehensive speech processing toolkit and PyTorch-based trainer designed for building end-to-end speech recognition, synthesis, and translation models. It provides a structured framework for developing automatic speech recognition systems using transducer and encoder-decoder architectures, alongside engines for text-to-speech synthesis and speech translation pipelines. The project distinguishes itself through a recipe-based workflow execution system that ensures experimental reproducibility by running standardized sequences of scripts for data preparation and model training. It

This project is a PyTorch implementation of the YOLOv3 object detection architecture. It functions as a real-time object detector and computer vision framework designed to identify and locate multiple objects within images using bounding boxes and class labels. The system allows for both the use of pretrained weights for immediate image analysis and the training of custom models using datasets with bounding box annotations. It provides a programmatic interface to integrate detection capabilities directly into other software applications. The framework includes tools for model evaluation to m

RT-DETR is a real-time object detection model based on the detection transformer architecture. It is implemented as a computer vision model for both the PyTorch and PaddlePaddle deep learning platforms, designed to identify and locate multiple objects in images and video streams. The model eliminates the need for anchor generation and non-maximum suppression by utilizing a transformer-based approach. It focuses on high-performance detection, balancing precision and low latency for live environment deployment. The system employs a hybrid encoder and multi-scale feature fusion to extract globa

This project is a PyTorch implementation of the EfficientDet architecture designed for real-time object detection. It provides a neural network and inference engine capable of identifying and locating multiple objects within images or video streams. The implementation includes pretrained computer vision models with optimized weights, enabling immediate inference and fine-tuning without the need for training from scratch. The project covers the full pipeline for computer vision model optimization, including custom object detection training and model weight optimization. It incorporates struct

This is a PyTorch object detection framework that implements the Single Shot MultiBox Detector for identifying and localizing multiple objects within images and video. The project provides a neural network architecture designed for single-shot object detection, which predicts bounding boxes and class labels in one pass. The implementation includes a real-time object detector capable of processing live video streams to track and label objects across sequential frames. It also features a complete computer vision training pipeline for preparing image datasets and training model weights. The fra

This project is a computer vision framework designed for the real-time detection of human body keypoints and skeletal structures. It provides an integrated toolkit for training, optimizing, and executing pose estimation models specifically for deployment on edge computing hardware. The framework distinguishes itself by utilizing part affinity field mapping to encode spatial relationships between joints, which are then processed through a greedy parsing algorithm to reconstruct human skeletons from visual data. To ensure high-performance execution, the library incorporates model quantization a

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

Sn1per is a vulnerability management platform and penetration testing orchestrator designed to automate reconnaissance, vulnerability scanning, and exploit verification. It functions as a dockerized security toolkit that coordinates multiple tools into a unified automated pipeline to identify security flaws across network and web assets. The platform features an attack surface manager for discovering internet-facing assets through OSINT, DNS enumeration, and certificate transparency. It distinguishes itself with an AI-powered security analyzer that uses large language models to summarize scan

SegFormer is a semantic segmentation framework and transformer-based model designed for pixel-level image classification. It provides a deep learning architecture that assigns class labels to pixels using a hierarchical transformer encoder and a multi-layer perceptron decoder. The framework utilizes a hierarchical transformer encoder to process multi-scale features through a pyramid of blocks and an all-MLP decoder to aggregate these features without complex attention mechanisms. It incorporates overlap patch embedding to preserve local continuity and sequential self-attention reduction to ma

This project is a web-based user interface for interacting with large language models via API keys. It functions as an OpenAI API client and a general LLM web chat interface, allowing users to send prompts and receive responses through a private web portal. The application features a security layer with password-based access control to restrict public usage. It supports custom request routing and proxy configurations to bypass network restrictions, and it is available as a progressive web app for native-like installation on mobile devices. The interface includes rich text rendering for Markd

AzurLaneAutoScript is a mobile game automation system designed to perform repetitive gameplay tasks unattended. It functions as a screenshot-driven bot that controls Android devices, emulators, and cloud phones via ADB and uiautomator2, using computer vision to make interaction decisions instead of fixed timers. The project distinguishes itself through an advanced computer vision suite that includes local optical character recognition and perspective-aware grid detection. These tools allow the bot to parse 3D game maps, compute vanishing points, and normalize grid-centered objects for precise

Dejavu is a containerized administration panel and web interface for managing data within Elasticsearch and OpenSearch clusters. It serves as a search index management tool for browsing, editing, and deleting records through a visual explorer rather than raw API queries. The project distinguishes itself by providing a search interface prototyping tool. This allows users to visually design search screens to test result relevancy and export the final layout configuration as usable code. The tool covers broad data management capabilities, including structured data import from CSV or JSON files

This project is a GraphQL web application with a React frontend that utilizes server-side rendering to generate HTML on the server for improved initial load times and search engine indexing. The application supports both static site generation for fast delivery via pre-rendered HTML files and containerized deployment to ensure consistent runtime behavior across different environments. The project includes capabilities for GraphQL data integration, frontend asset optimization through code-splitting, and component UI verification using snapshot testing. It also provides a mechanism for managin

AutoKeras is an automated machine learning framework and Keras AutoML library designed to discover the most effective deep learning model structures for a given dataset. It functions as a tool for deep learning architecture search, eliminating manual hyperparameter tuning by automatically searching for and optimizing neural network architectures. The framework provides capabilities for benchmarking and refining neural network designs to maximize performance. It includes a system for containerized machine learning deployment, allowing environments to be packaged into containers to ensure consi

This project is a WhatsApp chatbot that integrates large language models and image generation into the WhatsApp messaging platform. It acts as a bridge connecting WhatsApp messages to OpenAI services to provide automated text and visual responses. The bot features the ability to convert spoken audio messages into written text using automated speech recognition, facilitating conversational interactions via voice. It also functions as a generative image bot, creating custom visual assets from text descriptions. The system is designed for containerized deployment, using Docker to package the ap

Fastai is a high-level deep learning library built on PyTorch that provides a unified interface for managing the entire machine learning lifecycle. It functions as a comprehensive training toolkit, abstracting hardware management and automating complex training loops to simplify the construction and execution of neural network models. The framework is distinguished by its notebook-centric development environment and a type-dispatching data pipeline that automatically applies transformations based on input data formats. It emphasizes transfer learning through discriminative layer-wise optimiza

This project is a collection of responsive CSS Grid dashboard templates and a data visualization UI kit. It provides a set of HTML layouts designed for building analytics interfaces and monitoring views for KPIs and business metrics that adapt to different screen sizes. The toolkit is library-agnostic, allowing the connection of static HTML templates to any external data source or third-party charting library without requiring custom adapter code. It uses a template-driven approach to separate the visual structure of the dashboard from the underlying data. The capabilities cover the assembly

This project is a retrieval-augmented generation pipeline designed for building custom ChatGPT plugins that allow language models to query private or professional documents. It implements a full retrieval workflow, from processing and indexing document chunks to retrieving relevant context for natural language queries. The system distinguishes itself through a hybrid retrieval approach that combines dense vector embeddings with sparse keyword matching, further refined by a two-stage semantic re-ranking process. It includes specialized data privacy tools for screening personally identifiable i

Streama is a self-hosted media server and library manager designed for organizing and streaming personal collections of movies and television shows. It functions as a dockerized streaming application that provides a web-based media player for accessing video assets. The system distinguishes itself by supporting synchronized video playback, which coordinates the playback state and timeline across multiple clients in real time. It also enables remote media integration, allowing users to build a streaming collection that combines locally stored files with content hosted at external URLs. The pr