Coding & Development

PoseEstimationForMobile is an open-source project designed for real-time single-person pose estimation on Android and iOS devices. It leverages CPM and Hourglass models, implemented with TensorFlow, and incorporates inverted residuals (MobileNet V2) for optimized, real-time inference. The repository includes code for training both CPM and Hourglass models, along with demo source code for Android and iOS. This allows developers to integrate pose estimation capabilities into their mobile applications with high performance. The project provides pre-trained models and detailed instructions for setting up training environments, converting models for mobile deployment (Mace, TFLite, CoreML), and benchmarking performance across various mobile chipsets.

Pipeless is an open-source computer vision framework designed to accelerate the development and deployment of AI applications. It abstracts away complexities like code parallelization, multimedia pipelines, memory management, and model inference, allowing developers to build and deploy real-time computer vision applications rapidly. Inspired by serverless technologies, Pipeless enables users to define 'stages'—micro-pipelines that perform specific tasks. These stages can be dynamically combined per stream, supporting multi-stream processing and on-the-fly configuration changes. It supports industry-standard models and custom models across various inference runtimes like ONNX Runtime, CUDA, TensorRT, and OpenVINO, ensuring high performance on both CPU and GPU. Pipeless also offers multi-language support for hooks and built-in restart policies for robust operation on edge, IoT, or cloud environments.

Polycam is a comprehensive 3D scanning and photogrammetry tool available on iOS, Android, and web platforms, enabling users to capture reality and generate detailed 3D models and floor plans. It supports various capture modes including LiDAR, 360 photosphere, and photogrammetry, with AI-generated textures to enhance realism. Users can export models in multiple formats such as GLTF, OBJ, FBX, and USDZ, catering to different software needs. The tool also provides advanced features like instant 3D floor plans, automated measurements, and team collaboration, making it suitable for professionals in various industries. Polycam offers a free tier for beginners and paid plans with increased capture limits and export options.

semantic-segmentation is an open-source PyTorch library designed for state-of-the-art semantic segmentation models. It provides a flexible and customizable framework for computer vision researchers and developers. The library supports a wide array of datasets, making it suitable for various applications requiring precise pixel-level classification. Its focus on ease of use and customizability allows users to adapt models to specific needs, ensuring high accuracy for diverse computer vision projects. This tool is ideal for those looking to implement or experiment with advanced semantic segmentation techniques.

awesome-robotics-datasets is a comprehensive, open-source collection of datasets specifically curated for robotics and computer vision research and development. This GitHub repository serves as a valuable resource, offering links to numerous dataset collections, including those for SLAM (Simultaneous Localization and Mapping), computer vision tasks, and various place-specific datasets like driving, flying, underwater, and indoor environments. Researchers and developers can explore datasets from prominent institutions and projects such as KITTI, Waymo, nuScenes, and more. The collection is organized by topic and location, making it easy to find relevant data for specific applications in areas like localization, mapping, object tracking, and 3D reconstruction.

pytorch-yolo-v3 offers a PyTorch implementation of the YOLO v3 object detection algorithm, designed for efficient and real-time object recognition. This repository aims to improve upon existing ports by streamlining the code, removing redundant components, and providing clear documentation. It currently supports detection in single images, multiple images, and video streams, with options to adjust resolution and utilize half-precision floats for faster inference. The project serves as a driver code for research, with plans to include a training module in the future. It requires Python 3.5, OpenCV, and PyTorch 0.4.

pytorch-openpose offers a PyTorch implementation of the popular OpenPose framework, enabling robust body and hand pose estimation. This tool is particularly useful for researchers and developers working with computer vision and human-computer interaction, as it facilitates the conversion of existing OpenPose Caffe models to PyTorch. Beyond body and hand pose, it also supports the implementation of face keypoint detection, following similar procedures used for hand detection. The project provides clear instructions for setting up a Python 3.7 environment, installing necessary dependencies, and downloading pre-trained models. Demos are available for webcam, image, and video processing, making it accessible for immediate experimentation and integration into various projects.

Attendance-Management-system-using-face-recognition is an open-source project built with Python and OpenCV, designed to automate attendance tracking through facial recognition. Users can register new students by taking multiple images, which are then used to train the system's facial recognition model. Once trained, the system can automatically mark attendance for registered individuals by detecting their faces. It generates CSV files for attendance records, organized by subject, and allows users to view attendance data in a tabular format. This system requires users to set up their environment and adjust file paths, making it a technical solution for automated attendance.

The HuggingFace Trending Board, developed by openfree, serves as a discovery tool within the HuggingFace ecosystem. It is designed to help users stay informed about the latest and most popular AI models and spaces. By highlighting trending projects, the board allows developers, data scientists, and AI enthusiasts to quickly identify what's gaining traction in the community. This can be particularly useful for those looking to explore new technologies, find inspiration for their own projects, or understand current trends in AI development. Although the specific instance of the board mentioned is currently paused, its purpose is to offer a dynamic overview of the HuggingFace platform's most active and noteworthy contributions.

Awesome_Prompting_Papers_in_Computer_Vision is a comprehensive, curated list of research papers focusing on prompt-based techniques within the fields of computer vision and vision-language learning. This resource is designed to help researchers and practitioners stay abreast of the rapidly evolving advancements in visual prompting. It categorizes papers into key areas such as Vision Prompt, Vision-Language Prompt, Language-Interactable Prompt, and Vision-Language Instruction Tuning. Each entry typically includes links to the paper and often to associated code, making it a valuable hub for exploring foundational models, parameter-efficient adaptation, and multimodal learning approaches.

COCO-WholeBody is a comprehensive dataset designed for whole-body human pose estimation, building upon the COCO 2017 dataset. It offers extensive annotations for 133 keypoints per person, covering 17 for the body, 6 for feet, 68 for the face, and 42 for hands, along with bounding boxes for the person, face, and each hand. This dataset is crucial for researchers and developers working on advanced computer vision tasks, particularly in human pose analysis. The project provides evaluation tools and has been utilized in top-tier computer vision conferences, making it a valuable resource for academic and non-commercial research in the field.

GitFluence is an AI-driven solution designed to streamline the process of finding and utilizing Git commands. Developers can simply describe the desired outcome in natural language, and the tool's AI engine will suggest the most relevant Git commands. This eliminates the need to manually search through extensive documentation or recall complex command syntax, significantly accelerating the development workflow. By providing precise command suggestions, GitFluence helps users quickly copy and paste the correct commands directly into their terminal or command line interface, enhancing efficiency and reducing errors in Git operations. The platform aims to make Git more accessible and less time-consuming for all skill levels.

Luos-engine is an open-source, lightweight library designed to manage hardware products as a collection of independent software features. It functions as a real-time orchestrator for cyber-physical systems, facilitating the design, testing, and deployment of embedded applications and digital twins. The tool can be utilized on any microcontroller or computer, across various networks, promoting free and fast development of multi-electronic-board connected products. By using Luos-engine, developers can leverage existing work, accelerate time-to-market, and ensure robustness and universality of their applications. It supports development, debugging, validation, monitoring, and management from anywhere, promoting organized and effective development practices for scalability and adaptability.

ComponentLibraries.com serves as a comprehensive directory for UI component libraries, catering to both designers and developers. It simplifies the process of finding suitable UI kits and libraries by offering a curated selection for a wide range of coding frameworks such as React, Angular, Vue.js, Next.js, and design tools like Figma, Webflow, and Framer. The platform allows users to filter libraries by framework, design style, and functionality, including features like dark mode support, responsive layouts, Tailwind CSS compatibility, and accessibility. With over 100 different UI component libraries, including those for React Native, Ruby on Rails, and HTML, the directory is regularly updated to include new releases and trending options. It aims to save users time by providing detailed descriptions, key features, and direct links, eliminating the need to sift through outdated blogs or GitHub repositories.

E2E FT Marigold for Normals is an AI tool hosted on Hugging Face that specializes in generating surface normals from uploaded images. Users can input an image and receive two outputs: the raw data of the surface normals and a corresponding colored map. This tool is particularly useful for tasks requiring detailed surface information, such as 3D reconstruction, computer vision research, or graphics applications. It is licensed under Apache-2.0, making it accessible for various projects. The platform leverages Hugging Face's infrastructure, which offers different pricing tiers for storage, compute, and inference, catering to both individual developers and enterprise teams.

Maml is an open-source code repository for Model-Agnostic Meta-Learning (MAML), a technique designed for the fast adaptation of deep networks. Developed by cbfinn, this repository provides the foundational code accompanying the paper "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks" (Finn et al., ICML 2017). It specifically includes implementations for few-shot supervised learning domain experiments, covering tasks such as sinusoid regression, Omniglot classification, and MiniImagenet classification. The project is built using Python 2.* or 3.* and TensorFlow v1.0+, making it accessible for researchers and developers working in meta-learning and few-shot learning. Users can access data preparation instructions for Omniglot and MiniImagenet, and detailed usage instructions are available within the `main.py` file.

AI Dev Gallery is an open-source project from Microsoft designed for Windows developers to integrate AI capabilities into their applications. It provides a comprehensive learning resource with over 25 interactive samples powered by local AI models. Developers can easily browse, download, and run various AI models directly from platforms like Hugging Face and GitHub. The gallery also allows users to view the C# source code for samples and export standalone Visual Studio projects with a single click, facilitating hands-on learning and integration. It supports offline use once models are downloaded and features popular open-source models and APIs from the Microsoft Foundry on Windows. The project is completely open-source, encouraging contributions and feedback from the developer community.

Aporia, now acquired by Coralogix, was an AI Control Platform designed to ensure the privacy, security, and reliability of AI applications. It offered robust guardrails to effectively mitigate common AI issues such as hallucinations, data leakage, and prompt attacks in real time. The platform was trusted by both emerging tech startups and established Fortune 500 companies. Aporia Labs, a team of AI and cybersecurity specialists, continuously researched and developed cutting-edge methods for identifying and mitigating these threats, protecting brand reputation and user trust. The acquisition by Coralogix aims to integrate these capabilities into a broader observability solution.

AudioCLIP is an advanced AI model that expands the capabilities of the Contrastive Language-Image Pre-training (CLIP) framework to include audio processing. This innovative extension allows for joint representation learning across image, text, and audio modalities, facilitating tasks such as bimodal and unimodal classification and querying. Built upon prior research in robust time-frequency transformation of audio and environmental sound classification, AudioCLIP integrates the ESResNeXt audio-model with the CLIP framework using the AudioSet dataset. This combination enables the model to generalize to unseen datasets in a zero-shot inference fashion, achieving new state-of-the-art results in Environmental Sound Classification (ESC) tasks on datasets like UrbanSound8K and ESC-50.

Bottom-up-attention provides an open-source implementation of a bottom-up attention model, built upon multi-GPU training of Faster R-CNN with ResNet-101. It leverages object and attribute annotations from Visual Genome to generate output features corresponding to salient image regions. These features can serve as a direct replacement for traditional CNN features in attention-based image captioning and visual question answering (VQA) models. The approach has demonstrated state-of-the-art performance in image captioning on MSCOCO and won the 2017 VQA Challenge. The repository includes code for training the Faster R-CNN model and provides pretrained features for the MSCOCO dataset, making it a valuable resource for researchers and developers in computer vision.

DeepRL-Agents is an open-source repository offering a comprehensive collection of Deep Reinforcement Learning algorithms, all implemented using Tensorflow. This resource is ideal for individuals looking to understand and apply various RL techniques, from foundational Q-learning and policy gradient methods to more advanced concepts like Double-Dueling-DQN, Deep Recurrent Q-Networks, and Asynchronous Advantage Actor-Critic (A3C). The repository includes iPython notebooks for each algorithm, often accompanied by tutorial series published on Medium, making it a valuable educational and practical tool for learning about reinforcement learning.

DeepRL-TensorFlow2 is a GitHub repository offering straightforward implementations of a wide array of Deep Reinforcement Learning (DRL) algorithms, all built with TensorFlow2. The project prioritizes code clarity, making it an excellent resource for students and researchers delving into DRL. Each algorithm is contained within a single Python script, simplifying the learning process by eliminating the need to navigate multiple files. The repository is actively maintained and continuously updated with new DRL algorithms. It currently includes implementations for DQN, DRQN, DoubleDQN, DuelingDQN, A2C, A3C, PPO, and DDPG, with TRPO, TD3, and SAC noted as planned additions. The project also provides code snippets illustrating the core ideas behind each algorithm, such as using target networks and replay buffers in DQN, or advantage functions in A2C.

Mouse Hackathon is a dynamic platform designed for creative innovation using AI, specifically structured around 1-minute challenges. It serves as a Hugging Face Space by VIDraft, offering a collaborative environment for AI enthusiasts and innovators. The platform allows users to participate in the MOUSE-I Hackathon, providing clear information on dates, prize amounts, and participation steps. It also features language switching between English and Korean, alongside a news view, to keep participants informed and engaged. This tool is ideal for those looking to quickly experiment with AI concepts and engage in rapid prototyping within a competitive yet supportive hackathon setting.

dque is a fast, embedded, durable queue specifically designed for Go applications. It offers a persistent and scalable FIFO (First In, First Out) queuing solution that is compiled directly into your Golang program. Key features include durability, ensuring data survives program restarts, and scalability, as it's limited by disk space rather than RAM. dque supports concurrent usage and provides two performance modes: 'safe' for maximum data integrity with fsync on every operation, and 'turbo' for faster operations by letting the OS batch changes, with the option to manually flush. The queue is implemented using configurable segments, with only the head and tail segments held in memory, making it efficient for large queues. It's an ideal tool for developers needing a reliable, embedded message queuing system within their Go projects.