Search Results for "vision" - Page 7
Sort By:
Showing 271 open source projects for "vision"
View related business solutions-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
1
InternGPT
Open source demo platform where you can easily showcase your AI models
InternGPT is an open-source multimodal AI framework designed to extend large language models beyond text interactions into visual reasoning and image manipulation tasks. The system integrates conversational AI with computer vision models so users can interact with images, videos, and visual environments through natural language instructions. Unlike traditional chat systems that rely solely on text prompts, InternGPT allows users to interact with visual content using both language and nonverbal signals such as pointing or highlighting objects within images. ... -
2
Screenshot to Code
A neural network that transforms a design mock-up into static websites
Screenshot-to-code is a tool or prototype that attempts to convert UI screenshots (e.g., of mobile or web UIs) into code representations, likely generating layouts, HTML, CSS, or markup from image inputs. It is part of a research/proof-of-concept domain in UI automation and image-to-UI code generation. Mapping visual design to code constructs. Code/UI layout (HTML, CSS, or markup). Examples/demo scripts showing “image UI code”. -
3
Theseus
A library for differentiable nonlinear optimization
Theseus is a library for differentiable nonlinear optimization that lets you embed solvers like Gauss-Newton or Levenberg–Marquardt inside PyTorch models. Problems are expressed as factor graphs with variables on manifolds (e.g., SE(3), SO(3)), so classical robotics and vision tasks—bundle adjustment, pose graph optimization, hand–eye calibration—can be written succinctly and solved efficiently. Because solves are differentiable, you can backpropagate through optimization to learn cost weights, feature extractors, or initialization networks end-to-end. The implementation supports batched optimization on GPU, robust losses, damping strategies, and custom factors, making it practical for real-time systems. ... -
4
VisualGLM-6B
Chinese and English multimodal conversational language model
VisualGLM-6B is an open-source multimodal conversational language model developed by ZhipuAI that supports both images and text in Chinese and English. It builds on the ChatGLM-6B backbone, with 6.2 billion language parameters, and incorporates a BLIP2-Qformer visual module to connect vision and language. In total, the model has 7.8 billion parameters. Trained on a large bilingual dataset — including 30 million high-quality Chinese image-text pairs from CogView and 300 million English pairs — VisualGLM-6B is designed for image understanding, description, and question answering. Fine-tuning on long visual QA datasets further aligns the model’s responses with human preferences. ... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
NVIDIA Generative AI Examples
Generative AI reference workflows
...The repository includes examples covering topics such as retrieval-augmented generation pipelines, agent-based workflows, and multimodal AI applications that combine text, vision, and data processing. Many of the examples show how to deploy AI services using containerized environments, GPU acceleration, and microservices that can scale across modern infrastructure. Developers can explore sample chatbot applications, document question-answering systems, and knowledge-base pipelines that illustrate how generative AI can interact with external data sources. -
6
python realtime human deteciton
human detection using yolov8
I would give you more but im tired and it's 4:26 am. yotube video is slightly outdated but has more info. https://www.youtube.com/watch?v=UAkjyeTOyo4 -
7
OculiX
Visual Automation IDE — automate anything you see on screen
OculiX is the evolution of SikuliX, actively maintained with the full agreement of its original creator RaiMan. Automate any desktop application using image recognition (OpenCV) and OCR (Tesseract + PaddleOCR). No access to source code or DOM required — if you can see it, you can automate it. Key features: - Guided step-by-step recorder with live code preview - Image recognition via OpenCV 4.10 - Dual OCR: Tesseract (built-in) + PaddleOCR (neural, high precision) - Local and remote... -
8
CO3D (Common Objects in 3D)
Tooling for the Common Objects In 3D dataset
CO3Dv2 (Common Objects in 3D, version 2) is a large-scale 3D computer vision dataset and toolkit from Facebook Research designed for training and evaluating category-level 3D reconstruction methods using real-world data. It builds upon the original CO3Dv1 dataset, expanding both scale and quality—featuring 2× more sequences and 4× more frames, with improved image fidelity, more accurate segmentation masks, and enhanced annotations for object-centric 3D reconstruction. -
9
OpenFieldAI - AI Open Field Test Tracker
OpenFieldAI is an AI based Open Field Test Rodent Tracker
OpenFieldAI use AI-CNN to track rodents movement with pretrained OFAI models , or user could create their own model with YOLOv8 for inferencing. The software generates Centroid graph, Heat map and Line path and a spreadsheet containing all calculated parameters like - Speed - Time in and out of ROI - Distance - Entries/Exits for single/multiple pre-recorded videos or live webcam video. The ROI is assigned automatically in multiple video input , and can be manually given in single... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
imgclsmob Deep learning networks
Sandbox for training deep learning networks
imgclsmob is a deep learning research repository focused on implementing and experimenting with convolutional neural networks for computer vision tasks. The project serves as a sandbox for training and evaluating a wide variety of neural network architectures used in image analysis. It includes implementations of models used for tasks such as image classification, object detection, semantic segmentation, and pose estimation. The repository also contains scripts that help train models, evaluate performance, and convert trained networks between different frameworks. ... -
11
The Grand Complete Data Science Guide
Data Science Guide With Videos And Materials
The Grand Complete Data Science Materials is a repository curated by a data-science educator that aggregates a wide range of learning resources — from basic programming and math foundation to advanced topics in machine learning, deep learning, natural language processing, computer vision, and deployment practices — into a structured, centralized collection aimed at learners seeking a comprehensive path to data science mastery. The repository bundles tutorials, lecture notes, project outlines, course materials, and references across topics like Python, statistics, ML algorithms, deep learning, NLP, data preprocessing, model evaluation, and real-world problem solving. ... -
12
Tarsier
Vision utilities for web interaction agents
...We define interactable elements as buttons, links, or input fields that are visible on the page; Tarsier can also tag all textual elements if you pass tag_text_elements=True. Furthermore, we've developed an OCR algorithm to convert a page screenshot into a whitespace-structured string (almost like ASCII art) that an LLM even without vision can understand. Since current vision-language models still lack fine-grained representations needed for web interaction tasks, this is critical. -
13
QuizSolver
AI-powered quiz solver for Windows. Free to use, easy to set up.
QuizSolver is a free Windows app that uses AI vision to automatically read and answer quiz questions on your screen. It takes a screenshot, detects the answer buttons, sends the question to an AI model, and clicks the correct answer in seconds. Built-in support for Quizalize and Quipper. A Custom mode is available for other quiz sites, though results may vary. HOW TO SET UP: 1. -
14
Screen Recorder Studio
Screen Recorder Studio Screen Recorder Studio is a modern, lightweigh
...Key Features 🎥 High-quality screen recording 🎮 Gameplay recording with minimal performance impact 🖥️ Full-screen, window, and custom-region capture 🎙️ Microphone and system audio recording ⚡ Fast startup and lightweight resource usage 📁 Easy video export and file management 🎨 Modern, clean, user-friendly interface Vision join our discord in order to suggest or to communicate: https://discord.gg/YRhcgEGVjN -
15
Dosidicus
Tamagotchi-style digital pet with a neural network that can learn
Tamagotchi-style digital pet squid with a simple neural network https://github.com/ViciousSquid/Dosidicus/wiki Includes tools for visualising and understanding neural networks Design your own squid brain with GUI tools - watch it evolve and learn! The squid makes autonomous decisions based on current state (hunger, sleepiness, etc.). Implements a vision cone for food detection, simulating realistic foraging behavior. Hebbian learning algorithm runs every 30 seconds (configurable) Experiences from short-term and long-term memory can influence decision-making Squid can create new neurons in response to his environment (Neurogenesis) Design your own squid brain with GUI tools! ... -
16
Hero Planner
An easy to use GUI for creating team rotas and scheduling absences.
...Your Utility Belt: ✓ Super Speed: Intuitive drag-and-drop & bulk actions for lightning-fast updates. ✓ Compliance Shield: Real-time alerts guard against labour law violations and overtime risks. ✓ X-Ray Vision: Instantly visualize coverage gaps, conflicts, and staff availability. ✓ Universal Export: PDF, CSV, and HTML formats. ✓ Stealth Mode: Sleek Dark Mode & customizable themes. Built on Electron, React & Vite for blazing performance. Whether managing a small squad or a legion of 200+ staff, HERO Planner gives you the tools to save the day. ... -
17
surtr automation v4.0
Visual desktop automation, OCR, JSON & web automation toolkit
Surtr is a free, open-source Windows automation platform that combines computer vision, OCR, scripting, web automation, and developer tools into one powerful toolkit. Automate applications using image recognition instead of fragile screen coordinates, extract text from screenshots, receipts, and invoices with OCR, record actions into reusable scripts, build workflows visually in SurtrUI, or control everything remotely through the built-in WebUI. -
18
YOLOv5
YOLOv5 is the world's most loved vision AI
Introducing Ultralytics YOLOv8, the latest version of the acclaimed real-time object detection and image segmentation model. YOLOv8 is built on cutting-edge advancements in deep learning and computer vision, offering unparalleled performance in terms of speed and accuracy. Its streamlined design makes it suitable for various applications and easily adaptable to different hardware platforms, from edge devices to cloud APIs. Explore the YOLOv8 Docs, a comprehensive resource designed to help you understand and utilize its features and capabilities. ... -
19
Entropy Linux
Arch based, Modern, Midweight, Practical, Experimental, AMD, Szmelc
...Power & Flexibility: Designed for power users, sysadmins, and DevOps pros. Advanced Toolset: Custom utilities to boost productivity, AMD™ Optimized: Engineered for peak performance on AMD hardware. Part of a Vision: A key piece of an evolving ecosystem, connecting projects seamlessly. Entropy is a constantly evolving system—designed to be explored, tweaked, and refined. Some setup may be required, but that’s part of the fun. What to Expect? A robust, adaptable distro with powerful tools and limitless customization. Occasional bugs, experimental features, and hidden easter eggs because pushing limits isn’t always smooth! -
20
OSWorld
Benchmarking Multimodal Agents for Open-Ended Tasks
OSWorld is an open-source synthetic world environment designed for embodied AI research and multi-agent learning. It provides a richly simulated 3D world where multiple agents can interact, perform tasks, and learn complex behaviors. OSWorld emphasizes multi-modal interaction, enabling agents to process visual, auditory, and symbolic data for grounded learning in a simulated world. -
21
Image-Editor
AI based photo editing website for changing image background
...Image-Editor uses Python's cv2 library, which provides an easy and efficient way to work with images and videos, including a wide range of image processing and computer vision algorithms. With cv2, you can easily read, write, filter, and display images, and much more. Image-Editor uses Mediapipe's selfie_segmentation model for background removal in real-time video streams. This advanced model uses deep neural networks to detect and remove the background. -
22
CogVLM
A state-of-the-art open visual language model
...The flagship CogVLM-17B combines ~10B visual parameters with ~7B language parameters and supports 490×490 inputs; CogAgent-18B extends this to 1120×1120 and adds plan/next-action outputs plus grounded operation coordinates for GUI tasks. The repo provides multiple ways to run models (CLI, web demo, and OpenAI-Vision–style APIs), along with quantization options that reduce VRAM needs (e.g., 4-bit). It includes checkpoints for chat, base, and grounding variants, plus recipes for model-parallel inference and LoRA fine-tuning. The documentation covers task prompts for general dialogue, visual grounding (box→caption, caption→box, caption+boxes), and GUI agent workflows that produce structured actions with bounding boxes. -
23
InternVL
A Pioneering Open-Source Alternative to GPT-4o
InternVL is a large-scale multimodal foundation model designed to integrate computer vision and language understanding within a unified architecture. The project focuses on scaling vision models and aligning them with large language models so that they can perform tasks involving both visual and textual information. InternVL is trained on massive collections of image-text data, enabling it to learn representations that capture both visual patterns and semantic meaning. ... -
24
MakeHuman
This is the main repository for the MakeHuman application as such
...Mac users should be able to use the same instructions as windows users, although this has not been thoroughly tested. At the point of writing this, the source code is almost ready for a stable release. The testing vision for this code is to build a community release that includes main application and often-used, user-contributed plug-ins. We hope that the utility of this integrated functionality is sufficient to entice a larger cohort of testers who get value-added in exchange for the possibility of uncovering deficiencies in our application. -
25
DeepSeek VL
Towards Real-World Vision-Language Understanding
DeepSeek-VL is DeepSeek’s initial vision-language model that anchors their multimodal stack. It enables understanding and generation across visual and textual modalities—meaning it can process an image + a prompt, answer questions about images, caption, classify, or reason about visuals in context. The model is likely used internally as the visual encoder backbone for agent use cases, to ground perception in downstream tasks (e.g. answering questions about a screenshot).
