Search Results for "vision" - Page 12
Sort By:
Showing 800 open source projects for "vision"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
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.
-
1
GobLin GNU/Linux
GobLin: The GNU/Linux Operating System for Governments
...A customized distribution of the GNU/Linux operating system, adapted to the requirements of public administration. It is designed under the Free Software Philosophy, and open to be adapted in order to cover every level of public administration. With the vision of endowing the government offices with advanced management tools and software, we created a distribution of the GNU/Linux Operating System, adapted to the requirements of a modern administration, integrating free software tools. GobLin GNU/Linux is an own adaptation built on the base of Devuan GNU/Linux distro, a robust operating system resistant to failures, and widely used on internet servers, which guarantees stability in the execution of systems. ... -
2
napi
napi - Isolate and deploy APIs separately at build time
...Historically, tools like this have only been built by large consulting firms or contractors and kept behind the paywalls of consulting fees. napi aims to make these tools accessible to developers of all skill levels, without the cost. Our vision is to help you reduce your reliance on consultants and contractors, while gaining deeper insights into system architecture-level concerns. The added benefit? No more black-box consultant tools running on your code. -
3
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! -
4
3DPass
The Implementation of The Ledger of Things Node. Layer 1 decentralized
3DPass is an open-source Layer 1 blockchain written in Rust and built on Substrate. It introduces a novel consensus mechanism called Proof of Scan, where miners validate by running recognition algorithms on 3D objects. Each object produces a reproducible cryptographic fingerprint (HASH ID) that is stored on-chain. If the same object is submitted again, the network rejects it, ensuring that only one of a kind assets can be registered. This approach enforces authenticity at the content level,... -
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.
-
5
RenderTune
Free open-source high quality video rendering app
...RenderTune is free and open-source, making it accessible to everyone. Whether you're a content creator, musician, or just someone who loves to make videos, RenderTune is the ideal tool to bring your vision to life. Download RenderTune now and start creating stunning videos today! -
6
fileaxy
Fileaxy does file sync, de-duplication, image matching & bulk preview
Fileaxy is a file de-duplication, organization, synchronization, and bulk previewing tool which utilizes a new user interface for local file management. Using content hashing or machine vision algorithms, Fileaxy can detect identical files as well as similar names, images, videos, or fonts and correlate those to others based on naming conventions. Optionally integrates with ImageMagick, GraphicsMagick, FFmpeg, and Mac Sips file decoding with a simple button click. Fileaxy opens NO network connections and will NOT request passwords. ... -
7
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. -
8
Delphi : VRCalc++ OOSL (Script) and more
Delphi : VRCalc++ OOSL & + (Paged List, TextEditor, VRAstroVision ...)
Vincent Radio {Adrix.NT} Sources Library & Applications : Delphi C++ Java VRCalc++ C# VRCalc++ Object Oriented Scripting Language - Engine Source Pascal Code - Delphi Packages Build Prjs - VRCalc++ Scripted System Std RT Library - Guides & Docs (CHM, PDF, DOCX) - VCL & FMX (FireMonkey) Support - Script Test Code (Lang RTL VCL FMX) - Visual Stage Project : VCL & FMX Paged Lists & Iterators : Delphi C++ Java C# Multi-Dim Arrays & Direct Graph Classes : Delphi C++ Java VRCalc++ C# Delphi Drag&Drop Applications - VRCalc++ Script Executors: Terminal, VCL, FMX - VRMultiEdit - VRLazyCodeEditor - VR Astro Vision (Astrology) - Paged List Test - VRMosaic : Delphi C++Builder Java C# +with auto resolver - VR Free Chess 2D - VRBlocks - VRGraphStage - VR TTT OX + icons & bitmaps + VCL VisualStyles + Build Projects + instructions to build projects to build projects - Delphi : RAD Studio - C++ : Dev-C++ - java : NetBeans - C# : MS/VS adrixnt@hotmail.it -
9
OpenAI-API-dotnet
An unofficial C#/.NET SDK for accessing the OpenAI GPT-3 API
A simple C# .NET wrapper library to use with OpenAI's API. More context on my blog. This is my original unofficial wrapper library around the OpenAI API. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
10
Delphi : VRCalc++ and more Binary Exec
Delphi Java - VRCalc++ OOSL (Script) and + (Binary Exec Distro)
Vincent Radio {Adrix.NT} Embarcadero : Delphi : Executable Binaries Delphi : VRCalc++ Object Oriented Scripting Language : Engine + Ext Libraries VRCalc++ OOSL Visual Stage Project : VCL & FMX (FireMonkey) VRCalc++ Script Executor: - VCL Console - Terminal Console - FMX Console + VRCalc++ OOSL : VR System Scripted Standard Runtime Library Delphi Applics - VR Multi Editor : Smart Text Editor - VR Lazy Code Editor : Smart RTF Multi Lang Code Text Editor - VR Astro Vision : Astrology Program - VR Free Chess 2D : Chess Game Program - VR Mosaic : Puzzle Resolver Program (VCL, FMX) - VR Blocks game - VRGraphStage - VR TTT OX game - Embarcadero Binary Runtime Libraries - VR Binary Runtime Libraries for Delphi & C++Builder - Visual Styles Java Applications - Analog Clock - VR Hanoi Towers - VR Rects World Sample - VR Free Chess 2D - VR Mosaic with auto resolver - Action/Entity Model Test includes installation instructions adrixnt@hotmail.it -
11
Ai-Learn
The artificial intelligence learning roadmap compiles 200 cases
...The repository was created to help learners start self-study programs in artificial intelligence without getting overwhelmed by the large number of available resources. It organizes topics such as Python programming, mathematics for machine learning, data analysis, deep learning, computer vision, and natural language processing into a structured learning path. The project also provides a large collection of practical exercises and case studies that allow learners to apply theoretical knowledge through real projects. According to the repository description, it includes nearly two hundred hands-on AI examples developed through years of teaching experience. -
12
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. -
13
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. -
14
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. ... -
15
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. -
16
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). -
17
ApraPipes
A pipeline framework for developing video and image processing apps
ApraPipes is a C++ multimedia processing framework designed for building high-performance video/audio processing pipelines with GPU acceleration. It provides a modular, declarative architecture for creating complex media processing workflows that span camera capture, encoding/decoding, computer vision, AI operations, and output to files, streams, or displays. -
18
Encord Active
The toolkit to test, validate, and evaluate your models and surface
Encord Active is an open-source toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling to supercharge model performance. Encord Active has been designed as a all-in-one open source toolkit for improving your data quality and model performance. Use the intuitive UI to explore your data or access all the functionalities programmatically. Discover errors, outliers, and edge-cases within your data - all in one open source... -
19
crème de la crème of AI courses
This repository is a curated collection of links to various courses
...The repository organizes courses by topic, difficulty level, format, and release year, allowing learners to quickly identify relevant material depending on their experience and interests. Topics covered include deep learning, natural language processing, computer vision, large language models, linear algebra, reinforcement learning, and machine learning engineering. Because the repository links to well-known educational content such as university lecture series and professional training materials, it functions as a structured roadmap for individuals who want to develop expertise in artificial intelligence. -
20
Qwen-VL
Chat & pretrained large vision language model
Qwen-VL is Alibaba Cloud’s vision-language large model family, designed to integrate visual and linguistic modalities. It accepts image inputs (with optional bounding boxes) and text, and produces text (and sometimes bounding boxes) as output. The model variants (VL-Plus, VL-Max, etc.) have been upgraded for better visual reasoning, text recognition from images, fine-grained understanding, and support for high image resolutions / extreme aspect ratios. -
21
Zero to Mastery Deep Learning TensorFlow
All course materials for the Zero to Mastery Deep Learning with TF
...It is structured as a series of progressively complex Jupyter notebooks that emphasize writing and understanding code before diving into theory, reinforcing learning through repetition and application. The material covers core machine learning workflows including regression, classification, computer vision, natural language processing, and time series forecasting, allowing users to build a well-rounded understanding of modern AI tasks. It also integrates milestone projects that simulate real-world scenarios, helping users translate abstract concepts into deployable solutions. -
22
Machine Learning Notebooks
Machine Learning Notebooks
...Each notebook is intentionally lightweight, avoiding unnecessary complexity so that users can easily understand the core concepts and adapt the code to their own projects. The repository supports a wide range of applications, including natural language processing, computer vision, and general deep learning workflows. It is also designed to be easily extensible, allowing developers and researchers to build upon the provided examples without needing to restructure the codebase. -
23
Virtual viewer
Virtual viewer is a tool for Linux low vision computer users
Virtual viewer is a free, open source accessibility tool for Linux low vision computer users. It allows you to enlarge an area of the screen for better readability. It is inspired by Virtual Magnifying Glass . There is also the option to use it in dock mode like KMag. It doesn't support Wayland, only X11. This application is freely available under the open software license and users who want a feature or a new language to be added can contact the developer. -
24
HomeRobot
Mobile manipulation research tools for roboticists
HomeRobot is an open source robotics framework developed by Facebook Research (Meta AI) that provides a complete software stack for mobile manipulation in real-world and simulated environments. Designed for low-cost robots such as the Hello Robot Stretch, HomeRobot enables agents to perceive, navigate, and interact with their surroundings through vision and manipulation. The system focuses on Open Vocabulary Mobile Manipulation (OVMM) — a challenging task in which a robot must explore an unknown environment, identify an object by name, locate a suitable receptacle, and place the object appropriately. HomeRobot integrates perception, planning, and control under a unified architecture, supporting AI Habitat for simulation and ROS Noetic for real-world deployment. ... -
25
MATLAB Deep Learning Model Hub
Discover pretrained models for deep learning in MATLAB
Discover pre-trained models for deep learning in MATLAB. Pretrained image classification networks have already learned to extract powerful and informative features from natural images. Use them as a starting point to learn a new task using transfer learning. Inputs are RGB images, the output is the predicted label and score.
