Search Results for "vision" - Page 2
Sort By:
Showing 271 open source projects for "vision"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
Colossal-AI
Making large AI models cheaper, faster and more accessible
The Transformer architecture has improved the performance of deep learning models in domains such as Computer Vision and Natural Language Processing. Together with better performance come larger model sizes. This imposes challenges to the memory wall of the current accelerator hardware such as GPU. It is never ideal to train large models such as Vision Transformer, BERT, and GPT on a single GPU or a single machine. There is an urgent demand to train models in a distributed environment. ... -
2
hCaptcha Challenger
Gracefully face hCaptcha challenge with multimodal llms
...The framework includes support for multiple types of captcha challenges such as object selection, drag-and-drop puzzles, and image labeling tasks. It implements an agent-style workflow where the system interprets the challenge prompt, selects the appropriate vision model, and generates the required interaction automatically. -
3
RF-DETR
RF-DETR is a real-time object detection and segmentation
RF-DETR is an open-source computer vision framework that implements a real-time object detection and instance segmentation model based on transformer architectures. Developed by Roboflow, the project builds upon modern vision transformer backbones such as DINOv2 to achieve strong accuracy while maintaining efficient inference speeds suitable for real-time applications. The model is designed to detect objects and segment them within images or video streams using a unified detection pipeline. ... -
4
ViMax
Director, Screenwriter, Producer, and Video Generator All-in-One
ViMax is an open-source framework for performing large-scale multi-modal vision-language modeling and reasoning by combining powerful image encoders with advanced language models to solve complex visual tasks. It integrates components like visual encoders, cross-modal fusion techniques, and reasoning modules so that users can go beyond simple captioning or classification to perform tasks such as visual question answering, multi-image inference, and structured scene understanding. ... -
$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.
-
5
FiftyOne
The open-source tool for building high-quality datasets
The open-source tool for building high-quality datasets and computer vision models. Nothing hinders the success of machine learning systems more than poor-quality data. And without the right tools, improving a model can be time-consuming and inefficient. FiftyOne supercharges your machine learning workflows by enabling you to visualize datasets and interpret models faster and more effectively. Improving data quality and understanding your model’s failure modes are the most impactful ways to boost the performance of your model. ... -
6
Zerox OCR
PDF to Markdown with vision models
A dead simple way of OCR-ing a document for AI ingestion. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. The vision models just make sense. ZeroX is an open-source machine learning framework designed for fast experimentation and production deployment, optimized for speed and ease of use. -
7
DINOv3
Reference PyTorch implementation and models for DINOv3
...DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. The model supports multiple backbone architectures, including Vision Transformers (ViT), and can handle larger image resolutions with improved stability during training. The learned embeddings generalize robustly across tasks like classification, retrieval, and segmentation without fine-tuning, showing state-of-the-art transfer performance among self-supervised models. -
8
FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs
...Developed within the PaddlePaddle ecosystem, the toolkit focuses on providing high-performance deployment capabilities for modern AI models including large language models and vision-language systems. The platform enables developers to deploy trained models quickly using optimized inference pipelines that support GPUs, specialized AI accelerators, and other hardware architectures. FastDeploy includes advanced acceleration technologies such as speculative decoding, multi-token prediction, and efficient KV cache management to improve throughput and latency during inference. ... -
9
sunnypilot
Open source driver assistance system
...Its Modular Assistive Driving System provides more flexible engagement behavior than the upstream project. Neural-network lateral control, automatic lane changes, and configurable driving models expand steering customization. Smart cruise functions can use vehicle, vision, and offline OpenStreetMap data for speed-related assistance. Display customization, quiet mode, connected services, and remote device features extend the everyday driving experience. The project aims to preserve openpilot safety constraints while offering substantially more configuration. -
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.
-
10
JoyAI-VL-Interaction
An Open Real-time Video-Language Interaction System
JoyAI-VL-Interaction is an open real-time video-language interaction system built around an 8B-scale vision-first model. It is designed to watch a webcam or livestream continuously and decide whether to speak, stay silent, or delegate a harder task. Unlike turn-based assistants, it focuses on event-driven interaction where timing matters as much as answer quality. The repository releases the model, training recipe, time-aligned interaction data, and deployable system together. ... -
11
dots.ocr
Multilingual Document Layout Parsing in a Single Vision-Language Model
dots.ocr is a cutting-edge multilingual document parsing system built on a unified vision-language model that combines layout detection, text recognition, and structural understanding into a single architecture. Unlike traditional OCR pipelines that rely on multiple specialized components, dots.ocr integrates these processes end-to-end, reducing error propagation and improving consistency across tasks. The model is designed to recognize virtually any human script, making it highly effective for global and low-resource language scenarios. ... -
12
LingBot-VLA
A Pragmatic VLA Foundation Model
LingBot-VLA is an open-source Vision-Language-Action (VLA) foundational AI model designed to serve as a general “brain” for real-world robotic manipulation by grounding multimodal perception and language into actionable motions. It has been pretrained on tens of thousands of hours of real robotic interaction data across multiple robot platforms, which enables it to generalize well to diverse morphologies and tasks without needing extensive retraining on each new bot. -
13
MiniMind-V
"Big Model" trains a visual multimodal VLM with 26M parameters
MiniMind-V is an experimental open-source project that aims to train a very small multimodal vision–language model (VLM) from scratch with extremely low compute and cost, making research and experimentation accessible to more people. The repository showcases training workflows and code designed to produce a 26-million parameter model—including both image and text capabilities—using minimal resources in very little time, reflecting a trend toward democratizing AI research. -
14
Datasets
Hub of ready-to-use datasets for ML models
Datasets is a library for easily accessing and sharing datasets, and evaluation metrics for Natural Language Processing (NLP), computer vision, and audio tasks. Load a dataset in a single line of code, and use our powerful data processing methods to quickly get your dataset ready for training in a deep learning model. Backed by the Apache Arrow format, process large datasets with zero-copy reads without any memory constraints for optimal speed and efficiency. We also feature a deep integration with the Hugging Face Hub, allowing you to easily load and share a dataset with the wider NLP community. ... -
15
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
...MiniMax-VL-01 extends this core by adding a 303M-parameter Vision Transformer and a two-layer MLP projector in a ViT–MLP–LLM framework, allowing the model to process images at dynamic resolutions up to 2016×2016. -
16
FastVLM
This repository contains the official implementation of FastVLM
FastVLM is an efficiency-focused vision-language modeling stack that introduces FastViTHD, a hybrid vision encoder engineered to emit fewer visual tokens and slash encoding time, especially for high-resolution images. Instead of elaborate pruning stages, the design trades off resolution and token count through input scaling, simplifying the pipeline while maintaining strong accuracy. -
17
CogView4
CogView4, CogView3-Plus and CogView3(ECCV 2024)
...The model also supports fine-tuning and downstream customization, extending its applicability to creative content generation, human–computer interaction, and research on vision-language alignment. -
18
NVIDIA Isaac GR00T
NVIDIA Isaac GR00T N1.5 is the world's first open foundation model
NVIDIA Isaac‑GR00T N1.5 is an open-source foundation model engineered for generalized humanoid robot reasoning and manipulation skills. It accepts multimodal inputs—such as language and images—and uses a diffusion transformer architecture built upon vision-language encoders, enabling adaptive robot behaviors across diverse environments. It is designed to be customizable via post-training with real or synthetic data. The vision-language model remains frozen during both pretraining and finetuning, preserving language understanding and improving generalization. Streamlined MLP connection between vision encoder and LLM with added layer normalization. -
19
Three.js Object Sculptor
Codex plugin that turns attached object images into code-only
...Generated models include meaningful sockets and anchors for animation, transformation, physics, and destruction. Reference and rendered screenshots can be combined for AI vision review and scored self-correction. The workflow targets browser-friendly props and stylized reconstructions rather than photogrammetry or exact mesh extraction. -
20
Diffgram
Training data (data labeling, annotation, workflow) for all data types
...Annotation is required because raw media is considered to be unstructured and not usable without it. That’s why training data is required for many modern machine learning use cases including computer vision, natural language processing and speech recognition. -
21
Self-Operating Computer
A framework to enable multimodal models to operate a computer
The Self-Operating Computer Framework is an innovative system that enables multimodal models to autonomously operate a computer by interpreting the screen and executing mouse and keyboard actions to achieve specified objectives. This framework is compatible with various multimodal models and currently integrates with GPT-4o, o1, Gemini Pro Vision, Claude 3, and LLaVa. Notably, it was the first known project to implement a multimodal model capable of viewing and controlling a computer screen. The framework supports features like Optical Character Recognition (OCR) and Set-of-Mark (SoM) prompting to enhance visual grounding capabilities. It is designed to be compatible with macOS, Windows, and Linux (with X server installed), and is released under the MIT license. -
22
PyTorch Image Models
The largest collection of PyTorch image encoders / backbones
timm (PyTorch Image Models) is a premier library hosting a vast collection of state-of-the-art image classification models and backbones such as ResNet, EfficientNet, NFNet, Vision Transformer, ConvNeXt, and more. Created by Ross Wightman and now maintained by Hugging Face, it includes pretrained weights, data loaders, augmentations, optimizers, schedulers, and reference scripts for training, evaluation, inference, and model export. It's an essential toolkit for vision research and production workflows. -
23
supervision
We write your reusable computer vision tools
We write your reusable computer vision tools. Whether you need to load your dataset from your hard drive, draw detections on an image or video, or count how many detections are in a zone. You can count on us. -
24
The FreeMoCap Project
Free Motion Capture for Everyone
FreeMoCap is an open-source markerless motion capture system that enables users to record human movement using ordinary cameras and convert the footage into usable 3D motion data. The project’s goal is to democratize motion capture by removing the need for expensive suits or proprietary studio hardware, instead relying on computer vision and pose estimation pipelines. It processes synchronized video feeds to reconstruct skeletal motion, which can then be exported for animation, biomechanics research, or creative projects. FreeMoCap includes tools for calibration, recording, processing, and visualization, allowing users to move from raw footage to structured motion data within a single ecosystem. ... -
25
DINOv2
PyTorch code and models for the DINOv2 self-supervised learning
DINOv2 is a self-supervised vision learning framework that produces strong, general-purpose image representations without using human labels. It builds on the DINO idea of student–teacher distillation and adapts it to modern Vision Transformer backbones with a carefully tuned recipe for data augmentation, optimization, and multi-crop training. The core promise is that a single pretrained backbone can transfer well to many downstream tasks—from linear probing on classification to retrieval, detection, and segmentation—often requiring little or no fine-tuning. ...
