On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
Repository Index
47,133 repositories indexed
265–288 of 337 · Most stars
PyTorch Connectomics: segmentation toolbox for EM connectomics
- computer-vision
- neuroscience
- connectomics
- pytorch
Automated Testing for Set-Top Boxes and Smart TVs
- python
- test-automation
- set-top-box
- remote-control
Official community continuation of Harbor's vision
A simple, flexible, and extensible template for PyTorch. It's beautiful.
Face detection using deep learning.
- face-detection
- faster-rcnn
- rcnn
- object-detection
The technical vision paper for Polkadot, a heterogeneous extensible multi-chain.
This repository provides a set of tools and libraries to integrate Intel® OpenVINO™ Toolkit with ROS 2 (Robot Operating System), enabling efficient deployment of deep learning models for computer vision applications on Intel® hardware.
mutual layer for multiple agents from different environment or providers to work on same interface or device, toward the same final goal
- agent-supervision
- ai-agents
- ai-safety
- claude-code
The implementation code for "DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction"
- generative-adversarial-network
- mri-reconstruction
- computer-vision
- deep-learning
🥗 Provision, share, manage local and cloud developer environments.
- developer-tools
- cli
- python
- docker
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
- adversarial-attacks
- ai-safety
- autonomous-driving
- backdoor-attacks
OGraf is an Open specification for HTML based Graphics, used in live television and post production workflows.
- ebu
- graphics
- ograf
- television
NeuraVision — AI content generation platform (PHP backend engine: auth, credits, generation, analytics)
- ab-testing
- ai-platform
- analytics
- backend-api
TensorFlow Lite models for MIRNet for low-light image enhancement.
- tinyml
- tflite
- tensorflow2
- computer-vision
Lowest barrier of entry to Image Processing, Computer Vision and Neural Networks on the JavaVM
- clojure
- computer-vision
- kotlin
- opencv
Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0
- aloha
- flow-matching
- icra2026
- jax
This is a library that provides generic functionalities for the implementation of imports. In addition to maximum performance and optimized memory consumption, Pacemaker can also be used to implement imports in distributed scenarios that place the highest demands on speed and stability.
- magento
- import
- products
- categories
Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.
How to create a Cartoonizer Android app with TensorFlow Lite models.
- tensorflow-lite
- tflite
- computer-vision
- gans
AFI VISION BUILDER
To facilitate the introduction of ITU-R BT.2100 Hybrid Log-Gamma (HLG) production, BBC R&D have created a package of look-up tables (LUTs) that implement a range of key format conversions.
- high-dynamic-range
- high-dynamic-range-imaging
- television
- television-production
Web control panel to deploy apps on your servers (with Dokku)
- dokku
- devops
- control-panel
- provisioning
🌸 iOS11 demo application for flower classification.
- ios
- swift
- swift4
- vision