Stars
A fancy self-hosted monitoring tool
A free, open source, and extensible speech-to-text application that works completely offline.
Self-hosted YouTube downloader (web UI for youtube-dl / yt-dlp)
Text editor for your terminal: easy, powerful and fast
MCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
A multi core friendly rigid body physics and collision detection library. Written in C++. Suitable for games and VR applications. Used by Horizon Forbidden West and Death Stranding 2.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
Get 10X more out of Claude Code, Codex or any coding agent
Official PyTorch implementation of UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation (ACMMM 2021)
PyTorch implementation of over 30 realtime semantic segmentations models, e.g. BiSeNetv1, BiSeNetv2, CGNet, ContextNet, DABNet, DDRNet, EDANet, ENet, ERFNet, ESPNet, ESPNetv2, FastSCNN, ICNet, LEDN…
PaddlePaddle Docker images and K8s operators for PaddleOCR/Detection developers to use on public/private cloud.
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
这是一个deeplabv3-plus-pytorch的源码，可以用于训练自己的模型。
Real-time portrait segmentation for mobile devices
Dumps decrypted mach-o files from encrypted iPhone applications from memory to disk. This tool is necessary for security researchers to be able to look under the hood of encryption.
[CVPR 2024 Highlight] MonoNPHM: Dynamic Head Reconstruction from Monoculuar Videos
All-in-One Development Tool based on PaddlePaddle
Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
Background Matting: The World is Your Green Screen
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
Files for a tutorial to train SegNet for road scenes using the CamVid dataset
Headers. Not for documents. Not the opposite of footers.
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision