Openvision
deep learning vision detector/estimator
Install / Use
/learn @bububa/OpenvisionREADME
libopenvision deep learning visualization C library
Prerequest
- ncnn Install
- openmp
- vulkan(optional)
Build
git submodule update --init --recursuve
cd build
cmake .. # optional -DNCNN_VULKAN=OFF -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang
Features
- face
- aligner (for face keypoints alignment)
- detecter (for face location and keypoints detection)
- mtcnn Google Drive
- centerface Google Drive
- retainface Google Drive
- yoloface Google Drive
- scrfd Google Drive
- anticonv (for mask detection) Google Drive
- recognizer (face feature extration for classification)
- mobilenet Google Drive
- landmarker (for face landmarkers extraction)
- insightface Google Drive
- zq Google Drive
- scrfd Google Drive
- tracker (for face IOU calculation bettween frames)
- hopenet (for head pose detection) Google Drive
- hair (for hair segmentation) Google Drive
- eye
- lenet (eye status detector) Google Drive
- pose
- detector (for pose detection/estimation)
- ultralight Google Drive
- openpose Google Drive
- estimator (for pose estimation)
- ultralight Google Drive
- movenet Google Drive
- segmentor (for pose segmentation)
- deeplabv3plus Google Drive
- erdnet Google Drive
- rvm (RobustVideoMatting) Google Drive
- detector (for pose detection/estimation)
- hand
- detector (for hand detect)
- yolox Google Drive
- nanodet Google Drive
- pose (for hand pose estimation)
- handnet Google Drive
- pose3d (for 3d handpose detection)
- mediapipe Google Drive
- detector (for hand detect)
- styletransfer
- animegan2 Google Drive
- tracker
- lighttrack Google Drive
- counter
- p2pnet Google Drive
- golang binding (github.com/bububa/openvision/go)
Reference
Related Skills
proje
Interactive vocabulary learning platform with smart flashcards and spaced repetition for effective language acquisition.
YC-Killer
2.7kA library of enterprise-grade AI agents designed to democratize artificial intelligence and provide free, open-source alternatives to overvalued Y Combinator startups. If you are excited about democratizing AI access & AI agents, please star ⭐️ this repository and use the link in the readme to join our open source AI research team.
best-practices-researcher
The most comprehensive Claude Code skills registry | Web Search: https://skills-registry-web.vercel.app
groundhog
400Groundhog's primary purpose is to teach people how Cursor and all these other coding agents work under the hood. If you understand how these coding assistants work from first principles, then you can drive these tools harder (or perhaps make your own!).
