zuoqing1988/ZQCNN

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2214 stars · 499 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ZQCNN is a lightweight deep learning inference framework written in C/C++ that runs on Windows, Linux, and ARM-Linux. It ships with demos for face detection, face recognition, 106-point facial landmarks, head pose estimation, and OCR.

Use cases

• run face detection on cpu
• deploy face recognition on arm linux
• detect facial landmarks in images
• estimate head pose and gaze from video
• run a lightweight neural network inference engine without gpu
• recognize text from cropped image regions

When to choose

• you need fast cpu-only face detection or recognition on windows, linux, or arm devices
• you want a small self-contained inference framework without heavy dependencies
• you are building embedded or edge vision applications

When to avoid

• you need gpu acceleration or broad model ecosystem support like onnx or tensorflow
• you need production-grade OCR with text detection, which is not yet supported
• you prefer actively maintained mainstream frameworks like ncnn or opencv dnn

Facets

library · maturity maintenance

deep-learning llm-inference computer-vision image-processing ocr deep-learning computer-vision windows cpp c face-detection face-recognition mtcnn ssd landmark-detection inference-engine arm-neon inference linux arm

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zuoqing1988/ZQCNN")