KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#developer-tools #typescript #codex #ai-agents #claude-code #dsh #dsh-plugin #cli #macos #ai-agent #deepseek-harness #open-source

PaddleOCR-ncnn-CPP

★ 102 Open GitHub ↗

C++ implementations of PP-OCRv3/4/5/6 using ncnn for inference.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

This repository provides C++ implementations of PP-OCRv3/4/5/6, inspired by the official [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) project and using [ncnn](https://github.com/Tencent/ncnn) for inference.

The Release page contains a complete project archive that includes resources like models and images required to run the demo.

## Demo

## Usage

```bash
./main ../config.json ../images/ocr_img1.png
```

## Requirements

* OpenCV 4.11.0
* ncnn 20241226
* OpenMP 2.0+

## Benchmarks

I ran benchmarks on a VPS using `ocr_img1.png` (simple) and `ocr_img3.png` (complex). You can find those images inside the release page `archive.tar.gz`.

CPU: 2 x Intel(R) Xeon(R) Platinum (2) @ 2.50 GHz

## Tested on

* macOS 15
* Debian 12
* Windows 10/11

## Notes

Enabling FP16 may be faster but can cause NaN results on some devices. Edit `config.json` to enable or disable FP16.

## Implementation References

https://github.com/MhLiao/DB

https://github.com/nihui/ncnn-android-ppocrv5

https://github.com/FeiGeChuanShu/ncnn_paddleocr

https://github.com/PaddlePaddle/PaddleOCR

PaddleOCR-ncnn-CPP

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README