{"id":32445602,"url":"https://github.com/avafly/paddleocr-ncnn-cpp","last_synced_at":"2026-01-12T11:51:01.265Z","repository":{"id":311247294,"uuid":"1043042143","full_name":"Avafly/PaddleOCR-ncnn-CPP","owner":"Avafly","description":"C++ implementations of PP-OCRv3 and PP-OCRv5 using ncnn for inference.","archived":false,"fork":false,"pushed_at":"2025-10-23T01:47:45.000Z","size":297,"stargazers_count":19,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-23T03:30:14.258Z","etag":null,"topics":["cpp","crnn","db","deep-learning","ncnn","ocr","paddleocr"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Avafly.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-08-23T03:07:58.000Z","updated_at":"2025-10-23T01:47:49.000Z","dependencies_parsed_at":"2025-08-23T03:37:17.009Z","dependency_job_id":"cebfed7c-7838-475d-99dc-8aba0e203249","html_url":"https://github.com/Avafly/PaddleOCR-ncnn-CPP","commit_stats":null,"previous_names":["avafly/paddleocr-ncnn-cpp"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/Avafly/PaddleOCR-ncnn-CPP","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Avafly%2FPaddleOCR-ncnn-CPP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Avafly%2FPaddleOCR-ncnn-CPP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Avafly%2FPaddleOCR-ncnn-CPP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Avafly%2FPaddleOCR-ncnn-CPP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Avafly","download_url":"https://codeload.github.com/Avafly/PaddleOCR-ncnn-CPP/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Avafly%2FPaddleOCR-ncnn-CPP/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281055226,"owners_count":26436350,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-26T02:00:06.575Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cpp","crnn","db","deep-learning","ncnn","ocr","paddleocr"],"created_at":"2025-10-26T04:01:07.198Z","updated_at":"2026-01-07T15:14:21.424Z","avatar_url":"https://github.com/Avafly.png","language":"C++","readme":"This repository provides C++ implementations of PP-OCRv3 and PP-OCRv5, inspired by the official [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) project and using [ncnn](https://github.com/Tencent/ncnn) for inference.\n\nThe Release page contains a complete project archive that includes resources like models (v3 \u0026 v5) and images required to run the demo.\n\n## Demo\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://cdn.jsdelivr.net/gh/Avafly/ImageHostingService@master/uPic/PixPin_2025-08-22_23-55-24.png\" width = \"800\"\u003e\n\u003c/p\u003e\n\n## Usage\n\n```bash\n./main ../config.json ../images/ocr_img1.png\n```\n\n## Requirements\n\n* OpenCV 4.10.0\n* ncnn 20241226\n* OpenMP 3.0+\n\n## Benchmarks\n\nI ran benchmarks on a RPi 4B using `ocr_img1.png` (simple) and `ocr_img3.png` (complex). You can find those images inside the release page `archive.tar.gz`.\n\n|  Models  | Latency / Peak memory for ocr_img1 | Latency / Peak memory for ocr_img3 |\n| :------: | :--------------------------------: | :--------------------------------: |\n| PP-OCRv3 |        387.80 ms / 101.3 MB        |       5213.68 ms / 273.6 MB        |\n| PP-OCRv5 |        387.05 ms / 98.95 MB        |       6740.93 ms / 335.7 MB        |\n\n## Notes\n\nEnabling FP16 may be faster but can cause NaN results on some devices. Edit `config.json` to enable or disable FP16.\n\n## Implementation References\n\nhttps://github.com/MhLiao/DB\n\nhttps://github.com/nihui/ncnn-android-ppocrv5\n\nhttps://github.com/FeiGeChuanShu/ncnn_paddleocr\n\nhttps://github.com/PaddlePaddle/PaddleOCR","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favafly%2Fpaddleocr-ncnn-cpp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Favafly%2Fpaddleocr-ncnn-cpp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favafly%2Fpaddleocr-ncnn-cpp/lists"}