{"id":14959109,"url":"https://github.com/sunskyf/easypr-python","last_synced_at":"2026-02-25T23:03:21.322Z","repository":{"id":172646418,"uuid":"86538569","full_name":"SunskyF/EasyPR-python","owner":"SunskyF","description":"EasyPR-python","archived":false,"fork":false,"pushed_at":"2018-03-16T16:03:47.000Z","size":84,"stargazers_count":71,"open_issues_count":2,"forks_count":31,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-04-07T02:07:17.137Z","etag":null,"topics":["deep-learning","easypr","opencv","plate-detection","plate-recognition","tensorflow-examples"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SunskyF.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}},"created_at":"2017-03-29T04:32:24.000Z","updated_at":"2025-03-25T13:48:28.000Z","dependencies_parsed_at":null,"dependency_job_id":"56251c89-6744-4009-b0f1-d0d28f82c810","html_url":"https://github.com/SunskyF/EasyPR-python","commit_stats":{"total_commits":2,"total_committers":1,"mean_commits":2.0,"dds":0.0,"last_synced_commit":"c35b34876d63dbdee56719ebf419f4e3af99004a"},"previous_names":["sunskyf/easypr-python"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SunskyF%2FEasyPR-python","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SunskyF%2FEasyPR-python/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SunskyF%2FEasyPR-python/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SunskyF%2FEasyPR-python/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SunskyF","download_url":"https://codeload.github.com/SunskyF/EasyPR-python/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252038224,"owners_count":21684655,"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","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":["deep-learning","easypr","opencv","plate-detection","plate-recognition","tensorflow-examples"],"created_at":"2024-09-24T13:18:51.696Z","updated_at":"2026-02-25T23:03:21.287Z","avatar_url":"https://github.com/SunskyF.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ULPR (Universal License Plate Recognition)\nULPR(Universal License Plate Recognition)的设想是一个通用场景下的车牌识别系统。因为是从EasyPR出发，所以还是保留EasyPR-python的原库名。  \n1. 用python写了一下EasyPR，但其中应该还是有bug，速度慢是detect部分很慢，有python本身的锅，也有我没有优化的锅  \n2. 用deep的方法做检测和识别  \n\n## Requirements\npython 3  \ntensorflow 1.5.0  \nkeras  \n只在windows下进行了测试  \n\n## Data\n感谢[EasyPR](https://github.com/liuruoze/EasyPR)  \ndemo测试时使用了EasyPR的数据库  \n\n\n## Download\n训练easypr方法时，请下载easypr_train_data.zip放到data目录下  \n测试时请下载data.zip放到data目录下\neasypr的训练数据和各个模型的训练模型请从[百度云](https://pan.baidu.com/s/1bqmXEDD)上下载  \n将模型文件：\n\n1. whether\\_car\\_20180210T1049.zip\n2. chars\\_20180210T1038.zip\n3. mrcnn\\_20180212T2143.zip\n\n解压放在output下。  \n\n最后data文件夹下目录结构是  \n├─demo  \n├─easypr_train_data  \n│  ├─chars  \n│  └─whether_car  \n├─general_test  \n├─GDSL.txt  \n└─使用说明.txt  \noutput文件夹下目录结构是  \n├─chars_20180210T1038   \n\n├─mrcnn\\_20180212T2143\n\n└─whether_car_20180210T1049  \n\n## TODO\n[] 写博客  \n[] multi-label的车牌识别  \n[] 更好的根据mask获得车牌精确4个点的算法  \n[] 轻量化  \n\n## Done\n[x] 重构代码  \n[x] mask-rcnn  \n\n## Train\n可以参考scripts下的训练脚本  \n\n## Demo  \n切换不同方法时使用不同cfg即可，如将easypr.yml替换为maskrcnn.yml  \ndemo\n```bash\n# 用easypr的方法\npython demo.py --cfg cfgs/easypr.yml --path data/demo/test.jpg\n```\n\n功能测试\n```bash\npython func_test.py --cfg cfgs/easypr.yml\n```\n\n批量测试（data目录下需要有general_test目录）\n```bash\npython accuracy_test.py --cfg cfgs/easypr.yml\n```\n\n## Question\n1. 训练mrcnn因为使用自己的数据，请注意一下数据格式    \n\n## Reference\n[EasyPR](https://github.com/liuruoze/EasyPR)  \n[MaskRCNN](https://github.com/matterport/Mask_RCNN)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsunskyf%2Feasypr-python","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsunskyf%2Feasypr-python","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsunskyf%2Feasypr-python/lists"}