{"id":21714659,"url":"https://github.com/trickygo/ss_digit_recognition","last_synced_at":"2025-10-08T21:44:50.720Z","repository":{"id":35402544,"uuid":"203352511","full_name":"TrickyGo/SS_Digit_Recognition","owner":"TrickyGo","description":"数字验证码识别","archived":false,"fork":false,"pushed_at":"2022-03-11T23:56:45.000Z","size":34426,"stargazers_count":4,"open_issues_count":3,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-12T19:14:09.017Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TrickyGo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-08-20T10:21:03.000Z","updated_at":"2023-06-08T16:39:20.000Z","dependencies_parsed_at":"2022-08-08T08:00:46.118Z","dependency_job_id":null,"html_url":"https://github.com/TrickyGo/SS_Digit_Recognition","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/TrickyGo/SS_Digit_Recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2FSS_Digit_Recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2FSS_Digit_Recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2FSS_Digit_Recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2FSS_Digit_Recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TrickyGo","download_url":"https://codeload.github.com/TrickyGo/SS_Digit_Recognition/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2FSS_Digit_Recognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000702,"owners_count":26082837,"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":"2025-10-08T02:00:06.501Z","response_time":56,"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":[],"created_at":"2024-11-26T00:37:41.040Z","updated_at":"2025-10-08T21:44:50.687Z","avatar_url":"https://github.com/TrickyGo.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SS_Digit_Recognition\n\n## 部署部分（8/26更新）\n  1. flask_server.py（需要读取cnn_best.h5） ：在服务器上使用python3解释器运行，运行后将使用6000端口接收request\n  2. local_client.py : 本地读取验证码图片，然后调用服务器接口\n  3. server_config.json 配置文件，放在同一目录下即可\n  4. flask_web.py by 盛禹 8.27\n  5. templates/index.html by 盛禹 8.27 （使用uploads文件夹）\n  \n## 实验部分：\n### 文件说明：\n  1.cnn_captcha_break.0.5.py 执行后：首先定义CNN模型，然后读取同目录下的cnn_best.h5参数，然后将同目录下的test文件夹所有图片读入并print识别结果。图片可为任意大小的.jpg或.png（可以截个屏放在test里）, 为了提高检查率，请尽量使图片接近37*120（验证码原图大小）。\n  \n  2.cnn_best.h5 是 \u003c1.cnn_captcha_break.0.5.py\u003e 所需要读取的网络参数（我已经训练的差不多的，其实并未充分训练，可以继续）。\n  \n  \n  3.captcha_break_test_0.4.ipynb 是模型的训练过程。会读取train目录下的灰度图像进行训练，然后生成\u003c2.cnn_best.h5\u003e。\n  \n  4.requirements.txt 是执行 \u003c1.cnn_captcha_break.0.5.py\u003e的所需libs\n\n### 使用方法:\n  cnn_capcha_break.py ：将网络参数文件\u003ccnn_best.h5\u003e和\u003ccnn_capcha_break.py\u003e放于同一文件夹下，所需识别的图片放入（test文件夹下），然后使用python解释器执行它（需提前安装好需要导入的包），观察打印结果。\n  \n  captcha_break_test_0.5.ipynb 使用方法：jupyter notebook\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrickygo%2Fss_digit_recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrickygo%2Fss_digit_recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrickygo%2Fss_digit_recognition/lists"}