{"id":19020753,"url":"https://github.com/librauee/dcic-ocr","last_synced_at":"2025-10-17T15:59:47.126Z","repository":{"id":107434653,"uuid":"485984592","full_name":"librauee/DCIC-OCR","owner":"librauee","description":"2022 DCIC OCR赛题","archived":false,"fork":false,"pushed_at":"2022-04-27T09:19:22.000Z","size":114,"stargazers_count":5,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-17T22:09:07.072Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://www.dcic-china.com/competitions/10023","language":"Python","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/librauee.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-04-26T23:55:25.000Z","updated_at":"2022-11-15T17:52:23.000Z","dependencies_parsed_at":"2023-05-17T11:30:36.345Z","dependency_job_id":null,"html_url":"https://github.com/librauee/DCIC-OCR","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/librauee%2FDCIC-OCR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/librauee%2FDCIC-OCR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/librauee%2FDCIC-OCR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/librauee%2FDCIC-OCR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/librauee","download_url":"https://codeload.github.com/librauee/DCIC-OCR/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250386750,"owners_count":21422028,"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":[],"created_at":"2024-11-08T20:18:34.717Z","updated_at":"2025-10-17T15:59:42.088Z","avatar_url":"https://github.com/librauee.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 基于文本字符的交易验证码识别\n* A榜第3、B榜第6\n\n* part2_code是队友@[Ernnnn](https://github.com/Ernnnn/)的\n## 解决方案\n\n* 使用基于多分类的思路，以effb4为主要模型\n* 使用多种数据增强手段进行增强，包括mixup、cutmix、fmix等\n* 使用imagecaptcha库进行数据生成\n* 使用EMA增强模型性能\n* 使用贝叶斯优化提升模型融合效果\n\n\n## 运行步骤\n1. 下载image文件夹内的镜像并用7z解压\n2. 将训练、测试数据分别放置于raw_data/train,raw_data/test\n3. 运行image/run.sh脚本即可得到结果\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flibrauee%2Fdcic-ocr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flibrauee%2Fdcic-ocr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flibrauee%2Fdcic-ocr/lists"}