{
  "fetched_at": "2026-10-20T07:02:43Z",
  "source_url": "https://www.kaggle.com/competitions/2018-competition-3/data",
  "pages": [
    {
      "name": "data-description",
      "content": "验证码识别任务，训练集20000，测试集20000。\n\n提交示例已给出，标签记为验证码识别结果。\n<ul>\n<li><strong>train文件夹</strong> - the training set</li>\n<li><strong>test文件夹<</strong> - th</strong> - the test set</li>\n<li><strong>sample_test_target.csv</strong> - a sample submission file in the correct format</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# 验证码识别任务\n本次竞赛的目的是能够实现对验证码进行识别。\n# 赛制介绍\n本次比赛系陶老师AI课程班课程内部第01次竞赛。\n\n流程：\n1.每位同学注册一个kaggle账号，并登入，然后打开指定链接，参与比赛每位同学可以查看相应的竞赛要求和数据集，提交成绩时需**备注学号**，否则成绩无效。\n\n2.从该平台下载数据集，本地调试算法，并在该平台上提交结果，提交完成后，即得相应的分数并可以查看公共排名结果。\n\n3.每人每天有且仅有二次提交机会，高分成绩直接覆盖低分成绩。\n\n4.比赛提供标准训练集（含标签），仅供参赛选手训练算法模型；提供标准测试数据集（无标签），供参赛选手提交评测结果参与排名。比赛中严禁使用外部数据集，一经发现，成绩作废。\n\n5.比赛截止时，将对所有参赛队伍代码进行审核，识别并剔除只靠人工标注而没有算法贡献的队伍与使用重复代码参赛的队伍。\n\n6.比赛截止时，将取得最高成绩的代码和对应文档提交。（注意：文档需有对问题解决过程、难点解决过程和核心代码分析等问题的体现。）\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:</p>\n<hr>\n<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids.&nbsp;For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>AuthorId,DuplicateAuthorIds<br>1,1<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}