{
  "fetched_at": "2026-10-24T11:55:32Z",
  "source_url": "https://www.kaggle.com/competitions/2020bmi707-assignment-2-q5/data",
  "pages": [
    {
      "name": "rules",
      "content": "\n    <h3>One account per participant</h3>\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n    <h3>No private sharing</h3>\n    <p>\n        Privately sharing code or data is not permitted.\n        It's okay to share code if made available to all participants on the forums.\n    </p>\n    <h3>Team Limits</h3>\n    <p>Each student is required to submit .</p>\n    <h3>Submission Limits</h3>\n    <p>You may submit a maximum of 2 entries per day.</p>\n    <p>You may select up to 2 final submissions for judging.</p>\n    <h3>Competition Timeline</h3>\n    <p>Start Date: <strong>April 15, 2020</strong></p>\n    <p>Entry Deadline: <strong>April 29, 2020 11:59 PM EDT</strong></p>\n    <p>End Date: <strong>May 2, 2020 11:59 PM EDT</strong></p>\n\t\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train.tar</strong> - the training set (Dropbox link: <a href=\"https://www.dropbox.com/s/feaakvusdvkep3n/train.tar\">https://www.dropbox.com/s/feaakvusdvkep3n/train.tar)</a></li>\n<li><strong>train.csv</strong> - the labels of the training set (Dropbox link: <a href=\"https://www.dropbox.com/s/9kebfecemhfkj7k/train.csv\">https://www.dropbox.com/s/9kebfecemhfkj7k/train.csv)</a></li>\n<li><strong>testPublic.tar</strong> - the public test set (the labels are not given). This dataset is used to generate the evaluation results for the leaderboard. (Dropbox link: <a href=\"https://www.dropbox.com/s/20d8b9z8znc2lmp/testPublic.tar\">https://www.dropbox.com/s/20d8b9z8znc2lmp/testPublic.tar</a>) </li>\n<li><strong>testPrivate.tar</strong> - the private test set (the labels are not given). This dataset is used to generate the final evaluation. (Dropbox link: <a href=\"https://www.dropbox.com/s/lun96wxiq84z7eg/testPrivate.tar\">https://www.dropbox.com/s/lun96wxiq84z7eg/testPrivate.tar</a>) </li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format. (Dropbox link: <a href=\"https://www.dropbox.com/s/a9o0lkszeusdmr9/sampleSubmission.csv\">https://www.dropbox.com/s/a9o0lkszeusdmr9/sampleSubmission.csv</a>)</li>\n</ul>\n<h2>Data fields in the submission</h2>\n<ul>\n<li><strong>Id</strong> - the file name of the image</li>\n<li><strong>Category</strong> - the diagnostic category of the image</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Question 5: Multiclass classification</h2>\n<p>In this question, we will build multiclass classifiers to distinguish different types of lung diseases using the NIHCXR8 data.</p>\n<p>Please download the training set and the validation set from the Data tab (https://www.kaggle.com/c/2020bmi707-assignment-2-q5/data). Please note that this dataset is different from the one we used in Questions 3 and 4. Please <b>DO NOT</b> use any additional dataset to train or augment your models.</p> \n<p>Feel free to use any (ImageNet or any custom) architecture to classify all available classes.</p>\n<p>In addition to participating in this BMI707 internal Kaggle contest, you would need to provide your answers to the questions and codes in the assignment writeup.</p>\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
    }
  ]
}