{
  "fetched_at": "2026-10-19T06:30:26Z",
  "source_url": "https://www.kaggle.com/competitions/bmi707-assignment-2-q5/data",
  "pages": [
    {
      "name": "rules",
      "content": "\n\t<!-- Begin Base Rules -->\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 11, 2018</strong></p>\n    <p>Entry Deadline: <strong>April 25, 2018 9:00 AM EDT</strong></p>\n    <p>End Date: <strong>April 25, 2018 9:00 AM EDT</strong></p>\n\t<!-- End Base Rules -->\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "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</li>\n<li><strong>train.csv</strong> - the labels of the training set</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. </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. </li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</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/bmi707-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>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://en.wikipedia.org/wiki/Sensitivity_and_specificity#Confusion_matrix\">accuracy</a>.</p>\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: Id and Category.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>Id,Category<br />00000041_004.png,0<br /><span style=\"font-size: 14px; line-height: 1.4em;\">00000057_003.png,1<br />00000067_002.png,2<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}