{
  "fetched_at": "2026-10-24T18:37:05Z",
  "source_url": "https://www.kaggle.com/competitions/2024bmi707-assignment-2-q5/data",
  "pages": [
    {
      "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": "rules",
      "content": "<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",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "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/2024bmi707-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 write-up.</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}