{
  "fetched_at": "2026-10-19T10:38:02Z",
  "source_url": "https://www.kaggle.com/competitions/ces117v/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The 'train' dataset contains all images in their respective folders. Each folder contains images related to a specific target class. The 'test' set 1000 randomly numbered images. Your goal is to accurately predict the likelihood that the image belongs a certain class using deep learning, i.e. Normal = 0, COVID = 1, Lung_Opacity = 2.\n\n### File and folder descriptions\n\n    train - the training image folder\n    test - the test image folder\n    submission.csv - a sample submission file in the correct format\n\nThe order of the rows in your submission does not matter, but the names of the filename's must be correct. The column named \"target\" is your prediction.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, you have to predict if an X-Ray image depicts COVID-19, non-COVID-19 lung opacity or a normal lung.\nThe data is made of two zip files:\n- train.zip contains 3 folders: one for each target class.\n- test.zip contains images randomly numbered. Each image contains an image of a certain class.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<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 image in the dataset</strong>, submission files should contain two columns: filename and target. \n</p><p>The file should contain a header and have the following format:</p>\n<pre>filename,target<br>img_282.png,0<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "You may participate in this competition as an individual or in a team of up to **TWO ** people. All teams must be created before the **21st of November 2021** at 23:59PM.\n\nTo ensure that competitors cannot game the system, test data are sampled into Public and Private data. Public scores are shown on the public leaderboard and constitute 80% of your \"Kaggle\" mark. Private scores (20%) will be published after the competition is over.\n\nMultiple accounts per user are not permitted, and neither is collaboration or membership across multiple teams. Individuals and their submissions originating from multiple accounts will be disqualified.\n\nCode must **NOT **be shared privately outside of a team. \n\nYou will have to submit your final code on Brightspace.\n\nEach team will submit a technical report on (Details on Brightspace).\n\n- Don't cheat!\n- Apply yourself!\n- Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}