{
  "fetched_at": "2026-10-19T13:56:46Z",
  "source_url": "https://www.kaggle.com/competitions/ctrl-shift-intelligence/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>This dataset for the doodle recognition challenge consists of 9 different classes and each image belongs to a <strong>unique</strong> class.</p>\n<p>The main <strong>train</strong> directory contains 9 folders, each having 700 grayscale images of 360x360 resolution. The directory structure has been simplified for classification i.e. the folder names in the train directory correspond to class name of all the doodles inside the folder.</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.zip</strong> - the training dataset</li>\n<li><strong>test.zip</strong> - the test set</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<a href=\"https://quickdraw.withgoogle.com\">\"Quick, Draw!\"</a> was released as an experimental game to educate the public in a playful way about how AI works. The game prompts users to draw an image depicting a certain category, such as ”banana,” “table,” etc.\nThe dataset for this doodle recognition challange has been derivied from a small subset of the huge amount of data collected by Google Quick Draw game. We recommend you to try the <a href=\"https://quickdraw.withgoogle.com\">game</a> yourself and get some intuition about this challenge. \n<h2>About</h2>\n<p>Club of Programmers IIT(BHU) Varanasi is back with Ctrl Shift Intelligence, the Machine Learning event of COPS Week 2021 exclusively for machine learning enthusiasts. In this year's competition, the task will be to classify the images into different classes. The dataset set contains exactly 6300 images belonging to 9 classes.</p>\n<br>\n<p>Some general guidelines:</p>\n<ul>\n    <li>There will be a public leader board and a private leader board.</li>\n    <li>After the competition the top performers will be asked to submit the code of their machine learning algorithm. Final standing will be evaluated only after the code evaluation.</li>\n    <li>Use of any external dataset is not allowed. The participants must only work with the dataset provided.</li>\n    <li>Note that predictions have to be made on test images.</li>\n<li>You can participate in teams having max size of 2 members.</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "General Guidelines:\n\n - You can participate in teams having max size of 2 members.\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<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 image in the test dataset</strong>, The submission file should contain two columns: Id and Category. The category names can be inferred from the directory names in the train dataset.</p>\n<p>The submission file should look like this:</p>\n<pre>Id,Category<br>0.png,alarm clock<br>1.png,skull<br>2.png,nail<br>...<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "The competition will begin on 07-02-2021 and will accept submissions till 09-02-2021, 11:59 P.M IST.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}