{
  "fetched_at": "2026-10-19T22:59:39Z",
  "source_url": "https://www.kaggle.com/competitions/emotion-detection-from-facial-expressions/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>The evaluation data is included and also available from the latest version of the <a href=\"https://github.com/muxspace/facial_expressions\">facial_expressions</a> repository. Only an example submission file is included here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This is the final project for <strong>DATA 622</strong>, Fall 2016 at CUNY MS Data Analytics. Using the <a href=\"https://github.com/muxspace/facial_expressions\">facial_expressions</a> repository, run your trained model on the images in the <code>test</code> directory. You'll need to normalize the images in size and color space.</p>\r\n<h2>Project Submission</h2>\r\n<p>To get a grade on the Kaggle portion of the final, submit your solution file to Kaggle. On Blackboard, you need to submit your code for training (from the images directory) and evaluating on the test set. Using a notebook is allowed <em>if</em> you order the steps chronologically! Points will be deducted for any work that is difficult to follow.</p>\r\n<p>In addition to the Kaggle submission, you are required to submit a short 3-4 page paper summarizing your work on Blackboard. The paper must discuss the following:</p>\r\n<ul>\r\n<li>an overview of the problem;</li>\r\n<li>why it's challenging;</li>\r\n<li>what techniques you used;</li>\r\n<li>comparison of performance;</li>\r\n<li>generalizable lessons learned/takeaways.</li>\r\n</ul>\r\n<h2>Acknowledgements</h2>\r\n<p>The data in facial_expressions comes from a variety of sources, including</p>\r\n<ul>\r\n<li><a href=\"http://vis-www.cs.umass.edu/lfw/\" style=\"font-size: 1em;\">Labeled Faces In The Wild</a></li>\r\n<li><a href=\"http://www.kasrl.org/jaffe.html\" style=\"font-size: 1em;\">The Japanese Female Facial Expression (JAFFE) Database</a></li>\r\n<li><a href=\"http://cvit.iiit.ac.in/projects/IMFDB/\" style=\"font-size: 1em;\">Indian Movie Face database (IMFDB)</a></li>\r\n<li><a href=\"http://vision.ucsd.edu/~iskwak/ExtYaleDatabase/ExtYaleB.html\" style=\"font-size: 1em;\">The Extended Yale Face Database B</a></li>\r\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Models are scored on classification accuracy. Since this is a multi-class problem, the score is simply the number of correct classifications divided by the total number of elements in the test set.</p>\r\n<h2>Submission Format</h2>\r\n<p>The solution file contains two columns: Image and Emotion. Image is the name of the image file and acts as a key. The emotion class is Emotion and must be in { anger, disgust, fear, happiness, neutral, sadness, surprise }.</p>\r\n<p>The file should contain a header and have the following format:</p>\r\n<pre>Image,Emotion<br />108a.jpg,happiness<br />110b.jpg,happiness<br />118a.jpg,fear<br />119a.jpg,surprise<br />11a.jpg,neutral<br />121a.jpg,fear<br /><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\r\n\t<!-- Begin Base Rules -->\r\n    <h3>One account per participant</h3>\r\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n    <h3>No private sharing outside teams</h3>\r\n    <p>\r\n        Privately sharing code or data outside of teams is not permitted.\r\n        It's okay to share code if made available to all participants on the forums.\r\n    </p>\r\n    <h3>Team Mergers</h3>\r\n    <p>Team mergers are not allowed in this competition.</p>\r\n\r\n    <h3>Team Limits</h3>\r\n    <p>There is no maximum team size.</p>\r\n    <h3>Submission Limits</h3>\r\n    <p>You may submit a maximum of 2 entries per day.</p>\r\n    <p>You may select up to 2 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>12/13/2016 12:22 AM UTC</strong></p>\r\n    <p>Merger Deadline: <strong>None</strong></p>\r\n    <p>Entry Deadline: <strong>None</strong></p>\r\n    <p>End Date: <strong>12/18/2016 11:59 PM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n<p>For the competition, the top 50% will get 10 points, while the bottom 50% will get 8 points.</p>\r\n<p>The paper will be graded separately and total 30 points.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}