{
  "fetched_at": "2026-10-23T21:33:58Z",
  "source_url": "https://www.kaggle.com/competitions/eecs442-w19-hw4/data",
  "pages": [
    {
      "name": "rules",
      "content": " - Individual submission only.\n - The leaderboard will close on 04/04/2019 8:00 pm. \n - Maximum Daily Submissions: 5.\n - Submission count will be refreshed at 8 pm every day.​\n - Honor Code applied.\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The kaggle testing data is under `p2/starter_set/kaggle/`. There are 114 images.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, we will see how well your facade segmentation network can perform. You are encouraged to try and improve your kaggle result, but you are not allowed to use the kaggle ground truth data as part of training.\n\nSubmitting works using the DICE metric and uses a run length encoding (RLE) output. Basically, if you were to produce a pixelwise mask for all 5 classes, it would lead to really large text files filled with values like:\n\n[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]\n\n[1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1]\n\n[1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1]\n\n[1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1]\n\n[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]\n\nTo avoid this, we are providing you a function to encode the above masks as a run length encoding. The run length encoding turns a list of 10 1's into something like [1, 10]. In this case 1 represents starting at the first index and 10 means 'running' for the next 10 instances. \n\nBecause you are able to use our function for run length encoding, this should not be an issue. But when you look at the sample submission, don't be worried by how strange it looks.\n\nTo create a submission, you need to generate test output for the 'kaggle' dataset we have provided  for you in the starter code. See the 'Evaluation' page for more information on how it will be scored.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>DICE</h2>\n\nDICE is a metric we are using for scoring segmentation submissions. See [Sørensen–Dice coefficient][1] for more details.\n\nIt is equal to:\n\n$$DSC =  \\frac{2 |X \\cap Y|}{|X|+ |Y|}$$\n\nThe numerator is the intersection of the ground truth mask and predicted mask. The denominator represents the cardinalities of both sets.\n\n\"The Sørensen index equals twice the number of elements common to both\nsets divided by the sum of the number of elements in each set.\"\n\nFor an intuition understanding, we can compare it to the [Jaccard Index][2]. The Jaccard Index is also known as the Intersection over Union (IoU). It is the intersection of two masks divided by the size of their union. \n\nThe two can be related in this way:\n\n$$J=S/(2-S)$$ and $$S=2J/(1+J)$$\n\n<h2>Submission Format</h2>\nFor every image in the dataset, the submission should contain 5 lines. Each line is the img_id which is contained in the file name plus a decimal in range 0.1-0.5. Then a run length encoding is the second column, and contains the active portions of the binary mask for that class.\n\n<p>The file should contain a header and have the following format:</p>\n<pre>img_id,predicted<br>\nimg_id + 0.1,1 10 30 30 70 100 200 20<br>\nimg_id + 0.2,1 10 30 30 70 100 200 20<br>\nimg_id + 0.3,1 10 30 30 70 100 200 20<br>\nimg_id + 0.4,1 10 30 30 70 100 200 20<br>\nimg_id + 0.5,1 10 30 30 70 100 200 20<br></pre>\n\n\n  [1]: https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient\n  [2]: https://en.wikipedia.org/wiki/Jaccard_index",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}