{
  "fetched_at": "2026-10-24T17:48:18Z",
  "source_url": "https://www.kaggle.com/competitions/cs-475-generative-models-for-mnist/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This is a noisy handwritten digit recognition competition.</p>\n<p>Data</p>\n<pre>Each sample is a 24x24 binary image. We vectorize each image as a 1x576 vector and stack N samples to represent the dataset as a matrix X of size Nx576. Each label takes value y in the set {0,1,2,...,9}.</pre>\n<pre>Sometimes it will be convenient to represent each label as a one-hot-vector, with one element set to one and the rest zero. The dataset labels can then be represented as a matrix, Y \\in {0,1}^{Nx10} such that the sum of each column adds up to 1.</pre>\n<p>File format</p>\n<pre>mnist/train/data<br>mnist/train/labels <br>mnist/val/data <br>mnist/val/labels<br>mnist/kaggle/data</pre>\n<p><br>There are three datasets:<br>large_train: training data (7000 samples)<br>val: validation data (2000 samples)<br>kaggle: kaggle competition test data (1000 samples, no labels provided)</p>\n<p><br>You should train on the training data and validate your models using the validation data. Once you are happy with your performance, you should predict the samples in kaggle and submit the results (see Evaluation).</p>\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is accuracy.</p>\n<p>Submission Format</p>\n<p>For every image in the dataset, submission files should contain two columns: Id and predicted label. Id is the index of each image in the gaggle set and predicted label is one of {0,1,2,...,9}.</p>\n<p>The file should contain a header and have the following format:</p>\n<p>Id,Prediction<br>0,2<br>1,5<br>2,6<br>3,0<br>4,2</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}