{
  "fetched_at": "2026-10-22T10:07:35Z",
  "source_url": "https://www.kaggle.com/competitions/cs475-nmnist-small/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>Data File: nmnist.h5 (48.22 MB)</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This is a noisy handwritten digit recognition competition.</p>\r\n<p>Data</p>\r\n<pre>Each sample is a 24x24 grayscale 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>\r\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>\r\n<p>File format</p>\r\n<pre>/large_train/data array (7000, 576) [float]<br />/large_train/labels array (7000, 10) [int]<br />/val/data array (2000, 576) [float]<br />/val/labels array (2000, 10) [int]<br />/kaggle/data array (1000, 576) [float]</pre>\r\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>\r\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>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is accuracy.</p>\r\n<p>Submission Format</p>\r\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>\r\n<p>The file should contain a header and have the following format:</p>\r\n<p>Id,Prediction<br />1,5<br />2,6<br />3,0<br />4,2<br /><br /></p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "<!-- 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>Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.</p>\r\n<h3>Team Mergers</h3>\r\n<p>Team mergers are not allowed in this competition.</p>\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: 2/27/2017</p>\r\n<p>Merger Deadline: <strong>None</strong></p>\r\n<p>Entry Deadline: <strong>None</strong></p>\r\n<p>End Date: 3/10/2017 3:00 PM EST</p>\r\n<!-- End Base Rules -->\r\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}