{
  "fetched_at": "2026-10-19T07:44:11Z",
  "source_url": "https://www.kaggle.com/competitions/2018-characters-classification/data",
  "pages": [
    {
      "name": "rules",
      "content": " - Don't cheat and apply yourself!\n - Use CNN architecture.\n - You have 3 submissions per day.\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "#Data\nData stored as numpy arrays (use function [numpy.load](https://docs.scipy.org/doc/numpy/reference/generated/numpy.load.html) to restore data) and compressed with bzip2.\n\nTrain set is splitted into 4 parts. Each file econtains matrix of shape [Nх2]. Grayscale image of character is stored at the first column. At the second column is unicode number of character.\n\nTest set is just array of grayscale images.\n\n#Example\n    import numpy as np\n    import matplotlib as pyplot\n\n    data = np.load('train-1.npy')\n    width, height = 8, 8\n\n    plt.figure(figsize=(16, 20))\n    for n, (image, tag) in enumerate(data, 1):\n        if n > width * height:\n            break\n        plt.subplot(height, width, n)\n        plt.title(tag)\n        plt.imshow(image, cmap='gray')",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "#Overview\nThe dataset consists of 332987 Chinese characters (1K classes). Train the best classifier based on cnn to outperform other participants.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "#Evaluation\nAccuracy is used as score metric. The test dataset has public (10%) and private (90%) parts.  The final results are determined by score on private set only.\n\n#Submission Format\nSubmission is csv file, which has header at the first line and two collumns: id of character and predicted unicode number.  You can seed small example below:\n<pre>Id,Category<br />1,61362<br /><span style=\"font-size: 14px; line-height: 1.4em;\">2,62644<br />3,60861<br /><span style=\"font-size: 14px; line-height: 1.4em;\">etc...<br /></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}