{
  "fetched_at": "2026-10-19T07:20:19Z",
  "source_url": "https://www.kaggle.com/competitions/cisc6000-deep-learning-hw2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# Task One\n1. cifar.train.npy 48000 pic in numpy array. 3 channel , 32 pixels by 32 pixels\n\n2. cifar.trainlabel 48000 related labels\n\n3. cifar.test.npy 12000 testing pics\n\n4. sample_submission.csv: this is an example that YOU should generate from the model.\n\n# Task Two\n1. train_clean_data.zip 30000 pics cleaned image data for training\n\n2. train_noise_data.zip 30000 pics noise image data for training\n\n3. test_clean_data.zip 20000 pics cleaned image data for testing\n\n4. test_noise_data.zip 20000 pics noise image data for testing\n\n5. labels.csv: 20K labels for images in (III) and (IV)\n\n6. M.weights.hdf5 Q2 question pre-train weight.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "General speaking this is a 10 classification problems and more difficult!\n\nAutoencoder\n\nIt needs total 3 hours running maybe!\n\nIn Kaggle:\n\n1. Submit your csv file of Q1(e) only (not table 1, just label of test dataset like sample_submission.csv)\n\n2. Download your latest version of all code as notebook format including Q1 and Q2\n\nIn Blackboard:\n\n1. Submit your table 1 and table 2, some graphs and some answers in pdf file.\n\n2. Submit your all code as notebook format including Q1 and Q2",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}