{
  "fetched_at": "2026-10-24T02:50:36Z",
  "source_url": "https://www.kaggle.com/competitions/computer2021-hw5/data",
  "pages": [
    {
      "name": "data-description",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is the homework 7 of Introduction to Computer 2021 spring by Prof. Ming-Syan Chen.\n\nIn this homework, you are required to build a convolutional neural network for image classification, possibly with some advanced training tips.\nPlease notice that utilizing external data or pre-trained model for training is prohibited.\n\n### Task Description\nImage Classification: Street View House Numbers\nTraining data: 68257 images\nValidation data: 5000 images\nTesting data: 26032 images\nExtra data: 531131 images\n\nPlease **DO NOT** use the testing data and other data, we will consider this as **CHEATING**.\n\n### Evaluation metric: \nCategorization Accuracy\n\n### Deadlines\nKaggle: 6/29 (Tue.) 07:59 in UTC+8 (No late submission!)\nCeiba: 6/29 (Tue.) 23:59 in UTC+8 (Late Submission Policy: 30% off per day)\n\n### Notes\nTeam Name: **student ID\\_anything**, e.g. b09901000\\_computer\nMaximum Daily Submission: 6\n\n### Contact TAs\nEmail: computer2021spring@gmail.com\nIf there is any question or concern, you can discuss on FB group or email us.\n\n### References:\nYuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y. Ng Reading Digits in Natural Images with Unsupervised Feature Learning NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011.\nLink: http://ufldl.stanford.edu/housenumbers",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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
    }
  ]
}