{
  "fetched_at": "2026-10-20T10:19:45Z",
  "source_url": "https://www.kaggle.com/competitions/2022-spring-khu-competition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "- 58388 Training dataset with label(Class당 150장)\n- 2000 Test dataset with label​(Class당 5장)\n- Class : 400\n- Image Size : 224x224\n\nBelow contents are the example of the format of the sets.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The goal is to achieve high performance in a given dataset using techniques learned in the lecture.\nYou can use any data augmentation techniques or DNN models or optimizer or tuning techniques to achieve optimal performance.\nTo prevent using a lot of GPU resources, you should use a network that can train by using the resources provided by Google Colab & Kaggle.\nThe Baseline on the Leaderboard is the ResNet34 results trained on Google Colab.\nPlease set your team name as Initial name, e.g., Team JH\nPlease merge team with your team member using Request Merge in Invite Others of Team tab.\n\nCAUTION\nYou can't use imagenet pretrained model and extra datasets for training.\nAnd also **you can't use test dataset for training.**\n\nTrain and Make the submission csv file\n\nhttps://gitlab.com/mlvc_lab/practical-machine-learning-qna/-/issues?scope=all&utf8=%E2%9C%93&state=all\n(log in with KHU account)\n\nCopy this Google Colab ipynb file on your google drive and use that.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## **Objective**\nThe network predicts which class a given image corresponds to. (0~399)\n\n---\n\n## **Performance evaluation indicator**\nThe evaluation indicator is the accuracy of comparing the predicted RMSE score by the model to the actual label.\n\n## Submission Format\n\nSubmitted files must be submitted as .csv files, and the results for test images must be listed in order.\nThe .csv file has a total of 2 columns.\n\nId: ID of the image\nCategory: Label from 0 to 399 (String)\n\n\nThe file should contain a header and have the following format:\n```\nAuthorId,DuplicateAuthorIds\nId, Category\n0, 1\n1, 377\n2, 123\n3, 43\nEtc.",
      "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 - You restricted to submit only 10 per day\n - Don't use any extra and test datasets!\n - Don't use pretrained model!\n - Don't exceed model parameter number larger than 5M(5,0000,000)\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}