{
  "fetched_at": "2026-10-19T11:06:16Z",
  "source_url": "https://www.kaggle.com/competitions/aist4010-spring2023-a1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "- `classification-data`: Each sub-folder in train, val and test contains images of one person, and the name of that sub-folder represents their ID.\n    - `train`: You are supposed to use the train data set to train your model for the classification task.\n    - `val`: You are supposed to use val data to validate the classification accuracy.\n    - `test`: You are supposed to assign IDs for images in test data and submit your result.\n- `test_list.txt`: This file contains the trials for Classification Test. The first column is the images name. Your task is to assign ID to each image and generate submission file based on the order given here.\n- `sample_submission.csv`: This is a sample submission file for this competition.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is the Kaggle part of Assignment 1.\n\nGiven an image of a person’s face, the task of classifying the ID of the face is known as face classification. The input to your system will be a face image and you will have to predict the ID of the face. The ground truth will be present in the training data and the network will be doing an\nMulti-class Classification to get the prediction. You are provided with a validation set for fine-tuning your model.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is accuracy.\n\n$$\naccuracy = \\frac{Number\\ of\\ correctly\\ classified\\ images}{Number\\ of\\ total\\ images}\n$$\n\n## Submission Format\n\n**For every author in the dataset**, the submission '.csv' file should contain two columns: `id` and `label`.\n\nThe file should contain a header and have the following format:\n```\nid,label\n0.jpg,23\n1.jpg,5\n2.jpg,764\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Importing additional data is **NOT ALLOWED**.\n- Directly calling model APIs is **NOT ALLOWED**.\n- Referring to open-source codes to implement the models is **NOT ALLOWED**. Rember to cite them in your report. \n- Loading pre-trained weights is **NOT ALLOWED**.\n- The deadline is 11:59 PM (HKT), Feb. 23, 2023. The competition will close 2 days later. You can use no more than **2 late days** for this assignment without punishment. And you have **6 late days** in total. Grades will be deducted by 25% for each additional late day.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}