{
  "fetched_at": "2026-10-24T22:32:35Z",
  "source_url": "https://www.kaggle.com/competitions/11785-s22-hw2p2s1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The training and validation data have similar structure, where all images belonging to a class are located in the folder with the class name. The test data is a collection of files that need to be assigned a class using the trained model.\n\n## Files\n\n*   **hw2p2_kaggle/content/kaggle_data/train/** - the training set\n*   **hw2p2_kaggle/content/kaggle_data/dev/** - the validation set\n*   **hw2p2_kaggle/content/kaggle_data/test/** - the test set\n*   **solutions_sample.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is part 1 Face Classification for HW2P2. In addition to this, you should also finish part 2 Face verification\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": "Evaluation will be done using categorization accuracy. It is simply the ratio of correctly predicted instances to the total number of instances in the dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Please refer to the course page.\n\nDon't cheat. Don't reuse complete code from online sources or friends.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}