{
  "fetched_at": "2026-10-19T08:03:27Z",
  "source_url": "https://www.kaggle.com/competitions/computer-vision-homework-2026/data",
  "pages": [
    {
      "name": "data-description",
      "content": "There are three folders: train, valid, and test. \nThe files in the \"train\" and \"valid\" folders are named in the following format \"{label}_12345.jpg\" ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this homework, you are tasked with building a convolutional neural network (CNN) for image classification, potentially incorporating advanced training techniques. You are allowed to use a pretrained model and fine-tune it on the provided dataset. However, using external datasets or pretrained models for training purposes is prohibited.\n\nStart by building a simple CNN as a baseline. Then, you can explore improving the model by designing a more effective architecture or experimenting with different data augmentation strategies to enhance performance.\n\nThe dataset consists of 20 food categories for classification, with 7,500 training samples, 2,000 validation samples, and 4,000 testing samples.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Since we have balanced data for both the training and testing sets, we simply use the testing accuracy as the evaluation metric. \n\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n\n    id, label\n    0, 0\n    1, 0\n    2, 10\n    etc.",
      "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!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "In this homework, you are required to build a convolutional neural network for image classification, possibly with some advanced training tips.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}