{
  "fetched_at": "2026-10-19T10:08:03Z",
  "source_url": "https://www.kaggle.com/competitions/deeplearning2021competition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Overview\nThe dataset contains a number of different subsets of the food-101 data. The data is preprocessed to have 64x64 size. There are 38782 training set and 20665 test set. It has 90 different classes. The original source of the dataset is from [this link](https://www.kaggle.com/kmader/food41), but you are not allowed to use the original data source as training set.\n\n-------------------------------------------------------------------------------------------------------------------------------\nData Acknowledgement\nThe data was repackaged from the original source (gzip) available at https://www.vision.ee.ethz.ch/datasets_extra/food-101/\n\nLicense\nThe Food-101 data set consists of images from Foodspotting [1]. Any use beyond scientific fair use must be negotiated with the respective picture owners according to the Foodspotting terms of use [2].\n[1] http://www.foodspotting.com/\n[2] http://www.foodspotting.com/terms/",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Kyung Hee University Deep Learning Lecture Project Challenge\nThe goal of this challenge is to achieve high performance in a given dataset using techniques learned in the lecture.\nYou can use any neural networks and find your own model architecture to find out how 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.\nThe baseline is the ResNet-34 result trained on Google Colab from TA and this code will be provided for all.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submission Format\nSubmission files should contain two columns: Id and Category. Id is the index of test images and 'Category' means the class of the test image.\n\nThe file should contain a header and have the following format:\n\nId,Category\n0,15\n1,21\n2,1",
      "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- Train with only Google Colab!\n- Do not use any external datasets and pre-trained models!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}