{
  "fetched_at": "2026-10-19T14:09:49Z",
  "source_url": "https://www.kaggle.com/competitions/fds-flower-classification-2021/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## File descriptions\n\n**training** - the training data \n\n**testing** - the testing data\n\n**train.csv** - the training labels (0 -> 16)\n\n**sample_submission.csv** - a sample submission file in the correct format\n\n**mapping.csv** - a file contains names for each label\n\n\n## Data fields\n\n**train.csv / sample_submission.csv**\n\n- `image` - the name of a image file\n\n- `class_id` - the ID for the flower\n\n**mapping.csv**\n\n- `class_id` - the ID for the flower\n\n- `class_name` - the name of the flower",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Did you know there are approximately 369,000 flowering plants discovered around the world in 2016? According to a report titled “State of the World’s Plants”, released by researchers at the Royal Botanic Gardens, Kew, in the United Kingdom, there are around 391,000 species of vascular plants discovered and 94 percent of them are flowering plants.\n\nHowever, in this competition, you are not going to classify all of 369,000 flowering plants, but only 17 of them. You will classify them via their images and you will be working with a dataset consisting of 1,088 labeled images used for training your model and 272 unlabeled images used in this competition to evaluate how well can your model classify flowers.\n\n## Acknowledgements\nWe thank Maria-Elena Nilsback and Andrew Zisserman for providing this dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [Categorization Accuracy](https://developers.google.com/machine-learning/crash-course/classification/accuracy). The Categorization Accuracy score, commonly used in multi-class classification, measures accuracy by calculating number of correct predictions divided by total number of predictions. The Categorization Accuracy score is given by:\n\n![An image](https://latex.codecogs.com/gif.latex?%5Cdpi%7B150%7D%20%5Ctext%7BAccuracy%7D%20%3D%20%5Cfrac%7B%5Ctext%7BNumber%20of%20correct%20predictions%7D%7D%7B%5Ctext%7BTotal%20number%20of%20predictions%7D%7D)\n\n## Submission Format\n\nSubmission files should contain two columns: **image** and **class\\_id** (**image** should be a list of filenames and **class\\_id** should be predicted label for each image\n\nThe file should contain a header and have the following format:\n\n```\nimage,class_id\ntest_000000.jpg,1\ntest_000001.jpg,5\ntest_000002.jpg,4\n```",
      "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!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}