{
  "fetched_at": "2026-10-19T12:20:14Z",
  "source_url": "https://www.kaggle.com/competitions/cp-3501-retinamnist-v-202501/data",
  "pages": [
    {
      "name": "data-description",
      "content": "You have training and test images in four resolutions, 28x28, 64x64, 128x128, 224x224.\n\n## Files\n\n*   **train.csv** - the training set\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Objective\n\nThe RetinaMNIST is based on the DeepDRiD24 challenge, see [https://www.nature.com/articles/s41597-022-01721-8](https://www.nature.com/articles/s41597-022-01721-8), which provides a dataset of 1,600 retina fundus images. The task is ordinal regression for 5-level grading of diabetic retinopathy severity. \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [Mean absolute error regression loss](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.mean_absolute_error.html) between the predicted values and the given true values.\n\n\n## Submission File\nFor each ID in the test set, you must predict a value (in the 0-5 range, fractional values are allowed) for the LABEL variable. The file should contain a header and have the following format, see the supplied submission_sample.csv:\n\n    image_id,label\n    test_idx_0.png,0.5\n    test_idx_1.png,0.9\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Don't cheat! - Apply yourself! - Have fun!\n- Do **not** publish your notebooks here. \n- Keep all notebooks **private** but share them with your instructor.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This is an in-class competition for the CP3501 course. It is based on the RetinaMNIST dataset of [https://www.nature.com/articles/s41597-022-01721-8](https://www.nature.com/articles/s41597-022-01721-8) and available from [https://medmnist.com/](https://medmnist.com/) and [https://github.com/MedMNIST/MedMNIST](https://github.com/MedMNIST/MedMNIST)\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}