{
  "fetched_at": "2026-10-19T11:28:38Z",
  "source_url": "https://www.kaggle.com/competitions/cifar100-image-classification-with-noisy-labels/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## CIFAR100 dataset with noisy labels\nModified by Jonghyun Choi (2021.5.23)\n\n## Note\n1. Filenames are all randomized.\n1. Some of the training samples' label are randomized for the noisy label\n1. Testing samples' label are *not* randomized\n1. Number of samples for training and testing are the same to the CIFAR100 dataset (except two files (one for training and one for testing) are removed from the original dataset for the duplicated label)\n1. Now, labels of the testing samples are removed for submission.\n\n### To use the dataset for the best test accuracy, plz do either\n1. Split the training set into training and validation\n2. Use cross validation",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## MLDL 2021 Spring @ GIST\nCoding assignment #2: Image category classification with CIFAR-100 dataset with noisy labels\n\n(Note: this is an individual basis assignment!)\n\n## Task\nGiven a set of images and their label, please train your model to classify a test image into the label. The label is class id string (looks like a number) - {00, 01, …, 09}. So, total of 100 classes.\n\nThe image size is 32 (width) by 32 (height) pixels in RGB (3) channels.\n\n## Evaluation metric\nTop-1 accuracy: Compare with the true label with the predicted label by your trained model.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Evaluation metric\n\nTop-1 accuracy: Compare with the true label with the predicted label by your trained model.",
      "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
    }
  ]
}