{
  "fetched_at": "2026-10-19T07:19:27Z",
  "source_url": "https://www.kaggle.com/competitions/csc532-fruits-categorical-classification-2024/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>The training and testing data are retrieved from an existing kaggle dataset:<br> \n<a href=\"https://www.kaggle.com/sriramr/fruits-fresh-and-rotten-for-classification\">https://www.kaggle.com/sriramr/fruits-fresh-and-rotten-for-classification</a></p>\nThe dataset contains augmented data by cropping and rotation and flipping.\n<p>Usage Information\n<br>\nLicense                 Unknown <br>\nVisibility                Public<br>\nDataset owner     Sriram Reddy Kalluri<br>\nLast updated       2018-08-24<br>\nDate created       2018-08-24<br>\nCurrent version   Version 1</p>\n\n<p>The validation data was mostly crowdsourced from the participants of the DLAI5 hackathon. Special thanks to the following contributors who provided real-life images, in chronological order of images received: Ramil Joaquin, Kmer Jaeriz Mesina, Adrian-Ver Federizo, Renel R. Dilao, Kelsey Kng, Sandipan Majhi, Sharmistha Bhattacharya.</p>\n\nA few validation images were extracted from <a href=\"https://www.kaggle.com/moltean/fruits\">https://www.kaggle.com/moltean/fruits</a> (Version 5).\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train folder</strong> - the training set in 6 sub-folders of freshapples, freshbanana, freshoranges, rottenapples, rottenbanana, rottenoranges</li>\n<li><strong>test folder</strong> - the test set in 6 sub-folders of freshapples, freshbanana, freshoranges, rottenapples, rottenbanana, rottenoranges</li>\n<li> <strong>validation folder</strong> - unseen images of freshapples, freshbanana, freshoranges, rottenapples, rottenbanana, rottenoranges\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format with the following code: <br> \"1\" for fresh apples; \"2\" for fresh banana; \"3\" for fresh oranges; \"4\" for rotten apples; \"5\" for rotten banana; \"6\" for rotten oranges</li>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This hackathon was created to demonstrate the process of setting up a competition, along with the peril of using public datasets. This competition is to classify \"fresh\" vs \"rotten\" apples, bananas, and oranges. However, such classification can be rather subjective and the training/testing datasets suggest that it is really \"fresh\" vs \"not-fresh\". The validation dataset was mostly crowdsourced from participants at the DLAI5 hackathon from pics taken by themselves, with minimal data augmentation. Data labeling was a partially crowdsourced effort as well. Special thanks to the following contributors who provided real-life images, in chronological order of images received: Ramil Joaquin, Kmer Jaeriz Mesina, Adrian-Ver Federizo, Renel R. Dilao, Kelsey Kng, Sandipan Majhi, Sharmistha Bhattacharya. \n\nWatch for DLAI8 that will be coming this summer for more challenging competitions.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is macro [F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:\nF1 = 2 p r / [p + r] where p = tp / [tp + fp] and r = tp / [tp +fn]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\nThe macro F1 is the arithmetic mean of the F1-score of each class.\n\n<H3>Submission Format</H3>\n\nFor every author in the dataset, submission files should contain two columns: ID and Code. Code should be a comma-delimited list.\n\nThe file should contain a header of ID and Code and have the following format:\n\nID=imagefilename.csv, Code={1, 2, 3, 4, 5, 6}",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This is based on https://www.kaggle.com/competitions/dlai5-bad-apples/overview which is a \"crowdsourcing\" hackathon challenge from The 5th Deep Learning and Artificial Intelligence (DLAI5) Summer School, running from May 6-10, 2021.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}