{
  "fetched_at": "2026-10-19T07:47:22Z",
  "source_url": "https://www.kaggle.com/competitions/d-tribe-hackathon-2020/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train<p>Training set<br>\n<ul>\n<li><strong>train<p>Training set of images for classification</h2>\n<li><strong>train map.csv<p>Labels for training set</h2>\n</ul>\n</h2>\n<li><strong>test<p>Testing/Submission set of images for classification</h2>\n<li><strong>sample submission.csv<p>A sample submission file in the correct format</h2>\n<h2>Data fields in csv files</h2>\n<ul>\n<li><strong>IMAGE</strong> - image name</li>\n<li><strong>LABEL</strong> - image label</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "<p><strong>Rules</strong></p>\n\n - You have to provide an algorithm with your trained model that has given the final result to be eligible for the prize\n - One account per participant:\n      You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n - Use of Automated Machine Learning Tools (AMLT):\n      This Competition does not permit the use of automated machine learning tool(s) (“AMLT”) in the creation of Submissions.      AMLT Teams are not eligible to win any prizes.\n\n - No private sharing outside teams:\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n - Team Mergers: Team mergers are not allowed. Each team needs to make all submissions individually.\n\n - Team Limits: \nThe maximum team size is 1. All submissions need to be done by a solo participant.\n\n - Submission Limits: \nYou may submit a maximum of 10 entries during the entire running period of the competition and can select two of your submission for final evaluation.\n\n - Code Sharing: \nWinning team must share their code/notebook and model to the organizer to be able to collect the prize.\n\n - Competition Timeline: \nStart date and time: 24 Dec 2020 11:00 AM IST. \nEnd date for final submission deadline: 24-Dec-2020 11:59 PM IST.\n\n - Submission License Type\nAll submissions will be licensed as Open-Source.\n\n - Eligibility: \nParticipants all over the world are invited to participate. \nParticipants must be over 18 years of age.\n\n - Dataset Usage: \nParticipants must only use the given dataset. Using any other dataset automatically disqualifies the team from the competition.\n\n - Competition Winner Selection: \nWinners of the competition will be selected on the accuracy metrics of mean F1-Score.\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>\nIt is difficult to keep track of changing abundance of insect biomass with sufficient accuracy. Current solutions include identifying specimens captured by camera traps manually, a process which can be time consuming as  well as labour intensive. Thus improved methods are needed. Automated image classification using machine learning is one such approach.\n<br>\n<br>\nThe D-Tribe Community challenges the participants to build an algorithm to help classify habitus images of ground beetles to species level. This dataset consists of 291 species spread across 57,027 train images and 6,337 test images.\n</p>\n<br>\n\n<p><strong>ABOUT D-TRIBE</strong>\n<br>\nD-Tribe is a community to learn, share and inspire career aspirants in emerging technologies including Data Science, Artificial Intelligence, Machine Learning, Deep Learning, Internet of Things (IoT) , Big Data etc.\n</p>\n<br>\n**Acknowledgement**\n\nThis Hackathon wouldn't have been possible without the works of :\n\nHansen, Oskar Liset Pryds, Svenning, Jens-Christian, Olsen, Kent, Dupont, Steen, Garner, Beulhah H., Iosifidis, Alexandros, … Høye, Toke T. (2019). Publication name \"Species-level image classification with convolutional neural network enable insect identification from habitus images \"",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "Timeline\n\n    December 24, 2020, 10:00 AM (IST) - Competition starts\n    December 24, 2020, 11:59 PM (IST) - Final submission deadline\n\nThe competition organizers reserve the right to update the contest timeline if they deem it necessary.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation pages describes how submissions will be scored and how you should upload your submission in this hackathon. </p>\n<hr>\n<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. 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:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The 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.</p>\n<h2>Submission Format</h2>\n<p><strong>For every images in the test folder</strong>, submission files should contain two columns: IMAGE and LABEL. LABEL should be a real number representing the class id (LABEL) of image as provided in training (train map.csv).</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>IMAGE,LABEL<br>U0TASLLFFGJRLBR.jpg,1<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prize",
      "content": " Only the top scoring participant qualifies for the grand prize with a certificate of accomplishment.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}