{
  "fetched_at": "2026-10-24T15:41:06Z",
  "source_url": "https://www.kaggle.com/competitions/cowboyoutfits/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<p>You will use <code>images</code> and <code>train.json</code> for training object detectors.</p>\n<p><code>valid.csv</code> contains the image_id and file_name columns for dev phase leaderboard.</p>\n<p><code>test.csv</code> contains the image_id and file_name columns for final phase leaderboard.</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Welcome to Cowboy Outfits Detection Competition!</h2>\n\n<p>This is an object detection competition with imbalanced data challenge. You will need to train a model to detect cowboy outfits in wild images. </p>\n\n<h2> Training Data Distribution </h2>\n<img src=\"https://user-images.githubusercontent.com/3307514/125567141-e58cf84b-bf76-40c3-b143-b1a11886070e.png\" alt=\"train_dist\">\n\n<h2>Example Image</h2>\n<img src=\"https://user-images.githubusercontent.com/3307514/125567483-0618156d-f140-46de-be91-290681d83d51.png\" alt=\"example\">\n\n<h2>Starter Kit</h2>\n<p>\nWe provide a notebook in Code for you to get ready for the training data/annotation. \nDue to the evaluation system restriction in Kaggle InClass competition, in the starter kit notebook, we will also provide you with an example of how to generating the prediction.json file so that you can use the Codalab competition platform to automatically evaluate your submissions.\n</p>\n\n<p>For more details, please refer to the Evaluation page.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://towardsdatascience.com/breaking-down-mean-average-precision-map-ae462f623a52\"> Mean Average Precition for Bounding Box IoU</a>. The Bbox IoU score, commonly used in object detection tasks, measures how accurate the model can localize objects of interest while being able to predict the true categories.\n</p><p>While there are many different settings you can tune for e.g. IoU threshold, we use the popular AP 0.5:0.95 metric used in <a href=\"https://cocodataset.org/#detection-eval\"> COCO</a> as the primary challenge metric.</p>\n\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should be json serialized list of annotations with the following keys: <code>image_id</code>, <code>category_id</code>, <code>bbox</code>, and <code>score</code>. <code>image_id</code> should be a unique image identifier provided by either <code>valid.csv</code> or <code>test.csv</code>. <code>category_id</code> should be a unique category id as in <br><code>category_id = {\n    'belt': 87,\n    'sunglasses': 1034,\n    'boot': 131,\n    'cowboy_hat': 318,\n    'jacket': 588}</code><br>\n<code>bbox</code> should be a list of 4 float coordinates. <code>score</code> should be a float number for confidence score, in range 0-1.\n</p>\n<p>The file should contain a serialized json string and have the following format:</p>\n<pre>[{\"image_id\": 2817499345625518079, \"category_id\": 588, \"bbox\": [0, 0, 0, 0], \"score\": 0.8323169745334087}, {\"image_id\": 4780409558104969215, \"category_id\": 131, \"bbox\": [0, 0, 0, 0], \"score\": 0.19203804173293615}, {\"image_id\": 7518610131770248858, \"category_id\": 1034, \"bbox\": [0, 0, 0, 0], \"score\": 0.1928978657543734},]</pre>\n\n<h2>Important!</h2>\nkaggle InClass Competition does not support custom score function so please submit your submission file to Codalab competition here: <a href=\"https://competitions.codalab.org/competitions/33573\"> submission link. </a>\n\n<b>Your submission to Kaggle will fail, don't worry! We will use the final phase leaderboard  on <a href=\"https://competitions.codalab.org/competitions/33573#results\"> CodaLab </a> to determine the winners, the competition will close on 08/07/2021 4:00 am UTC( 12:00 pm GMT+8).</b>\n\n<img src=\"https://user-images.githubusercontent.com/3307514/125879699-a5f5ff3a-e49a-4b20-8300-25210ba08220.png\">\n\nNote that you will need to submit the solution(link to notebook or projects) and details in order to be eligible for awards!",
      "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
    }
  ]
}