{
  "fetched_at": "2026-10-19T07:23:59Z",
  "source_url": "https://www.kaggle.com/competitions/egco-486-quiz-2025/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>This is a datasets of car images  with labeled. This Data contains around 5k images distributed under 3 categories (yellow, blue, orange, red, green, pink).</p>\n\n<h2>File descriptions</h2>\n<ul>\n<li><b>sample-submission.csv</b> - a sample submission file in the correct format</li>\n<li><b>starter_code.ipynb</b> - a python code to process a feature extraction, model and submission file</li>\n<li><b>./car_color/train</b> - the training set contain 6 folders (yellow, blue, orange, red, green, pink) contains 4k images</li>\n<li><b>./car_color/test</b> - the test set image contains around 1.5k images</li>\n</ul>\n",
      "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
    },
    {
      "name": "Description",
      "content": "<p>The Dataset consists of xxx high-quality images of vehicles, spanning multiple models and six distinct color categories: yellow, blue, orange, red, green, and pink, with each image carefully labeled to indicate its corresponding color class, making the dataset highly suitable for the development and evaluation of advanced vehicle color recognition systems that rely on accurate color classification. The dataset provides a diverse set of examples across different car models and colors, allowing researchers and developers to train machine learning models that can generalize well to real-world vehicle images in various environments and lighting conditions.</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Submissions are evaluated using categorization accuracy. Each image has been labeled with one true class. For each image, you must submit a set of the predicted labels.</p>\n\n<p>Before we delve into the details of each of the accuracy score, it is important to cover the four building blocks used to define the evaluation metrics:</p>\n\n- True Positive (TP) – Actual label is positive and prediction is also positive\n- True Negative (TN) – Actual label is negative and prediction is also negative\n- False Positive (FP) – Actual label is negative but prediction is positive\n- False Negative (FN) – Actual label is positive but prediction is negative\n\n![test](https://i.ibb.co/HnvkpfQ/Classification-Image.png)\n\n<p>Accuracy is the most basic version of evaluation metrics. It is calculated as the ratio of correct predictions (TP + TN) over all the predictions made (TP + TN + FP + FN).</p>\n\n![test](https://miro.medium.com/max/1210/1*N4Lo9Miw397g3XpX7o0CDw.png)\n\n<h3>Submission File</h3>\nYou must submit a csv file with the image file name and class.\n\nThe 6 classes to predict are:\n\n- yellow\n- blue\n- orange\n- red\n- green\n- pink\n\n<p>The order of the rows does not matter. The file must have a header and should look like the following:</p>\n\n<pre>id,classes\n1.jpg,blue\n2.jpg,red\n3.jpg,yellow\n...\n</pre> \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "## Practice Project : Car Color Classification\n|**Day-Time**\t | **Item** |\n| --- | --- |\n| Tuesday 18 November 2025 at 9:00 AM| Open |  |\n| Tuesday 18 November 2025 at 11:20 AM| Close |  |\n\n\n## Member\n\nThis competition is an individual format. All competitors must join the competition first.\n\n## Leaderboards\n\nEach group is allowed to send results 50 times per day. The score will be displayed into 2 parts:\n- 50 percents of dataset will be displayed in the Public Leaderboard where the contestants can check their scores at any time.\n- 50 percents of dataset will be stored and displayed in the Private Leaderboard which will be used to calculate the score to determine the result of the competition. The results will be displayed after the competition is over.\n\n\n## Evaluation Metric\nMetric: Categorization Accuracy\n\n## Submission\nTo submit the results, the test set should be predicted class result and collected into \".CSV\" file as shown in the example file \"sample_submission.csv\", otherwise Kaggle will not be able to calculate submission score.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}