{
  "fetched_at": "2026-10-19T07:35:16Z",
  "source_url": "https://www.kaggle.com/competitions/data558spring2019-competition1/data",
  "pages": [
    {
      "name": "rules",
      "content": "\n\t<!-- Begin Base Rules -->\n    <h3>One account per participant</h3>\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n    <h3>No sharing of code</h3>\n    <h3>Submission Limits</h3>\n    <p>You may submit a maximum of 3 entries per day.</p>\n    <p>You may select up to 2 final submissions for judging.</p>\n    <h3>Competition Timeline</h3>\n    <p>Start Date: <strong>TBA</strong></p>\n    <p>Merger Deadline: <strong>None</strong></p>\n    <p>Entry Deadline: <strong>None</strong></p>\n    <p>End Date: <strong>5/19/2019</strong></p>\n\t<!-- End Base Rules -->",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>The training set consists of 500 images from each of 10 categories of animals, from lorikeet to goose (see <a href=\"https://gist.github.com/jovianlin/5fb426c38fddfdf9a699a8824450c7dc\">here</a>, but note that the integer labels are not the same as ours). The validation and test sets each consist of 100 images from each of the 10 categories. The images in the training and validation sets are saved in folders by category. </p>\n<p>We are providing you a Python 3 script called \"extract_features.py\" that will extract features from the images. To use it you simply need to change the file path to the images and the file checkpoint28.pth.tar  at the top of the script. Do NOT use pre-trained models you might find elsewhere online to extract features. </p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.tar.gz</strong> - The images in the training set</li>\n<li><strong>val.tar.gz</strong> - The images in the validation set</li>\n<li><strong>test.tar.gz</strong> - The images in the test set</li>\n<li><strong>class_to_idx.json </strong> A mapping from the image categories to the numerical labels used in classification. This is also produced by the script extract_features.py. </li>\n<li><strong>sample_submission.csv</strong> - A sample submission file in the correct format</li>\n<li><strong>extract_features.py</strong> - A script that will extract features from the images </li>\n<li><strong>alexnet_model.py</strong> - A dependency of the above script</li>\n<li><strong>checkpoint28.pth.tar</strong> - Another dependency of the above script</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The goal of the data challenge is to learn how to use machine learning algorithms and gain understanding about them. The task you will perform is animal classification.\n\n<h2>What is expected </h2>\nEach week we will assign a homework question related to this competition. You are expected to   submit your predictions to the Kaggle website and submit your results, comments, and code on Canvas with your homework submission.\n\n<h2> Rules </h2>\n - You must do this individually. \n - You can submit results up to three times per day during the challenge. A leaderboard will be available during the challenge, which shows the best results per person, as measured on a subset of the test set. A different part of the test set will be used after the challenge to evaluate the results. \n - Registration has to be done with your uw.edu email address. \n - The most important rule is: DO IT YOURSELF. The goal of the data challenge is not get the best recognition rate on this data set at all costs, but instead to gain practical experience with machine learning algorithms and techniques.\n\n<h2>Acknowledgements</h2>\n<p>The dataset we are using comes from <a href=\"http://www.image-net.org/\">ImageNet</a>. </p>The goal of the data challenge is to learn how to use machine learning algorithms and gain understanding about them. The task you will perform is animal classification.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is classification accuracy, i.e., the percentage\nof species you correctly identify.</p>\n<hr>\n<h2>Submission Format</h2>\n<p>Submission files should contain two columns: Id and Category (the predicted category for that image). The file should contain a header and have the format described below. Id represents the number of the test example, ranging from 0 to 999. The prediction is the corresponding label, between 0 and 9. The Ids correspond to the file names in the test set.  The correspondence between the category labels and ImageNet categories may be found in the file class_to_idx.json.</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>Id,Category<br>0,1<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}