{
  "fetched_at": "2026-10-19T10:42:10Z",
  "source_url": "https://www.kaggle.com/competitions/cs4210-summer2022-assignment-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train_data.csv</strong> - the training data</li>\n<li><strong>train_target.csv</strong> - the corresponding training targets</li>\n<li><strong>test_data.csv</strong> - the testing data</li>\n<li><strong>sample-submission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n\n<p>The data has been randomly separated into two parts: training set and testing set. The training set consists of 16,175 examples for you to build your model. The test set consists of 3,965 examples which will be used to determine your score.</p>\n<p>Please note: </p>\n<p>1. The provided csv files have no index column and header row.</p>\n<p>2. In \"train_data.csv\" and \"test_data.csv\", each row contains 2304 pixel values (as each face image is of size 48*48 in pixels).</p>\n<p>3. \"train_target.csv\" stores the corresponding target to each row data in \"train_data.csv\" (0-Angry, 1-Happy, and 2-Neutral).</p>\n<p>4. When you save your predictions into a csv file, please follow the submission file format as shown in \"Evaluation\" section (the submission file requires the specific index column and header row, where the \"Id\" is a zero-based index corresponding to the order of testing data in the \"test_data.csv\" file).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2><strong>In-Class Competition: Facial Expression Classification</strong></h2>\n<p>Automatic human facial expression classification has lots of potential real life applications, such as customer service systems, personalized advertisement, and entertainment. In our assignment 2, we will focus on building a deep learning model for <strong>Facial Expression Classification</strong>.</p>\n\n<p>The training dataset and testing dataset are made available in the Data section. The training set consists of 16,175 examples for you to build your model. The test set consists of 3,965 examples which will be used to determine your score. Please check the Data section for more details.</p> \n\n<p> Please note that the data are from a real Kaggle competition, https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data</p>\n\n<p><strong>Specific Tasks:</strong><br />1. Develop your Deep Learning models for facial expression classification using Keras.<br />2. Gain experience in training neural network models.<br />3. Follow the submission file format and instructions to submit your predictions in Kaggle.<br />4. Zip your code and your final prediction file, and submit the zipped file in our course blackboard.</p>\n\n<p><strong>Some Useful Resources:</strong><br /></p>\n<ul>\n<li><a href=\"https://pytorch.org/tutorials/beginner/basics/intro.html\">Pytorch: LEARN THE BASICS\n</a></li>\n<li><a href=\"https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html\">Pytorch: TRAINING A CLASSIFIER\n</a></li>\n<li><a href=\"https://www.kaggle.com/code/basu369victor/pytorch-tutorial-the-classification/notebook\">PyTorch-Tutorial (The Classification)\n</a></li>\n<li><a href=\"https://pytorch.org/tutorials/recipes/recipes/custom_dataset_transforms_loader.html?highlight=custom%20dataset\">DEVELOPING CUSTOM PYTORCH DATALOADERS\n</a></li>\n<li><a href=\"https://towardsdatascience.com/pytorch-tabular-multiclass-classification-9f8211a123ab\">PyTorch [Tabular] —Multiclass Classification\n</a></li>\n<li><a href=\"https://pytorch.org/vision/stable/models.html\">Models and pre-trained weights</a></li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>This evaluation page describes how submissions will be scored and how students should format their submissions.  \n <p><strong>Metric</strong>: Categorization Accuracy</p>\n - <p><strong>The submission files should contain two columns: Id and\n   Expected. </strong>,</p><p>The format is as follows:</p>\n   <pre>Id,Category<br />0,2<br />1,1<br />2,0<br />3,2<br />etc.</pre>\n - <p><strong>You may submit a maximum of 20 entries per day. You may select up to 2 final submissions for judging.</strong></p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}