{
  "fetched_at": "2026-10-19T09:50:34Z",
  "source_url": "https://www.kaggle.com/competitions/datamining-ai/data",
  "pages": [
    {
      "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": "data-description",
      "content": "<p>The ImageNet dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. </p>\n<p>The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class. </p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - a 50000x3072 numpy array of float in range 0 to 255. Each row of the array stores a 32x32 colour image. The first 1024 entries contain the red channel values, the next 1024 the green, and the final 1024 the blue.</li>\n<li><strong>test.csv</strong> - a 10000x3072 numpy array of float in range 0 to 255. Each row of the array stores a 32x32 colour image. The first 1024 entries contain the red channel values, the next 1024 the green, and the final 1024 the blue.</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h1>EE226 2019 Spring</h1>\n\n<p>In this project, you are given pixel values extracted from images. Your task is to predict the label for each sample of the test images.</p>\n<p>You need to click the \"Join Competition\" button to join us.</p>\n\n<h2> Attention </h2>\n<p> Before submitting your predictions, please update your name with \"STUDENTID_NAME\" before submitting your predictions. You can update your name in the \"Team\" tab.</p>\n<p>Before the submission deadline (2019/4/21), you can only view the accuracy evaluated on 30% of the testing dataset on the leaderboard. After the deadline, we will reveal your model accuracy evaluated on the entire testing dataset, which your score will depend on. However, you do not need to worry that your score would be affected by 1 or 2 percent of accuracy loss; we will mark by the accuracy ranges.</p>\n<p>\nFor fairness, we set a few rules for you to obey --- violation against the rules will lead to score deduction:</p>\n<p>1. Please do not copy someone else's code. We will run plagiarism check after submission.</p>\n<p>2. Please do not download the dataset somewhere else to train your model. We have shuffled the dataset and will reproduce your experimental results using the dataset. Violation would be considered if there is a big gap between your reported results and our reproduced results.</p><p>3. Please do not use pre-trained model. Everything should be built from scratch.</p>\n<p>4. For us to reproduce your code, please follow the \"Environment\" instruction.</p>\n\n<p></p><h2> DataSet </h2>\n<p>You can click the \"Data\" button to get more information about our dataset and download it.</p>\n<p>There are two CSV files, one is the training file, and the other is the testing file. You need to train your neural network model using the training file and test the model by the testing file. Submit the prediction result of the testing file.</p>\n\n<h2> Environment</h2>\n<p>You need to use the \"Python\" to write the neural network model, and we highly recommend you to use the \"Python3.5.5\" \"Tensorflow1.3.0\"  \"Keras2.1.0\" and “Pytorch0.1.12\" for us to reproduce your code.</p>\n\n<h2> Submission</h2>\n<p>You can click the \" Submit Prediction\" button on the upper-right, and upload your prediction. The prediction file should be a CSV file,  and the first column name is \"ID\", the second is \"Category\".  </p> \n<p>When you upload the CSV file successfully, you can get a score about the precision for your prediction simultaneously.  </p> \n<p>There are only two submissions allowed for each person every day.  Please carefully arrange the schedule of your submission.</p>\n\n<h2>Requirements for uploading</h2>\n<p>You need to zip and upload the following files before the deadline:\n\n①your codes ②a readme.txt, which includes the scripts or instructions to run your codes.\n\nThe final zip file should be uploaded via our course website:   \nhttps://oc.sjtu.edu.cn\n</p>\n\n<h2>Deadline of this project</h2>\n<p>Deadline for submitting your predictions on Kaggle: 2019/4/21</p>\n\n<p>Deadline for uploading your readme and code via our course website: 2019/4/24</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>Metric</h2>\nThis competition is evaluated on the categorization accuracy of your predictions (the percentage of images you get correct).\n\n<h2>Submission Format</h2>\nFor every id, submission files should contain two columns: ID and Category. Category should be an integer representing the predicted label for id.  \n\n<p>The file should contain a header and have the following format:</p>\n<pre>ID,Category<br>1,1<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}