{
  "fetched_at": "2026-10-19T08:33:25Z",
  "source_url": "https://www.kaggle.com/competitions/e4040fall2019-assignment-2-task-5/data",
  "pages": [
    {
      "name": "rules",
      "content": "<h2>Rules</h2>\n<h3>General Rules</h3>\n - The goal of this competition is to classify the liquid amount of bottles as accurately as possible.\n - Students can implement <strong>any</strong> training methods taught in class or practiced in homework, <strong>or even external ideas not covered</strong>.\n - The baseline accuracy is 70% and is what everyone should achieve. 1 point will be reduced for each 1% below 70%. Top 10 students would have bonus points. \n - Students should participate in the competition using only Tensorflow 1.13.\n\n<h3>Submission details</h3>\n1. No groups! Each student must participate as a team with only one person. Please go to <strong>'Team'</strong>, use your name as the team name. \n2. A valid submission is a .csv file containing 2 columns in a similar format as the sample (prediction_labels_template.csv) that is available on this site.\n3. One can submit at most 20 times a day.\n4. The public leaderboard uses 70% of the test data to generate the accuracy. The final leaderboard will also consider the rest 30% of the test data. So what you see on the public leaderboard may be different from the final rankings (the private leaderboard). The bonus distribution would depend on the result of the <strong>private leaderboard</strong>.\n\n<h3>Academic integrity</h3>\n- Don't cheat! Discussions among each other are encouraged, but <strong>do not copy other people's results!!</strong> This will be considered as plagiarism.\n- If you use some external open source code you find on Internet, you must reference it.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>kaggle_train_128.zip</strong> - the training set. It contains 15000 images (3000 for each class), each of size 128*128. After extraction, there will be 5 sub-folders. The name of the sub-folder is the corresponding class.</li>\n<li><strong>kaggle_test_128.zip</strong> - the test set. It contains 3500 images, each of size 128*128.</li>\n<li><strong>prediction_labels_templates.csv</strong> - a sample csv file for your reference.</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>id</strong> - the id of an image</li>\n<li><strong>label</strong> - the label of an image (0, 1, 2, 3, 4)</li>\n</ul>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>1. Overview</h2>\n<p>This is the 5th part of your assignment 2. Here, you will be given a dataset of bottles, and you need to do a 5-class liquid amount classification task.\n<h2>2. Dataset</h2>\n<h3>2.1 Background</h3>\n<p>The bottle dataset was collected during ECBM E4040 Fall 2016. There are 2 types of bottles: <strong>coke bottle</strong> and <strong>water bottle</strong>, and the students were asked to take pictures with their cellphones. A post-processing was done to make sure each picture has the same size.</p>\n<p>There has 5 degrees of the liquid amount (<strong>this is what you need to classify</strong>):</p>\n+ 0%(labeled as 0)\n+ 25%(labeled as 1)\n+ 50%(labeled as 2)\n+ 75%(labeled as 3)\n+ 100%(labeled as 4)\n<p>The labels were manually created by students when they submitted their pictures, and only represents a visual estimation of the amount, not the true liquid amount.<\\p>\n<h3>2.2 Data Organization</h3>\n<p>**Training**: 15000 images (3000 for each class). The labels are indicated by their sub-folders in the data zip file.<\\p>\n<p>**Testing**: 3500 images (700 for each class). The labels are held by the CAs.<\\p>\n<h2>Notice: Please leave the \"Kernels\" tab unchanged.<\\h2>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}