{
  "fetched_at": "2026-10-19T11:07:03Z",
  "source_url": "https://www.kaggle.com/competitions/cse144-hw4-part2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The data is a subsample of[ ImageNet](https://ieeexplore.ieee.org/document/5206848). \n\n### Files\nThere are four files in the dataset: `train.pkl` and `test.pkl`, `helper.ipynb`, and `sample_submission.csv`.\n\n* `helper.ipynb`: code snippets for you to read the train and test data with pickle, and to display an image. You need to use Python3. \n\n* `train.pkl`: training data serialized with pickle. there are 10000 samples and 10000 corresponding labels. \n\n* `test.pkl`: test data serialized with pickle. there are 2000 samples, no label. \n\n* `sample_submission.csv`: to submit your predictions, you should use the exact same format as this. (except for changing the numbers in the label column to the one that's output from your model). The file should contain two columns: id and Label. id is the index of the test data, starting from 0 to 1999 for 2000 test samples. Label is corresponding classification label of that data, which is an integer from 1 to 10.  <p>The file should contain a header and have the following format:</p>\n> id,label<br>0,1<br>1,3<br>2,10<br>3,2<br>...<br>1999,5\n\n\n### Data Format\n`train.pkl`, after unpickling, is a dictionary with \"data\" and \"label\" fields. `test.pkl` contains just \"data\", no \"label\". There are 10000 samples in train and 2000 samples in test. \n\n\"data\"\n> numpy array with samples x 12288. For each sample, first 4096 numbers represent red channel, next 4096 numbers green channel, last 4096 numbers represent blue channel.\n\n\"label\"\n> number representing image class, indexing starts at 1 and ends at 10. Here are the ten classes:\n 1: 'dog',\n 2: 'rabbit',\n 3: 'deer',\n 4: 'elephant',\n 5: 'horse',\n 6: 'squirrel',\n 7: 'tiger',\n 8: 'wolf',\n 9: 'chimpanzee',\n 10: 'panda'. \n\n\n\n\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is an image classification in-class competition. The task is to use images of 10 different animals and train a model to classify them correctly. The details about the data is in the data tab. \n\nYou are to download the data, which is made of two parts: train, which has both data and the label, and test, which only has data and not the label. You will train a model, and then predict the labels of the test dataset, and submit that result here in Kaggle. \n\nThe accuracy score of your result will be shown in the leaderboard. The public leader board is scored on 50% of the test data, and the private leader board is scored on the other 50%. During the competition, you can submit results up to 20 times a day and see your result on public leaderboard. And when the competition is over, the final score will be shown in the private leaderboard. The two leaderboards, is to avoid people overfitting to the public leaderboard. \n\nYou are free to use any programming languages, packages, and machine learning models. \n\nThe grading of this part of the homework will be mostly based on the private leaderboard accuracy and ranking (40pts), and partially on the report (20pts). ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "\n### Evaluation Metric\n\nThe evaluation metric for this competition is Accuracy Score, which is defined by the percentage of correct classification among all samples. \n\n### Submission Format\nSubmission file should contain two columns: id and Label. id is the index of the test data, starting from 0 to 1999 for 2000 test samples. Label is corresponding classification label of that data, which is an integer from 1 to 10.  \n<p>The file should contain a header and have the following format:</p>\n<pre>id,label<br>0,1<br>1,3<br>2,10<br>3,2<br>...<br>1999,5</pre>",
      "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
    }
  ]
}