{
  "fetched_at": "2026-10-19T10:40:40Z",
  "source_url": "https://www.kaggle.com/competitions/ece590cifar/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": "## CIFAR-10 Dataset\nThe CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. \n\nThe 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. \n\nWe have modified the whole CIFAR-10 dataset a bit for its usage on ECE590 course. We resplitted the dataset and released 50,000 images for training and validation. We hold out 10,000 images for final evaluation on the Kaggle platform. Note that the dataset split is a little different from the original dataset split.\n\n## Reference\nLearning Multiple Layers of Features from Tiny Images, Alex Krizhevsky, 2009.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Description\nIt is exciting to design an image classifier for the CIFAR-10 task. You objective is to build a powerful neural network to achieve high accuracy on the CIFAR-10 classification dataset.\n\n## Memory Limit\n3 GB GPU memory limit for each neural network during training.\n\n## Submission Limit\n5 submission a day.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Evaluation\nWe will use the top-1 categorical accuracy as the evaluation metric. We will release your test result on 50% of the test dataset on the public leaderboard for you to further improve your model.\nYour final result is decided by the remaining 50% of the data in the test dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Submission Deadline",
      "content": "## Submission Deadline\nWe will accept your submission until 10/02/2019. We will use your best test score as the final result.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Grading & Extra Credit",
      "content": "## Grading\nYou will receive full credit if you can achieve more than 80\\% accuracy.\n\n## Extra Credit\n\n* An extra 5 points will be awarded if your test accuracy goes beyond 85%.\n* Another extra 5 points will be awarded if your test accuracy goes beyond 90%.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Rules",
      "content": "The rules for this competition is as follows:\n\n* DO NOT use pretrained models to get unfair advantage.\n* DO NOT train on the test image set.\n* DO NOT copy code from online repositories. (e.g. github, stackoverflow etc.). If you use other's code, please cite them properly.\n* You should open-source your code after you submit the lab report. We will look into it if we have further questions about your lab report.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}