{
  "fetched_at": "2026-10-19T07:38:24Z",
  "source_url": "https://www.kaggle.com/competitions/applications-of-deep-learning-wustl-spring-2021b/data",
  "pages": [
    {
      "name": "data-description",
      "content": "All images are 1024x1024 JPEG images stored with a low compression quality.  Because there are over 40K images, the file size would be very large if lossless PNG files were used.  You will likely need to decrease the image size before feeding into a neural network.  The zip down load contains the JPEG images with names such as mc-1.jpg.  There are also three CSV files\n\n* train.csv - Labeled training data.\n* test.csv - The file you should score and submit.\n* sample.csv - A sample submission file.\n\nThe label for this training set is a true (1)/false (0) value that indicates if the image is fake.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "You can find a video of the winning solution [here](https://www.youtube.com/watch?v=OlMG_8NqrdU).\n\nThis semester you will get a chance to try your hand at detecting fake images from real images.  I trained a [model](https://github.com/jeffheaton/pretrained-gan-minecraft) on images that I collected from the [Minecraft video game](https://en.wikipedia.org/wiki/Minecraft).  From the provided link, you have access to my trained model, and can generate more fake data, if you like.  However, if you would like additional real data, you will need to capture it from Minecraft yourself.\n\nThe following is a real image from Minecraft:\n![Real Minecraft](https://github.com/jeffheaton/jheaton_images/blob/main/kaggle/spring-2021/mc-34.jpg?raw=true)\n\nThis Minecraft image is obviously fake:\n\n![alt](https://github.com/jeffheaton/jheaton_images/blob/main/kaggle/spring-2021/mc-202.jpg?raw=true)\n\nSome images are not as easily guessed, such as this fake image:\n\n![alt](https://github.com/jeffheaton/jheaton_images/blob/main/kaggle/spring-2021/mc-493.jpg?raw=true)\n\nYou will also have to contend with multiple times of the day.  Darker images will be more difficult for your model.\n\n![alt](https://github.com/jeffheaton/jheaton_images/blob/main/kaggle/spring-2021/mc-477.jpg?raw=true)\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Your submission will be evaluated using the log loss.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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
    }
  ]
}