{
  "fetched_at": "2026-10-19T22:34:02Z",
  "source_url": "https://www.kaggle.com/competitions/exml-prelims-task-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The training data contains 24 images per class. Most images are of size ```(100px x 100px)```.\n<br><br><br>\n\n**Note: Augmentation Techniques are allowed**\n\n##Note : If you can't download the dataset, try downloading the files individually.\n\n#A note on hand labeling <br>\nPer the rules and spirit of this contest, please do not manually label your submissions.\n<br>\n<br>\nHowever, given that there is always one willing to cheat to rise to glory, **we reserve the right to wield the following anti-cheating measures:**\n\n- Ask to spot-check your code at any point in the competition. Failure to provide proof of algorithm within a reasonable time frame may result in disqualification.\n\n- Release a new test set towards the end of the competition and require predictions for this new set.\n\n- After the competition, require access to your model to verify that the solution does not utilize human intervention.\n\n**In short, if you cheat by hand labeling your predictions, expect to do it all over again, possibly many times.**  Thanks in advance for the fair competition and have fun.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "#Exun 2021-2022\nThe event is a part of our annual tech symposium [Exun 2021-22](https://reg.exun.co/invite). If you're interested in participating in other technical events, please check out our [invite](https://reg.exun.co/invite/events)!\n\n\n##Prelims Task-2\nIn this task, we will be giving you a dataset for classification of some world-known company logos. Your model has to learn to classify them. \n\n<br>\n**Make sure to register at [http://exun.co/independentreg](http://exun.co/independentreg) and fill out this [form](https://docs.google.com/forms/d/e/1FAIpQLSfQRjG7Uh-uJDxFr5-LYWX1R5zc_ezKJhjJv33doj6L7DkjdQ/viewform) after finalizing your Kaggle submissions.**",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "###Goal\nThe goal in this competition is to take an image of a logo and determine the company to which it belongs.\nFor every image in the test set, you should predict the correct label. \n```\nLabels :- (to be put in company column of your submission csv)\n\nAmazon - 0\nApple - 1\nDisney - 2\nFacebook - 3\nGoogle - 4\nIBM - 5\nIntel - 6\nNetflix - 7\n```\n\n\n###Metric\nThis competition is evaluated on the categorization accuracy of your predictions (the percentage of images you get correct).\n\n###Submission File Format\nThe file should contain a header and have the following format:\n```\nid,company\nvwitaAIDKb_390965,0\nxnJibWYcHP_87987,0\nvOzNfUKoeU_621007,0\netc.\n```\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "###One account per participant <br>\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n###No private sharing outside teams<br>\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n###Team Limits<br>\nThe maximum team size is 4\n\n###Submission Limits<br>\nYou may submit a maximum of 4 entries per day.\n\nYou may select up to 2 final submissions for judging.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "###11 Jan 12:00pm IST to 13 Jan 12:00pm IST",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}